Single-cell and transcriptomic profiling reveal stemness-driven immune evasion in obstructive sleep apnea (OSA) associated lung cancer.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:41584048", "kind": "science-record", "revision": 1, "content_hash": "sha256:c02dc8d7b9052e1efba5939eb5413a2b579ad5d8a950731415315f0073052f16", "created_at": "2026-11-01T10:25:54Z", "updated_at": "2026-11-01T10:25:54Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Single-cell and transcriptomic profiling reveal stemness-driven immune evasion in obstructive sleep apnea (OSA) associated lung cancer.", "doi": "10.7150/jca.126708", "pmid": "41584048", "authors": null, "journal": "Journal of Cancer", "year": 2026, "abstract": null, "claims": [{"id": "claim-1", "statement": "the headline numerical result the paper states for its main finding", "kind": "quantitative", "state": "complete", "target": {"value": 6.0, "unit": "genes", "tolerance": null, "source": "chars 1633-1836 of source sha256 91f394a118d8912a20f0a1a5ff2e9ab202282bd97f87e257fecbc4a123e6b2e0"}, "evidence": [{"asset": "source:pmid:41584048", "locator": "chars 1633-1836 of source sha256 91f394a118d8912a20f0a1a5ff2e9ab202282bd97f87e257fecbc4a123e6b2e0", "quote": "LASSO modeling identified a six-gene stemness signature (EIF5A, MELTF, SEMA3C, CPS1, TCN1, SELENOK), that consistently stratified patients into high- and low-risk groups across TCGA and GSE31210 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:41584048"], "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:41584048", "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:41584048' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:41584048", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.7150/jca.126708", "sha256": "sha256:91f394a118d8912a20f0a1a5ff2e9ab202282bd97f87e257fecbc4a123e6b2e0", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.7150/jca.126708", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}], "gaps": ["asset:source:pmid:41584048 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:41584048"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:41584048"]}, "gaps": ["corpus_record_absent"]}, "review": {"state": "partial", "machine_critique": {"status": "passed", "providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "full-text-reading-v1", "prompt_hash": "a659164fbcef65b79bb100112c37d833df6ace27aa5fbc59915b57e0072e9fea", "source_hash": "91f394a118d8912a20f0a1a5ff2e9ab202282bd97f87e257fecbc4a123e6b2e0", "raw_response_sha256": "sha256:f5da553d0f2d5b306ca92cca29fe73bc7f787578f497efd6cf4e4afba6d8e7fa", "raw_response_chars": 5969}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "aa23957ea3269ca59027bbc06d3a15049e57bfc90ed95225b0b851976740d067", "source_hash": "91f394a118d8912a20f0a1a5ff2e9ab202282bd97f87e257fecbc4a123e6b2e0", "raw_response_sha256": "sha256:c120c349771d4d732a4f36ed2791a1fcf6ea958b05c5aedd379e6f81b94c6c9f", "raw_response_chars": 65987}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "42a9df6ee6a734f42ca736df18dd0dc857e0f58c29be58494bd432c6fceb3669", "source_hash": "91f394a118d8912a20f0a1a5ff2e9ab202282bd97f87e257fecbc4a123e6b2e0", "raw_response": "{\"parent_value\":6,\"unit\":\"genes\",\"evidence\":\"LASSO modeling identified a six-gene stemness signature (EIF5A, MELTF, SEMA3C, CPS1, TCN1, SELENOK), that consistently stratified patients into high- and low-risk groups across TCGA and GSE31210 cohorts.\",\"target_result\":\"The study identified a six-gene stemness signature for prognostic stratification.