Machine learning-based identification of diagnostic and prognostic mitotic cell cycle genes in hepatocellular carcinoma.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40875626", "kind": "science-record", "revision": 1, "content_hash": "sha256:ae083392ce538618fe5d0810fac869c409c5cf088ca8ba153a8442c5e6c2628a", "created_at": "2026-11-01T10:25:52Z", "updated_at": "2026-11-01T10:25:52Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Machine learning-based identification of diagnostic and prognostic mitotic cell cycle genes in hepatocellular carcinoma.", "doi": "10.1371/journal.pone.0331118", "pmid": "40875626", "authors": null, "journal": "PloS one", "year": 2025, "abstract": null, "claims": [{"id": "claim-1", "statement": "the headline numerical result the paper states for its main finding", "kind": "quantitative", "state": "complete", "target": {"value": 1.0, "unit": "auc", "tolerance": null, "source": "chars 540-709 of source sha256 13ec18a6d8163faff8c2af16d640a2e474f6e6db1ae6051a41ffebb7ab68cbc8"}, "evidence": [{"asset": "source:pmid:40875626", "locator": "chars 540-709 of source sha256 13ec18a6d8163faff8c2af16d640a2e474f6e6db1ae6051a41ffebb7ab68cbc8", "quote": "The SVM-RFE model demonstrated high performance in TCGA (AUC = 1.0), and generalizability across GSE77509 (AUC = 0.95) and GSE144269 (AUC = 0.879), outperforming RF-RFE."}]}], "gaps": ["abstract", "authors"]}, "experiment": {"state": "partial", "objective": "the headline numerical result the paper states for its main finding", "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate and its interval from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The number a replication must land on, and the sentence it came from.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:40875626"], "outputs": ["the published estimate, its unit and its interval"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data behind the published result", "kind": "data-preparation", "state": "blocked", "blocked_on": "data:not_downloaded", "description": "The published result cannot be recomputed without the data the paper analysed.", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the source data with its provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the analysis programme", "kind": "analysis", "state": "blocked", "blocked_on": "no owned computational capability is bound to this experiment", "description": "Re-run the paper's analysis on the source data and produce the registered result. | SEP input not carried into the asset list: materials:the source data behind the published result in pmid:40875626", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the registered result"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:not_downloaded", "step:run_analysis blocked on no owned computational capability is bound to this experiment", "step:run_analysis input 'materials:the source data behind the published result in pmid:40875626' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40875626", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1371/journal.pone.0331118", "sha256": "sha256:13ec18a6d8163faff8c2af16d640a2e474f6e6db1ae6051a41ffebb7ab68cbc8", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1371/journal.pone.0331118", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}], "gaps": ["asset:source:pmid:40875626 not verified"]}, "analysis": {"state": "absent", "methods": [], "targets": [], "gaps": ["method", "targets"]}, "capability": {"state": "absent", "requirements": [], "gaps": ["capability"]}, "readiness": {"state": "partial", "tier": null, "blocking_axis": null, "blocked_on": null, "axes": {}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:40875626"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:40875626"]}, "gaps": ["corpus_record_absent"]}, "review": {"state": "partial", "machine_critique": {"status": "blocked", "providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "full-text-reading-v1", "prompt_hash": "165933a3765782b9783ba2fe15f4aef21cc6b06124fb9c2165b9cb7739f9dd8f", "source_hash": "13ec18a6d8163faff8c2af16d640a2e474f6e6db1ae6051a41ffebb7ab68cbc8", "raw_response_sha256": "sha256:2874b65f72892d66570038e6a365783384e431dfe268a67251a9493570066ef2", "raw_response_chars": 