Integrated single-cell and bulk RNA sequencing reveals prognostic and immunotherapy-associated myofibroblastic cancer-associated fibroblast subtypes in head and neck squamous cell carcinoma.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40687236", "kind": "science-record", "revision": 1, "content_hash": "sha256:68348740bf8e07d9aaf22da1fd91b2a6086f680b2ee7dc32eb6aa05023035775", "created_at": "2026-11-01T10:25:51Z", "updated_at": "2026-11-01T10:25:51Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Integrated single-cell and bulk RNA sequencing reveals prognostic and immunotherapy-associated myofibroblastic cancer-associated fibroblast subtypes in head and neck squamous cell carcinoma.", "doi": "10.21037/tcr-2025-649", "pmid": "40687236", "authors": null, "journal": "Translational cancer research", "year": 2025, "abstract": null, "claims": [{"id": "claim-1", "statement": "the headline numerical result the paper states for its main finding", "kind": "qualitative", "state": "blocked", "target": {"value": null, "unit": null, "tolerance": null, "source": null}, "evidence": []}], "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:40687236"], "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:40687236", "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:40687236' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40687236", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.21037/tcr-2025-649", "sha256": "sha256:40b537d9cd759d518d47ab97d355290175e2bb620f72856bce5559c3e2732d54", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.21037/tcr-2025-649", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}], "gaps": ["asset:source:pmid:40687236 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:40687236"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:40687236"]}, "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": "69d67f51a9305a333c12d56770054499c5ce997b2e121161dcb6ad953ee508da", "source_hash": "40b537d9cd759d518d47ab97d355290175e2bb620f72856bce5559c3e2732d54", "raw_response_sha256": "sha256:88b371349277b025e1c93e356e6dc0e691dd8b2c673af85475970082834fd4c1", "raw_response_chars": 5382}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "01052ac80903486c022dc0f0d4355ef6c1813565c78a2831b04557cfa3fb2fa9", "source_hash": "40b537d9cd759d518d47ab97d355290175e2bb620f72856bce5559c3e2732d54", "raw_response_sha256": "sha256:64f298ef6eaf50bd1eb2a4a6ad17ec2c7fbdbd24ca1ec3ef0a776f913979ff82", "raw_response_chars": 61501}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "1b36fbbfb2a180e444efc9016af82e33dc7b13efcdadb6485842ae654c61cd54", "source_hash": "40b537d9cd759d518d47ab97d355290175e2bb620f72856bce5559c3e2732d54", "raw_response": "{\"parent_value\":3,\"unit\":\"identified CAF subclusters\",\"evidence\":\"Among the three identified CAF subclusters, myCAFs showed the strongest association with patient prognosis and were enriched in pathways related to DNA repair, oxidative phosphorylation, and E2F targets.\",\"target_result\":\"Three CAF subclusters were identified, with myCAFs showing the strongest association with patient prognosis.\",\"number_stated\":true}", "reading": {"parent_value": 3, "unit": "identified CAF subclusters", "evidence": "Among the three identified CAF subclusters, myCAFs showed the strongest association with patient prognosis and were enriched in pathways related to DNA repair, oxidative phosphorylation, and E2F targets.", "target_result": "Three CAF subclusters were identified, with myCAFs showing the strongest association with patient prognosis.", "number_stated": true, "source_locator": "chars 6561-6764 of source sha256 40b537d9cd759d518d47ab97d355290175e2bb620f72856bce5559c3e2732d54"}, "recorded_at": "2026-10-31T15:23:13.229815+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "e1662d246ec69b0cfc4ac973ef8e309092fddb3cdc95654859f3a32b31491568", "source_hash": "40b537d9cd759d518d47ab97d355290175e2bb620f72856bce5559c3e2732d54", "raw_response": "<think>We need answer JSON only. Need parse task carefully. User asks find single numerical result replication of registered target has to reproduce. Registered target: headline numerical result paper states for main finding. Source seems abstract/results text but does not include numerical headline effect size. Need determine if any number attached to main finding. We must report headline number only, exact contiguous quote. If no number for registered target, false, parent_value 0, unit/evidence empty, target_result says what text states instead.