Exploring homology detection via k-means clustering of proteins embedded with a large language model.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40857396", "kind": "science-record", "revision": 3, "content_hash": "sha256:6626eb3f7099770d61aefd39b11cc934ad142e0740b075117b397b434d384df9", "created_at": "2026-11-01T20:30:58Z", "updated_at": "2026-11-01T22:14:37Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Exploring homology detection via k-means clustering of proteins embedded with a large language model.", "doi": "10.1093/bioinformatics/btaf472", "pmid": "40857396", "authors": ["Thomas Minotto", "Antoine Claessens", "Thomas D Otto"], "journal": "Bioinformatics (Oxford, England)", "year": 2025, "abstract": "MOTIVATION: Inferring protein homology from sequence information is essential for understanding species evolution and enabling functional annotation transfer. Besides similarity-based methods, several machine learning approaches have been developed using various ways of representing protein data.\nRESULTS: Here, we represent proteins with a biologically oriented large language model and apply k-means clustering to the embedded data to extract homology relationships. Although our approach lacks the sensitivity of other tools, we obtain better precision for the detection of n:m orthologs. Furthermore, we successfully reconstruct full orthologous groups from scratch, highlighting the growing potential of using large language models in combination with clustering algorithms for the analysis of protein data.\nAVAILABILITY AND IMPLEMENTATION: Datasets are available on OrthoMCL-DB as indicated in the Methods. Source code is available on GitHub at https://github.com/ThomasGTHB/OrthoLM and Zenodo at https://doi.org/10.5281/zenodo.16640170.", "claims": [{"id": "claim-method", "statement": "We applied unsupervised clustering with the k-means algorithm to create orthologous groups without any prior information on the composition of the groups.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40857396", "locator": "sections[6] \"2.2.2 Unsupervised clustering\" paragraph 2", "quote": "We applied unsupervised clustering with the k-means algorithm to create orthologous groups without any prior information on the composition of the groups."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Datasets are available on OrthoMCL-DB as indicated in the Methods. Source code is available on GitHub at https://github.com/ThomasGTHB/OrthoLM and Zenodo at https://doi.org/10.5281/zenodo.16640170.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40857396", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "Datasets are available on OrthoMCL-DB as indicated in the Methods. Source code is available on GitHub at https://github.com/ThomasGTHB/OrthoLM and Zenodo at https://doi.org/10.5281/zenodo.16640170."}], "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:40857396"], "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:40857396", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/bioinformatics/btaf472", "sha256": "sha256:d23fec999a647b3c627cd981139fd5f9bf1c7eee9bbf6e65c9da2159e403310d", "bytes": 39332, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/bioinformatics/btaf472", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12517335", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "clustering", "specific": "kmeans", "label": "Clustering", "dsl_operations": ["kmeans_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["feature_matrix"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "We applied unsupervised clustering with the k-means algorithm to create orthologous groups without any prior information on the composition of the groups."}}, {"id": "method-2", "family": "sequence_alignment", "specific": "blast", "label": "Sequence alignment / homology", "dsl_operations": ["sequence_align", "alignment_identity"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["sequence_records"], "evidence": {"score": 0.8, "band": "high", "quote": "BLAST"}}], "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": ["kmeans_fit"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: kmeans."}, "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": ["Datasets are available on OrthoMCL-DB as indicated in the Methods. Source code is available on GitHub at https://github.com/ThomasGTHB/OrthoLM and Zenodo at https://doi.org/10.5281/zenodo.16640170."], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": ["kmeans_fit"], "assets": ["source:pmid:40857396"], "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": "2026-11-01T20:00:26Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 10460, "completion_tokens": 1821, "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:40857396", "type": "paper", "label": "pmid:40857396"}, {"id": "source:pmid:40857396", "type": "manuscript", "label": "PMID 40857396 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:40857396", "type": "paper", "label": "pmid:40857396"}, {"id": "source:pmid:40857396", "type": "manuscript", "label": "PMID 40857396 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-40857396", "type": "extraction", "used": ["source:pmid:40857396"], "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:40857396", "parent_hash": "sha256:8ccbaf84be45cd044853e59ee343e75df3016f3fe4542dfe73ddf505e830a3b0", "fork_of": null, "generation": 2}, "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": "clustering", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["kmeans_fit"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["We applied unsupervised clustering with the k-means algorithm to create orthologous groups without any prior information on the composition of the groups."], "order_basis": "analysis_only", "id": "assay:1"}]}