Improving viral annotation with artificial intelligence.

Viruses of bacteria, "phages," are fundamental, poorly understood components of microbial community structure and function. Additionally, their dependence on hosts for replication positions phages as unique sensors of ecosystem features and environmental pressures. High-throughput sequencing approaches have begun to give us access to the diversity and range of phage populations in complex microbial community samples, and metagenomics is currently the primary tool with which we study phage populations. The study of phages by metagenomic sequencing, however, is fundamentally limited by viral diversity, which results in the vast majority of viral genomes and metagenome-annotated genomes lacking annotation. To harness bacteriophages for applications in human and environmental health and disease, we need new methods to organize and annotate viral sequence diversity. We recently demonstrated that methods that leverage self-supervised representation learning can supplement statistical sequence representations for remote viral protein homology detection in the ocean virome and propose that consideration of the functional content of viral sequences allows for the identification of similarity in otherwise sequence-diverse viruses and viral-like elements for biological discovery. In this review, we describe the potential and pitfalls of large language models for viral annotation. We describe the need for new approaches to annotate viral sequences in metagenomes, the fundamentals of what protein language models are and how one can use them for sequence annotation, the strengths and weaknesses of these models, and future directions toward developing better models for viral annotation more broadly.

Large language models improve annotation of prokaryotic viral proteins.

Viral genomes are poorly annotated in metagenomic samples, representing an obstacle to understanding viral diversity and function. Current annotation approaches rely on alignment-based sequence homology methods, which are limited by the paucity of characterized viral proteins and divergence among viral sequences. Here we show that protein language models can capture prokaryotic viral protein function, enabling new portions of viral sequence space to be assigned biologically meaningful labels. When applied to global ocean virome data, our classifier expanded the annotated fraction of viral protein families by 29%. Among previously unannotated sequences, we highlight the identification of an integrase defining a mobile element in marine picocyanobacteria and a capsid protein that anchors globally widespread viral elements. Furthermore, improved high-level functional annotation provides a means to characterize similarities in genomic organization among diverse viral sequences. Protein language models thus enhance remote homology detection of viral proteins, serving as a useful complement to existing approaches.

Large language models improve annotation of viral proteins.

Viral sequences are poorly annotated in environmental samples, a major roadblock to understanding how viruses influence microbial community structure. Current annotation approaches rely on alignment-based sequence ho-mology methods, which are limited by available viral sequences and sequence divergence in viral proteins. Here, we show that protein language model representations capture viral protein function beyond the limits of remote sequence homology by targeting two axes of viral sequence annotation: systematic labeling of protein families and function identification for biologic discovery. Protein language model representations capture protein functional properties specific to viruses and expand the annotated fraction of ocean virome viral protein sequences by 37%. Among unannotated viral protein families, we identify a novel DNA editing protein family that defines a new mobile element in marine picocyanobacteria. Protein language models thus significantly enhance remote homology detection of viral proteins and can be utilized to enable new biological discovery across diverse functional categories.

Word embeddings trained on published case reports are lightweight, effective for clinical tasks, and free of protected health information.

OBJECTIVE: Quantify tradeoffs in performance, reproducibility, and resource demands across several strategies for developing clinically relevant word embeddings. MATERIALS AND METHODS: We trained separate embeddings on all full-text manuscripts in the Pubmed Central (PMC) Open Access subset, case reports therein, the English Wikipedia corpus, the Medical Information Mart for Intensive Care (MIMIC) III dataset, and all notes in the University of Pennsylvania Health System (UPHS) electronic health record. We tested embeddings in six clinically relevant tasks including mortality prediction and de-identification, and assessed performance using the scaled Brier score (SBS) and the proportion of notes successfully de-identified, respectively. RESULTS: Embeddings from UPHS notes best predicted mortality (SBS 0.30, 95% CI 0.15 to 0.45) while Wikipedia embeddings performed worst (SBS 0.12, 95% CI -0.05 to 0.28). Wikipedia embeddings most consistently (78% of notes) and the full PMC corpus embeddings least consistently (48%) de-identified notes. Across all six tasks, the full PMC corpus demonstrated the most consistent performance, and the Wikipedia corpus the least. Corpus size ranged from 49 million tokens (PMC case reports) to 10 billion (UPHS). DISCUSSION: Embeddings trained on published case reports performed as least as well as embeddings trained on other corpora in most tasks, and clinical corpora consistently outperformed non-clinical corpora. No single corpus produced a strictly dominant set of embeddings across all tasks and so the optimal training corpus depends on intended use. CONCLUSION: Embeddings trained on published case reports performed comparably on most clinical tasks to embeddings trained on larger corpora. Open access corpora allow training of clinically relevant, effective, and reproducible embeddings.

modEnrichr: a suite of gene set enrichment analysis tools for model organisms.

High-throughput experiments produce increasingly large datasets that are difficult to analyze and integrate. While most data integration approaches focus on aligning metadata, data integration can be achieved by abstracting experimental results into gene sets. Such gene sets can be made available for reuse through gene set enrichment analysis tools such as Enrichr. Enrichr currently only supports gene sets compiled from human and mouse, limiting accessibility for investigators that study other model organisms. modEnrichr is an expansion of Enrichr for four model organisms: fish, fly, worm and yeast. The gene set libraries within FishEnrichr, FlyEnrichr, WormEnrichr and YeastEnrichr are created from the Gene Ontology, mRNA expression profiles, GeneRIF, pathway databases, protein domain databases and other organism-specific resources. Additionally, libraries were created by predicting gene function from RNA-seq co-expression data processed uniformly from the gene expression omnibus for each organism. The modEnrichr suite of tools provides the ability to convert gene lists across species using an ortholog conversion tool that automatically detects the species. For complex analyses, modEnrichr provides API access that enables submitting batch queries. In summary, modEnrichr leverages existing model organism databases and other resources to facilitate comprehensive hypothesis generation through data integration.