BACKGROUND: Prokaryotic viruses referred to as phages can be divided into virulent and temperate phages. Distinguishing virulent and temperate phage-derived sequences in metavirome data is important for elucidating their different roles in interactions with bacterial hosts and regulation of microbial communities. However, there is no experimental or computational approach to effectively classify their sequences in culture-independent metavirome. We present a new computational method, DeePhage, which can directly and rapidly judge each read or contig as a virulent or temperate phage-derived fragment. FINDINGS: DeePhage uses a "one-hot" encoding form to represent DNA sequences in detail. Sequence signatures are detected via a convolutional neural network to obtain valuable local features. The accuracy of DeePhage on 5-fold cross-validation reaches as high as 89%, nearly 10% and 30% higher than that of 2 similar tools, PhagePred and PHACTS. On real metavirome, DeePhage correctly predicts the highest proportion of contigs when using BLAST as annotation, without apparent preferences. Besides, DeePhage reduces running time vs PhagePred and PHACTS by 245 and 810 times, respectively, under the same computational configuration. By direct detection of the temperate viral fragments from metagenome and metavirome, we furthermore propose a new strategy to explore phage transformations in the microbial community. The ability to detect such transformations provides us a new insight into the potential treatment for human disease. CONCLUSIONS: DeePhage is a novel tool developed to rapidly and efficiently identify 2 kinds of phage fragments especially for metagenomics analysis. DeePhage is freely available via http://cqb.pku.edu.cn/ZhuLab/DeePhage or https://github.com/shufangwu/DeePhage.

BACKGROUND: Recently many new deep learning-based variant-calling methods like DeepVariant have emerged as more accurate compared with conventional variant-calling algorithms such as GATK HaplotypeCaller, Sterlka2, and Freebayes albeit at higher computational costs. Therefore, there is a need for more scalable and higher performance workflows of these deep learning methods. Almost all existing cluster-scaled variant-calling workflows that use Apache Spark/Hadoop as big data frameworks loosely integrate existing single-node pre-processing and variant-calling applications. Using Apache Spark just for distributing/scheduling data among loosely coupled applications or using I/O-based storage for storing the output of intermediate applications does not exploit the full benefit of Apache Spark in-memory processing. To achieve this, we propose a native Spark-based workflow that uses Python and Apache Arrow to enable efficient transfer of data between different workflow stages. This benefits from the ease of programmability of Python and the high efficiency of Arrow's columnar in-memory data transformations. RESULTS: Here we present a scalable, parallel, and efficient implementation of next-generation sequencing data pre-processing and variant-calling workflows. Our design tightly integrates most pre-processing workflow stages, using Spark built-in functions to sort reads by coordinates and mark duplicates efficiently. Our approach outperforms state-of-the-art implementations by >2 times for the pre-processing stages, creating a scalable and high-performance solution for DeepVariant for both CPU-only and CPU + GPU clusters. CONCLUSIONS: We show the feasibility and easy scalability of our approach to achieve high performance and efficient resource utilization for variant-calling analysis on high-performance computing clusters using the standardized Apache Arrow data representations. All codes, scripts, and configurations used to run our implementations are publicly available and open sourced; see https://github.com/abs-tudelft/variant-calling-at-scale.

Machine learning brings the hope of finding new biomarkers extracted from cohorts with rich biomedical measurements. A good biomarker is one that gives reliable detection of the corresponding condition. However, biomarkers are often extracted from a cohort that differs from the target population. Such a mismatch, known as a dataset shift, can undermine the application of the biomarker to new individuals. Dataset shifts are frequent in biomedical research, e.g.,  because of recruitment biases. When a dataset shift occurs, standard machine-learning techniques do not suffice to extract and validate biomarkers. This article provides an overview of when and how dataset shifts break machine-learning-extracted biomarkers, as well as detection and correction strategies.

BACKGROUND: B-cell immunoglobulin repertoires with paired heavy and light chain can be determined by means of 10X single-cell V(D)J sequencing. Precise and quick analysis of 10X single-cell immunoglobulin repertoires remains a challenge owing to the high diversity of immunoglobulin repertoires and a lack of specialized software that can analyze such diverse data. FINDINGS: In this study, specialized software for 10X single-cell immunoglobulin repertoire analysis was developed. SCIGA (Single-Cell Immunoglobulin Repertoire Analysis) is an easy-to-use pipeline that performs read trimming, immunoglobulin sequence assembly and annotation, heavy and light chain pairing, statistical analysis, visualization, and multiple sample integration analysis, which is all achieved by using a 1-line command. Then SCIGA was used to profile the single-cell immunoglobulin repertoires of 9 patients with coronavirus disease 2019 (COVID-19). Four neutralizing antibodies against severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) were identified from these repertoires. CONCLUSIONS: SCIGA provides a complete and quick analysis for 10X single-cell V(D)J sequencing datasets. It can help researchers to interpret B-cell immunoglobulin repertoires with paired heavy and light chain.

