BACKGROUND: Recent research recommends that epi-transcriptome regulation through post-transcriptional RNA modifications is essential for all sorts of RNA. Exact identification of RNA modification is vital for understanding their purposes and regulatory mechanisms. However, traditional experimental methods of identifying RNA modification sites are relatively complicated, time-consuming, and laborious. Machine learning approaches have been applied in the procedures of RNA sequence features extraction and classification in a computational way, which may supplement experimental approaches more efficiently. Recently, convolutional neural network (CNN) and long short-term memory (LSTM) have been demonstrated achievements in modification site prediction on account of their powerful functions in representation learning. However, CNN can learn the local response from the spatial data but cannot learn sequential correlations. And LSTM is specialized for sequential modeling and can access both the contextual representation but lacks spatial data extraction compared with CNN. There is strong motivation to construct a prediction framework using natural language processing (NLP), deep learning (DL) for these reasons. RESULTS: This study presents an ensemble multiscale deep learning predictor (EMDLP) to identify RNA methylation sites in an NLP and DL way. It organically combines the dilated convolution and Bidirectional LSTM (BiLSTM), which helps to take better advantage of the local and global information for site prediction. The first step of EMDLP is to represent the RNA sequences in an NLP way. Thus, three encodings, e.g., RNA word embedding, One-hot encoding, and RGloVe, which is an improved learning method of word vector representation based on GloVe, are adopted to decipher sites from the viewpoints of the local and global information. Then, a dilated convolutional Bidirectional LSTM network (DCB) model is constructed with the dilated convolutional neural network (DCNN) followed by BiLSTM to extract potential contributing features for methylation site prediction. Finally, these three encoding methods are integrated by a soft vote to obtain better predictive performance. Experiment results on m1A and m6A reveal that the area under the receiver operating characteristic(AUROC) of EMDLP obtains respectively 95.56%, 85.24%, and outperforms the state-of-the-art models. To maximize user convenience, a user-friendly webserver for EMDLP was publicly available at http://www.labiip.net/EMDLP/index.php ( http://47.104.130.81/EMDLP/index.php ). CONCLUSIONS: We developed a predictor for m1A and m6A methylation sites.

BACKGROUND: Precision medicine for cancer treatment relies on an accurate pathological diagnosis. The number of known tumor classes has increased rapidly, and reliance on traditional methods of histopathologic classification alone has become unfeasible. To help reduce variability, validation costs, and standardize the histopathological diagnostic process, supervised machine learning models using DNA-methylation data have been developed for tumor classification. These methods require large labeled training data sets to obtain clinically acceptable classification accuracy. While there is abundant unlabeled epigenetic data across multiple databases, labeling pathology data for machine learning models is time-consuming and resource-intensive, especially for rare tumor types. Semi-supervised learning (SSL) approaches have been used to maximize the utility of labeled and unlabeled data for classification tasks and are effectively applied in genomics. SSL methods have not yet been explored with epigenetic data nor demonstrated beneficial to central nervous system (CNS) tumor classification. RESULTS: This paper explores the application of semi-supervised machine learning on methylation data to improve the accuracy of supervised learning models in classifying CNS tumors. We comprehensively evaluated 11 SSL methods and developed a novel combination approach that included a self-training with editing using support vector machine (SETRED-SVM) model and an L2-penalized, multinomial logistic regression model to obtain high confidence labels from a few labeled instances. Results across eight random forest and neural net models show that the pseudo-labels derived from our SSL method can significantly increase prediction accuracy for 82 CNS tumors and 9 normal controls. CONCLUSIONS: The proposed combination of semi-supervised technique and multinomial logistic regression holds the potential to leverage the abundant publicly available unlabeled methylation data effectively. Such an approach is highly beneficial in providing additional training examples, especially for scarce tumor types, to boost the prediction accuracy of supervised models.

BACKGROUND: Computer-aided drug design provides an effective method of identifying lead compounds. However, success rates are significantly bottlenecked by the lack of accurate and reliable scoring functions needed to evaluate binding affinities of protein-ligand complexes. Therefore, many scoring functions based on machine learning or deep learning have been developed to improve prediction accuracies in recent years. In this work, we proposed a novel featurization method, generating a new scoring function model based on 3D convolutional neural network. RESULTS: This work showed the results from testing four architectures and three featurization methods, and outlined the development of a novel deep 3D convolutional neural network scoring function model. This model simplified feature engineering, and in combination with Grad-CAM made the intermediate layers of the neural network more interpretable. This model was evaluated and compared with other scoring functions on multiple independent datasets. The Pearson correlation coefficients between the predicted binding affinities by our model and the experimental data achieved 0.7928, 0.7946, 0.6758, and 0.6474 on CASF-2016 dataset, CASF-2013 dataset, CSAR_HiQ_NRC_set, and Astex_diverse_set, respectively. Overall, our model performed accurately and stably enough in the scoring power to predict the binding affinity of a protein-ligand complex. CONCLUSIONS: These results indicate our model is an excellent scoring function, and performs well in scoring power for accurately and stably predicting the protein-ligand affinity. Our model will contribute towards improving the success rate of virtual screening, thus will accelerate the development of potential drugs or novel biologically active lead compounds.

BACKGROUND: With the rapid development of high-throughput sequencing technology, the cost of whole genome sequencing drops rapidly, which leads to an exponential growth of genome data. How to efficiently compress the DNA data generated by large-scale genome projects has become an important factor restricting the further development of the DNA sequencing industry. Although the compression of DNA bases has achieved significant improvement in recent years, the compression of quality score is still challenging. RESULTS: In this paper, by reinvestigating the inherent correlations between the quality score and the sequencing process, we propose a novel lossless quality score compressor based on adaptive coding order (ACO). The main objective of ACO is to traverse the quality score adaptively in the most correlative trajectory according to the sequencing process. By cooperating with the adaptive arithmetic coding and an improved in-context strategy, ACO achieves the state-of-the-art quality score compression performances with moderate complexity for the next-generation sequencing (NGS) data. CONCLUSIONS: The competence enables ACO to serve as a candidate tool for quality score compression, ACO has been employed by AVS(Audio Video coding Standard Workgroup of China) and is freely available at https://github.com/Yoniming/ACO.

BACKGROUND: The ubiquity of pedigrees in many scientific areas calls for versatile and user-friendly software. Previously published online pedigree tools have limited support for complex pedigrees and do not provide analysis of relatedness between pedigree members. RESULTS: We introduce QuickPed, a web application for interactive pedigree creation and analysis. It supports complex inbreeding and comes with a rich built-in library of common and interesting pedigrees. The program calculates all standard coefficients of relatedness, including inbreeding, kinship and identity coefficients, and offers specialised plots for visualising relatedness. It also implements a novel algorithm for describing pairwise relationships in words. CONCLUSION: QuickPed is a user-friendly pedigree tool aimed at researchers, case workers and teachers. It contains a number of features not found in other similar tools, and represents a significant addition to the body of pedigree software by making advanced relatedness analyses available for non-bioinformaticians.

BACKGROUND: Myocardial infarction can lead to malignant arrhythmia, heart failure, and sudden death. Clinical studies have shown that early identification of and timely intervention for acute MI can significantly reduce mortality. The traditional MI risk assessment models are subjective, and the data that go into them are difficult to obtain. Generally, the assessment is only conducted among high-risk patient groups. OBJECTIVE: To construct an artificial intelligence-based risk prediction model of myocardial infarction (MI) for continuous and active monitoring of inpatients, especially those in noncardiovascular departments, and early warning of MI. METHODS: The imbalanced data contain 59 features, which were constructed into a specific dataset through proportional division, upsampling, downsampling, easy ensemble, and w-easy ensemble. Then, the dataset was traversed using supervised machine learning, with recursive feature elimination as the top-layer algorithm and random forest, gradient boosting decision tree (GBDT), logistic regression, and support vector machine as the bottom-layer algorithms, to select the best model out of many through a variety of evaluation indices. RESULTS: GBDT was the best bottom-layer algorithm, and downsampling was the best dataset construction method. In the validation set, the F1 score and accuracy of the 24-feature downsampling GBDT model were both 0.84. In the test set, the F1 score and accuracy of the 24-feature downsampling GBDT model were both 0.83, and the area under the curve was 0.91. CONCLUSION: Compared with traditional models, artificial intelligence-based machine learning models have better accuracy and real-time performance and can reduce the occurrence of in-hospital MI from a data-driven perspective, thereby increasing the cure rate of patients and improving their prognosis.

