MOTIVATION: The reproducibility crisis has highlighted the importance of improving the way bioinformatics data analyses are implemented, executed, and shared. To address this, various tools such as content versioning systems, workflow management systems, and software environment management systems have been developed. While these tools are becoming more widely used, there is still much work to be done to increase their adoption. The most effective way to ensure reproducibility becomes a standard part of most bioinformatics data analysis projects is to integrate it into the curriculum of bioinformatics Master's programs. RESULTS: In this article, we present the Reprohackathon, a Master's course that we have been running for the last 3 years at Université Paris-Saclay (France), and that has been attended by a total of 123 students. The course is divided into two parts. The first part includes lessons on the challenges related to reproducibility, content versioning systems, container management, and workflow systems. In the second part, students work on a data analysis project for 3-4 months, reanalyzing data from a previously published study. The Reprohackaton has taught us many valuable lessons, such as the fact that implementing reproducible analyses is a complex and challenging task that requires significant effort. However, providing in-depth teaching of the concepts and the tools during a Master's degree program greatly improves students' understanding and abilities in this area.

MOTIVATION: Modern methods for computation-intensive tasks in sequence analysis (e.g. read mapping, sequence alignment, genome assembly, etc.) often first transform each sequence into a list of short, regular-length seeds so that compact data structures and efficient algorithms can be employed to handle the ever-growing large-scale data. Seeding methods using kmers (substrings of length k) have gained tremendous success in processing sequencing data with low mutation/error rates. However, they are much less effective for sequencing data with high error rates as kmers cannot tolerate errors. RESULTS: We propose SubseqHash, a strategy that uses subsequences, rather than substrings, as seeds. Formally, SubseqHash maps a string of length n to its smallest subsequence of length k, k < n, according to a given order overall length-k strings. Finding the smallest subsequence of a string by enumeration is impractical as the number of subsequences grows exponentially. To overcome this barrier, we propose a novel algorithmic framework that consists of a specifically designed order (termed ABC order) and an algorithm that computes the minimized subsequence under an ABC order in polynomial time. We first show that the ABC order exhibits the desired property and the probability of hash collision using the ABC order is close to the Jaccard index. We then show that SubseqHash overwhelmingly outperforms the substring-based seeding methods in producing high-quality seed-matches for three critical applications: read mapping, sequence alignment, and overlap detection. SubseqHash presents a major algorithmic breakthrough for tackling the high error rates and we expect it to be widely adapted for long-reads analysis. AVAILABILITY AND IMPLEMENTATION: SubseqHash is freely available at https://github.com/Shao-Group/subseqhash.

MOTIVATION: Branch lengths and topology of a species tree are essential in most downstream analyses, including estimation of diversification dates, characterization of selection, understanding adaptation, and comparative genomics. Modern phylogenomic analyses often use methods that account for the heterogeneity of evolutionary histories across the genome due to processes such as incomplete lineage sorting. However, these methods typically do not generate branch lengths in units that are usable by downstream applications, forcing phylogenomic analyses to resort to alternative shortcuts such as estimating branch lengths by concatenating gene alignments into a supermatrix. Yet, concatenation and other available approaches for estimating branch lengths fail to address heterogeneity across the genome. RESULTS: In this article, we derive expected values of gene tree branch lengths in substitution units under an extension of the multispecies coalescent (MSC) model that allows substitutions with varying rates across the species tree. We present CASTLES, a new technique for estimating branch lengths on the species tree from estimated gene trees that uses these expected values, and our study shows that CASTLES improves on the most accurate prior methods with respect to both speed and accuracy. AVAILABILITY AND IMPLEMENTATION: CASTLES is available at https://github.com/ytabatabaee/CASTLES.

MOTIVATION: Utilizing AI-driven approaches for drug-target interaction (DTI) prediction require large volumes of training data which are not available for the majority of target proteins. In this study, we investigate the use of deep transfer learning for the prediction of interactions between drug candidate compounds and understudied target proteins with scarce training data. The idea here is to first train a deep neural network classifier with a generalized source training dataset of large size and then to reuse this pre-trained neural network as an initial configuration for re-training/fine-tuning purposes with a small-sized specialized target training dataset. To explore this idea, we selected six protein families that have critical importance in biomedicine: kinases, G-protein-coupled receptors (GPCRs), ion channels, nuclear receptors, proteases, and transporters. In two independent experiments, the protein families of transporters and nuclear receptors were individually set as the target datasets, while the remaining five families were used as the source datasets. Several size-based target family training datasets were formed in a controlled manner to assess the benefit provided by the transfer learning approach. RESULTS: Here, we present a systematic evaluation of our approach by pre-training a feed-forward neural network with source training datasets and applying different modes of transfer learning from the pre-trained source network to a target dataset. The performance of deep transfer learning is evaluated and compared with that of training the same deep neural network from scratch. We found that when the training dataset contains fewer than 100 compounds, transfer learning outperforms the conventional strategy of training the system from scratch, suggesting that transfer learning is advantageous for predicting binders to under-studied targets. AVAILABILITY AND IMPLEMENTATION: The source code and datasets are available at https://github.com/cansyl/TransferLearning4DTI. Our web-based service containing the ready-to-use pre-trained models is accessible at https://tl4dti.kansil.org.

MOTIVATION: Accurately assessing contacts between DNA fragments inside the nucleus with Hi-C experiment is crucial for understanding the role of 3D genome organization in gene regulation. This challenging task is due in part to the high sequencing depth of Hi-C libraries required to support high-resolution analyses. Most existing Hi-C data are collected with limited sequencing coverage, leading to poor chromatin interaction frequency estimation. Current computational approaches to enhance Hi-C signals focus on the analysis of individual Hi-C datasets of interest, without taking advantage of the facts that (i) several hundred Hi-C contact maps are publicly available and (ii) the vast majority of local spatial organizations are conserved across multiple cell types. RESULTS: Here, we present RefHiC-SR, an attention-based deep learning framework that uses a reference panel of Hi-C datasets to facilitate the enhancement of Hi-C data resolution of a given study sample. We compare RefHiC-SR against tools that do not use reference samples and find that RefHiC-SR outperforms other programs across different cell types, and sequencing depths. It also enables high-accuracy mapping of structures such as loops and topologically associating domains. AVAILABILITY AND IMPLEMENTATION: https://github.com/BlanchetteLab/RefHiC.

MOTIVATION: Alignment-free, k-mer based genotyping methods are a fast alternative to alignment-based methods and are particularly well suited for genotyping larger cohorts. The sensitivity of algorithms, that work with k-mers, can be increased by using spaced seeds, however, the application of spaced seeds in k-mer based genotyping methods has not been researched yet. RESULTS: We add a spaced seeds functionality to the genotyping software PanGenie and use it to calculate genotypes. This significantly improves sensitivity and F-score when genotyping SNPs, indels, and structural variants on reads with low (5×) and high (30×) coverage. Improvements are greater than what could be achieved by just increasing the length of contiguous k-mers. Effect sizes are particularly large for low coverage data. If applications implement effective algorithms for hashing of spaced k-mers, spaced k-mers have the potential to become an useful technique in k-mer based genotyping. AVAILABILITY AND IMPLEMENTATION: The source code of our proposed tool MaskedPanGenie is openly available on https://github.com/hhaentze/MaskedPangenie.

MOTIVATION: RNA design is the search for a sequence or set of sequences that will fold to desired structure, also known as the inverse problem of RNA folding. However, the sequences designed by existing algorithms often suffer from low ensemble stability, which worsens for long sequence design. Additionally, for many methods only a small number of sequences satisfying the MFE criterion can be found by each run of design. These drawbacks limit their use cases. RESULTS: We propose an innovative optimization paradigm, SAMFEO, which optimizes ensemble objectives (equilibrium probability or ensemble defect) by iterative search and yields a very large number of successfully designed RNA sequences as byproducts. We develop a search method which leverages structure level and ensemble level information at different stages of the optimization: initialization, sampling, mutation, and updating. Our work, while being less complicated than others, is the first algorithm that is able to design thousands of RNA sequences for the puzzles from the Eterna100 benchmark. In addition, our algorithm solves the most Eterna100 puzzles among all the general optimization based methods in our study. The only baseline solving more puzzles than our work is dependent on handcrafted heuristics designed for a specific folding model. Surprisingly, our approach shows superiority on designing long sequences for structures adapted from the database of 16S Ribosomal RNAs. AVAILABILITY AND IMPLEMENTATION: Our source code and data used in this article is available at https://github.com/shanry/SAMFEO.

The classic quantitative measure of phylogenetic diversity (PD) has been used to address problems in conservation biology, microbial ecology, and evolutionary biology. PD is the minimum total length of the branches in a phylogeny required to cover a specified set of taxa on the phylogeny. A general goal in the application of PD has been identifying a set of taxa of size k that maximize PD on a given phylogeny; this has been mirrored in active research to develop efficient algorithms for the problem. Other descriptive statistics, such as the minimum PD, average PD, and standard deviation of PD, can provide invaluable insight into the distribution of PD across a phylogeny (relative to a fixed value of k). However, there has been limited or no research on computing these statistics, especially when required for each clade in a phylogeny, enabling direct comparisons of PD between clades. We introduce efficient algorithms for computing PD and the associated descriptive statistics for a given phylogeny and each of its clades. In simulation studies, we demonstrate the ability of our algorithms to analyze large-scale phylogenies with applications in ecology and evolutionary biology. The software is available at https://github.com/flu-crew/PD_stats.

MOTIVATION: Signal peptides (SPs) are short amino acid segments present at the N-terminus of newly synthesized proteins that facilitate protein translocation into the lumen of the endoplasmic reticulum, after which they are cleaved off. Specific regions of SPs influence the efficiency of protein translocation, and small changes in their primary structure can abolish protein secretion altogether. The lack of conserved motifs across SPs, sensitivity to mutations, and variability in the length of the peptides make SP prediction a challenging task that has been extensively pursued over the years. RESULTS: We introduce TSignal, a deep transformer-based neural network architecture that utilizes BERT language models and dot-product attention techniques. TSignal predicts the presence of SPs and the cleavage site between the SP and the translocated mature protein. We use common benchmark datasets and show competitive accuracy in terms of SP presence prediction and state-of-the-art accuracy in terms of cleavage site prediction for most of the SP types and organism groups. We further illustrate that our fully data-driven trained model identifies useful biological information on heterogeneous test sequences. AVAILABILITY AND IMPLEMENTATION: TSignal is available at: https://github.com/Dumitrescu-Alexandru/TSignal.

MOTIVATION: The introduction of portable DNA sequencers such as the Oxford Nanopore Technologies MinION has enabled real-time and in the field DNA sequencing. However, in the field sequencing is actionable only when coupled with in the field DNA classification. This poses new challenges for metagenomic software since mobile deployments are typically in remote locations with limited network connectivity and without access to capable computing devices. RESULTS: We propose new strategies to enable in the field metagenomic classification on mobile devices. We first introduce a programming model for expressing metagenomic classifiers that decomposes the classification process into well-defined and manageable abstractions. The model simplifies resource management in mobile setups and enables rapid prototyping of classification algorithms. Next, we introduce the compact string B-tree, a practical data structure for indexing text in external storage, and we demonstrate its viability as a strategy to deploy massive DNA databases on memory-constrained devices. Finally, we combine both solutions into Coriolis, a metagenomic classifier designed specifically to operate on lightweight mobile devices. Through experiments with actual MinION metagenomic reads and a portable supercomputer-on-a-chip, we show that compared with the state-of-the-art solutions Coriolis offers higher throughput and lower resource consumption without sacrificing quality of classification. AVAILABILITY AND IMPLEMENTATION: Source code and test data are available from http://score-group.org/?id=smarten.

MOTIVATION: Despite the advances in sequencing technology, massive proteins with known sequences remain functionally unannotated. Biological network alignment (NA), which aims to find the node correspondence between species' protein-protein interaction (PPI) networks, has been a popular strategy to uncover missing annotations by transferring functional knowledge across species. Traditional NA methods assumed that topologically similar proteins in PPIs are functionally similar. However, it was recently reported that functionally unrelated proteins can be as topologically similar as functionally related pairs, and a new data-driven or supervised NA paradigm has been proposed, which uses protein function data to discern which topological features correspond to functional relatedness. RESULTS: Here, we propose GraNA, a deep learning framework for the supervised NA paradigm for the pairwise NA problem. Employing graph neural networks, GraNA utilizes within-network interactions and across-network anchor links for learning protein representations and predicting functional correspondence between across-species proteins. A major strength of GraNA is its flexibility to integrate multi-faceted non-functional relationship data, such as sequence similarity and ortholog relationships, as anchor links to guide the mapping of functionally related proteins across species. Evaluating GraNA on a benchmark dataset composed of several NA tasks between different pairs of species, we observed that GraNA accurately predicted the functional relatedness of proteins and robustly transferred functional annotations across species, outperforming a number of existing NA methods. When applied to a case study on a humanized yeast network, GraNA also successfully discovered functionally replaceable human-yeast protein pairs that were documented in previous studies. AVAILABILITY AND IMPLEMENTATION: The code of GraNA is available at https://github.com/luo-group/GraNA.

MOTIVATION: With advances in long-read transcriptome sequencing, we can now fully sequence transcripts, which greatly improves our ability to study transcription processes. A popular long-read transcriptome sequencing technique is Oxford Nanopore Technologies (ONT), which through its cost-effective sequencing and high throughput, has the potential to characterize the transcriptome in a cell. However, due to transcript variability and sequencing errors, long cDNA reads need substantial bioinformatic processing to produce a set of isoform predictions from the reads. Several genome and annotation-based methods exist to produce transcript predictions. However, such methods require high-quality genomes and annotations and are limited by the accuracy of long-read splice aligners. In addition, gene families with high heterogeneity may not be well represented by a reference genome and would benefit from reference-free analysis. Reference-free methods to predict transcripts from ONT, such as RATTLE, exist, but their sensitivity is not comparable to reference-based approaches. RESULTS: We present isONform, a high-sensitivity algorithm to construct isoforms from ONT cDNA sequencing data. The algorithm is based on iterative bubble popping on gene graphs built from fuzzy seeds from the reads. Using simulated, synthetic, and biological ONT cDNA data, we show that isONform has substantially higher sensitivity than RATTLE albeit with some loss in precision. On biological data, we show that isONform's predictions have substantially higher consistency with the annotation-based method StringTie2 compared with RATTLE. We believe isONform can be used both for isoform construction for organisms without well-annotated genomes and as an orthogonal method to verify predictions of reference-based methods. AVAILABILITY AND IMPLEMENTATION: https://github.com/aljpetri/isONform.

MOTIVATION: Complex phenotypes, such as many common diseases and morphological traits, are controlled by multiple genetic factors, namely genetic mutations and genes, and are influenced by environmental conditions. Deciphering the genetics underlying such traits requires a systemic approach, where many different genetic factors and their interactions are considered simultaneously. Many association mapping techniques available nowadays follow this reasoning, but have some severe limitations. In particular, they require binary encodings for the genetic markers, forcing the user to decide beforehand whether to use, e.g. a recessive or a dominant encoding. Moreover, most methods cannot include any biological prior or are limited to testing only lower-order interactions among genes for association with the phenotype, potentially missing a large number of marker combinations. RESULTS: We propose HOGImine, a novel algorithm that expands the class of discoverable genetic meta-markers by considering higher-order interactions of genes and by allowing multiple encodings for the genetic variants. Our experimental evaluation shows that the algorithm has a substantially higher statistical power compared to previous methods, allowing it to discover genetic mutations statistically associated with the phenotype at hand that could not be found before. Our method can exploit prior biological knowledge on gene interactions, such as protein-protein interaction networks, genetic pathways, and protein complexes, to restrict its search space. Since computing higher-order gene interactions poses a high computational burden, we also develop a more efficient search strategy and support computation to make our approach applicable in practice, leading to substantial runtime improvements compared to state-of-the-art methods. AVAILABILITY AND IMPLEMENTATION: Code and data are available at https://github.com/BorgwardtLab/HOGImine.

