SMR-guided molecular subtyping and machine learning model reveals novel prognostic biomarkers and therapeutic targets in non-small cell lung adenocarcinoma.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:39794414", "kind": "science-record", "revision": 1, "content_hash": "sha256:8bf91c9cd7e45ff40bfb9fb75ceb62bb4c4bbc7c816ff80a5ff970fcbd1f4d76", "created_at": "2026-11-01T10:25:49Z", "updated_at": "2026-11-01T10:25:49Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "SMR-guided molecular subtyping and machine learning model reveals novel prognostic biomarkers and therapeutic targets in non-small cell lung adenocarcinoma.", "doi": "10.1038/s41598-025-85471-8", "pmid": "39794414", "authors": null, "journal": "Scientific reports", "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": 0.75, "unit": "auc", "tolerance": null, "source": "chars 1101-1241 of source sha256 87e7c1d154f5ac705536a39009085d1ca627dd795547495063e7af19c7cb4678"}, "evidence": [{"asset": "source:pmid:39794414", "locator": "chars 1101-1241 of source sha256 87e7c1d154f5ac705536a39009085d1ca627dd795547495063e7af19c7cb4678", "quote": "The Random Survival Forest (RSF) model exhibited robust prognostic predictive capabilities across multiple independent cohorts (AUC > 0.75)."}]}], "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:39794414"], "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:39794414", "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:39794414' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:39794414", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1038/s41598-025-85471-8", "sha256": "sha256:87e7c1d154f5ac705536a39009085d1ca627dd795547495063e7af19c7cb4678", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1038/s41598-025-85471-8", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}], "gaps": ["asset:source:pmid:39794414 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:39794414"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:39794414"]}, "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": "775f6d7f294307b0b84a5f7dd000459d899cc8c13456cb726c6c6007cbb2fc86", "source_hash": "87e7c1d154f5ac705536a39009085d1ca627dd795547495063e7af19c7cb4678", "raw_response_sha256": "sha256:33c31c66b09a117b22956f6bc51bf7f6e0ca75eb5d657ae1fdf003f9d4b45d61", "raw_response_chars": 5622}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "d66c83f1e8aa2143cf2ca264229995cfb20aba9f8de2d3934c27b6562e804c5e", "source_hash": "87e7c1d154f5ac705536a39009085d1ca627dd795547495063e7af19c7cb4678", "raw_response_sha256": "sha256:ea82f14f99d46e64408eed8aaab0b8ab71e0fabb0ba407b66a5725fd48f6017c", "raw_response_chars": 72916}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "288d62e2ab5906f8fafd230cef859153d63a6393bd1321d0a269b512c68baf0b", "source_hash": "87e7c1d154f5ac705536a39009085d1ca627dd795547495063e7af19c7cb4678", "raw_response": "{\"parent_value\":0.75,\"unit\":\"AUC\",\"evidence\":\"The Random Survival Forest (RSF) model exhibited robust prognostic predictive capabilities across multiple independent cohorts (AUC > 0.75).\",\"target_result\":\"The RSF model exhibited robust prognostic predictive capabilities across multiple independent cohorts (AUC > 0.75).\",\"number_stated\":true}", "reading": {"parent_value": 0.75, "unit": "AUC", "evidence": "The Random Survival Forest (RSF) model exhibited robust prognostic predictive capabilities across multiple independent cohorts (AUC > 0.75).", "target_result": "The RSF model exhibited robust prognostic predictive capabilities across multiple independent cohorts (AUC > 0.75).", "number_stated": true, "source_locator": "chars 1101-1241 of source sha256 87e7c1d154f5ac705536a39009085d1ca627dd795547495063e7af19c7cb4678"}, "recorded_at": "2026-10-31T15:20:26.496511+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "a3ebd6b90f0859b807e399009ad32664b6dbb35d86baf5b64fd486bc6afd1574", "source_hash": "87e7c1d154f5ac705536a39009085d1ca627dd795547495063e7af19c7cb4678", "raw_response": "<think>We need answer JSON only. Need identify single numerical result replication registered target headline numerical result paper states for main finding. Need parse. Registered target generic: \"the headline numerical result the paper states for its main finding\". Likely AUC &gt; 0.75 is headline numerical result? Paper abstract main finding says RSF model robust prognostic predictive capabilities across cohorts (AUC &gt; 0.75). Asked value paper itself states, unit paper prints. Need perhaps number 0.75 with unit \"AUC\". Exact contiguous quote containing number and attribution to target. Could be 867 samples? 321 genes, 26 prognostic genes, AUC &gt; 0.75. They ask \"single numerical result that a replication of registered target has to reproduce.\" Registered target wording likely target is headline numerical result main finding, perhaps AUC &gt; 0.75. Need output parent_value number. Should it be 0.75, unit \"AUC\", evidence exact contiguous clause: \"The Random Survival Forest (RSF) model exhibited robust prognostic predictive capabilities across multiple independent cohorts (AUC &gt; 0.75).\" target_result description. number_stated true.