BACKGROUND: Due to their diverse bioactivity, natural product (NP)s have been developed as commercial products in the pharmaceutical, food and cosmetic sectors as natural compound (NC)s and in the form of extracts. Following administration, NCs typically interact with multiple target proteins to elicit their effects. Various machine learning models have been developed to predict multi-target modulating NCs with desired physiological effects. However, due to deficiencies with existing chemical-protein interaction datasets, which are mostly single-labeled and limited, the existing models struggle to predict new chemical-protein interactions. New techniques are needed to overcome these limitations. RESULTS: We propose a novel NC discovery model called OptNCMiner that offers various advantages. The model is trained via end-to-end learning with a feature extraction step implemented, and it predicts multi-target modulating NCs through multi-label learning. In addition, it offers a few-shot learning approach to predict NC-protein interactions using a small training dataset. OptNCMiner achieved better prediction performance in terms of recall than conventional classification models. It was tested for the prediction of NC-protein interactions using small datasets and for a use case scenario to identify multi-target modulating NCs for type 2 diabetes mellitus complications. CONCLUSIONS: OptNCMiner identifies NCs that modulate multiple target proteins, which facilitates the discovery and the understanding of biological activity of novel NCs with desirable health benefits.

BACKGROUND: Modern sequencing technologies have generated low-cost microbiome survey datasets, across sample sites, conditions, and treatments, on an unprecedented scale and throughput. These datasets often come with a phylogenetic tree that provides a unique opportunity to examine how shared evolutionary history affects the different patterns in host-associated microbial communities. RESULTS: In this paper, we describe an R package, phyloMDA, for phylogeny-aware microbiome data analysis. It includes the Dirichlet-tree multinomial model for multivariate abundance data, tree-guided empirical Bayes estimation of microbial compositions, and tree-based multiscale regression methods with relative abundances as predictors. CONCLUSION: phyloMDA is a versatile and user-friendly tool to analyze microbiome data while incorporating the phylogenetic information and addressing some of the challenges posed by the data.

BACKGROUND: Some circular RNAs (circRNAs) can be translated into functional peptides by small open reading frames (ORFs) in a cap-independent manner. Internal ribosomal entry site (IRES) and N6-methyladenosine (m6A) were reported to drive translation of circRNAs. Experimental methods confirming the presence of IRES and m6A site are time consuming and labor intensive. Lacking computational tools to predict ORFs, IRESs and m6A sites for circRNAs makes it harder. RESULTS: In this report, we present circPrimer 2.0, a Java based software for annotating circRNAs and predicting ORFs, IRESs, and m6A sites of circRNAs. circPrimer 2.0 has a graphical and a command-line interface that enables the tool to be embed into an analysis pipeline. CONCLUSIONS: circprimer 2.0 is an easy-to-use software for annotating circRNAs and predicting translation potential of circRNAs, and freely available at www.bio-inf.cn .

BACKGROUND: Plant breeding and crop research rely on experimental phenotyping trials. These trials generate data for large numbers of traits and plant varieties that needs to be captured efficiently and accurately to support further research and downstream analysis. Traditionally scored by hand, phenotypic data is nowadays collected using spreadsheets or specialized apps. While many solutions exist, which increase efficiency and reduce errors, none offer the same familiarity as printed field plans which have been used for decades and offer an intuitive overview over the trial setup, previously recorded data and plots still requiring scoring. RESULTS: We introduce GridScore which utilizes cutting-edge web technologies to reproduce the familiarity of printed field plans while enhancing the phenotypic data collection process by adding advanced features like georeferencing, image tagging and speech recognition. GridScore is a cross-platform open-source plant phenotyping app that combines barcode-based systems with a guided data collection approach while offering a top-down view onto the data collected in a field layout. GridScore is compared to existing tools across a wide spectrum of criteria including support for barcodes, multiple platforms, and visualizations. CONCLUSION: Compared to its competition, GridScore shows strong performance across the board offering a complete manual phenotyping experience.

BACKGROUND: The three-dimensional nuclear arrangement of chromatin impacts many cellular processes operating at the DNA level in animal and plant systems. Chromatin organization is a dynamic process that can be affected by biotic and abiotic stresses. Three-dimensional imaging technology allows to follow these dynamic changes, but only a few semi-automated processing methods currently exist for quantitative analysis of the 3D chromatin organization. RESULTS: We present an automated method, Nuclear Object DetectionJ (NODeJ), developed as an imageJ plugin. This program segments and analyzes high intensity domains in nuclei from 3D images. NODeJ performs a Laplacian convolution on the mask of a nucleus to enhance the contrast of intra-nuclear objects and allow their detection. We reanalyzed public datasets and determined that NODeJ is able to accurately identify heterochromatin domains from a diverse set of Arabidopsis thaliana nuclei stained with DAPI or Hoechst. NODeJ is also able to detect signals in nuclei from DNA FISH experiments, allowing for the analysis of specific targets of interest. CONCLUSION AND AVAILABILITY: NODeJ allows for efficient automated analysis of subnuclear structures by avoiding the semi-automated steps, resulting in reduced processing time and analytical bias. NODeJ is written in Java and provided as an ImageJ plugin with a command line option to perform more high-throughput analyses. NODeJ can be downloaded from https://gitlab.com/axpoulet/image2danalysis/-/releases with source code, documentation and further information avaliable at https://gitlab.com/axpoulet/image2danalysis . The images used in this study are publicly available at https://www.brookes.ac.uk/indepth/images/ and https://doi.org/10.15454/1HSOIE .

BACKGROUND: Transcription factors (TFs) bind regulatory DNA regions with sequence specificity, form complexes and regulate gene expression. In cooperative TF-TF binding, two transcription factors bind onto a shared DNA binding site as a pair. Previous work has demonstrated pairwise TF-TF-DNA interactions with position weight matrices (PWMs), which may however not sufficiently take into account the complexity and flexibility of pairwise binding. RESULTS: We propose two random forest (RF) methods for joint TF-TF binding site prediction: ComBind and JointRF. We train models with previously published large-scale CAP-SELEX DNA libraries, which comprise DNA sequences enriched for binding of a selected TF pair. JointRF builds a random forest with sub-sequences selected from CAP-SELEX DNA reads with previously proposed pairwise PWM. JointRF outperforms (area under receiver operating characteristics curve, AUROC, 0.75) the current state-of-the-art method i.e. orientation and spacing specific pairwise PWMs (AUROC 0.59). Thus, JointRF may be utilized to improve prediction accuracy for pre-determined binding preferences. However, pairwise TF binding is currently considered flexible; a pair may bind DNA with different orientations and amounts of dinucleotide gaps or overlap between the two motifs. Thus, we developed ComBind, which utilizes random forests by considering simultaneously multiple orientations and spacings of the two factors. Our approach outperforms (AUROC 0.78) PWMs, as well as JointRF (p<0.00195). ComBind provides an approach for predicting TF-TF binding sites without prior knowledge on pairwise binding preferences. However, more research is needed to assess ComBind eligibility for practical applications. CONCLUSIONS: Random forest is well suited for modeling pairwise TF-TF-DNA binding specificities, and ComBind provides an improvement to pairwise binding site prediction accuracy.