MOTIVATION: Transcriptional dynamics are governed by the action of regulatory proteins and are fundamental to systems ranging from normal development to disease. RNA velocity methods for tracking phenotypic dynamics ignore information on the regulatory drivers of gene expression variability through time. RESULTS: We introduce scKINETICS (Key regulatory Interaction NETwork for Inferring Cell Speed), a dynamical model of gene expression change which is fit with the simultaneous learning of per-cell transcriptional velocities and a governing gene regulatory network. Fitting is accomplished through an expectation-maximization approach designed to learn the impact of each regulator on its target genes, leveraging biologically motivated priors from epigenetic data, gene-gene coexpression, and constraints on cells' future states imposed by the phenotypic manifold. Applying this approach to an acute pancreatitis dataset recapitulates a well-studied axis of acinar-to-ductal transdifferentiation whilst proposing novel regulators of this process, including factors with previously appreciated roles in driving pancreatic tumorigenesis. In benchmarking experiments, we show that scKINETICS successfully extends and improves existing velocity approaches to generate interpretable, mechanistic models of gene regulatory dynamics. AVAILABILITY AND IMPLEMENTATION: All python code and an accompanying Jupyter notebook with demonstrations are available at http://github.com/dpeerlab/scKINETICS.

MOTIVATION: Recent methods for selective sweep detection cast the problem as a classification task and use summary statistics as features to capture region characteristics that are indicative of a selective sweep, thereby being sensitive to confounding factors. Furthermore, they are not designed to perform whole-genome scans or to estimate the extent of the genomic region that was affected by positive selection; both are required for identifying candidate genes and the time and strength of selection. RESULTS: We present ASDEC (https://github.com/pephco/ASDEC), a neural-network-based framework that can scan whole genomes for selective sweeps. ASDEC achieves similar classification performance to other convolutional neural network-based classifiers that rely on summary statistics, but it is trained 10× faster and classifies genomic regions 5× faster by inferring region characteristics from the raw sequence data directly. Deploying ASDEC for genomic scans achieved up to 15.2× higher sensitivity, 19.4× higher success rates, and 4× higher detection accuracy than state-of-the-art methods. We used ASDEC to scan human chromosome 1 of the Yoruba population (1000Genomes project), identifying nine known candidate genes.

MOTIVATION: Minimal perfect hashing is the problem of mapping a static set of n distinct keys into the address space {1,…,n} bijectively. It is well-known that n log 2(e) bits are necessary to specify a minimal perfect hash function (MPHF) f, when no additional knowledge of the input keys is to be used. However, it is often the case in practice that the input keys have intrinsic relationships that we can exploit to lower the bit complexity of f. For example, consider a string and the set of all its distinct k-mers as input keys: since two consecutive k-mers share an overlap of k-1 symbols, it seems possible to beat the classic  log 2(e) bits/key barrier in this case. Moreover, we would like f to map consecutive k-mers to consecutive addresses, as to also preserve as much as possible their relationship in the codomain. This is a useful feature in practice as it guarantees a certain degree of locality of reference for f, resulting in a better evaluation time when querying consecutive k-mers. RESULTS: Motivated by these premises, we initiate the study of a new type of locality-preserving MPHF designed for k-mers extracted consecutively from a collection of strings. We design a construction whose space usage decreases for growing k and discuss experiments with a practical implementation of the method: in practice, the functions built with our method can be several times smaller and even faster to query than the most efficient MPHFs in the literature.

MOTIVATION: Alternative RNA splicing plays a crucial role in defining protein function. However, despite its relevance, there is a lack of tools that characterize effects of splicing on protein interaction networks in a mechanistic manner (i.e. presence or absence of protein-protein interactions due to RNA splicing). To fill this gap, we present Linear Integer programming for Network reconstruction using transcriptomics and Differential splicing data Analysis (LINDA) as a method that integrates resources of protein-protein and domain-domain interactions, transcription factor targets, and differential splicing/transcript analysis to infer splicing-dependent effects on cellular pathways and regulatory networks. RESULTS: We have applied LINDA to a panel of 54 shRNA depletion experiments in HepG2 and K562 cells from the ENCORE initiative. Through computational benchmarking, we could show that the integration of splicing effects with LINDA can identify pathway mechanisms contributing to known bioprocesses better than other state of the art methods, which do not account for splicing. Additionally, we have experimentally validated some of the predicted splicing effects that the depletion of HNRNPK in K562 cells has on signalling.

MOTIVATION: Boolean networks are simple but efficient mathematical formalism for modelling complex biological systems. However, having only two levels of activation is sometimes not enough to fully capture the dynamics of real-world biological systems. Hence, the need for multi-valued networks (MVNs), a generalization of Boolean networks. Despite the importance of MVNs for modelling biological systems, only limited progress has been made on developing theories, analysis methods, and tools that can support them. In particular, the recent use of trap spaces in Boolean networks made a great impact on the field of systems biology, but there has been no similar concept defined and studied for MVNs to date. RESULTS: In this work, we generalize the concept of trap spaces in Boolean networks to that in MVNs. We then develop the theory and the analysis methods for trap spaces in MVNs. In particular, we implement all proposed methods in a Python package called trapmvn. Not only showing the applicability of our approach via a realistic case study, we also evaluate the time efficiency of the method on a large collection of real-world models. The experimental results confirm the time efficiency, which we believe enables more accurate analysis on larger and more complex multi-valued models. AVAILABILITY AND IMPLEMENTATION: Source code and data are freely available at https://github.com/giang-trinh/trap-mvn.

MOTIVATION: Single-cell RNA-sequencing technologies have greatly enhanced our understanding of heterogeneous cell populations and underlying regulatory processes. However, structural (spatial or temporal) relations between cells are lost during cell dissociation. These relations are crucial for identifying associated biological processes. Many existing tissue-reconstruction algorithms use prior information about subsets of genes that are informative with respect to the structure or process to be reconstructed. When such information is not available, and in the general case when the input genes code for multiple processes, including being susceptible to noise, biological reconstruction is often computationally challenging. RESULTS: We propose an algorithm that iteratively identifies manifold-informative genes using existing reconstruction algorithms for single-cell RNA-seq data as subroutine. We show that our algorithm improves the quality of tissue reconstruction for diverse synthetic and real scRNA-seq data, including data from the mammalian intestinal epithelium and liver lobules. AVAILABILITY AND IMPLEMENTATION: The code and data for benchmarking are available at github.com/syq2012/iterative_weight_update_for_reconstruction.

MOTIVATION: Transcriptomics data are becoming more accessible due to high-throughput and less costly sequencing methods. However, data scarcity prevents exploiting deep learning models' full predictive power for phenotypes prediction. Artificially enhancing the training sets, namely data augmentation, is suggested as a regularization strategy. Data augmentation corresponds to label-invariant transformations of the training set (e.g. geometric transformations on images and syntax parsing on text data). Such transformations are, unfortunately, unknown in the transcriptomic field. Therefore, deep generative models such as generative adversarial networks (GANs) have been proposed to generate additional samples. In this article, we analyze GAN-based data augmentation strategies with respect to performance indicators and the classification of cancer phenotypes. RESULTS: This work highlights a significant boost in binary and multiclass classification performances due to augmentation strategies. Without augmentation, training a classifier on only 50 RNA-seq samples yields an accuracy of, respectively, 94% and 70% for binary and tissue classification. In comparison, we achieved 98% and 94% of accuracy when adding 1000 augmented samples. Richer architectures and more expensive training of the GAN return better augmentation performances and generated data quality overall. Further analysis of the generated data shows that several performance indicators are needed to assess its quality correctly. AVAILABILITY AND IMPLEMENTATION: All data used for this research are publicly available and comes from The Cancer Genome Atlas. Reproducible code is available on the GitLab repository: https://forge.ibisc.univ-evry.fr/alacan/GANs-for-transcriptomics.

MOTIVATION: The analysis of bacterial isolates to detect plasmids is important due to their role in the propagation of antimicrobial resistance. In short-read sequence assemblies, both plasmids and bacterial chromosomes are typically split into several contigs of various lengths, making identification of plasmids a challenging problem. In plasmid contig binning, the goal is to distinguish short-read assembly contigs based on their origin into plasmid and chromosomal contigs and subsequently sort plasmid contigs into bins, each bin corresponding to a single plasmid. Previous works on this problem consist of de novo approaches and reference-based approaches. De novo methods rely on contig features such as length, circularity, read coverage, or GC content. Reference-based approaches compare contigs to databases of known plasmids or plasmid markers from finished bacterial genomes. RESULTS: Recent developments suggest that leveraging information contained in the assembly graph improves the accuracy of plasmid binning. We present PlasBin-flow, a hybrid method that defines contig bins as subgraphs of the assembly graph. PlasBin-flow identifies such plasmid subgraphs through a mixed integer linear programming model that relies on the concept of network flow to account for sequencing coverage, while also accounting for the presence of plasmid genes and the GC content that often distinguishes plasmids from chromosomes. We demonstrate the performance of PlasBin-flow on a real dataset of bacterial samples. AVAILABILITY AND IMPLEMENTATION: https://github.com/cchauve/PlasBin-flow.

MOTIVATION: Protein-ligand binding affinity prediction is a central task in drug design and development. Cross-modal attention mechanism has recently become a core component of many deep learning models due to its potential to improve model explainability. Non-covalent interactions (NCIs), one of the most critical domain knowledge in binding affinity prediction task, should be incorporated into protein-ligand attention mechanism for more explainable deep drug-target interaction models. We propose ArkDTA, a novel deep neural architecture for explainable binding affinity prediction guided by NCIs. RESULTS: Experimental results show that ArkDTA achieves predictive performance comparable to current state-of-the-art models while significantly improving model explainability. Qualitative investigation into our novel attention mechanism reveals that ArkDTA can identify potential regions for NCIs between candidate drug compounds and target proteins, as well as guiding internal operations of the model in a more interpretable and domain-aware manner. AVAILABILITY: ArkDTA is available at https://github.com/dmis-lab/ArkDTA. CONTACT: kangj@korea.ac.kr.

MOTIVATION: There exists a range of different quantification frameworks to estimate the synergistic effect of drug combinations. The diversity and disagreement in estimates make it challenging to determine which combinations from a large drug screening should be proceeded with. Furthermore, the lack of accurate uncertainty quantification for those estimates precludes the choice of optimal drug combinations based on the most favourable synergistic effect. RESULTS: In this work, we propose SynBa, a flexible Bayesian approach to estimate the uncertainty of the synergistic efficacy and potency of drug combinations, so that actionable decisions can be derived from the model outputs. The actionability is enabled by incorporating the Hill equation into SynBa, so that the parameters representing the potency and the efficacy can be preserved. Existing knowledge may be conveniently inserted due to the flexibility of the prior, as shown by the empirical Beta prior defined for the normalized maximal inhibition. Through experiments on large combination screenings and comparison against benchmark methods, we show that SynBa provides improved accuracy of dose-response predictions and better-calibrated uncertainty estimation for the parameters and the predictions. AVAILABILITY AND IMPLEMENTATION: The code for SynBa is available at https://github.com/HaotingZhang1/SynBa. The datasets are publicly available (DOI of DREAM: 10.7303/syn4231880; DOI of the NCI-ALMANAC subset: 10.5281/zenodo.4135059).

MOTIVATION: The acquisition of somatic mutations by a tumor can be modeled by a type of evolutionary tree. However, it is impossible to observe this tree directly. Instead, numerous algorithms have been developed to infer such a tree from different types of sequencing data. But such methods can produce conflicting trees for the same patient, making it desirable to have approaches that can combine several such tumor trees into a consensus or summary tree. We introduce The Weighted m-Tumor Tree Consensus Problem (W-m-TTCP) to find a consensus tree among multiple plausible tumor evolutionary histories, each assigned a confidence weight, given a specific distance measure between tumor trees. We present an algorithm called TuELiP that is based on integer linear programming which solves the W-m-TTCP, and unlike other existing consensus methods, allows the input trees to be weighted differently. RESULTS: On simulated data we show that TuELiP outperforms two existing methods at correctly identifying the true underlying tree used to create the simulations. We also show that the incorporation of weights can lead to more accurate tree inference. On a Triple-Negative Breast Cancer dataset, we show that including confidence weights can have important impacts on the consensus tree identified. AVAILABILITY: An implementation of TuELiP and simulated datasets are available at https://bitbucket.org/oesperlab/consensus-ilp/src/main/.

MOTIVATION: The increasing availability of high-throughput omics data allows for considering a new medicine centered on individual patients. Precision medicine relies on exploiting these high-throughput data with machine-learning models, especially the ones based on deep-learning approaches, to improve diagnosis. Due to the high-dimensional small-sample nature of omics data, current deep-learning models end up with many parameters and have to be fitted with a limited training set. Furthermore, interactions between molecular entities inside an omics profile are not patient specific but are the same for all patients. RESULTS: In this article, we propose AttOmics, a new deep-learning architecture based on the self-attention mechanism. First, we decompose each omics profile into a set of groups, where each group contains related features. Then, by applying the self-attention mechanism to the set of groups, we can capture the different interactions specific to a patient. The results of different experiments carried out in this article show that our model can accurately predict the phenotype of a patient with fewer parameters than deep neural networks. Visualizing the attention maps can provide new insights into the essential groups for a particular phenotype. AVAILABILITY AND IMPLEMENTATION: The code and data are available at https://forge.ibisc.univ-evry.fr/abeaude/AttOmics. TCGA data can be downloaded from the Genomic Data Commons Data Portal.

MOTIVATION: The Sequence Read Archive public database has reached 45 petabytes of raw sequences and doubles its nucleotide content every 2 years. Although BLAST-like methods can routinely search for a sequence in a small collection of genomes, making searchable immense public resources accessible is beyond the reach of alignment-based strategies. In recent years, abundant literature tackled the task of finding a sequence in extensive sequence collections using k-mer-based strategies. At present, the most scalable methods are approximate membership query data structures that combine the ability to query small signatures or variants while being scalable to collections up to 10 000 eukaryotic samples. Results. Here, we present PAC, a novel approximate membership query data structure for querying collections of sequence datasets. PAC index construction works in a streaming fashion without any disk footprint besides the index itself. It shows a 3-6 fold improvement in construction time compared to other compressed methods for comparable index size. A PAC query can need single random access and be performed in constant time in favorable instances. Using limited computation resources, we built PAC for very large collections. They include 32 000 human RNA-seq samples in 5 days, the entire GenBank bacterial genome collection in a single day for an index size of 3.5 TB. The latter is, to our knowledge, the largest sequence collection ever indexed using an approximate membership query structure. We also showed that PAC's ability to query 500 000 transcript sequences in less than an hour. AVAILABILITY AND IMPLEMENTATION: PAC's open-source software is available at https://github.com/Malfoy/PAC.

The rapid improvements in genomic sequencing technology have led to the proliferation of locally collected genomic datasets. Given the sensitivity of genomic data, it is crucial to conduct collaborative studies while preserving the privacy of the individuals. However, before starting any collaborative research effort, the quality of the data needs to be assessed. One of the essential steps of the quality control process is population stratification: identifying the presence of genetic difference in individuals due to subpopulations. One of the common methods used to group genomes of individuals based on ancestry is principal component analysis (PCA). In this article, we propose a privacy-preserving framework which utilizes PCA to assign individuals to populations across multiple collaborators as part of the population stratification step. In our proposed client-server-based scheme, we initially let the server train a global PCA model on a publicly available genomic dataset which contains individuals from multiple populations. The global PCA model is later used to reduce the dimensionality of the local data by each collaborator (client). After adding noise to achieve local differential privacy (LDP), the collaborators send metadata (in the form of their local PCA outputs) about their research datasets to the server, which then aligns the local PCA results to identify the genetic differences among collaborators' datasets. Our results on real genomic data show that the proposed framework can perform population stratification analysis with high accuracy while preserving the privacy of the research participants.

MOTIVATION: Spatial proteomics data have been used to map cell states and improve our understanding of tissue organization. More recently, these methods have been extended to study the impact of such organization on disease progression and patient survival. However, to date, the majority of supervised learning methods utilizing these data types did not take full advantage of the spatial information, impacting their performance and utilization. RESULTS: Taking inspiration from ecology and epidemiology, we developed novel spatial feature extraction methods for use with spatial proteomics data. We used these features to learn prediction models for cancer patient survival. As we show, using the spatial features led to consistent improvement over prior methods that used the spatial proteomics data for the same task. In addition, feature importance analysis revealed new insights about the cell interactions that contribute to patient survival. AVAILABILITY AND IMPLEMENTATION: The code for this work can be found at gitlab.com/enable-medicine-public/spatsurv.

