Development of a Serum Proteomic-Based Diagnostic Model for Lung Cancer Using Machine Learning Algorithms and Unveiling the Role of SLC16A4 in Tumor Progression and Immune Response.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40867526", "kind": "science-record", "revision": 2, "content_hash": "sha256:4a922cc7c271b01b2812989433ad9e7ff5e3511fa278c749266cb0613c3874b3", "created_at": "2026-11-01T10:25:52Z", "updated_at": "2026-11-01T14:01:47Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Development of a Serum Proteomic-Based Diagnostic Model for Lung Cancer Using Machine Learning Algorithms and Unveiling the Role of SLC16A4 in Tumor Progression and Immune Response.", "doi": "10.3390/biom15081081", "pmid": "40867526", "authors": null, "journal": "Biomolecules", "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:40867526"], "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:40867526", "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:40867526' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40867526", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3390/biom15081081", "sha256": "sha256:be4c6e3e7282e7c2a1d21db616bd3450798e41385a934296fb1ae88b76988589", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3390/biom15081081", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:40867526:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:59d54e5132ec21d8bb6584d086df405f90cc11e756c9a13e877524ac75cd97f3", "bytes": 1137, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[19]/table-wrap[1]#biomolecules-15-01081-t001", "version": null, "note": "Distribution of samples in the training set, testing set, and validation set.", "structure": {"pmcid": "PMC12383841", "section_index": 19, "section_title": "3.1. Dataset", "row_count": 12, "column_count": 7}, "table": {"label": "Table 1", "caption": "Distribution of samples in the training set, testing set, and validation set.", "rows": [["Characteristics", "Training(n = 144)", "Testing(n = 36)", "Validating(n = 16)", "All(n = 196)", "p"], ["Age", ">60", "56 (42.75%)", "14 (41.18%)", "4 (25.00%)", "74 (40.88%)", "0.602"], ["", "≤60", "75 (57.25%)", "20 (58.82%)", "12 (75.00%)", "107 (59.12%)"], ["gender", "female", "49 (36.84%)", "18 (50.00%)", "10 (62.50%)", "77 (41.62%)", "0.161"], ["", "male", "84 (63.16%)", "18 (50.00%)", "6 (37.50%)", "108 (58.38%)"], ["smoke", "no", "24 (68.57%)", "11 (84.62%)", "8 (100.00%)", "43 (76.79%)", "0.242"], ["", "yes", "11 (31.43%)", "2 (15.38%)", "0", "13 (23.21%)"], ["surgery", "no", "2 (5.71%)", "1 (7.69%)", "0", "3 (5.36%)", "0.896"], ["", "yes", "33 (94.29%)", "12 (92.31%)", "8 (100.00%)", "53 (94.64%)"], ["Disease type", "NegativeControl", "42 (29.17%)", "18 (50.00%)", "8 (50.00%)", "68 (34.69%)", "NA"], ["", "Disease control", "60 (41.67%)", "0", "0", "60 (30.61%)"], ["", "Cancer", "42 (29.17%)", "18 (50.00%)", "8 (50.00%)", "68 (34.69%)"]], "row_count": 12, "column_count": 7, "numeric_cells": 54, "header_rows": 1, "locator": "section[19]/table-wrap[1]#biomolecules-15-01081-t001"}}, {"id": "asset:table:pmid:40867526:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:fb87e3150b8d0e632089a3980a87dda543586e3d4a5dff5ddd78b3904593f2a0", "bytes": 1231, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[24]/table-wrap[1]#biomolecules-15-01081-t002", "version": null, "note": "Correlation of SLC16A4 expression with clinical characteristics in the TCGA lung cancer dataset.", "structure": {"pmcid": "PMC12383841", "section_index": 24, "section_title": "3.6. Association of SLC16A4 with Clinical Characteristics in Lung Cancer", "row_count": 23, "column_count": 5}, "table": {"label": "Table 2", "caption": "Correlation of SLC16A4 expression with clinical characteristics in the TCGA lung cancer dataset.", "rows": [["Characteristics", "N", "Expression", "p"], ["Gender", "female", "405", "2.580 ± 1.879", "<0.001"], ["", "male", "608", "1.812 ± 2.026", ""], ["Age", ">60", "720", "2.121 ± 2.014", "0.768"], ["", "≤60", "265", "2.079 ± 1.986", ""], ["M", "M0", "753", "2.049 ± 2.023", "0.002"], ["", "M1", "32", "3.241 ± 2.021", ""], ["N", "N0", "648", "2.103 ± 1.973", "0.041"], ["", "N1", "226", "1.871 ± 2.013", ""], ["", "N2", "114", "2.530 ± 2.119", ""], ["", "N3", "7", "2.073 ± 1.375", ""], ["T", "T1", "282", "2.505 ± 1.907", "0.002"], ["", "T2", "569", "1.968 ± 1.976", ""], ["", "T3", "118", "1.911 ± 2.241", ""], ["", "T4", "41", "1.995 ± 1.992", ""], ["Stage", "Stage I", "518", "2.186 ± 1.914", "0.001"], ["", "Stage II", "283", "1.853 ± 2.053", ""], ["", "Stage III", "167", "2.141 ± 2.089", ""], ["", "Stage IV", "33", "3.246 ± 1.989", ""], ["Smoke.history", "Current", "253", "1.736 ± 1.910", "<0.001"], ["", "Never", "94", "2.877 ± 1.819", ""], ["", "Reformed (>15)", "215", "2.615 ± 2.149", ""], ["", "Reformed (≤15)", "416", "1.914 ± 1.938", ""]], "row_count": 23, "column_count": 5, "numeric_cells": 55, "header_rows": 1, "locator": "section[24]/table-wrap[1]#biomolecules-15-01081-t002"}}], "gaps": ["asset:source:pmid:40867526 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:40867526", "asset:table:pmid:40867526:1", "asset:table:pmid:40867526:2"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:40867526"]}, "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": "7ab2ee4a673c079d03da2ed379f536b0e4d08f5f929ad6d9f3b595e8cc18395c", "source_hash": "be4c6e3e7282e7c2a1d21db616bd3450798e41385a934296fb1ae88b76988589", "raw_response_sha256": "sha256:3c31856f72172dbd827f32953b51103bf24819ca785909b94eac0c68bd7e272b", "raw_response_chars": 5751}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "2738fe29cebcd083e78abe39c2c7bc0d6d7f408431a152694e281c071a678821", "source_hash": "be4c6e3e7282e7c2a1d21db616bd3450798e41385a934296fb1ae88b76988589", "raw_response_sha256": "sha256:df6f525feff5fb42ae9405a0236a045a8f0e4fdcd1520b61f5c89f1554ad4811", "raw_response_chars": 79191}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "a7c51ad19f9c32aef6ee9cf2072c30fc2712d47093aa9baecf30df17b7452208", "source_hash": "be4c6e3e7282e7c2a1d21db616bd3450798e41385a934296fb1ae88b76988589", "raw_response": "{\"parent_value\":0,\"unit\":\"\",\"evidence\":\"\",\"target_result\":\"The text states that the study developed a lung cancer diagnostic model and identified SLC16A4 as a key protein, but it does not state a single headline numerical result for the main finding.\",\"number_stated\":false}", "reading": {"parent_value": 0, "unit": "", "evidence": "", "target_result": "The text states that the study developed a lung cancer diagnostic model and identified SLC16A4 as a key protein, but it does not state a single headline numerical result for the main finding.", "number_stated": false, "source_locator": null}, "recorded_at": "2026-10-31T15:33:10.109927+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "239e69b17b4ea81f8b1d52da937f9b71f309925b8d960484d5e3efba88472235", "source_hash": "be4c6e3e7282e7c2a1d21db616bd3450798e41385a934296fb1ae88b76988589", "raw_response": "<think>We need answer JSON only. Need assess source. Registered target headline numerical result main finding. Source text supplied seems abstract/methods/conclusion but no actual numerical performance result (AUC etc). Need number_stated false, parent_value 0, unit empty, evidence empty, target_result state what text does state instead. Need ensure \"headline number only\" but no number. target_result likely \"The text states that the diagnostic model showed strong diagnostic value and was validated... but it gives no numerical performance result for registered target.