BACKGROUND: The COVID-19 pandemic has increasingly accelerated the publication pace of scientific literature. How to efficiently curate and index this large amount of biomedical literature under the current crisis is of great importance. Previous literature indexing is mainly performed by human experts using Medical Subject Headings (MeSH), which is labor-intensive and time-consuming. Therefore, to alleviate the expensive time consumption and monetary cost, there is an urgent need for automatic semantic indexing technologies for the emerging COVID-19 domain. RESULTS: In this research, to investigate the semantic indexing problem for COVID-19, we first construct the new COVID-19 Semantic Indexing dataset, which consists of more than 80 thousand biomedical articles. We then propose a novel semantic indexing framework based on the multi-probe attention neural network (MPANN) to address the COVID-19 semantic indexing problem. Specifically, we employ a k-nearest neighbour based MeSH masking approach to generate candidate topic terms for each input article. We encode and feed the selected candidate terms as well as other contextual information as probes into the downstream attention-based neural network. Each semantic probe carries specific aspects of biomedical knowledge and provides informatively discriminative features for the input article. After extracting the semantic features at both term-level and document-level through the attention-based neural network, MPANN adopts a linear multi-view classifier to conduct the final topic prediction for COVID-19 semantic indexing. CONCLUSION: The experimental results suggest that MPANN promises to represent the semantic features of biomedical texts and is effective in predicting semantic topics for COVID-19 related biomedical articles.

BACKGROUND: DNA N4-methylcytosine is part of the restrictive modification system, which works by regulating some biological processes, for example, the initiation of DNA replication, mismatch repair and inactivation of transposon. However, using experimental methods to detect 4mC sites is time-consuming and expensive. Besides, considering the huge differences in the number of 4mC samples among different species, it is challenging to achieve a robust multi-species 4mC site prediction performance. Hence, it is of great significance to develop effective computational tools to identify 4mC sites. RESULTS: This work proposes a flexible deep learning-based framework to predict 4mC sites, called Hyb4mC. Hyb4mC adopts the DNA2vec method for sequence embedding, which captures more efficient and comprehensive information compared with the sequence-based feature method. Then, two different subnets are used for further analysis: Hyb_Caps and Hyb_Conv. Hyb_Caps is composed of a capsule neural network and can generalize from fewer samples. Hyb_Conv combines the attention mechanism with a text convolutional neural network for further feature learning. CONCLUSIONS: Extensive benchmark tests have shown that Hyb4mC can significantly enhance the performance of predicting 4mC sites compared with the recently proposed methods.

BACKGROUND: Addressing the laborious nature of traditional biological experiments by using an efficient computational approach to analyze RNA-binding proteins (RBPs) binding sites has always been a challenging task. RBPs play a vital role in post-transcriptional control. Identification of RBPs binding sites is a key step for the anatomy of the essential mechanism of gene regulation by controlling splicing, stability, localization and translation. Traditional methods for detecting RBPs binding sites are time-consuming and computationally-intensive. Recently, the computational method has been incorporated in researches of RBPs. Nevertheless, lots of them not only rely on the sequence data of RNA but also need additional data, for example the secondary structural data of RNA, to improve the performance of prediction, which needs the pre-work to prepare the learnable representation of structural data. RESULTS: To reduce the dependency of those pre-work, in this paper, we introduce DeepPN, a deep parallel neural network that is constructed with a convolutional neural network (CNN) and graph convolutional network (GCN) for detecting RBPs binding sites. It includes a two-layer CNN and GCN in parallel to extract the hidden features, followed by a fully connected layer to make the prediction. DeepPN discriminates the RBP binding sites on learnable representation of RNA sequences, which only uses the sequence data without using other data, for example the secondary or tertiary structure data of RNA. DeepPN is evaluated on 24 datasets of RBPs binding sites with other state-of-the-art methods. The results show that the performance of DeepPN is comparable to the published methods. CONCLUSION: The experimental results show that DeepPN can effectively capture potential hidden features in RBPs and use these features for effective prediction of binding sites.

BACKGROUND: Target drugs play an important role in the clinical treatment of virus diseases. Virus-encoded proteins are widely used as targets for target drugs. However, they cannot cope with the drug resistance caused by a mutated virus and ignore the importance of host proteins for virus replication. Some methods use interactions between viruses and their host proteins to predict potential virus-target host proteins, which are less susceptible to mutated viruses. However, these methods only consider the network topology between the virus and the host proteins, ignoring the influences of protein complexes. Therefore, we introduce protein complexes that are less susceptible to drug resistance of mutated viruses, which helps recognize the unknown virus-target host proteins and reduce the cost of disease treatment. RESULTS: Since protein complexes contain virus-target host proteins, it is reasonable to predict virus-target human proteins from the perspective of the protein complexes. We propose a coverage clustering-core-subsidiary protein complex recognition method named CCA-SE that integrates the known virus-target host proteins, the human protein-protein interaction network, and the known human protein complexes. The proposed method aims to obtain the potential unknown virus-target human host proteins. We list part of the targets after proving our results effectively in enrichment experiments. CONCLUSIONS: Our proposed CCA-SE method consists of two parts: one is CCA, which is to recognize protein complexes, and the other is SE, which is to select seed nodes as the core of protein complexes by using seed expansion. The experimental results validate that CCA-SE achieves efficient recognition of the virus-target host proteins.

Glioma is the most aggressive and dangerous primary brain tumor with a survival time of less than 14 months. Segmentation of tumors is a necessary task in the image processing of the gliomas and is important for its timely diagnosis and starting a treatment. Using 3D U-net architecture to perform semantic segmentation on brain tumor dataset is at the core of deep learning. In this paper, we present a unique cloud-based 3D U-Net method to perform brain tumor segmentation using BRATS dataset. The system was effectively trained by using Adam optimization solver by utilizing multiple hyper parameters. We got an average dice score of 95% which makes our method the first cloud-based method to achieve maximum accuracy. The dice score is calculated by using Sørensen-Dice similarity coefficient. We also performed an extensive literature review of the brain tumor segmentation methods implemented in the last five years to get a state-of-the-art picture of well-known methodologies with a higher dice score. In comparison to the already implemented architectures, our method ranks on top in terms of accuracy in using a cloud-based 3D U-Net framework for glioma segmentation.

Author information: (1)Inserm, Univ Brest, EFS, UMR 1078, GGB, 29200, Brest, France. anthony.herzig@inserm.fr. (2)Institute of Genetics and Biophysics A. Buzzati-Traverso - CNR, Naples, Italy. (3)IRCCS Neuromed, Pozzilli, Isernia, Italy. (4)Inserm, Université Paris Cité, UMR 1141, NeuroDiderot, 75019, Paris, France. (5)CESP Inserm U1018, Université Paris-Saclay, UVSQ, Villejuif, France.

BACKGROUND: Alternative splicing can increase the diversity of gene functions by generating multiple isoforms with different sequences and functions. However, the extent to which splicing events have functional consequences remains unclear and predicting the impact of splicing events on protein activity is limited to gene-specific analysis. RESULTS: To accelerate the identification of functionally relevant alternative splicing events we created SAPFIR, a predictor of protein features associated with alternative splicing events. This webserver tool uses InterProScan to predict protein features such as functional domains, motifs and sites in the human and mouse genomes and link them to alternative splicing events. Alternative protein features are displayed as functions of the transcripts and splice sites. SAPFIR could be used to analyze proteins generated from a single gene or a group of genes and can directly identify alternative protein features in large sequence data sets. The accuracy and utility of SAPFIR was validated by its ability to rediscover previously validated alternative protein domains. In addition, our de novo analysis of public datasets using SAPFIR indicated that only a small portion of alternative protein domains was conserved between human and mouse, and that in human, genes involved in nervous system process, regulation of DNA-templated transcription and aging are more likely to produce isoforms missing functional domains due to alternative splicing. CONCLUSION: Overall SAPFIR represents a new tool for the rapid identification of functional alternative splicing events and enables the identification of cellular functions affected by a defined splicing program. SAPFIR is freely available at https://bioinfo-scottgroup.med.usherbrooke.ca/sapfir/ , a website implemented in Python, with all major browsers supported. The source code is available at https://github.com/DelongZHOU/SAPFIR .