MOTIVATION: Metagenomic binning methods to reconstruct metagenome-assembled genomes (MAGs) from environmental samples have been widely used in large-scale metagenomic studies. The recently proposed semi-supervised binning method, SemiBin, achieved state-of-the-art binning results in several environments. However, this required annotating contigs, a computationally costly and potentially biased process. RESULTS: We propose SemiBin2, which uses self-supervised learning to learn feature embeddings from the contigs. In simulated and real datasets, we show that self-supervised learning achieves better results than the semi-supervised learning used in SemiBin1 and that SemiBin2 outperforms other state-of-the-art binners. Compared to SemiBin1, SemiBin2 can reconstruct 8.3-21.5% more high-quality bins and requires only 25% of the running time and 11% of peak memory usage in real short-read sequencing samples. To extend SemiBin2 to long-read data, we also propose ensemble-based DBSCAN clustering algorithm, resulting in 13.1-26.3% more high-quality genomes than the second best binner for long-read data. AVAILABILITY AND IMPLEMENTATION: SemiBin2 is available as open source software at https://github.com/BigDataBiology/SemiBin/ and the analysis scripts used in the study can be found at https://github.com/BigDataBiology/SemiBin2_benchmark.

MOTIVATION: Synthetic lethality (SL) is a promising strategy for anticancer therapy, as inhibiting SL partners of genes with cancer-specific mutations can selectively kill the cancer cells without harming the normal cells. Wet-lab techniques for SL screening have issues like high cost and off-target effects. Computational methods can help address these issues. Previous machine learning methods leverage known SL pairs, and the use of knowledge graphs (KGs) can significantly enhance the prediction performance. However, the subgraph structures of KG have not been fully explored. Besides, most machine learning methods lack interpretability, which is an obstacle for wide applications of machine learning to SL identification. RESULTS: We present a model named KR4SL to predict SL partners for a given primary gene. It captures the structural semantics of a KG by efficiently constructing and learning from relational digraphs in the KG. To encode the semantic information of the relational digraphs, we fuse textual semantics of entities into propagated messages and enhance the sequential semantics of paths using a recurrent neural network. Moreover, we design an attentive aggregator to identify critical subgraph structures that contribute the most to the SL prediction as explanations. Extensive experiments under different settings show that KR4SL significantly outperforms all the baselines. The explanatory subgraphs for the predicted gene pairs can unveil prediction process and mechanisms underlying synthetic lethality. The improved predictive power and interpretability indicate that deep learning is practically useful for SL-based cancer drug target discovery. AVAILABILITY AND IMPLEMENTATION: The source code is freely available at https://github.com/JieZheng-ShanghaiTech/KR4SL.

MOTIVATION: Knowing the relation between cell types is crucial for translating experimental results from mice to humans. Establishing cell type matches, however, is hindered by the biological differences between the species. A substantial amount of evolutionary information between genes that could be used to align the species is discarded by most of the current methods since they only use one-to-one orthologous genes. Some methods try to retain the information by explicitly including the relation between genes, however, not without caveats. RESULTS: In this work, we present a model to transfer and align cell types in cross-species analysis (TACTiCS). First, TACTiCS uses a natural language processing model to match genes using their protein sequences. Next, TACTiCS employs a neural network to classify cell types within a species. Afterward, TACTiCS uses transfer learning to propagate cell type labels between species. We applied TACTiCS on scRNA-seq data of the primary motor cortex of human, mouse, and marmoset. Our model can accurately match and align cell types on these datasets. Moreover, our model outperforms Seurat and the state-of-the-art method SAMap. Finally, we show that our gene matching method results in better cell type matches than BLAST in our model. AVAILABILITY AND IMPLEMENTATION: The implementation is available on GitHub (https://github.com/kbiharie/TACTiCS). The preprocessed datasets and trained models can be downloaded from Zenodo (https://doi.org/10.5281/zenodo.7582460).

MOTIVATION: Interactions among microbes within microbial communities have been shown to play crucial roles in human health. In spite of recent progress, low-level knowledge of bacteria driving microbial interactions within microbiomes remains unknown, limiting our ability to fully decipher and control microbial communities. RESULTS: We present a novel approach for identifying species driving interactions within microbiomes. Bakdrive infers ecological networks of given metagenomic sequencing samples and identifies minimum sets of driver species (MDS) using control theory. Bakdrive has three key innovations in this space: (i) it leverages inherent information from metagenomic sequencing samples to identify driver species, (ii) it explicitly takes host-specific variation into consideration, and (iii) it does not require a known ecological network. In extensive simulated data, we demonstrate identifying driver species identified from healthy donor samples and introducing them to the disease samples, we can restore the gut microbiome in recurrent Clostridioides difficile (rCDI) infection patients to a healthy state. We also applied Bakdrive to two real datasets, rCDI and Crohn's disease patients, uncovering driver species consistent with previous work. Bakdrive represents a novel approach for capturing microbial interactions. AVAILABILITY AND IMPLEMENTATION: Bakdrive is open-source and available at: https://gitlab.com/treangenlab/bakdrive.

MOTIVATION: The size of available omics datasets is steadily increasing with technological advancement in recent years. While this increase in sample size can be used to improve the performance of relevant prediction tasks in healthcare, models that are optimized for large datasets usually operate as black boxes. In high-stakes scenarios, like healthcare, using a black-box model poses safety and security issues. Without an explanation about molecular factors and phenotypes that affected the prediction, healthcare providers are left with no choice but to blindly trust the models. We propose a new type of artificial neural network, named Convolutional Omics Kernel Network (COmic). By combining convolutional kernel networks with pathway-induced kernels, our method enables robust and interpretable end-to-end learning on omics datasets ranging in size from a few hundred to several hundreds of thousands of samples. Furthermore, COmic can be easily adapted to utilize multiomics data. RESULTS: We evaluated the performance capabilities of COmic on six different breast cancer cohorts. Additionally, we trained COmic models on multiomics data using the METABRIC cohort. Our models performed either better or similar to competitors on both tasks. We show how the use of pathway-induced Laplacian kernels opens the black-box nature of neural networks and results in intrinsically interpretable models that eliminate the need for post hoc explanation models. AVAILABILITY AND IMPLEMENTATION: Datasets, labels, and pathway-induced graph Laplacians used for the single-omics tasks can be downloaded at https://ibm.ent.box.com/s/ac2ilhyn7xjj27r0xiwtom4crccuobst/folder/48027287036. While datasets and graph Laplacians for the METABRIC cohort can be downloaded from the above mentioned repository, the labels have to be downloaded from cBioPortal at https://www.cbioportal.org/study/clinicalData?id=brca\_metabric. COmic source code as well as all scripts necessary to reproduce the experiments and analysis are publicly available at https://github.com/jditz/comics.

MOTIVATION: The exponential growth of genomic sequencing data has created ever-expanding repositories of gene networks. Unsupervised network integration methods are critical to learn informative representations for each gene, which are later used as features for downstream applications. However, these network integration methods must be scalable to account for the increasing number of networks and robust to an uneven distribution of network types within hundreds of gene networks. RESULTS: To address these needs, we present Gemini, a novel network integration method that uses memory-efficient high-order pooling to represent and weight each network according to its uniqueness. Gemini then mitigates the uneven network distribution through mixing up existing networks to create many new networks. We find that Gemini leads to more than a 10% improvement in F1 score, 15% improvement in micro-AUPRC, and 63% improvement in macro-AUPRC for human protein function prediction by integrating hundreds of networks from BioGRID, and that Gemini's performance significantly improves when more networks are added to the input network collection, while Mashup and BIONIC embeddings' performance deteriorates. Gemini thereby enables memory-efficient and informative network integration for large gene networks and can be used to massively integrate and analyze networks in other domains. AVAILABILITY AND IMPLEMENTATION: Gemini can be accessed at: https://github.com/MinxZ/Gemini.

MOTIVATION: The Chemical Master Equation (CME) is a set of linear differential equations that describes the evolution of the probability distribution on all possible configurations of a (bio-)chemical reaction system. Since the number of configurations and therefore the dimension of the CME rapidly increases with the number of molecules, its applicability is restricted to small systems. A widely applied remedy for this challenge is moment-based approaches which consider the evolution of the first few moments of the distribution as summary statistics for the complete distribution. Here, we investigate the performance of two moment-estimation methods for reaction systems whose equilibrium distributions encounter fat-tailedness and do not possess statistical moments. RESULTS: We show that estimation via stochastic simulation algorithm (SSA) trajectories lose consistency over time and estimated moment values span a wide range of values even for large sample sizes. In comparison, the method of moments returns smooth moment estimates but is not able to indicate the non-existence of the allegedly predicted moments. We furthermore analyze the negative effect of a CME solution's fat-tailedness on SSA run times and explain inherent difficulties. While moment-estimation techniques are a commonly applied tool in the simulation of (bio-)chemical reaction networks, we conclude that they should be used with care, as neither the system definition nor the moment-estimation techniques themselves reliably indicate the potential fat-tailedness of the CME's solution.

MOTIVATION: Deep learning-based molecule generation becomes a new paradigm of de novo molecule design since it enables fast and directional exploration in the vast chemical space. However, it is still an open issue to generate molecules, which bind to specific proteins with high-binding affinities while owning desired drug-like physicochemical properties. RESULTS: To address these issues, we elaborate a novel framework for controllable protein-oriented molecule generation, named CProMG, which contains a 3D protein embedding module, a dual-view protein encoder, a molecule embedding module, and a novel drug-like molecule decoder. Based on fusing the hierarchical views of proteins, it enhances the representation of protein binding pockets significantly by associating amino acid residues with their comprising atoms. Through jointly embedding molecule sequences, their drug-like properties, and binding affinities w.r.t. proteins, it autoregressively generates novel molecules having specific properties in a controllable manner by measuring the proximity of molecule tokens to protein residues and atoms. The comparison with state-of-the-art deep generative methods demonstrates the superiority of our CProMG. Furthermore, the progressive control of properties demonstrates the effectiveness of CProMG when controlling binding affinity and drug-like properties. After that, the ablation studies reveal how its crucial components contribute to the model respectively, including hierarchical protein views, Laplacian position encoding as well as property control. Last, a case study w.r.t. protein illustrates the novelty of CProMG and the ability to capture crucial interactions between protein pockets and molecules. It's anticipated that this work can boost de novo molecule design. AVAILABILITY AND IMPLEMENTATION: The code and data underlying this article are freely available at https://github.com/lijianing0902/CProMG.

MOTIVATION: Gene regulatory networks (GRNs) in a cell provide the tight feedback needed to synchronize cell actions. However, genes in a cell also take input from, and provide signals to other neighboring cells. These cell-cell interactions (CCIs) and the GRNs deeply influence each other. Many computational methods have been developed for GRN inference in cells. More recently, methods were proposed to infer CCIs using single cell gene expression data with or without cell spatial location information. However, in reality, the two processes do not exist in isolation and are subject to spatial constraints. Despite this rationale, no methods currently exist to infer GRNs and CCIs using the same model. RESULTS: We propose CLARIFY, a tool that takes GRNs as input, uses them and spatially resolved gene expression data to infer CCIs, while simultaneously outputting refined cell-specific GRNs. CLARIFY uses a novel multi-level graph autoencoder, which mimics cellular networks at a higher level and cell-specific GRNs at a deeper level. We applied CLARIFY to two real spatial transcriptomic datasets, one using seqFISH and the other using MERFISH, and also tested on simulated datasets from scMultiSim. We compared the quality of predicted GRNs and CCIs with state-of-the-art baseline methods that inferred either only GRNs or only CCIs. The results show that CLARIFY consistently outperforms the baseline in terms of commonly used evaluation metrics. Our results point to the importance of co-inference of CCIs and GRNs and to the use of layered graph neural networks as an inference tool for biological networks. AVAILABILITY AND IMPLEMENTATION: The source code and data is available at https://github.com/MihirBafna/CLARIFY.

MOTIVATION: The 3D structures of RNA play a critical role in understanding their functionalities. There exist several computational methods to study RNA 3D structures by identifying structural motifs and categorizing them into several motif families based on their structures. Although the number of such motif families is not limited, a few of them are well-studied. Out of these structural motif families, there exist several families that are visually similar or very close in structure, even with different base interactions. Alternatively, some motif families share a set of base interactions but maintain variation in their 3D formations. These similarities among different motif families, if known, can provide a better insight into the RNA 3D structural motifs as well as their characteristic functions in cell biology. RESULTS: In this work, we proposed a method, RNAMotifComp, that analyzes the instances of well-known structural motif families and establishes a relational graph among them. We also have designed a method to visualize the relational graph where the families are shown as nodes and their similarity information is represented as edges. We validated our discovered correlations of the motif families using RNAMotifContrast. Additionally, we used a basic Naïve Bayes classifier to show the importance of RNAMotifComp. The relational analysis explains the functional analogies of divergent motif families and illustrates the situations where the motifs of disparate families are predicted to be of the same family. AVAILABILITY AND IMPLEMENTATION: Source code publicly available at https://github.com/ucfcbb/RNAMotifFamilySimilarity.

MOTIVATION: Huge datasets containing whole-genome sequences of bacterial strains are now commonplace and represent a rich and important resource for modern genomic epidemiology and metagenomics. In order to efficiently make use of these datasets, efficient indexing data structures-that are both scalable and provide rapid query throughput-are paramount. RESULTS: Here, we present Themisto, a scalable colored k-mer index designed for large collections of microbial reference genomes, that works for both short and long read data. Themisto indexes 179 thousand Salmonella enterica genomes in 9 h. The resulting index takes 142 gigabytes. In comparison, the best competing tools Metagraph and Bifrost were only able to index 11 000 genomes in the same time. In pseudoalignment, these other tools were either an order of magnitude slower than Themisto, or used an order of magnitude more memory. Themisto also offers superior pseudoalignment quality, achieving a higher recall than previous methods on Nanopore read sets. AVAILABILITY AND IMPLEMENTATION: Themisto is available and documented as a C++ package at https://github.com/algbio/themisto available under the GPLv2 license.

MOTIVATION: Low-copy repeats (LCRs) or segmental duplications are long segments of duplicated DNA that cover > 5% of the human genome. Existing tools for variant calling using short reads exhibit low accuracy in LCRs due to ambiguity in read mapping and extensive copy number variation. Variants in more than 150 genes overlapping LCRs are associated with risk for human diseases. METHODS: We describe a short-read variant calling method, ParascopyVC, that performs variant calling jointly across all repeat copies and utilizes reads independent of mapping quality in LCRs. To identify candidate variants, ParascopyVC aggregates reads mapped to different repeat copies and performs polyploid variant calling. Subsequently, paralogous sequence variants that can differentiate repeat copies are identified using population data and used for estimating the genotype of variants for each repeat copy. RESULTS: On simulated whole-genome sequence data, ParascopyVC achieved higher precision (0.997) and recall (0.807) than three state-of-the-art variant callers (best precision = 0.956 for DeepVariant and best recall = 0.738 for GATK) in 167 LCR regions. Benchmarking of ParascopyVC using the genome-in-a-bottle high-confidence variant calls for HG002 genome showed that it achieved a very high precision of 0.991 and a high recall of 0.909 across LCR regions, significantly better than FreeBayes (precision = 0.954 and recall = 0.822), GATK (precision = 0.888 and recall = 0.873) and DeepVariant (precision = 0.983 and recall = 0.861). ParascopyVC demonstrated a consistently higher accuracy (mean F1 = 0.947) than other callers (best F1 = 0.908) across seven human genomes. AVAILABILITY AND IMPLEMENTATION: ParascopyVC is implemented in Python and is freely available at https://github.com/tprodanov/ParascopyVC.

