Predicting the Lung Adenocarcinoma and Its Biomarkers by Integrating Gene Expression and DNA Methylation Data.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:35846148", "kind": "science-record", "revision": 4, "content_hash": "sha256:cf4c677899033f0db9df5149f805e18489e250398ae10ff2049d2f3bbdcdcbd6", "created_at": "2026-11-01T18:14:55Z", "updated_at": "2026-11-01T22:07:03Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Predicting the Lung Adenocarcinoma and Its Biomarkers by Integrating Gene Expression and DNA Methylation Data.", "doi": "10.3389/fgene.2022.926927", "pmid": "35846148", "authors": ["Wang-Ren Qiu", "Bei-Bei Qi", "Wei-Zhong Lin", "Shou-Hua Zhang", "Wang-Ke Yu", "Shun-Fa Huang"], "journal": "Frontiers in genetics", "year": 2022, "abstract": "The early symptoms of lung adenocarcinoma patients are inapparent, and the clinical diagnosis of lung adenocarcinoma is primarily through X-ray examination and pathological section examination, whereas the discovery of biomarkers points out another direction for the diagnosis of lung adenocarcinoma with the development of bioinformatics technology. However, it is not accurate and trustworthy to diagnose lung adenocarcinoma due to omics data with high-dimension and low-sample size (HDLSS) features or biomarkers produced by utilizing only single omics data. To address the above problems, the feature selection methods of biological analysis are used to reduce the dimension of gene expression data (GSE19188) and DNA methylation data (GSE139032, GSE49996). In addition, the Cartesian product method is used to expand the sample set and integrate gene expression data and DNA methylation data. The classification is built by using a deep neural network and is evaluated on K-fold cross validation. Moreover, gene ontology analysis and literature retrieving are used to analyze the biological relevance of selected genes, TCGA database is used for survival analysis of these potential genes through Kaplan-Meier estimates to discover the detailed molecular mechanism of lung adenocarcinoma. Survival analysis shows that COL5A2 and SERPINB5 are significant for identifying lung adenocarcinoma and are considered biomarkers of lung adenocarcinoma.", "claims": [{"id": "claim-method", "statement": "Five-fold cross validation is also used to obtain the average values of accuracy and AUROC.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:35846148", "locator": "sections[11] \"The Impact of Different Classifiers on Performance\" paragraph 3", "quote": "Five-fold cross validation is also used to obtain the average values of accuracy and AUROC."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:35846148", "locator": "sections[14] \"Data Availability Statement\" paragraph 2", "quote": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": null, "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:35846148"], "outputs": ["the published estimate and its evidence"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data from the named repository", "kind": "data-preparation", "state": "complete", "blocked_on": null, "description": "The GEO series accession resolves and its sample accessions are listed. This lane did not download the dataset or read its licence.", "duration_hours": null, "parameters": {}, "inputs": ["data:geo:GSE139032"], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "complete", "blocked_on": null, "description": "Apply the paper's statistical method to the resolved series and compare the result with the published target.", "duration_hours": null, "parameters": {}, "inputs": ["data:geo:GSE139032"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:35846148", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fgene.2022.926927", "sha256": "sha256:89b127c7175ca3d1fffd97351b9d48eab08c6bd4f4983ab000c2f5fce7e23231", "bytes": 