BACKGROUND: The human body is inhabited by a diverse community of commensal non-pathogenic bacteria, many of which are essential for our health. By contrast, pathogenic bacteria have the ability to invade their hosts and cause a disease. Characterizing the differences between pathogenic and commensal non-pathogenic bacteria is important for the detection of emerging pathogens and for the development of new treatments. Previous methods for classification of bacteria as pathogenic or non-pathogenic used either raw genomic reads or protein families as features. Using protein families instead of reads provided a better interpretability of the resulting model. However, the accuracy of protein-families-based classifiers can still be improved. RESULTS: We developed a wide scope pathogenicity classifier (WSPC), a new protein-content-based machine-learning classification model. We trained WSPC on a newly curated dataset of 641 bacterial genomes, where each genome belongs to a different species. A comparative analysis we conducted shows that WSPC outperforms existing models on two benchmark test sets. We observed that the most discriminative protein-family features in WSPC are widely spread among bacterial species. These features correspond to proteins that are involved in the ability of bacteria to survive and replicate during an infection, rather than proteins that are directly involved in damaging or invading the host.

BACKGROUND: Hepatocellular carcinoma (HCC) is a primary malignant tumor that accounts for approximately 90% of all cases of primary liver cancer worldwide. Microtubule alterations may contribute to the broad spectrum of resistance to chemotherapy, tumor development, and cell survival. This study aimed to assess the value of ribonucleic acid export 1 (RAE1), as a regulator of microtubules, in the diagnosis and prognosis of HCC, and to analyze its correlation with genetic mutations and pathways in HCC. RESULTS: The mRNA and protein levels of RAE1 were significantly elevated in HCC tissues compared with those in normal tissues. The high expression level of RAE1 was correlated with T stage, pathologic stage, tumor status, histologic grade, and alpha-fetoprotein level. HCC patients with a higher expression level of RAE1 had a poorer prognosis, and the expression level of RAE1 showed the ability to accurately distinguish tumor tissues from normal tissues (area under the curve (AUC) = 0.951). The AUC values of 1-, 3-, and 5-year survival rates were all above 0.6. The multivariate Cox regression analysis showed that RAE1 expression level was an independent prognostic factor for a shorter overall survival of HCC patients. The rate of RAE1 genetic alterations was 1.1% in HCC samples. Gene ontology and kyoto encyclopedia of genes and genomes pathway enrichment analyses indicated the co-expressed genes of RAE1 were mainly related to chromosome segregation, DNA replication, and cell cycle checkpoint. Protein-protein interaction analysis showed that RAE1 was closely correlated with NUP205, NUP155, NUP214, NUP54, and NXF1, all playing important roles in cell division and mitotic checkpoint. CONCLUSION: RAE1 can be a potential diagnostic and prognostic biomarker associated with microtubules and a therapeutic target for HCC.

BACKGROUND: At present, the diagnostic ability of hepatocellular carcinoma (HCC) based on serum alpha-fetoprotein level is limited. Finding markers that can effectively distinguish cancer and non-cancerous tissues is important for improving the diagnostic efficiency of HCC. RESULTS: In this study, we developed a predictive model for HCC diagnosis using personalized biological pathways combined with a machine learning algorithm based on regularized regression and carry out relevant examinations. In two training sets, the overall cross-study-validated area under the receiver operating characteristic curve (AUROC), the area under the precision-recall curve and the Brier score of the diagnostic model were 0.987 [95%confidence interval (CI): 0.979-0.996], 0.981 and 0.091, respectively. Besides, the model showed good transferability in external validation set. In TCGA-LIHC cohort, the AUROC, AURPC and Brier score were 0.992 (95%CI: 0.985-0.998), 0.967 and 0.112, respectively. The diagnostic model has accomplished very impressive performance in distinguishing HCC from non-cancerous liver tissues. Moreover, we further analyzed the extracted biological pathways to explore molecular features and prognostic factors. The risk score generated from a 12-gene signature extracted from the characteristic pathways was correlated with some immune related pathways and served as an independent prognostic factor for HCC. CONCLUSION: We used personalized biological pathways analysis and machine learning algorithm to construct a highly accurate HCC diagnostic model. The excellent interpretable performance and good transferability of this model enables it with great potential for personalized medicine, which can assist clinicians in diagnosis for HCC patients.

BACKGROUND: Human protein kinases, the key players in phosphoryl signal transduction, have been actively investigated as drug targets for complex diseases such as cancer, immune disorders, and Alzheimer's disease, with more than 60 successful drugs developed in the past 30 years. However, many of these single-kinase inhibitors show low efficacy and drug resistance has become an issue. Owing to the occurrence of highly conserved catalytic sites and shared signaling pathways within a kinase family, multi-target kinase inhibitors have attracted attention. RESULTS: To design and identify such pan-kinase family inhibitors (PKFIs), we proposed PKFI sets for eight families using 200,000 experimental bioactivity data points and applied a graph convolutional network (GCN) to build classification models. Furthermore, we identified and extracted family-sensitive (only present in a family) pre-moieties (parts of complete moieties) by utilizing a visualized explanation (i.e., where the model focuses on each input) method for deep learning, gradient-weighted class activation mapping (Grad-CAM). CONCLUSIONS: This study is the first to propose the PKFI sets, and our results point out and validate the power of GCN models in understanding the pre-moieties of PKFIs within and across different kinase families. Moreover, we highlight the discoverability of family-sensitive pre-moieties in PKFI identification and drug design.

BACKGROUND: De novo genome assembly is essential to modern genomics studies. As it is not biased by a reference, it is also a useful method for studying genomes with high variation, such as cancer genomes. De novo short-read assemblers commonly use de Bruijn graphs, where nodes are sequences of equal length k, also known as k-mers. Edges in this graph are established between nodes that overlap by [Formula: see text] bases, and nodes along unambiguous walks in the graph are subsequently merged. The selection of k is influenced by multiple factors, and optimizing this value results in a trade-off between graph connectivity and sequence contiguity. Ideally, multiple k sizes should be used, so lower values can provide good connectivity in lesser covered regions and higher values can increase contiguity in well-covered regions. However, current approaches that use multiple k values do not address the scalability issues inherent to the assembly of large genomes. RESULTS: Here we present RResolver, a scalable algorithm that takes a short-read de Bruijn graph assembly with a starting k as input and uses a k value closer to that of the read length to resolve repeats. RResolver builds a Bloom filter of sequencing reads which is used to evaluate the assembly graph path support at branching points and removes paths with insufficient support. RResolver runs efficiently, taking only 26 min on average for an ABySS human assembly with 48 threads and 60 GiB memory. Across all experiments, compared to a baseline assembly, RResolver improves scaffold contiguity (NGA50) by up to 15% and reduces misassemblies by up to 12%. CONCLUSIONS: RResolver adds a missing component to scalable de Bruijn graph genome assembly. By improving the initial and fundamental graph traversal outcome, all downstream ABySS algorithms greatly benefit by working with a more accurate and less complex representation of the genome. The RResolver code is integrated into ABySS and is available at https://github.com/bcgsc/abyss/tree/master/RResolver .