MOTIVATION: As viruses that mainly infect bacteria, phages are key players across a wide range of ecosystems. Analyzing phage proteins is indispensable for understanding phages' functions and roles in microbiomes. High-throughput sequencing enables us to obtain phages in different microbiomes with low cost. However, compared to the fast accumulation of newly identified phages, phage protein classification remains difficult. In particular, a fundamental need is to annotate virion proteins, the structural proteins, such as major tail, baseplate, etc. Although there are experimental methods for virion protein identification, they are too expensive or time-consuming, leaving a large number of proteins unclassified. Thus, there is a great demand to develop a computational method for fast and accurate phage virion protein (PVP) classification. RESULTS: In this work, we adapted the state-of-the-art image classification model, Vision Transformer, to conduct virion protein classification. By encoding protein sequences into unique images using chaos game representation, we can leverage Vision Transformer to learn both local and global features from sequence "images". Our method, PhaVIP, has two main functions: classifying PVP and non-PVP sequences and annotating the types of PVP, such as capsid and tail. We tested PhaVIP on several datasets with increasing difficulty and benchmarked it against alternative tools. The experimental results show that PhaVIP has superior performance. After validating the performance of PhaVIP, we investigated two applications that can use the output of PhaVIP: phage taxonomy classification and phage host prediction. The results showed the benefit of using classified proteins over all proteins. AVAILABILITY AND IMPLEMENTATION: The web server of PhaVIP is available via: https://phage.ee.cityu.edu.hk/phavip. The source code of PhaVIP is available via: https://github.com/KennthShang/PhaVIP.

MOTIVATION: Non-canonical (or non-B) DNA are genomic regions whose three-dimensional conformation deviates from the canonical double helix. Non-B DNA play an important role in basic cellular processes and are associated with genomic instability, gene regulation, and oncogenesis. Experimental methods are low-throughput and can detect only a limited set of non-B DNA structures, while computational methods rely on non-B DNA base motifs, which are necessary but not sufficient indicators of non-B structures. Oxford Nanopore sequencing is an efficient and low-cost platform, but it is currently unknown whether nanopore reads can be used for identifying non-B structures. RESULTS: We build the first computational pipeline to predict non-B DNA structures from nanopore sequencing. We formalize non-B detection as a novelty detection problem and develop the GoFAE-DND, an autoencoder that uses goodness-of-fit (GoF) tests as a regularizer. A discriminative loss encourages non-B DNA to be poorly reconstructed and optimizing Gaussian GoF tests allows for the computation of P-values that indicate non-B structures. Based on whole genome nanopore sequencing of NA12878, we show that there exist significant differences between the timing of DNA translocation for non-B DNA bases compared with B-DNA. We demonstrate the efficacy of our approach through comparisons with novelty detection methods using experimental data and data synthesized from a new translocation time simulator. Experimental validations suggest that reliable detection of non-B DNA from nanopore sequencing is achievable. AVAILABILITY AND IMPLEMENTATION: Source code is available at https://github.com/bayesomicslab/ONT-nonb-GoFAE-DND.

MOTIVATION: The coronavirus disease 2019 (COVID-19) remains a global public health emergency. Although people, especially those with underlying health conditions, could benefit from several approved COVID-19 therapeutics, the development of effective antiviral COVID-19 drugs is still a very urgent problem. Accurate and robust drug response prediction to a new chemical compound is critical for discovering safe and effective COVID-19 therapeutics. RESULTS: In this study, we propose DeepCoVDR, a novel COVID-19 drug response prediction method based on deep transfer learning with graph transformer and cross-attention. First, we adopt a graph transformer and feed-forward neural network to mine the drug and cell line information. Then, we use a cross-attention module that calculates the interaction between the drug and cell line. After that, DeepCoVDR combines drug and cell line representation and their interaction features to predict drug response. To solve the problem of SARS-CoV-2 data scarcity, we apply transfer learning and use the SARS-CoV-2 dataset to fine-tune the model pretrained on the cancer dataset. The experiments of regression and classification show that DeepCoVDR outperforms baseline methods. We also evaluate DeepCoVDR on the cancer dataset, and the results indicate that our approach has high performance compared with other state-of-the-art methods. Moreover, we use DeepCoVDR to predict COVID-19 drugs from FDA-approved drugs and demonstrate the effectiveness of DeepCoVDR in identifying novel COVID-19 drugs. AVAILABILITY AND IMPLEMENTATION: https://github.com/Hhhzj-7/DeepCoVDR.

MOTIVATION: Single-cell RNA sequencing (scRNA-seq) offers a powerful tool to dissect the complexity of biological tissues through cell sub-population identification in combination with clustering approaches. Feature selection is a critical step for improving the accuracy and interpretability of single-cell clustering. Existing feature selection methods underutilize the discriminatory potential of genes across distinct cell types. We hypothesize that incorporating such information could further boost the performance of single cell clustering. RESULTS: We develop CellBRF, a feature selection method that considers genes' relevance to cell types for single-cell clustering. The key idea is to identify genes that are most important for discriminating cell types through random forests guided by predicted cell labels. Moreover, it proposes a class balancing strategy to mitigate the impact of unbalanced cell type distributions on feature importance evaluation. We benchmark CellBRF on 33 scRNA-seq datasets representing diverse biological scenarios and demonstrate that it substantially outperforms state-of-the-art feature selection methods in terms of clustering accuracy and cell neighborhood consistency. Furthermore, we demonstrate the outstanding performance of our selected features through three case studies on cell differentiation stage identification, non-malignant cell subtype identification, and rare cell identification. CellBRF provides a new and effective tool to boost single-cell clustering accuracy. AVAILABILITY AND IMPLEMENTATION: All source codes of CellBRF are freely available at https://github.com/xuyp-csu/CellBRF.

MOTIVATION: Recent advances in spatial proteomics technologies have enabled the profiling of dozens of proteins in thousands of single cells in situ. This has created the opportunity to move beyond quantifying the composition of cell types in tissue, and instead probe the spatial relationships between cells. However, most current methods for clustering data from these assays only consider the expression values of cells and ignore the spatial context. Furthermore, existing approaches do not account for prior information about the expected cell populations in a sample. RESULTS: To address these shortcomings, we developed SpatialSort, a spatially aware Bayesian clustering approach that allows for the incorporation of prior biological knowledge. Our method is able to account for the affinities of cells of different types to neighbour in space, and by incorporating prior information about expected cell populations, it is able to simultaneously improve clustering accuracy and perform automated annotation of clusters. Using synthetic and real data, we show that by using spatial and prior information SpatialSort improves clustering accuracy. We also demonstrate how SpatialSort can perform label transfer between spatial and nonspatial modalities through the analysis of a real world diffuse large B-cell lymphoma dataset. AVAILABILITY AND IMPLEMENTATION: Source code is available on Github at: https://github.com/Roth-Lab/SpatialSort.

Nanopore sequencers generate electrical raw signals in real-time while sequencing long genomic strands. These raw signals can be analyzed as they are generated, providing an opportunity for real-time genome analysis. An important feature of nanopore sequencing, Read Until, can eject strands from sequencers without fully sequencing them, which provides opportunities to computationally reduce the sequencing time and cost. However, existing works utilizing Read Until either (i) require powerful computational resources that may not be available for portable sequencers or (ii) lack scalability for large genomes, rendering them inaccurate or ineffective. We propose RawHash, the first mechanism that can accurately and efficiently perform real-time analysis of nanopore raw signals for large genomes using a hash-based similarity search. To enable this, RawHash ensures the signals corresponding to the same DNA content lead to the same hash value, regardless of the slight variations in these signals. RawHash achieves an accurate hash-based similarity search via an effective quantization of the raw signals such that signals corresponding to the same DNA content have the same quantized value and, subsequently, the same hash value. We evaluate RawHash on three applications: (i) read mapping, (ii) relative abundance estimation, and (iii) contamination analysis. Our evaluations show that RawHash is the only tool that can provide high accuracy and high throughput for analyzing large genomes in real-time. When compared to the state-of-the-art techniques, UNCALLED and Sigmap, RawHash provides (i) 25.8× and 3.4× better average throughput and (ii) significantly better accuracy for large genomes, respectively. Source code is available at https://github.com/CMU-SAFARI/RawHash.

MOTIVATION: Machine learning methods can be used to support scientific discovery in healthcare-related research fields. However, these methods can only be reliably used if they can be trained on high-quality and curated datasets. Currently, no such dataset for the exploration of Plasmodium falciparum protein antigen candidates exists. The parasite P.falciparum causes the infectious disease malaria. Thus, identifying potential antigens is of utmost importance for the development of antimalarial drugs and vaccines. Since exploring antigen candidates experimentally is an expensive and time-consuming process, applying machine learning methods to support this process has the potential to accelerate the development of drugs and vaccines, which are needed for fighting and controlling malaria. RESULTS: We developed PlasmoFAB, a curated benchmark that can be used to train machine learning methods for the exploration of P.falciparum protein antigen candidates. We combined an extensive literature search with domain expertise to create high-quality labels for P.falciparum specific proteins that distinguish between antigen candidates and intracellular proteins. Additionally, we used our benchmark to compare different well-known prediction models and available protein localization prediction services on the task of identifying protein antigen candidates. We show that available general-purpose services are unable to provide sufficient performance on identifying protein antigen candidates and are outperformed by our models that were trained on this tailored data. AVAILABILITY AND IMPLEMENTATION: PlasmoFAB is publicly available on Zenodo with DOI 10.5281/zenodo.7433087. Furthermore, all scripts that were used in the creation of PlasmoFAB and the training and evaluation of machine learning models are open source and publicly available on GitHub here: https://github.com/msmdev/PlasmoFAB.

MOTIVATION: The spectacular recent advances in protein and protein complex structure prediction hold promise for reconstructing interactomes at large-scale and residue resolution. Beyond determining the 3D arrangement of interacting partners, modeling approaches should be able to unravel the impact of sequence variations on the strength of the association. RESULTS: In this work, we report on Deep Local Analysis, a novel and efficient deep learning framework that relies on a strikingly simple deconstruction of protein interfaces into small locally oriented residue-centered cubes and on 3D convolutions recognizing patterns within cubes. Merely based on the two cubes associated with the wild-type and the mutant residues, DLA accurately estimates the binding affinity change for the associated complexes. It achieves a Pearson correlation coefficient of 0.735 on about 400 mutations on unseen complexes. Its generalization capability on blind datasets of complexes is higher than the state-of-the-art methods. We show that taking into account the evolutionary constraints on residues contributes to predictions. We also discuss the influence of conformational variability on performance. Beyond the predictive power on the effects of mutations, DLA is a general framework for transferring the knowledge gained from the available non-redundant set of complex protein structures to various tasks. For instance, given a single partially masked cube, it recovers the identity and physicochemical class of the central residue. Given an ensemble of cubes representing an interface, it predicts the function of the complex. AVAILABILITY AND IMPLEMENTATION: Source code and models are available at http://gitlab.lcqb.upmc.fr/DLA/DLA.git.

MOTIVATION: Proteins interact to form complexes to carry out essential biological functions. Computational methods such as AlphaFold-multimer have been developed to predict the quaternary structures of protein complexes. An important yet largely unsolved challenge in protein complex structure prediction is to accurately estimate the quality of predicted protein complex structures without any knowledge of the corresponding native structures. Such estimations can then be used to select high-quality predicted complex structures to facilitate biomedical research such as protein function analysis and drug discovery. RESULTS: In this work, we introduce a new gated neighborhood-modulating graph transformer to predict the quality of 3D protein complex structures. It incorporates node and edge gates within a graph transformer framework to control information flow during graph message passing. We trained, evaluated and tested the method (called DProQA) on newly-curated protein complex datasets before the 15th Critical Assessment of Techniques for Protein Structure Prediction (CASP15) and then blindly tested it in the 2022 CASP15 experiment. The method was ranked 3rd among the single-model quality assessment methods in CASP15 in terms of the ranking loss of TM-score on 36 complex targets. The rigorous internal and external experiments demonstrate that DProQA is effective in ranking protein complex structures. AVAILABILITY AND IMPLEMENTATION: The source code, data, and pre-trained models are available at https://github.com/jianlin-cheng/DProQA.

MOTIVATION: Structural variation (SV) is a class of genetic diversity whose importance is increasingly revealed by genome resequencing, especially with long-read technologies. One crucial problem when analyzing and comparing SVs in several individuals is their accurate genotyping, that is determining whether a described SV is present or absent in one sequenced individual, and if present, in how many copies. There are only a few methods dedicated to SV genotyping with long-read data, and all either suffer of a bias toward the reference allele by not representing equally all alleles, or have difficulties genotyping close or overlapping SVs due to a linear representation of the alleles. RESULTS: We present SVJedi-graph, a novel method for SV genotyping that relies on a variation graph to represent in a single data structure all alleles of a set of SVs. The long reads are mapped on the variation graph and the resulting alignments that cover allele-specific edges in the graph are used to estimate the most likely genotype for each SV. Running SVJedi-graph on simulated sets of close and overlapping deletions showed that this graph model prevents the bias toward the reference alleles and allows maintaining high genotyping accuracy whatever the SV proximity, contrary to other state of the art genotypers. On the human gold standard HG002 dataset, SVJedi-graph obtained the best performances, genotyping 99.5% of the high confidence SV callset with an accuracy of 95% in less than 30 min. AVAILABILITY AND IMPLEMENTATION: SVJedi-graph is distributed under an AGPL license and available on GitHub at https://github.com/SandraLouise/SVJedi-graph and as a BioConda package.

Microbial natural products represent a major source of bioactive compounds for drug discovery. Among these molecules, nonribosomal peptides (NRPs) represent a diverse class that include antibiotics, immunosuppressants, anticancer agents, toxins, siderophores, pigments, and cytostatics. The discovery of novel NRPs remains a laborious process because many NRPs consist of nonstandard amino acids that are assembled by nonribosomal peptide synthetases (NRPSs). Adenylation domains (A-domains) in NRPSs are responsible for selection and activation of monomers appearing in NRPs. During the past decade, several support vector machine-based algorithms have been developed for predicting the specificity of the monomers present in NRPs. These algorithms utilize physiochemical features of the amino acids present in the A-domains of NRPSs. In this article, we benchmarked the performance of various machine learning algorithms and features for predicting specificities of NRPSs and we showed that the extra trees model paired with one-hot encoding features outperforms the existing approaches. Moreover, we show that unsupervised clustering of 453 560 A-domains reveals many clusters that correspond to potentially novel amino acids. While it is challenging to predict the chemical structure of these amino acids, we developed novel techniques to predict their various properties, including polarity, hydrophobicity, charge, and presence of aromatic rings, carboxyl, and hydroxyl groups.

The tendency of an amino acid to adopt certain configurations in folded proteins is treated here as a statistical estimation problem. We model the joint distribution of the observed mainchain and sidechain dihedral angles (〈ϕ,ψ,χ1,χ2,…〉) of any amino acid by a mixture of a product of von Mises probability distributions. This mixture model maps any vector of dihedral angles to a point on a multi-dimensional torus. The continuous space it uses to specify the dihedral angles provides an alternative to the commonly used rotamer libraries. These rotamer libraries discretize the space of dihedral angles into coarse angular bins, and cluster combinations of sidechain dihedral angles (〈χ1,χ2,…〉) as a function of backbone 〈ϕ,ψ〉 conformations. A 'good' model is one that is both concise and explains (compresses) observed data. Competing models can be compared directly and in particular our model is shown to outperform the Dunbrack rotamer library in terms of model complexity (by three orders of magnitude) and its fidelity (on average 20% more compression) when losslessly explaining the observed dihedral angle data across experimental resolutions of structures. Our method is unsupervised (with parameters estimated automatically) and uses information theory to determine the optimal complexity of the statistical model, thus avoiding under/over-fitting, a common pitfall in model selection problems. Our models are computationally inexpensive to sample from and are geared to support a number of downstream studies, ranging from experimental structure refinement, de novo protein design, and protein structure prediction. We call our collection of mixture models as PhiSiCal (ϕψχal). AVAILABILITY AND IMPLEMENTATION: PhiSiCal mixture models and programs to sample from them are available for download at http://lcb.infotech.monash.edu.au/phisical.

