BPSS: a Nextflow pipeline for Bacterial Peptide Sequence Selection to detect protein diversity.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:41450201", "kind": "science-record", "revision": 2, "content_hash": "sha256:03c310d346c438e9e8fb6abdf9db7e3ead55a60326ad53e743bbbf8329a7730a", "created_at": "2026-11-01T20:31:25Z", "updated_at": "2026-11-01T21:36:13Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "BPSS: a Nextflow pipeline for Bacterial Peptide Sequence Selection to detect protein diversity.", "doi": "10.1093/bioinformatics/btaf677", "pmid": "41450201", "authors": ["Sylvère Bastien", "Pauline François", "Sara Moussadeq", "Jérôme Lemoine", "Karen Moreau", "François Vandenesch"], "journal": "Bioinformatics (Oxford, England)", "year": 2026, "abstract": "MOTIVATION: Sequence variability can be extremely high, particularly in bacteria due to the rapid accumulation of mutations linked to their high replication rate and environmental selection pressure, which often favors diversifying selection. For most species, there are no automated, computationally efficient tools available for constructing a nonredundant database covering the allelic variability of target proteins.\nRESULTS: We have thus developed Bacterial Peptide Sequence Selection, a Nextflow pipeline to define a minimal list of peptide sequences for detecting all variants of a protein of interest.\nAVAILABILITY AND IMPLEMENTATION: All the code and containers used are freely available on Gitlab from https://gitbio.ens-lyon.fr/ciri/stapath/bpss or on Zenodo (10.5281/zenodo.16894981) under GPLv3 open-source license and DockerHub platform from https://hub.docker.com/u/stapath.", "claims": [{"id": "claim-method", "statement": "Linear regression analysis suggests that WhatsGNU (Moustafa and Planet 2020) would exceed 64 GB of memory consumption with >128 000 genomes, while BPSS would reach this threshold only beyond 622 000 genomes.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41450201", "locator": "sections[9] \"3 Results and discussion\" paragraph 2", "quote": "Linear regression analysis suggests that WhatsGNU (Moustafa and Planet 2020) would exceed 64 GB of memory consumption with >128 000 genomes, while BPSS would reach this threshold only beyond 622 000 genomes."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The latest release of BPSS and documentation can be found at https://gitbio.ens-lyon.fr/ciri/stapath/bpss or at 10.5281/zenodo.16894981. All containers are freely available on DockerHub platform at https://hub.docker.com/u/stapath.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41450201", "locator": "sections[15] \"Data availability\" paragraph 2", "quote": "The latest release of BPSS and documentation can be found at https://gitbio.ens-lyon.fr/ciri/stapath/bpss or at 10.5281/zenodo.16894981. All containers are freely available on DockerHub platform at https://hub.docker.com/u/stapath."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Linear-regression estimates indicated that WhatsGNU would exceed 64 GB of memory at more than 128,000 genomes, whereas BPSS would exceed that threshold only beyond 622,000 genomes.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:41450201", "locator": "sections[9] \"3 Results and discussion\" paragraph 2", "quote": "Linear regression analysis suggests that WhatsGNU (Moustafa and Planet 2020) would exceed 64 GB of memory consumption with >128 000 genomes, while BPSS would reach this threshold only beyond 622 000 genomes."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "Linear-regression estimates indicated that WhatsGNU would exceed 64 GB of memory at more than 128,000 genomes, whereas BPSS would exceed that threshold only beyond 622,000 genomes.", "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:41450201"], "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:41450201", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/bioinformatics/btaf677", "sha256": "sha256:da820be42f61284a679e30a74940b0ea962f0f4cde051792b6c54785c10a2fe5", "bytes": 21651, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/bioinformatics/btaf677", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12797209", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "regression_modelling", "specific": "ols", "label": "Regression modelling", "dsl_operations": ["ols_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["predictors_and_outcome"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Linear regression analysis suggests that WhatsGNU (Moustafa and Planet 2020) would exceed 64 GB of memory consumption with >128 000 genomes, while BPSS would reach this threshold only beyond 622 000 genomes."}}], "targets": [], "gaps": []}, "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": true, "required_operations": ["ols_fit"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: ols."}, "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": ["The latest release of BPSS and documentation can be found at https://gitbio.ens-lyon.fr/ciri/stapath/bpss or at 10.5281/zenodo.16894981. All containers are freely available on DockerHub platform at https://hub.docker.com/u/stapath."], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": ["ols_fit"], "assets": ["source:pmid:41450201"], "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": "2026-11-01T20:08:52Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 6493, "completion_tokens": 1585, "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:41450201", "type": "paper", "label": "pmid:41450201"}, {"id": "source:pmid:41450201", "type": "manuscript", "label": "PMID 41450201 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:41450201", "type": "paper", "label": "pmid:41450201"}, {"id": "source:pmid:41450201", "type": "manuscript", "label": "PMID 41450201 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-41450201", "type": "extraction", "used": ["source:pmid:41450201"], "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:41450201", "parent_hash": "sha256:5015d8fdb8af056e1e0319c94635cceeda536f3bc48cc975a0d3abb7106e6df7", "fork_of": null, "generation": 1}, "gaps": ["execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"], "assays": [{"role": "analysis", "definition_id": "regression_modelling", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["ols_fit"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Linear regression analysis suggests that WhatsGNU (Moustafa and Planet 2020) would exceed 64 GB of memory consumption with >128 000 genomes, while BPSS would reach this threshold only beyond 622 000 genomes."], "order_basis": "analysis_only", "id": "assay:1"}]}