Integration of Multi-Scale Profiling and Machine Learning Reveals the Prognostic Role of Extracellular Matrix-Related Cancer-Associated Fibroblasts in Lung Adenocarcinoma.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40657391", "kind": "science-record", "revision": 1, "content_hash": "sha256:52182a4f3b2a81c2b80a49b759eed460d08fc9346db13e7dac3caf9dd42aa456", "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": "Integration of Multi-Scale Profiling and Machine Learning Reveals the Prognostic Role of Extracellular Matrix-Related Cancer-Associated Fibroblasts in Lung Adenocarcinoma.", "doi": "10.7150/ijms.113580", "pmid": "40657391", "authors": null, "journal": "International journal of medical sciences", "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": 28.0, "unit": "ecafs-related genes", "tolerance": null, "source": "chars 1239-1425 of source sha256 7788e5098a964daa3f06d3a727fa664a872a057286a2d759e21a4969735e05d8"}, "evidence": [{"asset": "source:pmid:40657391", "locator": "chars 1239-1425 of source sha256 7788e5098a964daa3f06d3a727fa664a872a057286a2d759e21a4969735e05d8", "quote": "A prognostic model incorporating 28 eCAFs-related genes, validated through 101-machine learning algorithms, effectively stratified patients into high- and low-risk groups across cohorts."}]}], "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:40657391"], "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:40657391", "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:40657391' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40657391", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.7150/ijms.113580", "sha256": "sha256:7788e5098a964daa3f06d3a727fa664a872a057286a2d759e21a4969735e05d8", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.7150/ijms.113580", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}], "gaps": ["asset:source:pmid:40657391 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:40657391"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:40657391"]}, "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": "ceb60bff39d4bb5b450e01b83d017f6206fc92b389b410eafb58d31028ac72fe", "source_hash": "7788e5098a964daa3f06d3a727fa664a872a057286a2d759e21a4969735e05d8", "raw_response_sha256": "sha256:bce3ee03123343af21b1599245c6ead18ef3596ae74ae089ee62d4a7883c857d", "raw_response_chars": 4770}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "dbda8e8ce30d73d0023a781dc49d04867f4640dbb9311ed66082569f1525e8ed", "source_hash": "7788e5098a964daa3f06d3a727fa664a872a057286a2d759e21a4969735e05d8", "raw_response_sha256": "sha256:ddcf938c4c4bc98e55cf019eb6f8b1c13a7f9399242fc24c614a60af29bd8d3b", "raw_response_chars": 74662}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "dbbed125bf502f0bbb5fd6e407fc09551c34bd22cfdf41b20356a01994f325dd", "source_hash": "7788e5098a964daa3f06d3a727fa664a872a057286a2d759e21a4969735e05d8", "raw_response": "{\"parent_value\":28,\"unit\":\"eCAFs-related genes\",\"evidence\":\"A prognostic model incorporating 28 eCAFs-related genes, validated through 101-machine learning algorithms, effectively stratified patients into high- and low-risk groups across cohorts.\",\"target_result\":\"The paper states that the prognostic model incorporated 28 eCAFs-related genes.\",\"number_stated\":true}", "reading": {"parent_value": 28, "unit": "eCAFs-related genes", "evidence": "A prognostic model incorporating 28 eCAFs-related genes, validated through 101-machine learning algorithms, effectively stratified patients into high- and low-risk groups across cohorts.", "target_result": "The paper states that the prognostic model incorporated 28 eCAFs-related genes.", "number_stated": true, "source_locator": "chars 1239-1425 of source sha256 7788e5098a964daa3f06d3a727fa664a872a057286a2d759e21a4969735e05d8"}, "recorded_at": "2026-10-31T15:27:10.281225+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "3a87a2c0c6e291fefb9bdec213f59cb495039763cd7008e065609fe1a33b0736", "source_hash": "7788e5098a964daa3f06d3a727fa664a872a057286a2d759e21a4969735e05d8", "raw_response": "<think>We need answer JSON only. Need interpret target headline numerical result paper states main finding. Source abstract: prognostic model incorporating 28 eCAFs-related genes, validated through 101-machine learning algorithms, stratified groups. What single numerical result replication target has to reproduce? Likely 28 eCAFs-related genes? Registered target \"headline numerical result the paper itself states for its main finding.