\" Exact source doesn't contain headline numerical result. Need not invent source. JSON schema exactly. They insist evidence exact quotation if number; false leave evidence empty. target_result says what text states instead. Could quote wording? \"The study constructed a lung cancer diagnostic machine learning model using serum proteomic data from lung cancer patients, demonstrating strong diagnostic value.\" We can state this exact sentence. Need maybe model performance results omitted. Let's formulate concise. parent_value 0, unit \"\", evidence \"\", target_result maybe \"The text states: “In conclusion, this study constructed a lung cancer diagnostic machine learning model using serum proteomic data from lung cancer patients, demonstrating strong diagnostic value.” It reports no numerical value for the main diagnostic result.\" This states source wording. Is quotation exact? Yes from source. Number 0 itself required but number_stated false. Unit empty.\n\nNeed consider whether any numerical result qualifies, e.g thresholds logFC &gt;0.3 etc. But registered target headline main finding, not methods. No model performance metric. Thus false.\n\nReturn valid JSON no markdown. Ensure curly apostrophe okay.</think>\n\n{\"parent_value\":0,\"unit\":\"\",\"evidence\":\"\",\"target_result\":\"The text states that the study constructed a lung cancer diagnostic machine learning model using serum proteomic data and “demonstrating strong diagnostic value,” but it provides no numerical result for this main finding.\",\"number_stated\":false}", "reading": {"parent_value": 0, "unit": "", "evidence": "", "target_result": "The text states that the study constructed a lung cancer diagnostic machine learning model using serum proteomic data and “demonstrating strong diagnostic value,” but it provides no numerical result for this main finding.", "number_stated": false, "source_locator": null}, "recorded_at": "2026-10-31T15:33:21.698244+00:00"}], "agreement": false, "disagreements": {"target_result": {"minimax": "unknown", "minimax_alt": "unclear", "decisive": false}, "physical_methods": {"minimax": ["functional assays", "DNA methylation validation experiments"], "minimax_alt": ["SLC16A4 overexpression functional assays assessing lung cancer cell proliferation and cellular senescence", "5-aza DNA methylation validation experiments compared with negative-control groups"], "decisive": false}, "analysis_methods": {"minimax": ["nnet", "glmnet", "svm", "XGBoost", "limma", "PCAS", "GCAS", "Spearman correlation analysis", "GSEA", "unpaired Student's t-test", "one-way analysis of variance (ANOVA)"], "minimax_alt": ["Differential plasma-protein expression analysis using the limma package", "Diagnostic model development using nnet, glmnet, svm, and XGBoost", "PCAS analysis of SLC16A4 expression in LUAD and LUSC tumor and normal tissues", "GCAS analysis of SLC16A4 expression across multiple GEO lung cancer datasets", "Spearman correlation analysis using the psych package", "Gene set enrichment analysis using the ClusterProfiler R package", "Drug-sensitivity analysis using the oncoPredict tool", "Unpaired Student’s t-test", "One-way analysis of variance"], "decisive": false}, "statistical_method": {"minimax": "", "minimax_alt": "Machine learning algorithms (nnet, glmnet, svm, and XGBoost)", "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:e4f333af584cbb44464b35ec3074880fe097540af178160649eb72af39416ab5", "type": "sep_package", "label": "SEP v1 package for pmid:40867526"}], "activities": [{"id": "activity:conversion:pmid:40867526", "type": "conversion", "used": ["package:e4f333af584cbb44464b35ec3074880fe097540af178160649eb72af39416ab5"], "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": "pmid:40867526", "parent_hash": "sha256:a51bbb7ab18c69d39c07f67cd878fa5c253a4f816870666d6aa9f7cd09bba0f3", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:40867526 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:40867526' does not resolve to a declared asset", "targets"]}