TransFactor-prediction of pro-viral SARS-CoV-2 host factors using a protein language model.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40929136", "kind": "science-record", "revision": 3, "content_hash": "sha256:c2045aadea6b4e2b7522c3631ec68979285af5eb300ada7d9a8be747d593f682", "created_at": "2026-11-01T20:31:01Z", "updated_at": "2026-11-01T22:14:41Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "TransFactor-prediction of pro-viral SARS-CoV-2 host factors using a protein language model.", "doi": "10.1093/bioinformatics/btaf491", "pmid": "40929136", "authors": ["Yang An", "Valter Bergant", "Samuele Firmani", "Corinna Grünke", "Batiste Bonnal", "Alexander Henrici", "Andreas Pichlmair", "Benjamin Schubert", "Annalisa Marsico"], "journal": "Bioinformatics (Oxford, England)", "year": 2025, "abstract": "MOTIVATION: Recent pandemics have revealed significant gaps in our understanding of viral pathogenesis, exposing an urgent need for methods to identify and prioritize key host proteins (host factors) as potential targets for antiviral treatments. De novo generation of experimental datasets is limited by their heterogeneity, and for looming future pandemics, may not be feasible due to limitations of experimental approaches.\nRESULTS: Here, we present TransFactor, a computational framework for predicting and prioritizing candidate host factors using only protein sequence data. It leverages the pre-trained ESM-2 protein language model, fine-tuned on a limited set of experimentally determined host factors aggregated from 33 independent SARS-CoV-2 studies. TransFactor outperforms machine and deep learning baselines and its predictions align with Gene Ontology enrichments of known host factors, but also provide interpretability through a computational alanine scan, enabling the identification of pro-viral protein domains such as COMM, PX, and RRM, that may be used to direct experimental investigations of virus biology and guide rational design of antiviral therapies. Our findings demonstrate the potential of transformer-based models to advance host factor prediction, providing a framework extendable to orthogonal input modalities and other infectious diseases, enhancing our preparedness for current and future viral threats.\nAVAILABILITY AND IMPLEMENTATION: Source code is available at https://github.com/marsico-lab/TransFactor. A full reproducibility package, including code, trained models, and data, is archived on Zenodo (https://doi.org/10.5281/zenodo.16793684).", "claims": [{"id": "claim-method", "statement": "For domain-wise statistical testing of significant deviations of Δy^Ala (Fig. 4, available as supplementary data at Bioinformatics online), we used the one-sided Wilcoxon rank-sum test and compared Δy^Ala values within domains to all values across all proteins for any given alanine scan window. The thus obtained P-values were further FDR-adjusted.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40929136", "locator": "sections[10] \"2.6 Model’s interpretation through computational alanine scan\" paragraph 3", "quote": "For domain-wise statistical testing of significant deviations of Δy^Ala (Fig. 4, available as supplementary data at Bioinformatics online), we used the one-sided Wilcoxon rank-sum test and compared Δy^Ala values within domains to all values across all proteins for any given alanine scan window. The thus obtained P-values were further FDR-adjusted."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Source code is available at https://github.com/marsico-lab/TransFactor. A full reproducibility package, including code, trained models, and data, is archived on Zenodo (https://doi.org/10.5281/zenodo.16793684).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40929136", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "Source code is available at https://github.com/marsico-lab/TransFactor. A full reproducibility package, including code, trained models, and data, is archived on Zenodo (https://doi.org/10.5281/zenodo.16793684)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "TransFactor outperforms machine and deep learning baselines, its predictions align with Gene Ontology enrichments of known host factors, and a computational alanine scan identifies potentially pro-viral protein domains such as COMM, PX, and RRM.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:40929136", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "TransFactor outperforms machine and deep learning baselines and its predictions align with Gene Ontology enrichments of known host factors, but also provide interpretability through a computational alanine scan, enabling the identification of pro-viral protein domains such as COMM, PX, and RRM, that may be used to direct experimental investigations of virus biology and guide rational design of antiviral therapies."