MOTIVATION: Extracellular particles (EPs) are the focus of a rapidly growing area of exploration due to the widespread interest in understanding their roles in health and disease. However, despite the general need for EP data sharing and established community standards for data reporting, no standard repository for EP flow cytometry data captures rigor and minimum reporting standards such as those defined by MIFlowCyt-EV (https://doi.org/10.1080/20013078.2020.1713526). We sought to address this unmet need by developing the NanoFlow Repository. RESULTS: We have developed The NanoFlow Repository to provide the first implementation of the MIFlowCyt-EV framework. AVAILABILITY AND IMPLEMENTATION: The NanoFlow Repository is freely available and accessible online at https://genboree.org/nano-ui/. Public datasets can be explored and downloaded at https://genboree.org/nano-ui/ld/datasets. The NanoFlow Repository's backend is built using the Genboree software stack that powers the ClinGen Resource, specifically the Linked Data Hub (LDH), a REST API framework written in Node.js, developed initially to aggregate data within ClinGen (https://ldh.clinicalgenome.org/ldh/ui/about). NanoFlow's LDH (NanoAPI) is available at https://genboree.org/nano-api/srvc. NanoAPI is supported by a Node.js Genboree authentication and authorization service (GbAuth), a graph database called ArangoDB, and an Apache Pulsar message queue (NanoMQ) to manage data inflows into NanoAPI. The website for NanoFlow Repository is built with Vue.js and Node.js (NanoUI) and supports all major browsers.

MOTIVATION: Codon usage preference patterns have been associated with modulation of translation efficiency, protein folding, and mRNA decay. However, new studies support that codon pair usage has also a remarkable effect at the gene expression level. Here, we expand the concept of CAI to answer if codon pair usage patterns can be understood in terms of codon usage bias, or if they offer new information regarding coding translation efficiency. RESULTS: Through the implementation of a weighting strategy to consider the dicodon contributions, we observe that the dicodon-based measure has greater correlations with gene expression level than CAI. Interestingly, we have noted that dicodons associated with a low value of adaptiveness are related to dicodons which mediate strong translational inhibition in yeast. We have also noticed that some codon-pairs have a smaller dicodon contribution than estimated by the product of the respective codon contributions. AVAILABILITY AND IMPLEMENTATION: Scripts, implemented in Python, are freely available for download at https://zenodo.org/record/7738276#.ZBIDBtLMIdU.

MOTIVATION: Nanopore sequencing is emerging as a key pillar in the genomic technology landscape but computational constraints limiting its scalability remain to be overcome. The translation of raw current signal data into DNA or RNA sequence reads, known as 'basecalling', is a major friction in any nanopore sequencing workflow. Here, we exploit the advantages of the recently developed signal data format 'SLOW5' to streamline and accelerate nanopore basecalling on high-performance computing (HPC) and cloud environments. RESULTS: SLOW5 permits highly efficient sequential data access, eliminating a potential analysis bottleneck. To take advantage of this, we introduce Buttery-eel, an open-source wrapper for Oxford Nanopore's Guppy basecaller that enables SLOW5 data access, resulting in performance improvements that are essential for scalable, affordable basecalling. AVAILABILITY AND IMPLEMENTATION: Buttery-eel is available at https://github.com/Psy-Fer/buttery-eel.

MOTIVATION: Imaging Spatial Transcriptomics techniques characterize gene expression in cells in their native context by imaging barcoded probes for mRNA with single molecule resolution. However, the need to acquire many rounds of high-magnification imaging data limits the throughput and impact of existing methods. RESULTS: We describe the Joint Sparse method for Imaging Transcriptomics, an algorithm for decoding lower magnification Imaging Spatial Transcriptomics data than that used in standard experimental workflows. Joint Sparse method for Imaging Transcriptomics incorporates codebook knowledge and sparsity assumptions into an optimization problem, which is less reliant on well separated optical signals than current pipelines. Using experimental data obtained by performing Multiplexed Error-Robust Fluorescence in situ Hybridization on tissue from mouse brain, we demonstrate that Joint Sparse method for Imaging Transcriptomics enables improved throughput and recovery performance over standard decoding methods. AVAILABILITY AND IMPLEMENTATION: Software implementation of JSIT, together with example files, is available at https://github.com/jpbryan13/JSIT.

MOTIVATION: Elementary flux modes are a well-known tool for analyzing metabolic networks. The whole set of elementary flux modes (EFMs) cannot be computed in most genome-scale networks due to their large cardinality. Therefore, different methods have been proposed to compute a smaller subset of EFMs that can be used for studying the structure of the network. These latter methods pose the problem of studying the representativeness of the calculated subset. In this article, we present a methodology to tackle this problem. RESULTS: We have introduced the concept of stability for a particular network parameter and its relation to the representativeness of the EFM extraction method studied. We have also defined several metrics to study and compare the EFM biases. We have applied these techniques to compare the relative behavior of previously proposed methods in two case studies. Furthermore, we have presented a new method for the EFM computation (PiEFM), which is more stable (less biased) than previous ones, has suitable representativeness measures, and exhibits better variability in the extracted EFMs. AVAILABILITY AND IMPLEMENTATION: Software and additional material are freely available at https://github.com/biogacop/PiEFM.

MOTIVATION: With the recent breakthroughs in sequencing technology, phylogeny estimation at a larger scale has become a huge opportunity. For accurate estimation of large-scale phylogeny, substantial endeavor is being devoted in introducing new algorithms or upgrading current approaches. In this work, we endeavor to improve the Quartet Fiduccia and Mattheyses (QFM) algorithm to resolve phylogenetic trees of better quality with better running time. QFM was already being appreciated by researchers for its good tree quality, but fell short in larger phylogenomic studies due to its excessively slow running time. RESULTS: We have re-designed QFM so that it can amalgamate millions of quartets over thousands of taxa into a species tree with a great level of accuracy within a short amount of time. Named "QFM Fast and Improved (QFM-FI)", our version is 20 000× faster than the previous version and 400× faster than the widely used variant of QFM implemented in PAUP* on larger datasets. We have also provided a theoretical analysis of the running time and memory requirements of QFM-FI. We have conducted a comparative study of QFM-FI with other state-of-the-art phylogeny reconstruction methods, such as QFM, QMC, wQMC, wQFM, and ASTRAL, on simulated as well as real biological datasets. Our results show that QFM-FI improves on the running time and tree quality of QFM and produces trees that are comparable with state-of-the-art methods. AVAILABILITY AND IMPLEMENTATION: QFM-FI is open source and available at https://github.com/sharmin-mim/qfm_java.

SUMMARY: I present here the R/Bioconductor package BRGenomics, which provides fast and flexible methods for post-alignment processing and analysis of high-resolution genomics data within an interactive R environment. Utilizing GenomicRanges and other core Bioconductor packages, BRGenomics provides various methods for data importation and processing, read counting and aggregation, spike-in and batch normalization, re-sampling methods for robust 'metagene' analyses, and various other functions for cleaning and modifying sequencing and annotation data. Simple yet flexible, the included methods are optimized for handling multiple datasets simultaneously, make extensive use of parallel processing, and support multiple strategies for efficiently storing and quantifying different kinds of data, including whole reads, quantitative single-base data, and run-length encoded coverage information. BRGenomics has been used to analyze ATAC-seq, ChIP-seq/ChIP-exo, PRO-seq/PRO-cap, and RNA-seq data; is built to be unobtrusive and maximally compatible with the Bioconductor ecosystem; is extensively tested; and includes complete documentation, examples, and tutorials. AVAILABILITY AND IMPLEMENTATION: BRGenomics is an R package distributed through Bioconductor (https://bioconductor.org/packages/BRGenomics). Full documentation with examples and tutorials are available online (https://mdeber.github.io).

SUMMARY: Biological data repositories are an invaluable source of publicly available research evidence. Unfortunately, the lack of convergence of the scientific community on a common metadata annotation strategy has resulted in large amounts of data with low FAIRness (Findable, Accessible, Interoperable and Reusable). The possibility of generating high-quality insights from their integration relies on data curation, which is typically an error-prone process while also being expensive in terms of time and human labour. Here, we present ESPERANTO, an innovative framework that enables a standardized semi-supervised harmonization and integration of toxicogenomics metadata and increases their FAIRness in a Good Laboratory Practice-compliant fashion. The harmonization across metadata is guaranteed with the definition of an ad hoc vocabulary. The tool interface is designed to support the user in metadata harmonization in a user-friendly manner, regardless of the background and the type of expertise. AVAILABILITY AND IMPLEMENTATION: ESPERANTO and its user manual are freely available for academic purposes at https://github.com/fhaive/esperanto. The input and the results showcased in Supplementary File S1 are available at the same link.

SUMMARY: Adaptive Immune Receptor Repertoire Sequencing is a rapidly developing field that has advanced understanding of the role of the adaptive immune system in health and disease. Numerous tools have been developed to analyse the complex data produced by this technique but work to compare their accuracy and reliability has been limited. Thorough, systematic assessment of their performance is dependent on the ability to produce high quality simulated datasets with known ground truth. We have developed AIRRSHIP, a flexible and fast Python package that produces synthetic human B cell receptor sequences. AIRRSHIP uses a comprehensive set of reference data to replicate key mechanisms in the immunoglobulin recombination process, with a particular focus on junctional complexity. Repertoires generated by AIRRSHIP are highly similar to published data and all steps in the sequence generation process are recorded. These data can be used to not only determine the accuracy of repertoire analysis tools but can also, by tuning of the large number of user-controllable parameters, give insight into factors that contribute to inaccuracies in results. AVAILABILITY AND IMPLEMENTATION: AIRRSHIP is implemented in Python. It is available via https://github.com/Cowanlab/airrship and on PyPI at https://pypi.org/project/airrship/. Documentation can be found at https://airrship.readthedocs.io/.

SUMMARY: Generate Indexes for Libraries (GIL) is a software tool for generating primers to be used in the production of multiplexed sequencing libraries. GIL can be customized in numerous ways to meet user specifications, including length, sequencing modality, color balancing, and compatibility with existing primers, and produces ordering and demultiplexing-ready outputs. AVAILABILITY AND IMPLEMENTATION: GIL is written in Python and is freely available on GitHub under the MIT license: https://github.com/de-Boer-Lab/GIL and can be accessed as a web-application implemented in Streamlit at https://dbl-gil.streamlitapp.com.

MOTIVATION: The generation of parameter files for molecular dynamics (MD) simulations of small molecules that are suitable for force fields commonly applied to proteins and nucleic acids is often challenging. The ACPYPE software and website aid the generation of such parameter files. RESULTS: ACPYPE uses OpenBabel and ANTECHAMBER to generate MD input files in Gromacs, AMBER, CHARMM, and CNS formats. It can now take a SMILES string as input, in addition to the original PDB or mol2 coordinate files, with GAFF2 support and GLYCAM force field conversion added. It can be installed locally via Anaconda, PyPI, and Docker distributions, while the web server at https://bio2byte.be/acpype/ was updated with an API, and provides visualization of results for uploaded molecules as well as a pre-generated set of 3738 drug molecules. AVAILABILITY AND IMPLEMENTATION: The web application is freely available at https://www.bio2byte.be/acpype/ and the open-source code can be found at https://github.com/alanwilter/acpype.

SUMMARY: We present pygenomics, a Python package for working with genomic intervals and bioinformatic data files. The package implements interval operations, provides both API and CLI, and supports reading and writing data in widely used bioinformatic formats, including BAM, BED, GFF3, and VCF. The source code of pygenomics is provided with in-source documentation and type annotations and adheres to the functional programming paradigm. These features facilitate seamless integration of pygenomics routines into scripts and pipelines. The package is implemented in pure Python using its standard library only and contains the property-based testing framework. Comparison of pygenomics with other Python bioinformatic packages with relation to features and performance is presented. The performance comparison covers operations with genomic intervals, read alignments, and genomic variants and demonstrates that pygenomics is suitable for computationally effective analysis. AVAILABILITY AND IMPLEMENTATION: The source code is available at https://gitlab.com/gtamazian/pygenomics.

MOTIVATION: The recognition of mentions of species names in text is a critically important task for biomedical text mining. While deep learning-based methods have made great advances in many named entity recognition tasks, results for species name recognition remain poor. We hypothesize that this is primarily due to the lack of appropriate corpora. RESULTS: We introduce the S1000 corpus, a comprehensive manual re-annotation and extension of the S800 corpus. We demonstrate that S1000 makes highly accurate recognition of species names possible (F-score =93.1%), both for deep learning and dictionary-based methods. AVAILABILITY AND IMPLEMENTATION: All resources introduced in this study are available under open licenses from https://jensenlab.org/resources/s1000/. The webpage contains links to a Zenodo project and three GitHub repositories associated with the study.

MOTIVATION: While the search for associations between genetic markers and complex traits has led to the discovery of tens of thousands of trait-related genetic variants, the vast majority of these only explain a small fraction of the observed phenotypic variation. One possible strategy to overcome this while leveraging biological prior is to aggregate the effects of several genetic markers and to test entire genes, pathways or (sub)networks of genes for association to a phenotype. The latter, network-based genome-wide association studies, in particular suffer from a vast search space and an inherent multiple testing problem. As a consequence, current approaches are either based on greedy feature selection, thereby risking that they miss relevant associations, or neglect doing a multiple testing correction, which can lead to an abundance of false positive findings. RESULTS: To address the shortcomings of current approaches of network-based genome-wide association studies, we propose networkGWAS, a computationally efficient and statistically sound approach to network-based genome-wide association studies using mixed models and neighborhood aggregation. It allows for population structure correction and for well-calibrated P-values, which are obtained through circular and degree-preserving network permutations. networkGWAS successfully detects known associations on diverse synthetic phenotypes, as well as known and novel genes in phenotypes from Saccharomycescerevisiae and Homo sapiens. It thereby enables the systematic combination of gene-based genome-wide association studies with biological network information. AVAILABILITY AND IMPLEMENTATION: https://github.com/BorgwardtLab/networkGWAS.git.

MOTIVATION: The shape of a cell is tightly controlled, and reflects important processes including actomyosin activity, adhesion properties, cell differentiation, and polarization. Hence, it is informative to link cell shape to genetic and other perturbations. However, most currently used cell shape descriptors capture only simple geometric features such as volume and sphericity. We propose FlowShape, a new framework to study cell shapes in a complete and generic way. RESULTS: In our framework a cell shape is represented by measuring the curvature of the shape and mapping it onto a sphere in a conformal manner. This single function on the sphere is next approximated by a series expansion: the spherical harmonics decomposition. The decomposition facilitates many analyses, including shape alignment and statistical cell shape comparison. The new tool is applied to perform a complete, generic analysis of cell shapes, using the early Caenorhabditis elegans embryo as a model case. We distinguish and characterize the cells at the seven-cell stage. Next, a filter is designed to identify protrusions on the cell shape to highlight lamellipodia in cells. Further, the framework is used to identify any shape changes following a gene knockdown of the Wnt pathway. Cells are first optimally aligned using the fast Fourier transform, followed by calculating an average shape. Shape differences between conditions are next quantified and compared to an empirical distribution. Finally, we put forward a highly performant implementation of the core algorithm, as well as routines to characterize, align and compare cell shapes, through the open-source software package FlowShape. AVAILABILITY AND IMPLEMENTATION: The data and code needed to recreate the results are freely available at https://doi.org/10.5281/zenodo.7778752. The most recent version of the software is maintained at https://bitbucket.org/pgmsembryogenesis/flowshape/.

MOTIVATION: Short tandem repeats (STRs) are regions of a genome containing many consecutive copies of the same short motif, possibly with small variations. Analysis of STRs has many clinical uses but is limited by technology mainly due to STRs surpassing the used read length. Nanopore sequencing, as one of long-read sequencing technologies, produces very long reads, thus offering more possibilities to study and analyze STRs. Basecalling of nanopore reads is however particularly unreliable in repeating regions, and therefore direct analysis from raw nanopore data is required. RESULTS: Here, we present WarpSTR, a novel method for characterizing both simple and complex tandem repeats directly from raw nanopore signals using a finite-state automaton and a search algorithm analogous to dynamic time warping. By applying this approach to determine the lengths of 241 STRs, we demonstrate that our approach decreases the mean absolute error of the STR length estimate compared to basecalling and STRique. AVAILABILITY AND IMPLEMENTATION: WarpSTR is freely available at https://github.com/fmfi-compbio/warpstr.

MOTIVATION: Single-cell multiomics technologies are emerging to characterize different molecular features of cells. This gives rise to an issue of combining various kinds of molecular features to dissect cell heterogeneity. Most single-cell multiomics integration methods focus on shared information among modalities while complementary information specific to each modality is often discarded. RESULTS: To disentangle and combine shared and complementary information across modalities, we develop a dual-modality factor model named scME by using deep factor modeling. Our results demonstrate that scME can generate a better joint representation of multiple modalities than those generated by other single-cell multiomics integration algorithms, which gives a clear elucidation of nuanced differences among cells. We also demonstrate that the joint representation of multiple modalities yielded by scME can provide salient information to improve both single-cell clustering and cell-type classification. Overall, scME will be an efficient method for combining various kinds of molecular features to facilitate the dissection of cell heterogeneity. AVAILABILITY AND IMPLEMENTATION: The code is public for academic use and available on the GitHub site (https://github.com/bucky527/scME).