BACKGROUND: Drug-target interactions (DTIs) are critical for drug repurposing and elucidation of drug mechanisms, and are manually curated by large databases, such as ChEMBL, BindingDB, DrugBank and DrugTargetCommons. However, the number of curated articles likely constitutes only a fraction of all the articles that contain experimentally determined DTIs. Finding such articles and extracting the experimental information is a challenging task, and there is a pressing need for systematic approaches to assist the curation of DTIs. To this end, we applied Bidirectional Encoder Representations from Transformers (BERT) to identify such articles. Because DTI data intimately depends on the type of assays used to generate it, we also aimed to incorporate functions to predict the assay format. RESULTS: Our novel method identified 0.6 million articles (along with drug and protein information) which are not previously included in public DTI databases. Using 10-fold cross-validation, we obtained ~ 99% accuracy for identifying articles containing quantitative drug-target profiles. The F1 micro for the prediction of assay format is 88%, which leaves room for improvement in future studies. CONCLUSION: The BERT model in this study is robust and the proposed pipeline can be used to identify previously overlooked articles containing quantitative DTIs. Overall, our method provides a significant advancement in machine-assisted DTI extraction and curation. We expect it to be a useful addition to drug mechanism discovery and repurposing.

BACKGROUND: Microbial communities in the human body, also known as human microbiota, impact human health, such as colorectal cancer (CRC). However, the different roles that microbial communities play in healthy and disease hosts remain largely unknown. The microbial communities are typically recorded through the taxa counts of operational taxonomic units (OTUs). The sparsity and high correlations among OTUs pose major challenges for understanding the microbiota-disease relation. Furthermore, the taxa data are structured in the sense that OTUs are related evolutionarily by a hierarchical structure. RESULTS: In this study, we borrow the idea of super-variant from statistical genetics, and propose a new concept called super-taxon to exploit hierarchical structure of taxa for microbiome studies, which is essentially a combination of taxonomic units. Specifically, we model a genus which consists of a set of OTUs at low hierarchy and is designed to reflect both marginal and joint effects of OTUs associated with the risk of CRC to address these issues. We first demonstrate the power of super-taxon in detecting highly correlated OTUs. Then, we identify CRC-associated OTUs in two publicly available datasets via a discovery-validation procedure. Specifically, four species of two genera are found to be associated with CRC: Parvimonas micra, Parvimonas sp., Peptostreptococcus stomatis, and Peptostreptococcus anaerobius. More importantly, for the first time, we report the joint effect of Parvimonas micra and Parvimonas sp. (p = 0.0084) as well as that of Peptostrepto-coccus stomatis and Peptostreptococcus anaerobius (p = 8.21e-06) on CRC. The proposed approach provides a novel and useful tool for identifying disease-related microbes by taking the hierarchical structure of taxa into account and further sheds new lights on their potential joint effects as a community in disease development. CONCLUSIONS: Our work shows that proposed approaches are effective to study the microbiota-disease relation taking into account for the sparsity, hierarchical and correlated structure among microbes.

BACKGROUND: There is a growing body of evidence from biological experiments suggesting that microRNAs (miRNAs) play a significant regulatory role in both diverse cellular activities and pathological processes. Exploring miRNA-disease associations not only can decipher pathogenic mechanisms but also provide treatment solutions for diseases. As it is inefficient to identify undiscovered relationships between diseases and miRNAs using biotechnology, an explosion of computational methods have been advanced. However, the prediction accuracy of existing models is hampered by the sparsity of known association network and single-category feature, which is hard to model the complicated relationships between diseases and miRNAs. RESULTS: In this study, we advance a new computational framework (GATMDA) to discover unknown miRNA-disease associations based on graph attention network with multi-source information, which effectively fuses linear and non-linear features. In our method, the linear features of diseases and miRNAs are constructed by disease-lncRNA correlation profiles and miRNA-lncRNA correlation profiles, respectively. Then, the graph attention network is employed to extract the non-linear features of diseases and miRNAs by aggregating information of each neighbor with different weights. Finally, the random forest algorithm is applied to infer the disease-miRNA correlation pairs through fusing linear and non-linear features of diseases and miRNAs. As a result, GATMDA achieves impressive performance: an average AUC of 0.9566 with five-fold cross validation, which is superior to other previous models. In addition, case studies conducted on breast cancer, colon cancer and lymphoma indicate that 50, 50 and 48 out of the top fifty prioritized candidates are verified by biological experiments. CONCLUSIONS: The extensive experimental results justify the accuracy and utility of GATMDA and we could anticipate that it may regard as a utility tool for identifying unobserved disease-miRNA relationships.

BACKGROUND: While it has been known that human protein kinases mediate most signal transductions in cells and their dysfunction can result in inflammatory diseases and cancers, it remains a challenge to find effective kinase inhibitor as drugs for these diseases. One major challenge is the compensatory upregulation of related kinases following some critical kinase inhibition. To circumvent the compensatory effect, it is desirable to have inhibitors that inhibit all the kinases belonging to the same family, instead of targeting only a few kinases. However, finding inhibitors that target a whole kinase family is laborious and time consuming in wet lab. RESULTS: In this paper, we present a computational approach taking advantage of interpretable deep learning models to address this challenge. Specifically, we firstly collected 9,037 inhibitor bioassay results (with 3991 active and 5046 inactive pairs) for eight kinase families (including EGFR, Jak, GSK, CLK, PIM, PKD, Akt and PKG) from the ChEMBL25 Database and the Metz Kinase Profiling Data. We generated 238 binary moiety features for each inhibitor, and used the features as input to train eight deep neural networks (DNN) models to predict whether an inhibitor is active for each kinase family. We then employed the SHapley Additive exPlanations (SHAP) to analyze the importance of each moiety feature in each classification model, identifying moieties that are in the common kinase hinge sites across the eight kinase families, as well as moieties that are specific to some kinase families. We finally validated these identified moieties using experimental crystal structures to reveal their functional importance in kinase inhibition. CONCLUSION: With the SHAP methodology, we identified two common moieties for eight kinase families, 9 EGFR-specific moieties, and 6 Akt-specific moieties, that bear functional importance in kinase inhibition. Our result suggests that SHAP has the potential to help finding effective pan-kinase family inhibitors.

BACKGROUND: Nested and overlapping events are particularly frequent and informative structures in biomedical event extraction. However, state-of-the-art neural models either neglect those structures during learning or use syntactic features and external tools to detect them. To overcome these limitations, this paper presents and compares two neural models: a novel EXhaustive Neural Network (EXNN) and a Search-Based Neural Network (SBNN) for detection of nested and overlapping events. RESULTS: We evaluate the proposed models as an event detection component in isolation and within a pipeline setting. Evaluation in several annotated biomedical event extraction datasets shows that both EXNN and SBNN achieve higher performance in detecting nested and overlapping events, compared to the state-of-the-art model Turku Event Extraction System (TEES). CONCLUSIONS: The experimental results reveal that both EXNN and SBNN are effective for biomedical event extraction. Furthermore, results on a pipeline setting indicate that our models improve detection of events compared to models that use either gold or predicted named entities.

BACKGROUND: Due to the growing amount of COVID-19 research literature, medical experts, clinical scientists, and researchers frequently struggle to stay up to date on the most recent findings. There is a pressing need to assist researchers and practitioners in mining and responding to COVID-19-related questions on time. METHODS: This paper introduces CoQUAD, a question-answering system that can extract answers related to COVID-19 questions in an efficient manner. There are two datasets provided in this work: a reference-standard dataset built using the CORD-19 and LitCOVID initiatives, and a gold-standard dataset prepared by the experts from a public health domain. The CoQUAD has a Retriever component trained on the BM25 algorithm that searches the reference-standard dataset for relevant documents based on a question related to COVID-19. CoQUAD also has a Reader component that consists of a Transformer-based model, namely MPNet, which is used to read the paragraphs and find the answers related to a question from the retrieved documents. In comparison to previous works, the proposed CoQUAD system can answer questions related to early, mid, and post-COVID-19 topics. RESULTS: Extensive experiments on CoQUAD Retriever and Reader modules show that CoQUAD can provide effective and relevant answers to any COVID-19-related questions posed in natural language, with a higher level of accuracy. When compared to state-of-the-art baselines, CoQUAD outperforms the previous models, achieving an exact match ratio score of 77.50% and an F1 score of 77.10%. CONCLUSION: CoQUAD is a question-answering system that mines COVID-19 literature using natural language processing techniques to help the research community find the most recent findings and answer any related questions.