\" Need infer perhaps headline number from paper title/abstract. Numbers: 15 tumors, cohorts sample sizes, 28 genes, 101 algorithms. Which is headline numerical result? Maybe 28 eCAF-related genes is core main finding. Need quote exact contiguous clause containing number, whole clause. Evidence exact quote. Unit must printed unit. Parent_value 28, unit perhaps \"eCAFs-related genes\". Evidence: \"A prognostic model incorporating 28 eCAFs-related genes, validated through 101-machine learning algorithms, effectively stratified patients into high- and low-risk groups across cohorts.\" This contains two numerical values, ambiguity perhaps exact clause includes both. They ask single headline number. Could quote \"A prognostic model incorporating 28 eCAFs-related genes\" but that's not clause? Exact contiguous quotation, attribution can be target direct. Need \"headline number only\" and quote whole clause when attribution through wording. This sentence could quote full sentence though includes 101. Does evidence contain number and extra number confuse? Maybe target likely 28. The \"main finding\" is prognostic role, model incorporating 28 genes validated through 101 algorithms. Headline numerical result likely 28 genes. Unit \"eCAFs-related genes.\" Need not overthink.\n\nCould target instead be \"101-machine learning algorithms\" as replication of registered target? Usually prompts in benchmark ask \"single numerical result that replication of registered target has to reproduce\"; registered target generic \"headline numerical result ... main finding\". In abstracts, headline result often e.g. \"model incorporating 28 genes, validated through 101 algorithms\". Which number is main numerical result? 28 eCAFs-related genes is signature size, likely headline. 101 algorithms sounds method. Could headline be \"28 eCAFs-related genes\". Unit should exact printed unit. \"eCAFs-related genes\" plausible. Evidence exact contiguous quote. Target_result perhaps \"28 eCAFs-related genes\" or \"true\". Schema string. Need mention value and unit. Could target_result: \"The prognostic model incorporates 28 eCAFs-related genes.\" But that's paraphrase okay except evidence exact quote. They explicitly ask headline number only, perhaps output parent_value 28, unit \"eCAFs-related genes\", evidence exact, target_result maybe \"28 eCAFs-related genes\". Number stated true.\n\nNeed ensure no markdown. Exact quote: In abstract: \"A prognostic model incorporating 28 eCAFs-related genes, validated through 101-machine learning algorithms, effectively stratified patients into high- and low-risk groups across cohorts.\" Full exact. Unit printed \"eCAFs-related genes\". Could quote whole sentence. parent_value number 28.\n\nBut maybe \"101-machine learning algorithms\" is headline number because replication of main finding must reproduce 28 genes? Let's parse wording: \"find the single numerical result that a replication of the registered target has to reproduce. Report the headline number only: the value the paper itself states for the registered target\". REGISTERED TARGET: \"the headline numerical result the paper itself states for its main finding\". It may be task to identify result in source. Main finding includes eCAFs dominant and poor survival, but no quantitative result. Then model incorporates 28 genes. The headline numerical result perhaps 28. They ask \"If the text states no number for the registered target, set false...\" Since target main finding maybe no numerical value attached to eCAFs poor prognosis. But likely source selected because abstract has clear headline number 28. We need distinguish target definition deliberately broad and perhaps asks exact source. \"A prognostic model incorporating 28 eCAFs-related genes, validated through 101-machine learning algorithms...\" Both numbers. Which is headline? Perhaps 28 is main finding (signature size), 101 is validation method count. Unit for 28 genes. Could they expect 28.\n\nCould evidence be narrower: \"A prognostic model incorporating 28 eCAFs-related genes\" exact contiguous. User says \"When that is how the text links them, quote the whole clause so a reader can check attribution for themselves.\" Full clause extends through cohorts. Better full sentence. Yet extra number 101 may violate \"headline number only\"? Evidence can include extra contextual number, but ideally exact phrase. They demand \"exact, contiguous quotation ... contains the number; do not shorten it, do not add ellipsis and do not paraphrase it.