MOTIVATION: DNA CpG methylation (CpGm) has proven to be a crucial epigenetic factor in the mammalian gene regulatory system. Assessment of DNA CpG methylation values via whole-genome bisulfite sequencing (WGBS) is, however, computationally extremely demanding. RESULTS: We present FAst MEthylation calling (FAME), the first approach to quantify CpGm values directly from bulk or single-cell WGBS reads without intermediate output files. FAME is very fast but as accurate as standard methods, which first produce BS alignment files before computing CpGm values. We present experiments on bulk and single-cell bisulfite datasets in which we show that data analysis can be significantly sped-up and help addressing the current WGBS analysis bottleneck for large-scale datasets without compromising accuracy. AVAILABILITY AND IMPLEMENTATION: An implementation of FAME is open source and licensed under GPL-3.0 at https://github.com/FischerJo/FAME.

MOTIVATION: Long-read transcriptome sequencing (LRTS) has the potential to enhance our understanding of alternative splicing and the complexity of this process requires the use of versatile computational tools, with the ability to accommodate various stages of the workflow with maximum flexibility. RESULTS: We introduce IsoTools, a Python-based LRTS analysis framework that offers a wide range of functionality for transcriptome reconstruction and quantification of transcripts. Furthermore, we integrate a graph-based method for identifying alternative splicing events and a statistical approach based on the beta-binomial distribution for detecting differential events. To demonstrate the effectiveness of our methods, we applied IsoTools to PacBio LRTS data of human hepatocytes treated with the histone deacetylase inhibitor valproic acid. Our results indicate that LRTS can provide valuable insights into alternative splicing, particularly in terms of complex and differential splicing patterns, in comparison to short-read RNA-seq. AVAILABILITY AND IMPLEMENTATION: IsoTools is available on GitHub and PyPI, and its documentation, including tutorials, CLI, and API references, can be found at https://isotools.readthedocs.io/.

MOTIVATION: The prediction of reliable Drug-Target Interactions (DTIs) is a key task in computer-aided drug design and repurposing. Here, we present a new approach based on data fusion for DTI prediction built on top of the NXTfusion library, which generalizes the Matrix Factorization paradigm by extending it to the nonlinear inference over Entity-Relation graphs. RESULTS: We benchmarked our approach on five datasets and we compared our models against state-of-the-art methods. Our models outperform most of the existing methods and, simultaneously, retain the flexibility to predict both DTIs as binary classification and regression of the real-valued drug-target affinity, competing with models built explicitly for each task. Moreover, our findings suggest that the validation of DTI methods should be stricter than what has been proposed in some previous studies, focusing more on mimicking real-life DTI settings where predictions for previously unseen drugs, proteins, and drug-protein pairs are needed. These settings are exactly the context in which the benefit of integrating heterogeneous information with our Entity-Relation data fusion approach is the most evident. AVAILABILITY AND IMPLEMENTATION: All software and data are available at https://github.com/eugeniomazzone/CPI-NXTFusion and https://pypi.org/project/NXTfusion/.

MOTIVATION: Single-cell RNA sequencing enables researchers to study cellular heterogeneity at single-cell level. To this end, identifying cell types of cells with clustering techniques becomes an important task for downstream analysis. However, challenges of scRNA-seq data such as pervasive dropout phenomena hinder obtaining robust clustering outputs. Although existing studies try to alleviate these problems, they fall short of fully leveraging the relationship information and mainly rely on reconstruction-based losses that highly depend on the data quality, which is sometimes noisy. RESULTS: This work proposes a graph-based prototypical contrastive learning method, named scGPCL. Specifically, scGPCL encodes the cell representations using Graph Neural Networks on cell-gene graph that captures the relational information inherent in scRNA-seq data and introduces prototypical contrastive learning to learn cell representations by pushing apart semantically dissimilar pairs and pulling together similar ones. Through extensive experiments on both simulated and real scRNA-seq data, we demonstrate the effectiveness and efficiency of scGPCL. AVAILABILITY AND IMPLEMENTATION: Code is available at https://github.com/Junseok0207/scGPCL.

MOTIVATION: Transcriptional profiles of diverse tissues provide significant insights in both fundamental and translational researches, while transcriptome information is not always available for tissues that require invasive biopsies. Alternatively, predicting tissue expression profiles from more accessible "surrogate" samples, especially blood transcriptome, has become a promising strategy when invasive procedures are not practical. However, existing approaches ignore tissue-shared intrinsic relevance, inevitably limiting predictive performance. RESULTS: We propose a unified deep learning-based multi-task learning framework, multi-tissue transcriptome mapping (MTM), enabling the prediction of individualized expression profiles from any available tissue of an individual. By jointly leveraging individualized cross-tissue information from reference samples through multi-task learning, MTM achieves superior sample-level and gene-level performance on unseen individuals. With the high prediction accuracy and the ability to preserve individualized biological variations, MTM could facilitate both fundamental and clinical biomedical research. AVAILABILITY AND IMPLEMENTATION: MTM's code and documentation are available upon publication on GitHub (https://github.com/yangence/MTM).

SUMMARY: mpwR is an R package for a standardized comparison of mass spectrometry (MS)-based proteomic label-free workflows recorded by data-dependent or data-independent spectral acquisition. The user-friendly design allows easy access to compare the influence of sample preparation procedures, combinations of liquid chromatography (LC)-MS setups, as well as intra- and inter-software differences on critical performance measures across an unlimited number of analyses. mpwR supports outputs of commonly used software for bottom-up proteomics, such as ProteomeDiscoverer, Spectronaut, MaxQuant, and DIA-NN. AVAILABILITY AND IMPLEMENTATION: mpwR is available as an open-source R package. Release versions can be accessed on CRAN (https://CRAN.R-project.org/package=mpwR) for all major operating systems. The development version is maintained on GitHub (https://github.com/okdll/mpwR) and full documentation with examples and workflow templates is provided via the package website (https://okdll.github.io/mpwR/).

SUMMARY: The RaggedExperiment R / Bioconductor package provides lossless representation of disparate genomic ranges across multiple specimens or cells, in conjunction with efficient and flexible calculations of rectangular-shaped summaries for downstream analysis. Applications include statistical analysis of somatic mutations, copy number, methylation, and open chromatin data. RaggedExperiment is compatible with multimodal data analysis as a component of MultiAssayExperiment data objects, and simplifies data representation and transformation for software developers and analysts. MOTIVATION AND RESULTS: Measurement of copy number, mutation, single nucleotide polymorphism, and other genomic attributes that may be stored as VCF files produce "ragged" genomic ranges data: i.e. across different genomic coordinates in each sample. Ragged data are not rectangular or matrix-like, presenting informatics challenges for downstream statistical analyses. We present the RaggedExperiment R/Bioconductor data structure for lossless representation of ragged genomic data, with associated reshaping tools for flexible and efficient calculation of tabular representations to support a wide range of downstream statistical analyses. We demonstrate its applicability to copy number and somatic mutation data across 33 TCGA cancer datasets.

MOTIVATION: Variational autoencoders (VAEs) have rapidly increased in popularity in biological applications and have already successfully been used on many omic datasets. Their latent space provides a low-dimensional representation of input data, and VAEs have been applied, e.g. for clustering of single-cell transcriptomic data. However, due to their non-linear nature, the patterns that VAEs learn in the latent space remain obscure. Hence, the lower-dimensional data embedding cannot directly be related to input features. RESULTS: To shed light on the inner workings of VAE and enable direct interpretability of the model through its structure, we designed a novel VAE, OntoVAE (Ontology guided VAE) that can incorporate any ontology in its latent space and decoder part and, thus, provide pathway or phenotype activities for the ontology terms. In this work, we demonstrate that OntoVAE can be applied in the context of predictive modeling and show its ability to predict the effects of genetic or drug-induced perturbations using different ontologies and both, bulk and single-cell transcriptomic datasets. Finally, we provide a flexible framework, which can be easily adapted to any ontology and dataset. AVAILABILITY AND IMPLEMENTATION: OntoVAE is available as a python package under https://github.com/hdsu-bioquant/onto-vae.

SUMMARY: The UNited RESisdue (UNRES) package for coarse-grained simulations, which has recently been optimized to treat large protein systems, has been implemented on Graphical Processor Units (GPUs). An over 100-time speed-up of the GPU code (run on an NVIDIA A100) with respect to the sequential code and an 8.5 speed-up with respect to the parallel Open Multi-Processing (OpenMP) code (run on 32 cores of 2 AMD EPYC 7313 Central Processor Units (CPUs)) has been achieved for large proteins (with size over 10 000 residues). Due to the averaging over the fine-grain degrees of freedom, 1 time unit of UNRES simulations is equivalent to about 1000 time units of laboratory time; therefore, millisecond time scale of large protein systems can be reached with the UNRES-GPU code. AVAILABILITY AND IMPLEMENTATION: The source code of UNRES-GPU along with the benchmarks used for tests is available at https://projects.task.gda.pl/eurohpcpl-public/unres.

SUMMARY: Mapping genetic interactions and essentiality networks in human cell lines has been used to identify vulnerabilities of cells carrying specific genetic alterations and to associate novel functions to genes, respectively. In vitro and in vivo genetic screens to decipher these networks are resource-intensive, limiting the throughput of samples that can be analyzed. In this application note, we provide an R package we call Genetic inteRaction and EssenTiality neTwork mApper (GRETTA). GRETTA is an accessible tool for in silico genetic interaction screens and essentiality network analyses using publicly available data, requiring only basic R programming knowledge. AVAILABILITY AND IMPLEMENTATION: The R package, GRETTA, is licensed under GNU General Public License v3.0 and freely available at https://github.com/ytakemon/GRETTA and https://doi.org/10.5281/zenodo.6940757, with documentation and tutorial. A Singularity container is also available at https://cloud.sylabs.io/library/ytakemon/gretta/gretta.

MOTIVATION: Replicability is the cornerstone of scientific research. The current statistical method for high-dimensional replicability analysis either cannot control the false discovery rate (FDR) or is too conservative. RESULTS: We propose a statistical method, JUMP, for the high-dimensional replicability analysis of two studies. The input is a high-dimensional paired sequence of p-values from two studies and the test statistic is the maximum of p-values of the pair. JUMP uses four states of the p-value pairs to indicate whether they are null or non-null. Conditional on the hidden states, JUMP computes the cumulative distribution function of the maximum of p-values for each state to conservatively approximate the probability of rejection under the composite null of replicability. JUMP estimates unknown parameters and uses a step-up procedure to control FDR. By incorporating different states of composite null, JUMP achieves a substantial power gain over existing methods while controlling the FDR. Analyzing two pairs of spatially resolved transcriptomic datasets, JUMP makes biological discoveries that otherwise cannot be obtained by using existing methods. AVAILABILITY AND IMPLEMENTATION: An R package JUMP implementing the JUMP method is available on CRAN (https://CRAN.R-project.org/package=JUMP).

SUMMARY: Multimodal single-cell sequencing data provide detailed views into the molecular biology of cells. To allow for interactive analyses of such rich data and to readily derive insights from it, new analysis solutions are required. In this work, we present Cellenium, our new scalable visual analytics web application that enables users to semantically integrate and organize all their single-cell RNA-, ATAC-, and CITE-sequencing studies. Users can then find relevant studies and analyze single-cell data within and across studies. An interactive cell annotation feature allows for adding user-defined cell types. AVAILABILITY AND IMPLEMENTATION: Source code and documentation are freely available under an MIT license and are available on GitHub (https://github.com/Bayer-Group/cellenium). The server backend is implemented in PostgreSQL, Python 3, and GraphQL, the frontend is written in ReactJS, TypeScript, and Mantine css, and plots are generated using plotlyjs, seaborn, vega-lite, and nivo.rocks. The application is dockerized and can be deployed and orchestrated on a standard workstation via docker-compose.

MOTIVATION: Spatial transcriptomics (ST) can reveal the existence and extent of spatial variation of gene expression in complex tissues. Such analyses could help identify spatially localized processes underlying a tissue's function. Existing tools to detect spatially variable genes assume a constant noise variance across spatial locations. This assumption might miss important biological signals when the variance can change across locations. RESULTS: In this article, we propose NoVaTeST, a framework to identify genes with location-dependent noise variance in ST data. NoVaTeST models gene expression as a function of spatial location and allows the noise to vary spatially. NoVaTeST then statistically compares this model to one with constant noise and detects genes showing significant spatial noise variation. We refer to these genes as "noisy genes." In tumor samples, the noisy genes detected by NoVaTeST are largely independent of the spatially variable genes detected by existing tools that assume constant noise, and provide important biological insights into tumor microenvironments. AVAILABILITY AND IMPLEMENTATION: An implementation of the NoVaTeST framework in Python along with instructions for running the pipeline is available at https://github.com/abidabrar-bracu/NoVaTeST.

MOTIVATION: An imperative step in drug discovery is the prediction of drug-disease associations (DDAs), which tries to uncover potential therapeutic possibilities for already validated drugs. It is costly and time-consuming to predict DDAs using wet experiments. Graph Neural Networks as an emerging technique have shown superior capacity of dealing with DDA prediction. However, existing Graph Neural Networks-based DDA prediction methods suffer from sparse supervised signals. As graph contrastive learning has shined in mitigating sparse supervised signals, we seek to leverage graph contrastive learning to enhance the prediction of DDAs. Unfortunately, most conventional graph contrastive learning-based models corrupt the raw data graph to augment data, which are unsuitable for DDA prediction. Meanwhile, these methods could not model the interactions between nodes effectively, thereby reducing the accuracy of association predictions. RESULTS: A model is proposed to tap potential drug candidates for diseases, which is called Similarity Measures-based Graph Co-contrastive Learning (SMGCL). For learning embeddings from complicated network topologies, SMGCL includes three essential processes: (i) constructs three views based on similarities between drugs and diseases and DDA information; (ii) two graph encoders are performed over the three views, so as to model both local and global topologies simultaneously; and (iii) a graph co-contrastive learning method is introduced, which co-trains the representations of nodes to maximize the agreement between them, thus generating high-quality prediction results. Contrastive learning serves as an auxiliary task for improving DDA predictions. Evaluated by cross-validations, SMGCL achieves pleasing comprehensive performances. Further proof of the SMGCL's practicality is provided by case study of Alzheimer's disease. AVAILABILITY AND IMPLEMENTATION: https://github.com/Jcmorz/SMGCL.

MOTIVATION: With the exponential growth of expression and protein-protein interaction (PPI) data, the identification of functional modules in PPI networks that show striking changes in molecular activity or phenotypic signatures becomes of particular interest to reveal process-specific information that is correlated with cellular or disease states. This requires both the identification of network nodes with reliability scores and the availability of an efficient technique to locate the network regions with the highest scores. In the literature, a number of heuristic methods have been suggested. We propose SEMtree(), a set of tree-based structure discovery algorithms, combining graph and statistically interpretable parameters together with a user-friendly R package based on structural equation models framework. RESULTS: Condition-specific changes from differential expression and gene-gene co-expression are recovered with statistical testing of node, directed edge, and directed path difference between groups. In the end, from a list of seed (i.e. disease) genes or gene P-values, the perturbed modules with undirected edges are generated with five state-of-the-art active subnetwork detection methods. The latter are supplied to causal additive trees based on Chu-Liu-Edmonds' algorithm (Chow and Liu, Approximating discrete probability distributions with dependence trees. IEEE Trans Inform Theory 1968;14:462-7) in SEMtree() to be converted in directed trees. This conversion allows to compare the methods in terms of directed active subnetworks. We applied SEMtree() to both Coronavirus disease (COVID-19) RNA-seq dataset (GEO accession: GSE172114) and simulated datasets with various differential expression patterns. Compared to existing methods, SEMtree() is able to capture biologically relevant subnetworks with simple visualization of directed paths, good perturbation extraction, and classifier performance. AVAILABILITY AND IMPLEMENTATION: SEMtree() function is implemented in the R package SEMgraph, easily available at https://CRAN.R-project.org/package=SEMgraph.