\",\"number_stated\":true}", "reading": {"parent_value": 6, "unit": "genes", "evidence": "LASSO modeling identified a six-gene stemness signature (EIF5A, MELTF, SEMA3C, CPS1, TCN1, SELENOK), that consistently stratified patients into high- and low-risk groups across TCGA and GSE31210 cohorts.", "target_result": "The study identified a six-gene stemness signature for prognostic stratification.", "number_stated": true, "source_locator": "chars 1633-1836 of source sha256 91f394a118d8912a20f0a1a5ff2e9ab202282bd97f87e257fecbc4a123e6b2e0"}, "recorded_at": "2026-10-31T15:17:05.472080+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "4d693a337add1fcc1925f707b5c4bfae54f4c40f9844bbe399f7aa9bfd4c5582", "source_hash": "91f394a118d8912a20f0a1a5ff2e9ab202282bd97f87e257fecbc4a123e6b2e0", "raw_response": "<think>We need answer JSON only. Need determine single numerical result headline for registered target main finding. Source abstract says LASSO identified six-gene signature. Is headline numerical result likely six-gene stemness signature. Need exact contiguous quotation containing number and attribution whole clause. \"LASSO modeling identified a six-gene stemness signature (EIF5A, MELTF, SEMA3C, CPS1, TCN1, SELENOK), that consistently stratified patients into high- and low-risk groups across TCGA and GSE31210 cohorts.\" Number spelled six, but parent_value number 6. Evidence exact quote must contain number. Unit likely \"genes\" (paper prints six-gene; unit printed perhaps \"genes\"). They request unit must be unit paper prints. Could unit be \"genes\". Headline numerical result = six-gene stemness signature. But perhaps main finding headline number might be \"six-gene\" yes. Need output target_result string perhaps \"A six-gene stemness signature...\" no paraphrase? Evidence exact quote. number_stated true. parent_value 6. unit \"genes\". target_result can state textual result. Need ensure evidence contiguous exact quotation. Quote whole clause. We need not calculate. Let's formulate valid JSON, no markdown.\n\nQuestion 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, not a value you calculated...\" Since number spelled \"six\", parent_value 6. Is that considered calculated? No numerical lexical value. Unit \"genes\". Evidence exact contiguous. \"LASSO modeling identified a six-gene stemness signature (EIF5A, MELTF, SEMA3C, CPS1, TCN1, SELENOK), that consistently stratified patients into high- and low-risk groups across TCGA and GSE31210 cohorts.\" Exact punctuation. target_result maybe \"LASSO modeling identified a six-gene stemness signature.\" Is this paraphrase in field allowed. They demand headline number only perhaps target_result likely description. Schema includes target_result perhaps concise. Could say \"six-gene stemness signature\". Unit perhaps \"genes\" and evidence says six-gene. They said report headline number only perhaps parent_value 6 and unit. target_result likely \"A six-gene stemness signature...\" We should use paper wording.\n\nNeed exact quote perhaps just sentence. Ensure no accidental alteration: source: \"LASSO modeling identified a six-gene stemness signature (EIF5A, MELTF, SEMA3C, CPS1, TCN1, SELENOK), that consistently stratified patients into high- and low-risk groups across TCGA and GSE31210 cohorts.\" Exact. Unit paper prints? \"six-gene\" gives unit genes. Good.\n\nJSON:\n{\"parent_value\":6,\"unit\":\"genes\",\"evidence\":\"...\",\"target_result\":\"LASSO modeling identified a six-gene stemness signature.\",\"number_stated\":true}\n\nCould target_result include direct quotation? \"six-gene stemness signature\" perhaps. The instruction says report headline number only perhaps target_result is intended natural result. But all schema required. Should target_result be exact source wording perhaps safest: \"LASSO modeling identified a six-gene stemness signature\". Yet if report headline number only maybe no extraneous numerical info. Evidence has names and cohorts no other numbers except TCGA/GSE31210 identifiers (contains numbers but numerical result one; okay). Could choose only exact clause containing six-gene to avoid other numbers: \"LASSO modeling identified a six-gene stemness signature (EIF5A, MELTF, SEMA3C, CPS1, TCN1, SELENOK), that consistently stratified patients into high- and low-risk groups across TCGA and GSE31210 cohorts.\" There are identifiers. Whole clause attribution is clear. Is \"that...