BACKGROUND: G-quadruplexes (G4s), formed within guanine-rich nucleic acids, are secondary structures involved in important biological processes. Although every G4 motif has the potential to form a stable G4 structure, not every G4 motif would, and accurate energy-based methods are needed to assess their structural stability. Here, we present a decision tree-based prediction tool, G4Boost, to identify G4 motifs and predict their secondary structure folding probability and thermodynamic stability based on their sequences, nucleotide compositions, and estimated structural topologies. RESULTS: G4Boost predicted the quadruplex folding state with an accuracy greater then 93% and an F1-score of 0.96, and the folding energy with an RMSE of 4.28 and R2 of 0.95 only by the means of sequence intrinsic feature. G4Boost was successfully applied and validated to predict the stability of experimentally-determined G4 structures, including for plants and humans. CONCLUSION: G4Boost outperformed the three machine-learning based prediction tools, DeepG4, Quadron, and G4RNA Screener, in terms of both accuracy and F1-score, and can be highly useful for G4 prediction to understand gene regulation across species including plants and humans.

BACKGROUND: This paper presents a new R/Bioconductor package, rprimer, for design of degenerate oligos and PCR assays for sequence variable viruses. A multiple DNA sequence alignment is used as input data, while the outputs consist of comprehensive tables (data frames) and dashboard-like plots. The workflow can be run directly from the R console or through a graphical user interface (Shiny application). Here, rprimer is demonstrated and evaluated by using it to design two norovirus genogroup I (GI) assays: one RT-qPCR assay for quantitative detection and one RT‑PCR assay for Sanger sequencing and polymerase-capsid based genotyping. RESULTS: The assays generated were evaluated using stool samples testing positive for norovirus GI. The RT-qPCR assay accurately amplified and quantified all samples and showed comparable performance to a widely-used standardised assay, while the RT-PCR assay resulted in successful sequencing and genotyping of all samples. Merits and limitations of the package were identified through comparison with three similar freely available software packages. Several features were comparable across the different tools, but important advantages of rprimer were its speed, flexibility in oligo design and capacity for visualisation. CONCLUSIONS: An R/Bioconductor package, rprimer, was developed and shown to be successful in designing primers and probes for quantitative detection and genotyping of a sequence-variable virus. The package provides an efficient, flexible and visual approach to degenerate oligo design, and can therefore assist in virus research and method development.

BACKGROUND: The biological relevance and accuracy of gene expression data depend on the adequacy of data normalization. This is both due to its role in resolving and accounting for technical variation and errors, and its defining role in shaping the viewpoint of biological interpretations. Still, the choice of the normalization method is often not explicitly motivated although this choice may be particularly decisive for conclusions in studies involving pronounced cellular plasticity. In this study, we highlight the consequences of using three fundamentally different modes of normalization for interpreting RNA-seq data from human skeletal muscle undergoing exercise-training-induced growth. Briefly, 25 participants conducted 12 weeks of high-load resistance training. Muscle biopsy specimens were sampled from m. vastus lateralis before, after two weeks of training (week 2) and after the intervention (week 12), and were subsequently analyzed using RNA-seq. Transcript counts were modeled as (1) per-library-size, (2) per-total-RNA, and (3) per-sample-size (per-mg-tissue). RESULT: Initially, the three modes of transcript modeling led to the identification of three unique sets of stable genes, which displayed differential expression profiles. Specifically, genes showing stable expression across samples in the per-library-size dataset displayed training-associated increases in per-total-RNA and per-sample-size datasets. These gene sets were then used for normalization of the entire dataset, providing transcript abundance estimates corresponding to each of the three biological viewpoints (i.e., per-library-size, per-total-RNA, and per-sample-size). The different normalization modes led to different conclusions, measured as training-associated changes in transcript expression. Briefly, for 27% and 20% of the transcripts, training was associated with changes in expression in per-total-RNA and per-sample-size scenarios, but not in the per-library-size scenario. At week 2, this led to opposite conclusions for 4% of the transcripts between per-library-size and per-sample-size datasets (↑ vs. ↓, respectively). CONCLUSION: Scientists should be explicit with their choice of normalization strategies and should interpret the results of gene expression analyses with caution. This is particularly important for data sets involving a limited number of genes or involving growing or differentiating cellular models, where the risk of biased conclusions is pronounced.

BACKGROUND: Several computational advances have been achieved in the drug discovery field, promoting the identification of novel drug-target interactions and new leads. However, most of these methodologies have been overlooking the importance of providing explanations to the decision-making process of deep learning architectures. In this research study, we explore the reliability of convolutional neural networks (CNNs) at identifying relevant regions for binding, specifically binding sites and motifs, and the significance of the deep representations extracted by providing explanations to the model's decisions based on the identification of the input regions that contributed the most to the prediction. We make use of an end-to-end deep learning architecture to predict binding affinity, where CNNs are exploited in their capacity to automatically identify and extract discriminating deep representations from 1D sequential and structural data. RESULTS: The results demonstrate the effectiveness of the deep representations extracted from CNNs in the prediction of drug-target interactions. CNNs were found to identify and extract features from regions relevant for the interaction, where the weight associated with these spots was in the range of those with the highest positive influence given by the CNNs in the prediction. The end-to-end deep learning model achieved the highest performance both in the prediction of the binding affinity and on the ability to correctly distinguish the interaction strength rank order when compared to baseline approaches. CONCLUSIONS: This research study validates the potential applicability of an end-to-end deep learning architecture in the context of drug discovery beyond the confined space of proteins and ligands with determined 3D structure. Furthermore, it shows the reliability of the deep representations extracted from the CNNs by providing explainability to the decision-making process.

BACKGROUND: Pan-omics, pan-cancer analysis has advanced our understanding of the molecular heterogeneity of cancer. However, such analyses have been limited in their ability to use information from multiple sources of data (e.g., omics platforms) and multiple sample sets (e.g., cancer types) to predict clinical outcomes. We address the issue of prediction across multiple high-dimensional sources of data and sample sets by using molecular patterns identified by BIDIFAC+, a method for integrative dimension reduction of bidimensionally-linked matrices, in a Bayesian hierarchical model. Our model performs variable selection through spike-and-slab priors that borrow information across clustered data. We use this model to predict overall patient survival from the Cancer Genome Atlas with data from 29 cancer types and 4 omics sources and use simulations to characterize the performance of the hierarchical spike-and-slab prior. RESULTS: We found that molecular patterns shared across all or most cancers were largely not predictive of survival. However, our model selected patterns unique to subsets of cancers that differentiate clinical tumor subtypes with markedly different survival outcomes. Some of these subtypes were previously established, such as subtypes of uterine corpus endometrial carcinoma, while others may be novel, such as subtypes within a set of kidney carcinomas. Through simulations, we found that the hierarchical spike-and-slab prior performs best in terms of variable selection accuracy and predictive power when borrowing information is advantageous, but also offers competitive performance when it is not. CONCLUSIONS: We address the issue of prediction across multiple sources of data by using results from BIDIFAC+ in a Bayesian hierarchical model for overall patient survival. By incorporating spike-and-slab priors that borrow information across cancers, we identified molecular patterns that distinguish clinical tumor subtypes within a single cancer and within a group of cancers. We also corroborate the flexibility and performance of using spike-and-slab priors as a Bayesian variable selection approach.