\n\nNeed identify source states qualitative main finding: myCAFs subtype most relevant to prognosis HNSCC, lower myCAF scores responded better immunotherapy, etc. Numerical results present (seven types, 11 clusters, three subtypes, PCA 30 dimensions resolution 0.3), but these aren't headline numerical result for main finding. Could perhaps target headline number be \"three subtypes\"? Yet registered target says \"the headline numerical result the paper states for its main finding.\" They expect a numeric result, likely need identify if abstract has a value. Here abstract lacks effect sizes. We should say no number stated. target_result what text states instead. Evidence empty. Need exact quote? For no number no evidence required per instruction. target_result could quote qualitative result perhaps. They say \"say in target_result what the text does state instead.\" Need perhaps exact wording: \"the myCAFs were found to be the subtype most relevant to the prognosis of HNSCC...\" and \"patients with lower myCAF scores responded better to immunotherapy.\" Should target_result be concise. Unit empty. parent 0 number_stated false.\n\nCould \"three\" count as numerical result? Text states \"The CAFs were then re-categorized into following three subtypes...\" That's a number central perhaps headline result. But replication target asks \"single numerical result that a replication of the registered target has to reproduce.\" Usually these benchmark prompts target specific parent metric from source, often source has sentence like \"AUC = 0.XX\". Registered target vague deliberately. We need assess. Main finding in this paper qualitative; numerical headline may be \"myCAF subtype most relevant to prognosis\", but no hazard ratio, P, AUC. Counts are methods/descriptive, not headline numerical result. So false.\n\nNeed JSON valid. target_result perhaps: \"The text states qualitatively that myCAFs were the subtype most relevant to HNSCC prognosis and that patients with lower myCAF scores responded better to immunotherapy; it gives no headline numerical result for that finding.\"</think>\n\n{\"parent_value\":0,\"unit\":\"\",\"evidence\":\"\",\"target_result\":\"The myCAFs were the subtype most relevant to HNSCC prognosis, and patients with lower myCAF scores responded better to immunotherapy; no numerical result for this main finding is stated.\",\"number_stated\":false}", "reading": {"parent_value": 0, "unit": "", "evidence": "", "target_result": "The myCAFs were the subtype most relevant to HNSCC prognosis, and patients with lower myCAF scores responded better to immunotherapy; no numerical result for this main finding is stated.", "number_stated": false, "source_locator": null}, "recorded_at": "2026-10-31T15:23:12.605762+00:00"}], "agreement": false, "disagreements": {"target_result": {"minimax": "The percentage of myofibroblast-like cancer-associated fibroblasts (myCAFs) was reduced in HNSCC following immunotherapy; no numerical percentage or effect size is stated in the supplied text.", "minimax_alt": "The supplied text does not state a numerical effect estimate for the main finding; it reports that myCAFs showed the strongest association with HNSCC patient prognosis, among three identified CAF subtypes.", "decisive": false}, "analysis_methods": {"minimax": ["Integrated single-cell and bulk RNA sequencing", "Principal component analysis", "DoRothEA transcription-factor analysis", "scMetabolism metabolic-activity analysis", "Univariate and multivariate analyses", "Seurat immune-cell-modulation analysis", "clusterProfiler pathway analysis", "Kaplan-Meier survival analysis", "Log-rank test"], "minimax_alt": ["Integrated single-cell and bulk RNA sequencing (RNA-seq) analysis", "Seurat", "Principal component analysis (PCA)", "SingleR", "DoRothEA", "scMetabolism", "Univariate and multivariate analyses", "clusterProfiler", "Cancer Therapeutics Response Portal (CTRP)", "PRISM Repurposing datasets"], "decisive": false}, "statistical_method": {"minimax": "Wilcoxon test", "minimax_alt": "Kaplan-Meier curves and the log-rank test", "decisive": true}, "number_stated": {"minimax": true, "minimax_alt": false, "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:318f27cef1fe5a05b04573b07f1a7ec6215f06c94cc0eef60673bfb204d4da11", "type": "sep_package", "label": "SEP v1 package for pmid:40687236"}], "activities": [{"id": "activity:conversion:pmid:40687236", "type": "conversion", "used": ["package:318f27cef1fe5a05b04573b07f1a7ec6215f06c94cc0eef60673bfb204d4da11"], "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": "c96234e0-b75d-40b1-8bd4-ac0fe7c7e59c", "parent_hash": "318f27cef1fe5a05b04573b07f1a7ec6215f06c94cc0eef60673bfb204d4da11", "fork_of": null, "generation": 1}, "gaps": ["abstract", "asset:source:pmid:40687236 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:40687236' does not resolve to a declared asset", "targets"]}