MOTIVATION: Motifs play a crucial role in computational biology, as they provide valuable information about the binding specificity of proteins. However, conventional motif discovery methods typically rely on simple combinatoric or probabilistic approaches, which can be biased by heuristics such as substring-masking for multiple motif discovery. In recent years, deep neural networks have become increasingly popular for motif discovery, as they are capable of capturing complex patterns in data. Nonetheless, inferring motifs from neural networks remains a challenging problem, both from a modeling and computational standpoint, despite the success of these networks in supervised learning tasks. RESULTS: We present a principled representation learning approach based on a hierarchical sparse representation for motif discovery. Our method effectively discovers gapped, long, or overlapping motifs that we show to commonly exist in next-generation sequencing datasets, in addition to the short and enriched primary binding sites. Our model is fully interpretable, fast, and capable of capturing motifs in a large number of DNA strings. A key concept emerged from our approach-enumerating at the image level-effectively overcomes the k-mers paradigm, enabling modest computational resources for capturing the long and varied but conserved patterns, in addition to capturing the primary binding sites. AVAILABILITY AND IMPLEMENTATION: Our method is available as a Julia package under the MIT license at https://github.com/kchu25/MOTIFs.jl, and the results on experimental data can be found at https://zenodo.org/record/7783033.

MOTIVATION: Mathematical models of biological processes altered in cancer are built using the knowledge of complex networks of signaling pathways, detailing the molecular regulations inside different cell types, such as tumor cells, immune and other stromal cells. If these models mainly focus on intracellular information, they often omit a description of the spatial organization among cells and their interactions, and with the tumoral microenvironment. RESULTS: We present here a model of tumor cell invasion simulated with PhysiBoSS, a multiscale framework, which combines agent-based modeling and continuous time Markov processes applied on Boolean network models. With this model, we aim to study the different modes of cell migration and to predict means to block it by considering not only spatial information obtained from the agent-based simulation but also intracellular regulation obtained from the Boolean model. Our multiscale model integrates the impact of gene mutations with the perturbation of the environmental conditions and allows the visualization of the results with 2D and 3D representations. The model successfully reproduces single and collective migration processes and is validated on published experiments on cell invasion. In silico experiments are suggested to search for possible targets that can block the more invasive tumoral phenotypes. AVAILABILITY AND IMPLEMENTATION: https://github.com/sysbio-curie/Invasion_model_PhysiBoSS.

MOTIVATION: Tandem mass spectrometry is an essential technology for characterizing chemical compounds at high sensitivity and throughput, and is commonly adopted in many fields. However, computational methods for automated compound identification from their MS/MS spectra are still limited, especially for novel compounds that have not been previously characterized. In recent years, in silico methods were proposed to predict the MS/MS spectra of compounds, which can then be used to expand the reference spectral libraries for compound identification. However, these methods did not consider the compounds' 3D conformations, and thus neglected critical structural information. RESULTS: We present the 3D Molecular Network for Mass Spectra Prediction (3DMolMS), a deep neural network model to predict the MS/MS spectra of compounds from their 3D conformations. We evaluated the model on the experimental spectra collected in several spectral libraries. The results showed that 3DMolMS predicted the spectra with the average cosine similarity of 0.691 and 0.478 with the experimental MS/MS spectra acquired in positive and negative ion modes, respectively. Furthermore, 3DMolMS model can be generalized to the prediction of MS/MS spectra acquired by different labs on different instruments through minor fine-tuning on a small set of spectra. Finally, we demonstrate that the molecular representation learned by 3DMolMS from MS/MS spectra prediction can be adapted to enhance the prediction of chemical properties such as the elution time in the liquid chromatography and the collisional cross section measured by ion mobility spectrometry, both of which are often used to improve compound identification. AVAILABILITY AND IMPLEMENTATION: The codes of 3DMolMS are available at https://github.com/JosieHong/3DMolMS and the web service is at https://spectrumprediction.gnps2.org.

MOTIVATION: Computational approaches for identifying the protein-ligand binding affinity can greatly facilitate drug discovery and development. At present, many deep learning-based models are proposed to predict the protein-ligand binding affinity and achieve significant performance improvement. However, protein-ligand binding affinity prediction still has fundamental challenges. One challenge is that the mutual information between proteins and ligands is hard to capture. Another challenge is how to find and highlight the important atoms of the ligands and residues of the proteins. RESULTS: To solve these limitations, we develop a novel graph neural network strategy with the Vina distance optimization terms (GraphscoreDTA) for predicting protein-ligand binding affinity, which takes the combination of graph neural network, bitransport information mechanism and physics-based distance terms into account for the first time. Unlike other methods, GraphscoreDTA can not only effectively capture the protein-ligand pairs' mutual information but also highlight the important atoms of the ligands and residues of the proteins. The results show that GraphscoreDTA significantly outperforms existing methods on multiple test sets. Furthermore, the tests of drug-target selectivity on the cyclin-dependent kinase and the homologous protein families demonstrate that GraphscoreDTA is a reliable tool for protein-ligand binding affinity prediction. AVAILABILITY AND IMPLEMENTATION: The resource codes are available at https://github.com/CSUBioGroup/GraphscoreDTA.

MOTIVATION: Due to the rapid growth of the genetic database size, genealogical search, a process of inferring familial relatedness by identifying DNA matches, has become a viable approach to help individuals finding missing family members or law enforcement agencies locating suspects. A fast and accurate method is needed to search an out-of-database individual against millions of individuals. Most existing approaches only offer all-versus-all within panel match. Some prototype algorithms offer one-versus-all query from out-of-panel individual, but they do not tolerate errors. RESULTS: A new method, random projection-based identity-by-descent (IBD) detection (RaPID) query, is introduced to make fast genealogical search possible. RaPID-Query identifies IBD segments between a query haplotype and a panel of haplotypes. By integrating matches over multiple PBWT indexes, RaPID-Query manages to locate IBD segments quickly with a given cutoff length while allowing mismatched sites. A single query against all UK biobank autosomal chromosomes was completed within 2.76 seconds on average, with the minimum length 7 cM and 700 markers. RaPID-Query achieved a 0.016 false negative rate and a 0.012 false positive rate simultaneously on a chromosome 20 sequencing panel having 86 265 sites. This is comparable to the state-of-the-art IBD detection method TPBWT(out-of-sample) and Hap-IBD. The high-quality IBD segments yielded by RaPID-Query were able to distinguish up to fourth degree of the familial relatedness for a given individual pair, and the area under the receiver operating characteristic curve values are at least 97.28%. AVAILABILITY AND IMPLEMENTATION: The RaPID-Query program is available at https://github.com/ucfcbb/RaPID-Query.

MOTIVATION: With the great number of peptide sequences produced in the postgenomic era, it is highly desirable to identify the various functions of therapeutic peptides quickly. Furthermore, it is a great challenge to predict accurate multi-functional therapeutic peptides (MFTP) via sequence-based computational tools. RESULTS: Here, we propose a novel multi-label-based method, named ETFC, to predict 21 categories of therapeutic peptides. The method utilizes a deep learning-based model architecture, which consists of four blocks: embedding, text convolutional neural network, feed-forward network, and classification blocks. This method also adopts an imbalanced learning strategy with a novel multi-label focal dice loss function. multi-label focal dice loss is applied in the ETFC method to solve the inherent imbalance problem in the multi-label dataset and achieve competitive performance. The experimental results state that the ETFC method is significantly better than the existing methods for MFTP prediction. With the established framework, we use the teacher-student-based knowledge distillation to obtain the attention weight from the self-attention mechanism in the MFTP prediction and quantify their contributions toward each of the investigated activities. AVAILABILITY AND IMPLEMENTATION: The source code and dataset are available via: https://github.com/xialab-ahu/ETFC.

MOTIVATION: Gene network reconstruction from gene expression profiles is a compute- and data-intensive problem. Numerous methods based on diverse approaches including mutual information, random forests, Bayesian networks, correlation measures, as well as their transforms and filters such as data processing inequality, have been proposed. However, an effective gene network reconstruction method that performs well in all three aspects of computational efficiency, data size scalability, and output quality remains elusive. Simple techniques such as Pearson correlation are fast to compute but ignore indirect interactions, while more robust methods such as Bayesian networks are prohibitively time consuming to apply to tens of thousands of genes. RESULTS: We developed maximum capacity path (MCP) score, a novel maximum-capacity-path-based metric to quantify the relative strengths of direct and indirect gene-gene interactions. We further present MCPNet, an efficient, parallelized gene network reconstruction software based on MCP score, to reverse engineer networks in unsupervised and ensemble manners. Using synthetic and real Saccharomyces cervisiae datasets as well as real Arabidopsis thaliana datasets, we demonstrate that MCPNet produces better quality networks as measured by AUPRC, is significantly faster than all other gene network reconstruction software, and also scales well to tens of thousands of genes and hundreds of CPU cores. Thus, MCPNet represents a new gene network reconstruction tool that simultaneously achieves quality, performance, and scalability requirements. AVAILABILITY AND IMPLEMENTATION: Source code freely available for download at https://doi.org/10.5281/zenodo.6499747 and https://github.com/AluruLab/MCPNet, implemented in C++ and supported on Linux.

MOTIVATION: Cancer is a molecular complex and heterogeneous disease. Each type of cancer is usually composed of several subtypes with different treatment responses and clinical outcomes. Therefore, subtyping is a crucial step in cancer diagnosis and therapy. The rapid advances in high-throughput sequencing technologies provide an increasing amount of multi-omics data, which benefits our understanding of cancer genetic architecture, and yet poses new challenges in multi-omics data integration. RESULTS: We propose a graph convolutional network model, called MRGCN for multi-omics data integrative representation. MRGCN simultaneously encodes and reconstructs multiple omics expression and similarity relationships into a shared latent embedding space. In addition, MRGCN adopts an indicator matrix to denote the situation of missing values in partial omics, so that the full and partial multi-omics processing procedures are combined in a unified framework. Experimental results on 11 multi-omics datasets show that cancer subtypes obtained by MRGCN with superior enriched clinical parameters and log-rank test P-values in survival analysis over many typical integrative methods. AVAILABILITY AND IMPLEMENTATION: https://github.com/Polytech-bioinf/MRGCN.git https://figshare.com/articles/software/MRGCN/23058503.

MOTIVATION: Transcriptomic data can be used to describe the mechanism of action (MOA) of a chemical compound. However, omics data tend to be complex and prone to noise, making the comparison of different datasets challenging. Often, transcriptomic profiles are compared at the level of individual gene expression values, or sets of differentially expressed genes. Such approaches can suffer from underlying technical and biological variance, such as the biological system exposed on or the machine/method used to measure gene expression data, technical errors and further neglect the relationships between the genes. We propose a network mapping approach for knowledge-driven comparison of transcriptomic profiles (KNeMAP), which combines genes into similarity groups based on multiple levels of prior information, hence adding a higher-level view onto the individual gene view. When comparing KNeMAP with fold change (expression) based and deregulated gene set-based methods, KNeMAP was able to group compounds with higher accuracy with respect to prior information as well as is less prone to noise corrupted data. RESULT: We applied KNeMAP to analyze the Connectivity Map dataset, where the gene expression changes of three cell lines were analyzed after treatment with 676 drugs as well as the Fortino et al. dataset where two cell lines with 31 nanomaterials were analyzed. Although the expression profiles across the biological systems are highly different, KNeMAP was able to identify sets of compounds that induce similar molecular responses when exposed on the same biological system. AVAILABILITY AND IMPLEMENTATION: Relevant data and the KNeMAP function is available at: https://github.com/fhaive/KNeMAP and 10.5281/zenodo.7334711.

SUMMARY: iTOL is a powerful and comprehensive phylogenetic tree visualization engine. However, adjusting to new templates can be time-consuming, especially when many templates are available. We developed an R package namely itol.toolkit to help users generate all 23 types of annotation files in iTOL. This R package also provides an all-in-one data structure to store data and themes, accelerating the step from metadata to annotation files of iTOL visualizations through automatic workflows. AVAILABILITY AND IMPLEMENTATION: The manual and source code are available at https://github.com/TongZhou2017/itol.toolkit.

MOTIVATION: Single-cell RNA sequencing (scRNA-seq) data, annotated by cell type, is useful in a variety of downstream biological applications, such as profiling gene expression at the single-cell level. However, manually assigning these annotations with known marker genes is both time-consuming and subjective. RESULTS: We present a Graph Convolutional Network (GCN)-based approach to automate the annotation process. Our process builds upon existing labeling approaches, using state-of-the-art tools to find cells with highly confident label assignments through consensus and spreading these confident labels with a semi-supervised GCN. Using simulated data and two scRNA-seq datasets from different tissues, we show that our method improves accuracy over a simple consensus algorithm and the average of the underlying tools. We also compare our method to a nonparametric neighbor majority approach, showing comparable results. We then demonstrate that our GCN method allows for feature interpretation, identifying important genes for cell type classification. We present our completed pipeline, written in PyTorch, as an end-to-end tool for automating and interpreting the classification of scRNA-seq data. AVAILABILITY AND IMPLEMENTATION: Our code for conducting the experiments in this paper and using our model is available at https://github.com/lewinsohndp/scSHARP.

MOTIVATION: Drug combination therapy shows significant advantages over monotherapy in cancer treatment. Since the combinational space is difficult to be traversed experimentally, identifying novel synergistic drug combinations based on computational methods has become a powerful tool for pre-screening. Among them, methods based on deep learning have far outperformed other methods. However, most deep learning-based methods are unstable and will give inconsistent predictions even by simply changing the input order of drugs. In addition, the insufficient experimental data of drug combination screening limits the generalization ability of existing models. These problems prevent the deep learning-based models from being in service. RESULTS: In this article, we propose CGMS to address the above problems. CGMS models a drug combination and a cell line as a heterogeneous complete graph, and generates the whole-graph embedding to characterize their interaction by leveraging the heterogeneous graph attention network. Based on the whole-graph embedding, CGMS can make a stable, order-independent prediction. To enhance the generalization ability of CGMS, we apply the multi-task learning technique to train the model on drug synergy prediction task and drug sensitivity prediction task simultaneously. We compare CGMS's generalization ability with six state-of-the-art methods on a public dataset, and CGMS significantly outperforms other methods in the leave-drug combination-out scenario, as well as in the leave-cell line-out and leave-drug-out scenarios. We further present the benefit of eliminating the order dependency and the discrimination power of whole-graph embeddings, interpret the rationality of the attention mechanism, and verify the contribution of multi-task learning. AVAILABILITY AND IMPLEMENTATION: The code of CGMS is available via https://github.com/TOJSSE-iData/CGMS.

MOTIVATION: The accumulation of multi-omics microbiome data provides an unprecedented opportunity to understand the diversity of bacterial, fungal, and viral components from different conditions. The changes in the composition of viruses, bacteria, and fungi communities have been associated with environments and critical illness. However, identifying and dissecting the heterogeneity of microbial samples and cross-kingdom interactions remains challenging. RESULTS: We propose HONMF for the integrative analysis of multi-modal microbiome data, including bacterial, fungal, and viral composition profiles. HONMF enables identification of microbial samples and data visualization, and also facilitates downstream analysis, including feature selection and cross-kingdom association analysis between species. HONMF is an unsupervised method based on hypergraph induced orthogonal non-negative matrix factorization, where it assumes that latent variables are specific for each composition profile and integrates the distinct sets of latent variables through graph fusion strategy, which better tackles the distinct characteristics in bacterial, fungal, and viral microbiome. We implemented HONMF on several multi-omics microbiome datasets from different environments and tissues. The experimental results demonstrate the superior performance of HONMF in data visualization and clustering. HONMF also provides rich biological insights by implementing discriminative microbial feature selection and bacterium-fungus-virus association analysis, which improves our understanding of ecological interactions and microbial pathogenesis. AVAILABILITY AND IMPLEMENTATION: The software and datasets are available at https://github.com/chonghua-1983/HONMF.