BACKGROUND: Single cell RNA-sequencing (scRNA-seq) has very rapidly become the new workhorse of modern biology providing an unprecedented global view on cellular diversity and heterogeneity. In particular, the structure of gene-gene expression correlation contains information on the underlying gene regulatory networks. However, interpretation of scRNA-seq data is challenging due to specific experimental error and biases that are unique to this kind of data including drop-out (or technical zeros). METHODS: To deal with this problem several methods for imputation of zeros for scRNA-seq have been developed. However, it is not clear how these processing steps affect inference of genetic networks from single cell data. Here, we introduce Biomodelling.jl, a tool for generation of synthetic scRNA-seq data using multiscale modelling of stochastic gene regulatory networks in growing and dividing cells. RESULTS: Our tool produces realistic transcription data with a known ground truth network topology that can be used to benchmark different approaches for gene regulatory network inference. Using this tool we investigate the impact of different imputation methods on the performance of several network inference algorithms. CONCLUSIONS: Biomodelling.jl provides a versatile and useful tool for future development and benchmarking of network inference approaches using scRNA-seq data.

BACKGROUND: Protein-protein interaction (PPI) plays an important role in regulating cells and signals. Despite the ongoing efforts of the bioassay group, continued incomplete data limits our ability to understand the molecular roots of human disease. Therefore, it is urgent to develop a computational method to predict PPIs from the perspective of molecular system. METHODS: In this paper, a highly efficient computational model, MTV-PPI, is proposed for PPI prediction based on a heterogeneous molecular network by learning inter-view protein sequences and intra-view interactions between molecules simultaneously. On the one hand, the inter-view feature is extracted from the protein sequence by k-mer method. On the other hand, we use a popular embedding method LINE to encode the heterogeneous molecular network to obtain the intra-view feature. Thus, the protein representation used in MTV-PPI is constructed by the aggregation of its inter-view feature and intra-view feature. Finally, random forest is integrated to predict potential PPIs. RESULTS: To prove the effectiveness of MTV-PPI, we conduct extensive experiments on a collected heterogeneous molecular network with the accuracy of 86.55%, sensitivity of 82.49%, precision of 89.79%, AUC of 0.9301 and AUPR of 0.9308. Further comparison experiments are performed with various protein representations and classifiers to indicate the effectiveness of MTV-PPI in predicting PPIs based on a complex network. CONCLUSION: The achieved experimental results illustrate that MTV-PPI is a promising tool for PPI prediction, which may provide a new perspective for the future interactions prediction researches based on heterogeneous molecular network.

BACKGROUND: Data transformations are commonly used in bioinformatics data processing in the context of data projection and clustering. The most used Euclidean metric is not scale invariant and therefore occasionally inappropriate for complex, e.g., multimodal distributed variables and may negatively affect the results of cluster analysis. Specifically, the squaring function in the definition of the Euclidean distance as the square root of the sum of squared differences between data points has the consequence that the value 1 implicitly defines a limit for distances within clusters versus distances between (inter-) clusters. METHODS: The Euclidean distances within a standard normal distribution (N(0,1)) follow a N(0,[Formula: see text]) distribution. The EDO-transformation of a variable X is proposed as [Formula: see text] following modeling of the standard deviation s by a mixture of Gaussians and selecting the dominant modes via item categorization. The method was compared in artificial and biomedical datasets with clustering of untransformed data, z-transformed data, and the recently proposed pooled variable scaling. RESULTS: A simulation study and applications to known real data examples showed that the proposed EDO scaling method is generally useful. The clustering results in terms of cluster accuracy, adjusted Rand index and Dunn's index outperformed the classical alternatives. Finally, the EDO transformation was applied to cluster a high-dimensional genomic dataset consisting of gene expression data for multiple samples of breast cancer tissues, and the proposed approach gave better results than classical methods and was compared with pooled variable scaling. CONCLUSIONS: For multivariate procedures of data analysis, it is proposed to use the EDO transformation as a better alternative to the established z-standardization, especially for nontrivially distributed data. The "EDOtrans" R package is available at https://cran.r-project.org/package=EDOtrans .

BACKGROUND: The Open Targets (OT) Platform integrates a wide range of data sources on target-disease associations to facilitate identification of potential therapeutic drug targets to treat human diseases. However, due to the complexity that targets are usually functionally pleiotropic and efficacious for multiple indications, challenges in identifying novel target to indication associations remain. Specifically, persistent need exists for new methods for integration of novel target-disease association evidence and biological knowledge bases via advanced computational methods. These offer promise for increasing power for identification of the most promising target-disease pairs for therapeutic development. Here we introduce a novel approach by integrating additional target-disease features with machine learning models to further uncover druggable disease to target indications. RESULTS: We derived novel target-disease associations as supplemental features to OT platform-based associations using three data sources: (1) target tissue specificity from GTEx expression profiles; (2) target semantic similarities based on gene ontology; and (3) functional interactions among targets by embedding them from protein-protein interaction (PPI) networks. Machine learning models were applied to evaluate feature importance and performance benchmarks for predicting targets with known drug indications. The evaluation results show the newly integrated features demonstrate higher importance than current features in OT. In addition, these also show superior performance over association benchmarks and may support discovery of novel therapeutic indications for highly pursued targets. CONCLUSION: Our newly generated features can be used to represent additional underlying biological relatedness among targets and diseases to further empower improved performance for predicting novel indications for drug targets through advanced machine learning models. The proposed methodology enables a powerful new approach for systematic evaluation of drug targets with novel indications.

Abundant datasets generated from various big science projects on diseases have presented great challenges and opportunities, which contributed to unfolding the complexity of diseases. The discovery of disease-associated molecular networks for each individual plays an important role in personalized therapy and precision treatment of cancer-based on the reference networks. However, there are no effective ways to distinguish the consistency of different reference networks. In this study, we developed a statistical method, i.e. a sample-specific differential network (SSDN), to construct and analyze such networks based on gene expression of a single sample against a reference dataset. We proved that the SSDN is structurally consistent even with different reference datasets if the reference dataset can follow certain conditions. The SSDN also can be used to identify patient-specific disease modules or network biomarkers as well as predict the potential driver genes of a tumor sample.

Distinct gene expression patterns within cells are foundational for the diversity of functions and unique characteristics observed in specific contexts, such as human tissues and cell types. Though some biological processes commonly occur across contexts, by harnessing the vast amounts of available gene expression data, we can decipher the processes that are unique to a specific context. Therefore, with the goal of developing a portrait of context-specific patterns to better elucidate how they govern distinct biological processes, this work presents a large-scale exploration of transcriptomic signatures across three different contexts (i.e., tissues, cell types, and cell lines) by leveraging over 600 gene expression datasets categorized into 98 subcontexts. The strongest pairwise correlations between genes from these subcontexts are used for the construction of co-expression networks. Using a network-based approach, we then pinpoint patterns that are unique and common across these subcontexts. First, we focused on patterns at the level of individual nodes and evaluated their functional roles using a human protein-protein interactome as a referential network. Next, within each context, we systematically overlaid the co-expression networks to identify specific and shared correlations as well as relations already described in scientific literature. Additionally, in a pathway-level analysis, we overlaid node and edge sets from co-expression networks against pathway knowledge to identify biological processes that are related to specific subcontexts or groups of them. Finally, we have released our data and scripts at https://zenodo.org/record/5831786 and https://github.com/ContNeXt/ , respectively and developed ContNeXt ( https://contnext.scai.fraunhofer.de/ ), a web application to explore the networks generated in this work.

BACKGROUND: Despite remarkable advances in cancer research, cancer remains one of the leading causes of death worldwide. Early detection of cancer and localization of the tissue of its origin are key to effective treatment. Here, we leverage technological advances in machine learning or artificial intelligence to design a novel framework for cancer diagnostics. Our proposed framework detects cancers and their tissues of origin using a unified model of cancers encompassing 33 cancers represented in The Cancer Genome Atlas (TCGA). Our model exploits the learned features of different cancers reflected in the respective dysregulated epigenomes, which arise early in carcinogenesis and differ remarkably between different cancer types or subtypes, thus holding a great promise in early cancer detection. RESULTS: Our comprehensive assessment of the proposed model on the 33 different tissues of origin demonstrates its ability to detect and classify cancers to a high accuracy (> 99% overall F-measure). Furthermore, our model distinguishes cancers from pre-cancerous lesions to metastatic tumors and discriminates between hypomethylation changes due to age related epigenetic drift and true cancer. CONCLUSIONS: Beyond detection of primary cancers, our proposed computational model also robustly detects tissues of origin of secondary cancers, including metastatic cancers, second primary cancers, and cancers of unknown primaries. Our assessment revealed the ability of this model to characterize pre-cancer samples, a significant step forward in early cancer detection. Deployed broadly this model can deliver accurate diagnosis for a greatly expanded target patient population.