BACKGROUND: Long-read sequencing has enabled unprecedented surveys of structural variation across the entire human genome. To maximize the potential of long-read sequencing in this context, novel mapping methods have emerged that have primarily focused on either speed or accuracy. Various heuristics and scoring schemas have been implemented in widely used read mappers (minimap2 and NGMLR) to optimize for speed or accuracy, which have variable performance across different genomic regions and for specific structural variants. Our hypothesis is that constraining read mapping to the use of a single gap penalty across distinct mutational hot spots reduces read alignment accuracy and impedes structural variant detection. FINDINGS: We tested our hypothesis by implementing a read-mapping pipeline called Vulcan that uses two distinct gap penalty modes, which we refer to as dual-mode alignment. The high-level idea is that Vulcan leverages the computed normalized edit distance of the mapped reads via minimap2 to identify poorly aligned reads and realigns them using the more accurate yet computationally more expensive long-read mapper (NGMLR). In support of our hypothesis, we show that Vulcan improves the alignments for Oxford Nanopore Technology long reads for both simulated and real datasets. These improvements, in turn, lead to improved accuracy for structural variant calling performance on human genome datasets compared to either of the read-mapping methods alone. CONCLUSIONS: Vulcan is the first long-read mapping framework that combines two distinct gap penalty modes for improved structural variant recall and precision. Vulcan is open-source and available under the MIT License at https://gitlab.com/treangenlab/vulcan.

BACKGROUND: The microbiota of the female reproductive tract is increasingly recognized as playing fundamental roles in animal reproduction. To explore the relative contribution of reproductive tract microbiomes to egg production in chickens, we investigated the microbiota in multiple reproductive and digestive tract sites from 128 female layer (egg-producing) chickens in comparable environments. RESULTS: We identified substantial differences between the diversity, composition, and predicted function of site-associated microbiota. Differences in reproductive tract microbiota were more strongly associated with egg production than those in the digestive tract. We identified 4 reproductive tract microbial species, Bacteroides fragilis, Bacteroides salanitronis, Bacteroides barnesiae, and Clostridium leptum, that were related to immune function and potentially contribute to enhanced egg production. CONCLUSIONS: These findings provide insights into the diverse microbiota characteristics of reproductive and digestive tracts and may help in designing strategies for controlling and manipulating chicken reproductive tract microbiota to improve egg production.

BACKGROUND: Recent technological advances have resulted in an unprecedented increase in publicly available biomedical data, yet the reuse of the data is often precluded by experimental bias and a lack of annotation depth and consistency. Missing annotations makes it impossible for researchers to find datasets specific to their needs. FINDINGS: Here, we investigate RNA-sequencing metadata prediction based on gene expression values. We present a deep-learning-based domain adaptation algorithm for the automatic annotation of RNA-sequencing metadata. We show, in multiple experiments, that our model is better at integrating heterogeneous training data compared with existing linear regression-based approaches, resulting in improved tissue type classification. By using a model architecture similar to Siamese networks, the algorithm can learn biases from datasets with few samples. CONCLUSION: Using our novel domain adaptation approach, we achieved metadata annotation accuracies up to 15.7% better than a previously published method. Using the best model, we provide a list of >10,000 novel tissue and sex label annotations for 8,495 unique SRA samples. Our approach has the potential to revive idle datasets by automated annotation making them more searchable.

BACKGROUND: Artifact chimeric reads are enriched in next-generation sequencing data generated from formalin-fixed paraffin-embedded (FFPE) samples. Previous work indicated that these reads are characterized by erroneous split-read support that is interpreted as evidence of structural variants. Thus, a large number of false-positive structural variants are detected. To our knowledge, no tool is currently available to specifically call or filter structural variants in FFPE samples. To overcome this gap, we developed 2 R packages: SimFFPE and FilterFFPE. RESULTS: SimFFPE is a read simulator, specifically designed for next-generation sequencing data from FFPE samples. A mixture of characteristic artifact chimeric reads, as well as normal reads, is generated. FilterFFPE is a filtration algorithm, removing artifact chimeric reads from sequencing data while keeping real chimeric reads. To evaluate the performance of FilterFFPE, we performed structural variant calling with 3 common tools (Delly, Lumpy, and Manta) with and without prior filtration with FilterFFPE. After applying FilterFFPE, the mean positive predictive value improved from 0.27 to 0.48 in simulated samples and from 0.11 to 0.27 in real samples, while sensitivity remained basically unchanged or even slightly increased. CONCLUSIONS: FilterFFPE improves the performance of SV calling in FFPE samples. It was validated by analysis of simulated and real data.