MOTIVATION: Recent advances in multimodal single-cell omics technologies enable multiple modalities of molecular attributes, such as gene expression, chromatin accessibility, and protein abundance, to be profiled simultaneously at a global level in individual cells. While the increasing availability of multiple data modalities is expected to provide a more accurate clustering and characterization of cells, the development of computational methods that are capable of extracting information embedded across data modalities is still in its infancy. RESULTS: We propose SnapCCESS for clustering cells by integrating data modalities in multimodal single-cell omics data using an unsupervised ensemble deep learning framework. By creating snapshots of embeddings of multimodality using variational autoencoders, SnapCCESS can be coupled with various clustering algorithms for generating consensus clustering of cells. We applied SnapCCESS with several clustering algorithms to various datasets generated from popular multimodal single-cell omics technologies. Our results demonstrate that SnapCCESS is effective and more efficient than conventional ensemble deep learning-based clustering methods and outperforms other state-of-the-art multimodal embedding generation methods in integrating data modalities for clustering cells. The improved clustering of cells from SnapCCESS will pave the way for more accurate characterization of cell identity and types, an essential step for various downstream analyses of multimodal single-cell omics data. AVAILABILITY AND IMPLEMENTATION: SnapCCESS is implemented as a Python package and is freely available from https://github.com/PYangLab/SnapCCESS under the open-source license of GPL-3. The data used in this study are publicly available (see section 'Data availability').

MOTIVATION: Deep learning has moved to the forefront of tandem mass spectrometry-driven proteomics and authentic prediction for peptide fragmentation is more feasible than ever. Still, at this point spectral prediction is mainly used to validate database search results or for confined search spaces. Fully predicted spectral libraries have not yet been efficiently adapted to large search space problems that often occur in metaproteomics or proteogenomics. RESULTS: In this study, we showcase a workflow that uses Prosit for spectral library predictions on two common metaproteomes and implement an indexing and search algorithm, Mistle, to efficiently identify experimental mass spectra within the library. Hence, the workflow emulates a classic protein sequence database search with protein digestion but builds a searchable index from spectral predictions as an in-between step. We compare Mistle to popular search engines, both on a spectral and database search level, and provide evidence that this approach is more accurate than a database search using MSFragger. Mistle outperforms other spectral library search engines in terms of run time and proves to be extremely memory efficient with a 4- to 22-fold decrease in RAM usage. This makes Mistle universally applicable to large search spaces, e.g. covering comprehensive sequence databases of diverse microbiomes. AVAILABILITY AND IMPLEMENTATION: Mistle is freely available on GitHub at https://github.com/BAMeScience/Mistle.

MOTIVATION: Interpretable deep learning (DL) models that can provide biological insights, in addition to accurate predictions, are of great interest to the biomedical community. Recently, interpretable DL models that incorporate signaling pathways have been proposed for drug response prediction (DRP). While these models improve interpretability, it is unclear whether this comes at the cost of less accurate DRPs, or a prediction improvement can also be obtained. RESULTS: We comprehensively and systematically assessed four state-of-the-art interpretable DL models using three pathway collections to assess their ability in making accurate predictions on unseen samples from the same dataset, as well as their generalizability to an independent dataset. Our results showed that models that explicitly incorporate pathway information in the form of a latent layer perform worse compared to models that incorporate this information implicitly. However, in most evaluation setups, the best performance was achieved using a black-box multilayer perceptron, and the performance of a random forests baseline was comparable to those of the interpretable models. Replacing the signaling pathways with randomly generated pathways showed a comparable performance for the majority of the models. Finally, the performance of all models deteriorated when applied to an independent dataset. These results highlight the importance of systematic evaluation of newly proposed models using carefully selected baselines. We provide different evaluation setups and baseline models that can be used to achieve this goal. AVAILABILITY AND IMPLEMENTATION: Implemented models and datasets are provided at https://doi.org/10.5281/zenodo.7787178 and https://doi.org/10.5281/zenodo.7101665, respectively.

MOTIVATION: Enhancers are vital cis-regulatory elements that regulate gene expression. Enhancer RNAs (eRNAs), a type of long noncoding RNAs, are transcribed from enhancer regions in the genome. The tissue-specific expression of eRNAs is crucial in the regulation of gene expression and cancer development. The methods that identify eRNAs based solely on genomic sequence data have high error rates because they do not account for tissue specificity. Specific histone modifications associated with eRNAs offer valuable information for their identification. However, identification of eRNAs using histone modification data requires the use of both RNA-seq and histone modification data. Unfortunately, many public datasets contain only one of these components, which impedes the accurate identification of eRNAs. RESULTS: We introduce DeepITEH, a deep learning framework that leverages RNA-seq data and histone modification data from multiple samples of the same tissue to enhance the accuracy of identifying eRNAs. Specifically, deepITEH initially categorizes eRNAs into two classes, namely, regularly expressed eRNAs and accidental eRNAs, using histone modification data from multiple samples of the same tissue. Thereafter, it integrates both sequence and histone modification features to identify eRNAs in specific tissues. To evaluate the performance of DeepITEH, we compared it with four existing state-of-the-art enhancer prediction methods, SeqPose, iEnhancer-RD, LSTMAtt, and FRL, on four normal tissues and four cancer tissues. Remarkably, seven of these tissues demonstrated a substantially improved specific eRNA prediction performance with DeepITEH, when compared with other methods. Our findings suggest that DeepITEH can effectively predict potential eRNAs on the human genome, providing insights for studying the eRNA function in cancer. AVAILABILITY AND IMPLEMENTATION: The source code and dataset of DeepITEH have been uploaded to https://github.com/lyli1013/DeepITEH.

MOTIVATION: Many studies have successfully used network information to prioritize candidate omics profiles associated with diseases. The metabolome, as the link between genotypes and phenotypes, has accumulated growing attention. Using a "multi-omics" network constructed with a gene-gene network, a metabolite-metabolite network, and a gene-metabolite network to simultaneously prioritize candidate disease-associated metabolites and gene expressions could further utilize gene-metabolite interactions that are not used when prioritizing them separately. However, the number of metabolites is usually 100 times fewer than that of genes. Without accounting for this imbalance issue, we cannot effectively use gene-metabolite interactions when simultaneously prioritizing disease-associated metabolites and genes. RESULTS: Here, we developed a Multi-omics Network Enhancement Prioritization (MultiNEP) framework with a weighting scheme to reweight contributions of different sub-networks in a multi-omics network to effectively prioritize candidate disease-associated metabolites and genes simultaneously. In simulation studies, MultiNEP outperforms competing methods that do not address network imbalances and identifies more true signal genes and metabolites simultaneously when we down-weight relative contributions of the gene-gene network and up-weight that of the metabolite-metabolite network to the gene-metabolite network. Applications to two human cancer cohorts show that MultiNEP prioritizes more cancer-related genes by effectively using both within- and between-omics interactions after handling network imbalance. AVAILABILITY AND IMPLEMENTATION: The developed MultiNEP framework is implemented in an R package and available at: https://github.com/Karenxzr/MultiNep.

MOTIVATION: Large-scale prediction of drug-target affinity (DTA) plays an important role in drug discovery. In recent years, machine learning algorithms have made great progress in DTA prediction by utilizing sequence or structural information of both drugs and proteins. However, sequence-based algorithms ignore the structural information of molecules and proteins, while graph-based algorithms are insufficient in feature extraction and information interaction. RESULTS: In this article, we propose NHGNN-DTA, a node-adaptive hybrid neural network for interpretable DTA prediction. It can adaptively acquire feature representations of drugs and proteins and allow information to interact at the graph level, effectively combining the advantages of both sequence-based and graph-based approaches. Experimental results have shown that NHGNN-DTA achieved new state-of-the-art performance. It achieved the mean squared error (MSE) of 0.196 on the Davis dataset (below 0.2 for the first time) and 0.124 on the KIBA dataset (3% improvement). Meanwhile, in the case of cold start scenario, NHGNN-DTA proved to be more robust and more effective with unseen inputs than baseline methods. Furthermore, the multi-head self-attention mechanism endows the model with interpretability, providing new exploratory insights for drug discovery. The case study on Omicron variants of SARS-CoV-2 illustrates the efficient utilization of drug repurposing in COVID-19. AVAILABILITY AND IMPLEMENTATION: The source code and data are available at https://github.com/hehh77/NHGNN-DTA.

MOTIVATION: Single-cell sequencing enables exploring the pathways and processes of cells, and cell populations. However, there is a paucity of pathway enrichment methods designed to tolerate the high noise and low gene coverage of this technology. When gene expression data are noisy and signals are sparse, testing pathway enrichment based on the genes expression may not yield statistically significant results, which is particularly problematic when detecting the pathways enriched in less abundant cells that are vulnerable to disturbances. RESULTS: In this project, we developed a Weighted Concept Signature Enrichment Analysis specialized for pathway enrichment analysis from single-cell transcriptomics (scRNA-seq). Weighted Concept Signature Enrichment Analysis took a broader approach for assessing the functional relations of pathway gene sets to differentially expressed genes, and leverage the cumulative signature of molecular concepts characteristic of the highly differentially expressed genes, which we termed as the universal concept signature, to tolerate the high noise and low coverage of this technology. We then incorporated Weighted Concept Signature Enrichment Analysis into an R package called "IndepthPathway" for biologists to broadly leverage this method for pathway analysis based on bulk and single-cell sequencing data. Through simulating technical variability and dropouts in gene expression characteristic of scRNA-seq as well as benchmarking on a real dataset of matched single-cell and bulk RNAseq data, we demonstrate that IndepthPathway presents outstanding stability and depth in pathway enrichment results under stochasticity of the data, thus will substantially improve the scientific rigor of the pathway analysis for single-cell sequencing data. AVAILABILITY AND IMPLEMENTATION: The IndepthPathway R package is available through: https://github.com/wangxlab/IndepthPathway.

MOTIVATION: Bone marrow (BM) examination is one of the most important indicators in diagnosing hematologic disorders and is typically performed under the microscope via oil-immersion objective lens with a total 100× objective magnification. On the other hand, mitotic detection and identification is critical not only for accurate cancer diagnosis and grading but also for predicting therapy success and survival. Fully automated BM examination and mitotic figure examination from whole-slide images is highly demanded but challenging and poorly explored. First, the complexity and poor reproducibility of microscopic image examination are due to the cell type diversity, delicate intralineage discrepancy within the multitype cell maturation process, cells overlapping, lipid interference and stain variation. Second, manual annotation on whole-slide images is tedious, laborious and subject to intraobserver variability, which causes the supervised information restricted to limited, easily identifiable and scattered cells annotated by humans. Third, when the training data are sparsely labeled, many unlabeled objects of interest are wrongly defined as background, which severely confuses AI learners. RESULTS: This article presents an efficient and fully automatic CW-Net approach to address the three issues mentioned above and demonstrates its superior performance on both BM examination and mitotic figure examination. The experimental results demonstrate the robustness and generalizability of the proposed CW-Net on a large BM WSI dataset with 16 456 annotated cells of 19 BM cell types and a large-scale WSI dataset for mitotic figure assessment with 262 481 annotated cells of five cell types. AVAILABILITY AND IMPLEMENTATION: An online web-based system of the proposed method has been created for demonstration (see https://youtu.be/MRMR25Mls1A).

MOTIVATION: Developing new crop varieties with superior performance is highly important to ensure robust and sustainable global food security. The speed of variety development is limited by long field cycles and advanced generation selections in plant breeding programs. While methods to predict yield from genotype or phenotype data have been proposed, improved performance and integrated models are needed. RESULTS: We propose a machine learning model that leverages both genotype and phenotype measurements by fusing genetic variants with multiple data sources collected by unmanned aerial systems. We use a deep multiple instance learning framework with an attention mechanism that sheds light on the importance given to each input during prediction, enhancing interpretability. Our model reaches 0.754 ± 0.024 Pearson correlation coefficient when predicting yield in similar environmental conditions; a 34.8% improvement over the genotype-only linear baseline (0.559 ± 0.050). We further predict yield on new lines in an unseen environment using only genotypes, obtaining a prediction accuracy of 0.386 ± 0.010, a 13.5% improvement over the linear baseline. Our multi-modal deep learning architecture efficiently accounts for plant health and environment, distilling the genetic contribution and providing excellent predictions. Yield prediction algorithms leveraging phenotypic observations during training therefore promise to improve breeding programs, ultimately speeding up delivery of improved varieties. AVAILABILITY AND IMPLEMENTATION: Available at https://github.com/BorgwardtLab/PheGeMIL (code) and https://doi.org/doi:10.5061/dryad.kprr4xh5p (data).

MOTIVATION: The primary regulatory step for protein synthesis is translation initiation, which makes it one of the fundamental steps in the central dogma of molecular biology. In recent years, a number of approaches relying on deep neural networks (DNNs) have demonstrated superb results for predicting translation initiation sites. These state-of-the art results indicate that DNNs are indeed capable of learning complex features that are relevant to the process of translation. Unfortunately, most of those research efforts that employ DNNs only provide shallow insights into the decision-making processes of the trained models and lack highly sought-after novel biologically relevant observations. RESULTS: By improving upon the state-of-the-art DNNs and large-scale human genomic datasets in the area of translation initiation, we propose an innovative computational methodology to get neural networks to explain what was learned from data. Our methodology, which relies on in silico point mutations, reveals that DNNs trained for translation initiation site detection correctly identify well-established biological signals relevant to translation, including (i) the importance of the Kozak sequence, (ii) the damaging consequences of ATG mutations in the 5'-untranslated region, (iii) the detrimental effect of premature stop codons in the coding region, and (iv) the relative insignificance of cytosine mutations for translation. Furthermore, we delve deeper into the Beta-globin gene and investigate various mutations that lead to the Beta thalassemia disorder. Finally, we conclude our work by laying out a number of novel observations regarding mutations and translation initiation. AVAILABILITY AND IMPLEMENTATION: For data, models, and code, visit github.com/utkuozbulak/mutate-and-observe.

MOTIVATION: Genome-scale metabolic network reconstructions (GENREs) are valuable for understanding cellular metabolism in silico. Several tools exist for automatic GENRE generation. However, these tools frequently (i) do not readily integrate with some of the widely-used suites of packaged methods available for network analysis, (ii) lack effective network curation tools, (iii) are not sufficiently user-friendly, and (iv) often produce low-quality draft reconstructions. RESULTS: Here, we present Reconstructor, a user-friendly, COBRApy-compatible tool that produces high-quality draft reconstructions with reaction and metabolite naming conventions that are consistent with the ModelSEED biochemistry database and includes a gap-filling technique based on the principles of parsimony. Reconstructor can generate SBML GENREs from three input types: annotated protein .fasta sequences (Type 1 input), a BLASTp output (Type 2), or an existing SBML GENRE that can be further gap-filled (Type 3). While Reconstructor can be used to create GENREs of any species, we demonstrate the utility of Reconstructor with bacterial reconstructions. We demonstrate how Reconstructor readily generates high-quality GENRES that capture strain, species, and higher taxonomic differences in functional metabolism of bacteria and are useful for further biological discovery. AVAILABILITY AND IMPLEMENTATION: The Reconstructor Python package is freely available for download. Complete installation and usage instructions and benchmarking data are available at http://github.com/emmamglass/reconstructor.

SUMMARY: Biomedical named entity recognition (NER) plays a crucial role in extracting information from documents in biomedical applications. However, many of these applications require NER models to operate at a document level, rather than just a sentence level. This presents a challenge, as the extension from a sentence model to a document model is not always straightforward. Despite the existence of document NER models that are able to make consistent predictions, they still fall short of meeting the expectations of researchers and practitioners in the field. To address this issue, we have undertaken an investigation into the underlying causes of inconsistent predictions. Our research has led us to believe that the use of adjectives and prepositions within entities may be contributing to low label consistency. In this article, we present our method, ConNER, to enhance a label consistency of modifiers such as adjectives and prepositions. By refining the labels of these modifiers, ConNER is able to improve representations of biomedical entities. The effectiveness of our method is demonstrated on four popular biomedical NER datasets. On three datasets, we achieve a higher F1 score than the previous state-of-the-art model. Our method shows its efficacy on two datasets, resulting in 7.5%-8.6% absolute improvements in the F1 score. Our findings suggest that our ConNER method is effective on datasets with intrinsically low label consistency. Through qualitative analysis, we demonstrate how our approach helps the NER model generate more consistent predictions. AVAILABILITY AND IMPLEMENTATION: Our code and resources are available at https://github.com/dmis-lab/ConNER/.