PheneBank: a literature-based database of phenotypes.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34788791", "kind": "science-record", "revision": 3, "content_hash": "sha256:7e52644bf25049b6f0a8be2e6eff59fa90b48572ad8c4a85c623025bd42b254a", "created_at": "2026-11-01T17:36:29Z", "updated_at": "2026-11-01T21:26:37Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "PheneBank: a literature-based database of phenotypes.", "doi": "10.1093/bioinformatics/btab740", "pmid": "34788791", "authors": ["Mohammad Taher Pilehvar", "Adam Bernard", "Damian Smedley", "Nigel Collier"], "journal": "Bioinformatics (Oxford, England)", "year": 2022, "abstract": "MOTIVATION: Significant effort has been spent by curators to create coding systems for phenotypes such as the Human Phenotype Ontology, as well as disease-phenotype annotations. We aim to support the discovery of literature-based phenotypes and integrate them into the knowledge discovery process.\nRESULTS: PheneBank is a Web-portal for retrieving human phenotype-disease associations that have been text-mined from the whole of Medline. Our approach exploits state-of-the-art machine learning for concept identification by utilizing an expert annotated rare disease corpus from the PMC Text Mining subset. Evaluation of the system for entities is conducted on a gold-standard corpus of rare disease sentences and for associations against the Monarch initiative data.\nAVAILABILITY AND IMPLEMENTATION: The PheneBank Web-portal freely available at http://www.phenebank.org. Annotated Medline data is available from Zenodo at DOI: 10.5281/zenodo.1408800. Semantic annotation software is freely available for non-commercial use at GitHub: https://github.com/pilehvar/phenebank.\nSUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.", "claims": [{"id": "claim-method", "statement": "We evaluated the Fisher Exact Test, the Dice coefficient and pointwise mutual information (PMI) ranking tuples from most significant to least significant.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34788791", "locator": "sections[3] \"3 Performance evaluation\" paragraph 4", "quote": "We evaluated the Fisher Exact Test, the Dice coefficient and pointwise mutual information (PMI) ranking tuples from most significant to least significant."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Annotated Medline data is available from Zenodo at DOI: 10.5281/zenodo.1408800.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34788791", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "Annotated Medline data is available from Zenodo at DOI: 10.5281/zenodo.1408800."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The Fisher Exact Test was the best-performing association-ranking method, with a 1% false discovery rate cutoff at P = 0.0025 after 1.8M tuples.", "kind": "quantitative", "target": {"value": 1.0, "unit": "per cent", "tolerance": null, "source": "Given that the Fisher Exact Test yields P-values, we then applied the Benjamini–Hochberg procedure to our dataset to find the cutoff for a false discovery rate of 1%; this occurs at P = 0.0025, after 1.8M tuples."}, "evidence": [{"asset": "source:pmid:34788791", "locator": "sections[3] \"3 Performance evaluation\" paragraph 4", "quote": "Results (Data available at DOI: 10.5281/zenodo.142283.) showed that the Fisher Exact Test is clearly the best-performing of the three methods."}, {"asset": "source:pmid:34788791", "locator": "sections[3] \"3 Performance evaluation\" paragraph 4", "quote": "Given that the Fisher Exact Test yields P-values, we then applied the Benjamini–Hochberg procedure to our dataset to find the cutoff for a false discovery rate of 1%; this occurs at P = 0.0025, after 1.8M tuples."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "The Fisher Exact Test was the best-performing association-ranking method, with a 1% false discovery rate cutoff at P = 0.0025 after 1.8M tuples.", "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:34788791"], "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:34788791", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/bioinformatics/btab740", "sha256": "sha256:165d19d17d9a7ae7582ee75397c6aaa9b164da17693db3497a2753325ef2aa29", "bytes": 8466, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/bioinformatics/btab740", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8796364", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "Fisher Exact Test with Benjamini–Hochberg false discovery rate correction", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "We evaluated the Fisher Exact Test, the Dice coefficient and pointwise mutual information (PMI) ranking tuples from most significant to least significant."}}], "targets": [{"id": "target-published-estimate", "claim_id": "claim-target-result", "operation": null, "expected_value": 1.0, "unit": "per cent", "tolerance": null, "state": "complete", "note": "The published estimate as the reader quoted it from the paper. No tolerance is published because the paper states none."}, {"id": "target-published-estimate-p-value", "claim_id": "claim-target-result", "operation": null, "expected_value": 0.0025, "unit": "p-value", "tolerance": null, "state": "complete", "note": "The threshold the paper applied to its own result, as the paper states it. A run that reproduces the effect is judged against this threshold."}], "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 (Fisher Exact Test with Benjamini–Hochberg false discovery rate correction), 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": ["Annotated Medline data is available from Zenodo at DOI: 10.5281/zenodo.1408800."], "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:34788791"], "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": "2026-11-01T17:07:50Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 3526, "completion_tokens": 1130, "cached_tokens": 128}}, "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:34788791", "type": "paper", "label": "pmid:34788791"}, {"id": "source:pmid:34788791", "type": "manuscript", "label": "PMID 34788791 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34788791", "type": "paper", "label": "pmid:34788791"}, {"id": "source:pmid:34788791", "type": "manuscript", "label": "PMID 34788791 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34788791", "type": "extraction", "used": ["source:pmid:34788791"], "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:34788791", "parent_hash": "sha256:a4a05efd1c812e1c6d9ca4b580138d5ee0c136e8479e15d9ac6dac94f0605e14", "fork_of": null, "generation": 2}, "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"]}