\" needed? No, attribution directly by LASSO modeling. Could quote shorter contiguous: \"LASSO modeling identified a six-gene stemness signature (EIF5A, MELTF, SEMA3C, CPS1, TCN1, SELENOK)\" but original has comma after closing parenthesis, so exact contiguous substring without comma still is exact quote. They say quote whole clause so reader can check attribution. This does. Exact punctuation? If omit comma, quote is still contiguous exact substring. But better full sentence. Numerical identifiers don't matter.\n\nCould there be another headline numerical result: 22 leukocyte subsets, 1,000 permutations, 10-fold cross validation, six-gene. Main finding specifically signature six genes. Yes.\n\nLet's final JSON only.</think>\n\n{\"parent_value\":6,\"unit\":\"genes\",\"evidence\":\"LASSO modeling identified a six-gene stemness signature (EIF5A, MELTF, SEMA3C, CPS1, TCN1, SELENOK), that consistently stratified patients into high- and low-risk groups across TCGA and GSE31210 cohorts.\",\"target_result\":\"LASSO modeling identified a six-gene stemness signature.\",\"number_stated\":true}", "reading": {"parent_value": 6, "unit": "genes", "evidence": "LASSO modeling identified a six-gene stemness signature (EIF5A, MELTF, SEMA3C, CPS1, TCN1, SELENOK), that consistently stratified patients into high- and low-risk groups across TCGA and GSE31210 cohorts.", "target_result": "LASSO modeling identified a six-gene stemness signature.", "number_stated": true, "source_locator": "chars 1633-1836 of source sha256 91f394a118d8912a20f0a1a5ff2e9ab202282bd97f87e257fecbc4a123e6b2e0"}, "recorded_at": "2026-10-31T15:17:11.515779+00:00"}], "agreement": true, "disagreements": {"target_result": {"minimax": "A six-gene stemness signature (EIF5A, MELTF, SEMA3C, CPS1, TCN1, SELENOK) that stratified lung adenocarcinoma patients into high- and low-risk groups.", "minimax_alt": "LASSO modeling identified a six-gene stemness signature (EIF5A, MELTF, SEMA3C, CPS1, TCN1, SELENOK), that consistently stratified patients into high- and low-risk groups across TCGA and GSE31210 cohorts.", "decisive": false}, "analysis_methods": {"minimax": ["Single-cell RNA sequencing analysis", "Bulk transcriptomic analysis", "CytoTRACE", "Transcriptome-based stemness scoring", "Differential expression analysis using limma", "Univariate Cox regression", "Least absolute shrinkage and selection operator (LASSO) Cox regression with 10-fold cross-validation", "Multivariate Cox regression", "Kaplan-Meier survival analysis", "Time-dependent receiver operating characteristic curves", "CIBERSORT", "ESTIMATE algorithm", "Wilcoxon rank-sum test", "Pearson correlation", "Spearman correlation", "Log-rank test", "oncoPredict"], "minimax_alt": ["CytoTRACE", "transcriptome-based stemness scoring", "limma (v3.54.2)", "univariate Cox regression", "least absolute shrinkage and selection operator (LASSO) Cox regression with 10-fold cross-validation", "weighted-expression risk-score calculation", "median-risk-score stratification", "Kaplan-Meier survival analysis", "time-dependent receiver operating characteristic (ROC) curves", "multivariate Cox regression", "CIBERSORT", "ESTIMATE algorithm", "Wilcoxon rank-sum test", "Student's t-test", "Pearson correlation", "Spearman correlation", "log-rank test", "oncoPredict"], "decisive": false}}, "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": "passed", "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.passed"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "package:d7bdb1c3b36fe2d0fd7a232910ecc7efa15cb3fe1af1c65523df3c689299795a", "type": "sep_package", "label": "SEP v1 package for pmid:41584048"}], "activities": [{"id": "activity:conversion:pmid:41584048", "type": "conversion", "used": ["package:d7bdb1c3b36fe2d0fd7a232910ecc7efa15cb3fe1af1c65523df3c689299795a"], "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": "0e411562-6cca-48d0-a27f-98567171b156", "parent_hash": "d7bdb1c3b36fe2d0fd7a232910ecc7efa15cb3fe1af1c65523df3c689299795a", "fork_of": null, "generation": 1}, "gaps": ["abstract", "asset:source:pmid:41584048 not verified", "authors", "capability", "corpus_record_absent", "execution.not_run", "method", "review.human_critique", "review.machine_critique.passed", "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:41584048' does not resolve to a declared asset", "targets"]}