\" \"do not shorten it\" likely means quote source passage fully, not just a fragment? They say \"When that is how the text links them, quote the whole clause\". So full sentence safest.\n\nCould target_result be \"The paper states that its prognostic model incorporates 28 eCAFs-related genes.\" But headline only perhaps target_result just \"28 eCAFs-related genes\". Need JSON proper escaped apostrophes no issue.\n\nUnit \"eCAFs-related genes\" printed. Does unit need simply \"genes\"? They say unit must be unit paper prints. It prints \"28 eCAFs-related genes\"; count's unit is genes, qualifier part of target. Likely unit \"genes\". They may expect \"eCAFs-related genes\". Usually schema expects e.g. parent_value 28, unit \"genes\". Better unit \"genes\" because unit is noun. But wording says unit the paper prints, and exact phrase is \"eCAFs-related genes.\" Could set \"eCAFs-related genes\" to preserve identity. Parent_value 28.\n\nLet's formulate:\n{\n \"parent_value\":28,\n \"unit\":\"eCAFs-related genes\",\n \"evidence\":\"A prognostic model incorporating 28 eCAFs-related genes, validated through 101-machine learning algorithms, effectively stratified patients into high- and low-risk groups across cohorts.\",\n \"target_result\":\"28 eCAFs-related genes\",\n \"number_stated\":true\n}\nWould \"headline number only\" target_result include text? They specifically schema includes target_result likely narrative. But \"Report headline number only\" means no explanations. target_result can \"28 eCAFs-related genes\". Good.\n\nNeed answer only JSON.</think>\n\n{\"parent_value\":28,\"unit\":\"eCAFs-related genes\",\"evidence\":\"A prognostic model incorporating 28 eCAFs-related genes, validated through 101-machine learning algorithms, effectively stratified patients into high- and low-risk groups across cohorts.\",\"target_result\":\"28 eCAFs-related genes\",\"number_stated\":true}", "reading": {"parent_value": 28, "unit": "eCAFs-related genes", "evidence": "A prognostic model incorporating 28 eCAFs-related genes, validated through 101-machine learning algorithms, effectively stratified patients into high- and low-risk groups across cohorts.", "target_result": "28 eCAFs-related genes", "number_stated": true, "source_locator": "chars 1239-1425 of source sha256 7788e5098a964daa3f06d3a727fa664a872a057286a2d759e21a4969735e05d8"}, "recorded_at": "2026-10-31T15:27:20.092778+00:00"}], "agreement": false, "disagreements": {"target_result": {"minimax": "A prognostic model incorporating 28 eCAFs-related genes, validated through 101-machine learning algorithms, stratified patients into high- and low-risk groups across cohorts.", "minimax_alt": "A prognostic model incorporating 28 eCAFs-related genes, validated through 101-machine learning algorithms, effectively stratified patients into high- and low-risk groups across cohorts.", "decisive": false}, "analysis_methods": {"minimax": ["single-cell RNA sequencing", "CIBERSORTx deconvolution", "Kaplan-Meier survival analysis", "Slingshot pseudotime trajectory analysis", "Gene Set Variation Analysis (GSVA)", "machine learning algorithms"], "minimax_alt": ["101-machine learning algorithms for prognostic-model validation", "CIBERSORTx deconvolution algorithm in absolute mode", "High-infiltration and low-infiltration stratification based on relative cellular-subset abundance", "Kaplan-Meier (KM) survival analysis", "Slingshot pseudotime trajectory analysis", "Gene Set Variation Analysis (GSVA)", "Gene Ontology (GO) enrichment analysis", "FindMarkers"], "decisive": false}, "statistical_method": {"minimax": "Kaplan-Meier (KM) survival analysis", "minimax_alt": "101-machine learning algorithms", "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:494af632873c165735a882ebc6f314967ebf4c2a6da806bdfa99696ccef0dcf4", "type": "sep_package", "label": "SEP v1 package for pmid:40657391"}], "activities": [{"id": "activity:conversion:pmid:40657391", "type": "conversion", "used": ["package:494af632873c165735a882ebc6f314967ebf4c2a6da806bdfa99696ccef0dcf4"], "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": "0d3899d3-dc7a-4f58-a713-05e8a2982f87", "parent_hash": "494af632873c165735a882ebc6f314967ebf4c2a6da806bdfa99696ccef0dcf4", "fork_of": null, "generation": 1}, "gaps": ["abstract", "asset:source:pmid:40657391 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:40657391' does not resolve to a declared asset", "targets"]}