5292}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "f3f6c509c082b880d5bf372e5b265775ed03f39fa8976ead102def45c4196da3", "source_hash": "13ec18a6d8163faff8c2af16d640a2e474f6e6db1ae6051a41ffebb7ab68cbc8", "raw_response_sha256": "sha256:17bcab203bf23928e7fc7e8d09ea0459f8f28c876c1a73201308041dad63c71e", "raw_response_chars": 42499}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "a5759a4792bfeaacefb719e424a848a1caf97160964be1a58e0db913a7fbfe49", "source_hash": "13ec18a6d8163faff8c2af16d640a2e474f6e6db1ae6051a41ffebb7ab68cbc8", "raw_response": "{\"parent_value\":1,\"unit\":\"AUC\",\"evidence\":\"The SVM-RFE model demonstrated high performance in TCGA (AUC = 1.0), and generalizability across GSE77509 (AUC = 0.95) and GSE144269 (AUC = 0.879), outperforming RF-RFE.\",\"target_result\":\"The SVM-RFE model achieved an AUC of 1.0 in the TCGA cohort.\",\"number_stated\":true}", "reading": {"parent_value": 1, "unit": "AUC", "evidence": "The SVM-RFE model demonstrated high performance in TCGA (AUC = 1.0), and generalizability across GSE77509 (AUC = 0.95) and GSE144269 (AUC = 0.879), outperforming RF-RFE.", "target_result": "The SVM-RFE model achieved an AUC of 1.0 in the TCGA cohort.", "number_stated": true, "source_locator": "chars 540-709 of source sha256 13ec18a6d8163faff8c2af16d640a2e474f6e6db1ae6051a41ffebb7ab68cbc8"}, "recorded_at": "2026-10-31T15:32:24.988692+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "a3bd3e489a0bda81d1101be63a41498601cf8842ea2d50f65cb593751458fddc", "source_hash": "13ec18a6d8163faff8c2af16d640a2e474f6e6db1ae6051a41ffebb7ab68cbc8", "raw_response": "<think>We need answer JSON only. Need interpret registered target headline numerical result main finding. Paper abstract has several. Need determine \"single numerical result that a replication of registered target has to reproduce\" likely headline number: perhaps AUC = 1.0 for SVM-RFE model in TCGA, main finding. Need identify stated value, unit paper prints. Evidence exact contiguous quote containing number. \"The SVM-RFE model demonstrated high performance in TCGA (AUC = 1.0), and generalizability across GSE77509 (AUC = 0.95) and GSE144269 (AUC = 0.879), outperforming RF-RFE.\" Headline number likely 1.0, unit perhaps AUC? They ask unit must be unit paper prints. Could say \"AUC\" as unit. Is 1.0 headline numerical result. Registered target phrased generic \"the headline numerical result the paper states for its main finding\". We need perhaps infer primary result is AUC 1.0. Other numbers: nine genes, eight genes, AUCs &gt;0.81. The headline numerical result likely diagnostic model's AUC = 1.0. Need quote whole clause attribution. Exact contiguous quotation, likely sentence. Output parent_value 1.0, unit \"AUC\", evidence exact sentence or relevant clause, target_result maybe \"SVM-RFE model AUC in TCGA\" or prose. number_stated true.\n\nNeed ensure source exact quotation perhaps \"The SVM-RFE model demonstrated high performance in TCGA (AUC = 1.0), and generalizability across GSE77509 (AUC = 0.95) and GSE144269 (AUC = 0.879), outperforming RF-RFE.\" Whole clause. If only \"The SVM-RFE model demonstrated high performance in TCGA (AUC = 1.0)\" exact contiguous and sufficient. They ask quote whole clause when target attached. Sentence includes other numbers but okay. Headline number singular perhaps 1.0. Unit \"AUC\" rather than unitless? JSON unit string. The paper prints AUC = 1.0, so unit \"AUC\". Could perhaps unit be \"AUC value\". Better exact paper label: \"AUC\". target_result: \"The SVM-RFE model demonstrated high performance in TCGA (AUC = 1.0).\" Fine.\n\nCould headline numerical result instead nine genes? Main finding identifies nine diagnostic genes and eight prognostic signature, but \"single numerical result replication of registered target\" target is headline numerical result, likely key performance metric. The title/main abstract: \"The SVM-RFE model demonstrated high performance in TCGA (AUC = 1.0)\" likely headline. Need only output JSON.\n\nEnsure no markdown.