BACKGROUND: Many wild species have suffered drastic population size declines over the past centuries, which have led to 'genomic erosion' processes characterized by reduced genetic diversity, increased inbreeding, and accumulation of harmful mutations. Yet, genomic erosion estimates of modern-day populations often lack concordance with dwindling population sizes and conservation status of threatened species. One way to directly quantify the genomic consequences of population declines is to compare genome-wide data from pre-decline museum samples and modern samples. However, doing so requires computational data processing and analysis tools specifically adapted to comparative analyses of degraded, ancient or historical, DNA data with modern DNA data as well as personnel trained to perform such analyses. RESULTS: Here, we present a highly flexible, scalable, and modular pipeline to compare patterns of genomic erosion using samples from disparate time periods. The GenErode pipeline uses state-of-the-art bioinformatics tools to simultaneously process whole-genome re-sequencing data from ancient/historical and modern samples, and to produce comparable estimates of several genomic erosion indices. No programming knowledge is required to run the pipeline and all bioinformatic steps are well-documented, making the pipeline accessible to users with different backgrounds. GenErode is written in Snakemake and Python3 and uses Conda and Singularity containers to achieve reproducibility on high-performance compute clusters. The source code is freely available on GitHub ( https://github.com/NBISweden/GenErode ). CONCLUSIONS: GenErode is a user-friendly and reproducible pipeline that enables the standardization of genomic erosion indices from temporally sampled whole genome re-sequencing data.

BACKGROUND: Next-generation sequencing pipelines often perform error correction as a preprocessing step to obtain cleaned input data. State-of-the-art error correction programs are able to reliably detect and correct the majority of sequencing errors. However, they also introduce new errors by making false-positive corrections. These correction mistakes can have negative impact on downstream analysis, such as k-mer statistics, de-novo assembly, and variant calling. This motivates the need for more precise error correction tools. RESULTS: We present CARE 2.0, a context-aware read error correction tool based on multiple sequence alignment targeting Illumina datasets. In addition to a number of newly introduced optimizations its most significant change is the replacement of CARE 1.0's hand-crafted correction conditions with a novel classifier based on random decision forests trained on Illumina data. This results in up to two orders-of-magnitude fewer false-positive corrections compared to other state-of-the-art error correction software. At the same time, CARE 2.0 is able to achieve high numbers of true-positive corrections comparable to its competitors. On a simulated full human dataset with 914M reads CARE 2.0 generates only 1.2M false positives (FPs) (and 801.4M true positives (TPs)) at a highly competitive runtime while the best corrections achieved by other state-of-the-art tools contain at least 3.9M FPs and at most 814.5M TPs. Better de-novo assembly and improved k-mer analysis show the applicability of CARE 2.0 to real-world data. CONCLUSION: False-positive corrections can negatively influence down-stream analysis. The precision of CARE 2.0 greatly reduces the number of those corrections compared to other state-of-the-art programs including BFC, Karect, Musket, Bcool, SGA, and Lighter. Thus, higher-quality datasets are produced which improve k-mer analysis and de-novo assembly in real-world datasets which demonstrates the applicability of machine learning techniques in the context of sequencing read error correction. CARE 2.0 is written in C++/CUDA for Linux systems and can be run on the CPU as well as on CUDA-enabled GPUs. It is available at https://github.com/fkallen/CARE .

BACKGROUND: An important initial phase of arguably most homology search and alignment methods such as required for genome alignments is seed finding. The seed finding step is crucial to curb the runtime as potential alignments are restricted to and anchored at the sequence position pairs that constitute the seed. To identify seeds, it is good practice to use sets of spaced seed patterns, a method that locally compares two sequences and requires exact matches at certain positions only. RESULTS: We introduce a new method for filtering alignment seeds that we call geometric hashing. Geometric hashing achieves a high specificity by combining non-local information from different seeds using a simple hash function that only requires a constant and small amount of additional time per spaced seed. Geometric hashing was tested on the task of finding homologous positions in the coding regions of human and mouse genome sequences. Thereby, the number of false positives was decreased about million-fold over sets of spaced seeds while maintaining a very high sensitivity. CONCLUSIONS: An additional geometric hashing filtering phase could improve the run-time, accuracy or both of programs for various homology-search-and-align tasks.

BACKGROUND: Drug-Drug interactions (DDIs) are a challenging problem in drug research. Drug combination therapy is an effective solution to treat diseases, but it can also cause serious side effects. Therefore, DDIs prediction is critical in pharmacology. Recently, researchers have been using deep learning techniques to predict DDIs. However, these methods only consider single information of the drug and have shortcomings in robustness and scalability. RESULTS: In this paper, we propose a multi-type feature fusion based on graph neural network model (MFFGNN) for DDI prediction, which can effectively fuse the topological information in molecular graphs, the interaction information between drugs and the local chemical context in SMILES sequences. In MFFGNN, to fully learn the topological information of drugs, we propose a novel feature extraction module to capture the global features for the molecular graph and the local features for each atom of the molecular graph. In addition, in the multi-type feature fusion module, we use the gating mechanism in each graph convolution layer to solve the over-smoothing problem during information delivery. We perform extensive experiments on multiple real datasets. The results show that MFFGNN outperforms some state-of-the-art models for DDI prediction. Moreover, the cross-dataset experiment results further show that MFFGNN has good generalization performance. CONCLUSIONS: Our proposed model can efficiently integrate the information from SMILES sequences, molecular graphs and drug-drug interaction networks. We find that a multi-type feature fusion model can accurately predict DDIs. It may contribute to discovering novel DDIs.

BACKGROUND: Elucidating cellular metabolism led to many breakthroughs in biotechnology, synthetic biology, and health sciences. To date, deriving metabolic fluxes by 13C tracer experiments is the most prominent approach for studying metabolic fluxes quantitatively, often with high accuracy and precision. However, the technique has a high demand for experimental resources. Alternatively, flux balance analysis (FBA) has been employed to estimate metabolic fluxes without labeling experiments. It is less informative but can benefit from the low costs and low experimental efforts and gain flux estimates in experimentally difficult conditions. Methods to integrate relevant experimental data have been emerged to improve FBA flux estimations. Data from transcription profiling is often selected since it is easy to generate at the genome scale, typically embedded by a discretization of differential and non-differential expressed genes coding for the respective enzymes. RESULT: We established the novel method Linear Programming based Gene Expression Model (LPM-GEM). LPM-GEM linearly embeds gene expression into FBA constraints. We implemented three strategies to reduce thermodynamically infeasible loops, which is a necessary prerequisite for such an omics-based model building. As a case study, we built a model of B. subtilis grown in eight different carbon sources. We obtained good flux predictions based on the respective transcription profiles when validating with 13C tracer based metabolic flux data of the same conditions. We could well predict the specific carbon sources. When testing the model on another, unseen dataset that was not used during training, good prediction performance was also observed. Furthermore, LPM-GEM outperformed a well-established model building methods. CONCLUSION: Employing LPM-GEM integrates gene expression data efficiently. The method supports gene expression-based FBA models and can be applied as an alternative to estimate metabolic fluxes when tracer experiments are inappropriate.

Erratum in BMC Bioinformatics. 2022 Jun 27;23(1):255.