HSDSnake: a user-friendly SnakeMake pipeline for analysis of duplicate genes in eukaryotic genomes.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40434911", "kind": "science-record", "revision": 2, "content_hash": "sha256:387f76e0b2e6d694126673abcfa8784f0b9aa46c26ce7fb85e69f99daee47838", "created_at": "2026-11-01T20:30:34Z", "updated_at": "2026-11-01T21:35:14Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "HSDSnake: a user-friendly SnakeMake pipeline for analysis of duplicate genes in eukaryotic genomes.", "doi": "10.1093/bioinformatics/btaf325", "pmid": "40434911", "authors": ["Xi Zhang", "Yining Hu", "David Roy Smith", "Zhenyu Cheng", "John M Archibald"], "journal": "Bioinformatics (Oxford, England)", "year": 2025, "abstract": "SUMMARY: Gene duplication is a well-known driver of molecular evolution-it acts as a source of genetic novelty, thereby providing the raw substrate for organismal adaption. However, detecting different types of gene duplicates and comparing them in sequence datasets can be difficult. Existing tools can identify and classify gene duplicates that have arisen by various processes, but have limitations; for example, some do not have a user-friendly workflow and can include many intermediate steps requiring manual adjustments of parameters and/or are not maintained for the benefit of research community members. Here, we have developed HSDSnake, a user-friendly SnakeMake pipeline that can detect and classify gene duplications into five categories: dispersed, proximal, tandem, transposed, and whole genome. It also curates and evaluates the highly similar gene duplicates (HSDs) in each gene duplication category with reliance on both sequence similarity and conserved domains. Lastly, the detected gene duplicates can be visualized within a KEGG functional pathway framework and the substitution rates (Ka, Ks, and their Ka/Ks ratio) can be analyzed for all the duplicate gene pairs. We demonstrate HSDSnake's capabilities by analyzing two reference genomes directly downloaded from NCBI and provide detailed instructions for each step.\nAVAILABILITY AND IMPLEMENTATION: The HSDSnake pipeline uses SnakeMake and Conda to run and install dependencies. The distribution version is available online at GitHub: https://github.com/zx0223winner/HSDSnake and the archived version at Zenodo is https://doi.org/10.5281/zenodo.15521945.", "claims": [{"id": "claim-method", "statement": "For example, a distribution curve of Ks values of syntenic blocks within A. thaliana are created by fitting the Gaussian mixture models (GMM).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40434911", "locator": "sections[3] \"3 Application\" paragraph 5", "quote": "For example, a distribution curve of Ks values of syntenic blocks within A. thaliana are created by fitting the Gaussian mixture models (GMM)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Supplementary data is available at Bioinformatics online.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40434911", "locator": "sections[10] \"Supplementary data\" paragraph 2", "quote": "Supplementary data is available at Bioinformatics online."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "", "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:40434911"], "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": "complete", "blocked_on": null, "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:obtain_source_data blocked on data:accession_absent"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40434911", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/bioinformatics/btaf325", "sha256": "sha256:8dedd38e01ec9472d1ed33ce5e98665fbfc932ac136cd8de6d3339e7fcfeaa7f", "bytes": 29343, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/bioinformatics/btaf325", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12202878", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "Gaussian mixture models (GMM)", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "For example, a distribution curve of Ks values of syntenic blocks within A. thaliana are created by fitting the Gaussian mixture models (GMM)."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "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": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (Gaussian mixture models (GMM)), but the corpus's method extractor could not map it onto a DSL operation, so the method is published but not expressible."}, "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": ["Supplementary data is available at Bioinformatics online."], "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:40434911"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "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": "2026-11-01T19:53:18Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 8835, "completion_tokens": 1198, "cached_tokens": 188}}, "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:40434911", "type": "paper", "label": "pmid:40434911"}, {"id": "source:pmid:40434911", "type": "manuscript", "label": "PMID 40434911 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:40434911", "type": "paper", "label": "pmid:40434911"}, {"id": "source:pmid:40434911", "type": "manuscript", "label": "PMID 40434911 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-40434911", "type": "extraction", "used": ["source:pmid:40434911"], "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:40434911", "parent_hash": "sha256:49286b4e2fc93658558dc5af34f145941ccdd59914904303fa3336ccfe949763", "fork_of": null, "generation": 1}, "gaps": ["execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"]}