\n\nNeed examine possibility headline number is 867 total samples. Main finding? They say title and abstract. Numerical result replication target perhaps \"AUC &gt; 0.75\". Question engineered to ask single numerical result paper states for registered target. Registered target itself: \"the headline numerical result the paper states for its main finding\". We must infer. Likely use abstract's standout performance metric. They want value only with unit exact printed. \"AUC &gt; 0.75\" unit perhaps \"AUC\" and value 0.75. Yet requirement parent_value number, unit string. Could unit be \"&gt;\"? They ask headline number only, unit must unit paper prints. Usually answer schema parent_value numeric and unit \"AUC\". Evidence retains &gt;. Need target_result perhaps \"AUC &gt; 0.75\". Exact quote.\n\nCould headline numerical result instead \"867 tumor samples\" because replication of registered target? Let's understand prompt semantics. They supply \"REGISTERED TARGET: the headline numerical result the paper states for its main finding\". They seek extraction. It might be a benchmark designed where target often specific like sample size. Here target is abstractly defined as headline numerical result. The paper abstract states several numbers. Which one is \"headline\"? RSF model AUC &gt; 0.75 likely key headline performance. \"main finding\" perhaps main finding is molecular subtyping / machine learning model, and headline numerical result is AUC &gt; 0.75. Need be precise.\n\nCould unit be \"AUC\" or perhaps no unit. \"AUC &gt; 0.75\" is dimensionless metric. Unit string can be \"AUC\". They explicitly say \"unit must be the unit the paper prints.\" Paper prints AUC. Fine.\n\nCould parent_value be 0.75 despite threshold. They request value, paper itself states. Evidence exact quote. target_result maybe \"AUC &gt; 0.75 for RSF model across multiple independent cohorts\". Since evidence exact quote. Ensure valid JSON escape &gt; no issue. No markdown.\n\nLet's not overcomplicate. But let's inspect all source. Abstract:\n- total 867 tumor samples\n- 321 genes\n- 26 prognostic genes\n- AUC &gt; 0.75\nConclusion says 206 key genes inconsistently.\nQuestion wording \"headline numerical result the paper states for its main finding\" likely asks main model performance, perhaps AUC. \"that a replication of the registered target has to reproduce\" indicates replication target metric. Could be sample count? A replication would need reproduce AUC &gt; .75. Sample size is design, not result. Number of genes likewise result but replication would reproduce candidates. AUC is performance headline.\n\nNeed perhaps include \"AUC &gt; 0.75\" unit string. parent_value schema only number no comparator, so target_result can preserve &gt;. unit maybe \"AUC\". Evidence whole clause. Let's formulate:\n{\n\"parent_value\":0.75,\n\"unit\":\"AUC\",\n\"evidence\":\"The Random Survival Forest (RSF) model exhibited robust prognostic predictive capabilities across multiple independent cohorts (AUC &gt; 0.75).\",\n\"target_result\":\"AUC &gt; 0.75\",\n\"number_stated\":true\n}\nDoes \"headline number only\" mean target_result should only value? They request headline number only likely don't report other values. This is okay. Evidence exact quote. Could unit be \"AUC &gt;\"? Usually unit means metric. I'd use \"AUC\". Maybe \"unit\": \"AUC (area under the curve)\" would not be printed exact phrase. No.\n\nNeed JSON only.</think>\n\n{\"parent_value\":0.75,\"unit\":\"AUC\",\"evidence\":\"The Random Survival Forest (RSF) model exhibited robust prognostic predictive capabilities across multiple independent cohorts (AUC > 0.75).\",\"target_result\":\"AUC > 0.75\",\"number_stated\":true}", "reading": {"parent_value": 0.75, "unit": "AUC", "evidence": "The Random Survival Forest (RSF) model exhibited robust prognostic predictive capabilities across multiple independent cohorts (AUC > 0.75).", "target_result": "AUC > 0.75", "number_stated": true, "source_locator": "chars 1101-1241 of source sha256 87e7c1d154f5ac705536a39009085d1ca627dd795547495063e7af19c7cb4678"}, "recorded_at": "2026-10-31T15:20:32.570878+00:00"}], "agreement": false, "disagreements": {"target_result": {"minimax": "The Random Survival Forest (RSF) model exhibited robust prognostic predictive capabilities across multiple independent cohorts (AUC > 0.75).", "minimax_alt": "AUC > 0.75", "decisive": false}, "analysis_methods": {"minimax": ["Random Survival Forest (RSF)", "ROC curves", "time-dependent ROC curves", "Kaplan-Meier survival analysis", "log-rank test", "univariate and multivariate Cox regression analyses"], "minimax_alt": ["Summary data-based Mendelian Randomization (SMR)", "Random Survival Forest (RSF)", "ROC curves", "time-dependent ROC curves", "univariate Cox regression analysis with the Wald test", "multivariate Cox regression analysis", "Kaplan-Meier survival analysis", "log-rank tests", "Wilcoxon test", "correlation analysis"], "decisive": false}, "statistical_method": {"minimax": "ROC curves and time-dependent ROC curves", "minimax_alt": "Random Survival Forest (RSF) model", "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:3f5dbafe06ed4479b8d5a845fde3e835f1b632ff8cf1900722fd949615c5e398", "type": "sep_package", "label": "SEP v1 package for pmid:39794414"}], "activities": [{"id": "activity:conversion:pmid:39794414", "type": "conversion", "used": ["package:3f5dbafe06ed4479b8d5a845fde3e835f1b632ff8cf1900722fd949615c5e398"], "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": "01f0efff-e79f-44d1-a5c8-d77944fd8f67", "parent_hash": "3f5dbafe06ed4479b8d5a845fde3e835f1b632ff8cf1900722fd949615c5e398", "fork_of": null, "generation": 1}, "gaps": ["abstract", "asset:source:pmid:39794414 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:39794414' does not resolve to a declared asset", "targets"]}