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "TransFactor outperforms machine and deep learning baselines, its predictions align with Gene Ontology enrichments of known host factors, and a computational alanine scan identifies potentially pro-viral protein domains such as COMM, PX, and RRM.", "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:40929136"], "outputs": ["the published estimate and its evidence"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data from the named repository", "kind": "data-preparation", "state": "blocked", "blocked_on": "data:accession_absent", "description": "The GEO series accession resolves and its sample accessions are listed. This lane did not download the dataset or read its licence.", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "blocked", "blocked_on": "method:group_comparison_wilcoxon", "description": "Apply the paper's statistical method to the resolved series and compare the result with the published target.", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:run_analysis blocked on method:group_comparison_wilcoxon", "step:obtain_source_data blocked on data:accession_absent"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40929136", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/bioinformatics/btaf491", "sha256": "sha256:4ef1c8a2a90374e2b4d81eeafe9b5470de87efe52b7dae45a5c3229fa73bca38", "bytes": 51030, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/bioinformatics/btaf491", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12449051", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "group_comparison", "specific": "wilcoxon", "label": "Group comparison", "dsl_operations": [], "missing_operations": ["group_comparison_wilcoxon"], "expressible": false, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "For domain-wise statistical testing of significant deviations of Δy^Ala (Fig. 4, available as supplementary data at Bioinformatics online), we used the one-sided Wilcoxon rank-sum test and compared Δy^Ala values within domains to all values across all proteins for any given alanine scan window. The thus obtained P-values were further FDR-adjusted."}}], "targets": [], "gaps": ["method.group_comparison_wilcoxon"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "blocked", "tier": "R4", "blocking_axis": "data", "blocked_on": "data:accession_absent", "axes": {"method": {"tier": "R1", "expressible": false, "required_operations": [], "missing_operations": ["group_comparison_wilcoxon"], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: wilcoxon."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R4", "reachable": false, "accessions": [], "resolved_accessions": [], "statements": ["Source code is available at https://github.com/marsico-lab/TransFactor. A full reproducibility package, including code, trained models, and data, is archived on Zenodo (https://doi.org/10.5281/zenodo.16793684)."], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:40929136"], "steps": []}, "must_build": {"dsl_operations": [{"operation": "group_comparison_wilcoxon", "unlocks_papers": null, "priority": null}], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:None"]}, "gaps": ["data:accession_absent"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T20:01:21Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 13214, "completion_tokens": 2157, "cached_tokens": 264}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:40929136", "type": "paper", "label": "pmid:40929136"}, {"id": "source:pmid:40929136", "type": "manuscript", "label": "PMID 40929136 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:40929136", "type": "paper", "label": "pmid:40929136"}, {"id": "source:pmid:40929136", "type": "manuscript", "label": "PMID 40929136 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-40929136", "type": "extraction", "used": ["source:pmid:40929136"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-None", "type": "accession_resolution", "used": ["data:geo:None"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}, {"id": "agent:minimax-reader", "type": "software", "label": "MiniMax literature reader"}], "source_run_id": "reading-sci-2026-11-01", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:40929136", "parent_hash": "sha256:2e75856514b72fa1e50165d2d542f983d0cb5432cb83a76b155cacf551304388", "fork_of": null, "generation": 2}, "gaps": ["execution.not_run", "method.group_comparison_wilcoxon", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent", "step:run_analysis blocked on method:group_comparison_wilcoxon"], "assays": [{"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["For domain-wise statistical testing of significant deviations of Δy^Ala (Fig. 4, available as supplementary data at Bioinformatics online), we used the one-sided Wilcoxon rank-sum test and compared Δy^Ala values within domains to all values across all proteins for any given alanine scan window. The thus obtained P-values were further FDR-adjusted."], "order_basis": "analysis_only", "id": "assay:1"}]}