BACKGROUND: Pooling cells from multiple biological samples prior to library preparation within the same single-cell RNA sequencing experiment provides several advantages, including lower library preparation costs and reduced unwanted technological variation, such as batch effects. Computational demultiplexing tools based on natural genetic variation between individuals provide a simple approach to demultiplex samples, which does not require complex additional experimental procedures. However, to our knowledge these tools have not been evaluated in cancer, where somatic variants, which could differ between cells from the same sample, may obscure the signal in natural genetic variation. RESULTS: Here, we performed in silico benchmark evaluations by combining raw sequencing reads from multiple single-cell samples in high-grade serous ovarian cancer, which has a high copy number burden, and lung adenocarcinoma, which has a high tumor mutational burden. Our results confirm that genetic demultiplexing tools can be effectively deployed on cancer tissue using a pooled experimental design, although high proportions of ambient RNA from cell debris reduce performance. CONCLUSIONS: This strategy provides significant cost savings through pooled library preparation. To facilitate similar analyses at the experimental design phase, we provide freely accessible code and a reproducible Snakemake workflow built around the best-performing tools found in our in silico benchmark evaluations, available at https://github.com/lmweber/snp-dmx-cancer.

BACKGROUND: The Investigation/Study/Assay (ISA) Metadata Framework is an established and widely used set of open source community specifications and software tools for enabling discovery, exchange, and publication of metadata from experiments in the life sciences. The original ISA software suite provided a set of user-facing Java tools for creating and manipulating the information structured in ISA-Tab-a now widely used tabular format. To make the ISA framework more accessible to machines and enable programmatic manipulation of experiment metadata, the JSON serialization ISA-JSON was developed. RESULTS: In this work, we present the ISA API, a Python library for the creation, editing, parsing, and validating of ISA-Tab and ISA-JSON formats by using a common data model engineered as Python object classes. We describe the ISA API feature set, early adopters, and its growing user community. CONCLUSIONS: The ISA API provides users with rich programmatic metadata-handling functionality to support automation, a common interface, and an interoperable medium between the 2 ISA formats, as well as with other life science data formats required for depositing data in public databases.

BACKGROUND: Targeted diagnosis and treatment options are dependent on insights drawn from multi-modal analysis of large-scale biomedical datasets. Advances in genomics sequencing, image processing, and medical data management have supported data collection and management within medical institutions. These efforts have produced large-scale datasets and have enabled integrative analyses that provide a more thorough look of the impact of a disease on the underlying system. The integration of large-scale biomedical data commonly involves several complex data transformation steps, such as combining datasets to build feature vectors for learning analysis. Thus, scalable data integration solutions play a key role in the future of targeted medicine. Though large-scale data processing frameworks have shown promising performance for many domains, they fail to support scalable processing of complex datatypes. SOLUTION: To address these issues and achieve scalable processing of multi-modal biomedical data, we present TraNCE, a framework that automates the difficulties of designing distributed analyses with complex biomedical data types. PERFORMANCE: We outline research and clinical applications for the platform, including data integration support for building feature sets for classification. We show that the system is capable of outperforming the common alternative, based on "flattening" complex data structures, and runs efficiently when alternative approaches are unable to perform at all.

BACKGROUND: High-quality phenotype definitions are desirable to enable the extraction of patient cohorts from large electronic health record repositories and are characterized by properties such as portability, reproducibility, and validity. Phenotype libraries, where definitions are stored, have the potential to contribute significantly to the quality of the definitions they host. In this work, we present a set of desiderata for the design of a next-generation phenotype library that is able to ensure the quality of hosted definitions by combining the functionality currently offered by disparate tooling. METHODS: A group of researchers examined work to date on phenotype models, implementation, and validation, as well as contemporary phenotype libraries developed as a part of their own phenomics communities. Existing phenotype frameworks were also examined. This work was translated and refined by all the authors into a set of best practices. RESULTS: We present 14 library desiderata that promote high-quality phenotype definitions, in the areas of modelling, logging, validation, and sharing and warehousing. CONCLUSIONS: There are a number of choices to be made when constructing phenotype libraries. Our considerations distil the best practices in the field and include pointers towards their further development to support portable, reproducible, and clinically valid phenotype design. The provision of high-quality phenotype definitions enables electronic health record data to be more effectively used in medical domains.