</think>\n\n{\"parent_value\":1.0,\"unit\":\"AUC\",\"evidence\":\"The SVM-RFE model demonstrated high performance in TCGA (AUC = 1.0), and generalizability across GSE77509 (AUC = 0.95) and GSE144269 (AUC = 0.879), outperforming RF-RFE.\",\"target_result\":\"The SVM-RFE model achieved an AUC of 1.0 in the TCGA cohort.\",\"number_stated\":true}", "reading": {"parent_value": 1.0, "unit": "AUC", "evidence": "The SVM-RFE model demonstrated high performance in TCGA (AUC = 1.0), and generalizability across GSE77509 (AUC = 0.95) and GSE144269 (AUC = 0.879), outperforming RF-RFE.", "target_result": "The SVM-RFE model achieved an AUC of 1.0 in the TCGA cohort.", "number_stated": true, "source_locator": "chars 540-709 of source sha256 13ec18a6d8163faff8c2af16d640a2e474f6e6db1ae6051a41ffebb7ab68cbc8"}, "recorded_at": "2026-10-31T15:32:26.314751+00:00"}], "agreement": false, "disagreements": {"target_result": {"minimax": "The SVM-RFE model achieved an AUC of 1.0 in TCGA and generalized with AUCs of 0.95 in GSE77509 and 0.879 in GSE144269; permutation testing confirmed that these AUCs were outside the null distribution for all datasets.", "minimax_alt": "The SVM-RFE diagnostic model achieved AUC = 1.0 in TCGA, with AUC = 0.95 in GSE77509 and AUC = 0.879 in GSE144269.", "decisive": false}, "analysis_methods": {"minimax": ["SVM-RFE", "RF-RFE", "permutation testing", "differential gene expression analysis", "TMM normalization", "limma normalization", "RMA normalization", "univariate Cox regression", "LASSO Cox regression", "Kaplan–Meier analysis"], "minimax_alt": ["SVM-RFE", "RF-RFE", "permutation testing", "TMM normalization with edgeR", "limma"], "decisive": false}, "statistical_method": {"minimax": "SVM-RFE, with AUC performance assessed across independent cohorts and confirmed using permutation testing", "minimax_alt": "Permutation testing", "decisive": true}}, "agreement_basis": {"policy": "decisive_fields", "decisive_fields": ["work_type", "number_stated", "parent_value", "unit"]}, "blinded": true}, "human_critique": {"status": "not_run", "reviewer": null, "signed_at": null, "conflict_checked": false, "commentary": null}, "stages": [{"key": "target_materials", "status": "pending", "reason": null, "evidence": null}, {"key": "independent_readings", "status": "blocked", "reason": "The independent readings are incomplete or disagree; the source evidence must resolve the difference.", "evidence": {"provider_errors": []}}, {"key": "source_resolution", "status": "pending", "reason": null, "evidence": null}, {"key": "protocol_reconstruction", "status": "pending", "reason": null, "evidence": null}, {"key": "control_execution", "status": "pending", "reason": null, "evidence": null}, {"key": "control_comparison", "status": "pending", "reason": null, "evidence": null}, {"key": "publication", "status": "pending", "reason": null, "evidence": null}], "gaps": ["review.human_critique", "review.machine_critique.blocked"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "package:8b90cf215743c2aae22c9e60009a2073dcb67176646ae6e44d8d48663a38a023", "type": "sep_package", "label": "SEP v1 package for pmid:40875626"}], "activities": [{"id": "activity:conversion:pmid:40875626", "type": "conversion", "used": ["package:8b90cf215743c2aae22c9e60009a2073dcb67176646ae6e44d8d48663a38a023"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:minimax", "type": "model", "label": "minimax"}, {"id": "agent:minimax_alt", "type": "model", "label": "minimax_alt"}, {"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}], "source_run_id": "run-20261023T122449232913", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "7cf25cd0-6ce9-4bd3-b87a-ecdc998ab0d6", "parent_hash": "8b90cf215743c2aae22c9e60009a2073dcb67176646ae6e44d8d48663a38a023", "fork_of": null, "generation": 1}, "gaps": ["abstract", "asset:source:pmid:40875626 not verified", "authors", "capability", "corpus_record_absent", "execution.not_run", "method", "review.human_critique", "review.machine_critique.blocked", "step:obtain_source_data blocked on data:not_downloaded", "step:run_analysis blocked on no owned computational capability is bound to this experiment", "step:run_analysis input 'materials:the source data behind the published result in pmid:40875626' does not resolve to a declared asset", "targets"]}