45181, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fgene.2022.926927", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC9280023", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE139032", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE139032", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE139032", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4127666", "GSM4127667", "GSM4127668", "GSM4127669", "GSM4127670", "GSM4127671", "GSM4127672", "GSM4127673", "GSM4127674", "GSM4127675", "GSM4127676", "GSM4127677", "GSM4127678", "GSM4127679", "GSM4127680", "GSM4127681", "GSM4127682", "GSM4127683", "GSM4127684", "GSM4127685", "GSM4127686", "GSM4127687", "GSM4127688", "GSM4127689", "GSM4127690", "GSM4127691", "GSM4127692", "GSM4127693", "GSM4127694", "GSM4127695", "GSM4127696", "GSM4127697", "GSM4127698", "GSM4127699", "GSM4127700", "GSM4127701", "GSM4127702", "GSM4127703", "GSM4127704", "GSM4127705", "GSM4127706", "GSM4127707", "GSM4127708", "GSM4127709", "GSM4127710", "GSM4127711", "GSM4127712", "GSM4127713", "GSM4127714", "GSM4127715", "GSM4127716", "GSM4127717", "GSM4127718", "GSM4127719", "GSM4127720", "GSM4127721", "GSM4127722", "GSM4127723", "GSM4127724", "GSM4127725", "GSM4127726", "GSM4127727", "GSM4127728", "GSM4127729", "GSM4127730", "GSM4127731", "GSM4127732", "GSM4127733", "GSM4127734", "GSM4127735", "GSM4127736", "GSM4127737", "GSM4127738", "GSM4127739", "GSM4127740", "GSM4127741", "GSM4127742", "GSM4127743", "GSM4127744", "GSM4127745", "GSM4127746", "GSM4127747", "GSM4127748", "GSM4127749", "GSM4127750", "GSM4127751", "GSM4127752", "GSM4127753", "GSM4127754", "GSM4127755", "GSM4127756", "GSM4127757", "GSM4127758", "GSM4127759", "GSM4127760", "GSM4127761", "GSM4127762", "GSM4127763", "GSM4127764", "GSM4127765", "GSM4127766", "GSM4127767", "GSM4127768", "GSM4127769", "GSM4127770", "GSM4127771", "GSM4127772", "GSM4127773", "GSM4127774", "GSM4127775", "GSM4127776", "GSM4127777", "GSM4127778", "GSM4127779", "GSM4127780", "GSM4127781", "GSM4127782", "GSM4127783", "GSM4127784", "GSM4127785", "GSM4127786", "GSM4127787", "GSM4127788", "GSM4127789", "GSM4127790", "GSM4127791", "GSM4127792", "GSM4127793", "GSM4127794", "GSM4127795", "GSM4127796", "GSM4127797", "GSM4127798", "GSM4127799", "GSM4127800", "GSM4127801", "GSM4127802", "GSM4127803", "GSM4127804", "GSM4127805", "GSM4127806", "GSM4127807", "GSM4127808", "GSM4127809", "GSM4127810", "GSM4127811", "GSM4127812", "GSM4127813", "GSM4127814", "GSM4127815", "GSM4127816", "GSM4127817", "GSM4127818", "GSM4127819"], "sample_count": 154, "group_sizes": null, "group_sizes_basis": null, "platform": "8490", "taxon": "Homo sapiens", "title": "DNA methylation profiling of lung adenocarcinomas and patient-matched non-malignant lung", "resolution_checked_at": "2026-11-01T18:06:43Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE19188", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE19188", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE19188", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM475656", "GSM475657", "GSM475658", "GSM475659", "GSM475660", "GSM475661", "GSM475662", "GSM475663", "GSM475664", "GSM475665", "GSM475666", "GSM475667", "GSM475668", "GSM475669", "GSM475670", "GSM475671", "GSM475672", "GSM475673", "GSM475674", "GSM475675", "GSM475676", "GSM475677", "GSM475678", "GSM475679", "GSM475680", "GSM475681", "GSM475682", "GSM475683", "GSM475684", "GSM475685", "GSM475686", "GSM475687", "GSM475688", "GSM475689", "GSM475690", "GSM475691", "GSM475692", "GSM475693", "GSM475694", "GSM475695", "GSM475696", "GSM475697", "GSM475698", "GSM475699", "GSM475700", "GSM475701", "GSM475702", "GSM475703", "GSM475704", "GSM475705", "GSM475706", "GSM475707", "GSM475708", "GSM475709", "GSM475710", "GSM475711", "GSM475712", "GSM475713", "GSM475714", "GSM475715", "GSM475716", "GSM475717", "GSM475718", "GSM475719", "GSM475720", "GSM475721", "GSM475722", "GSM475723", "GSM475724", "GSM475725", "GSM475726", "GSM475727", "GSM475728", "GSM475729", "GSM475730", "GSM475731", "GSM475732", "GSM475733", "GSM475734", "GSM475735", "GSM475736", "GSM475737", "GSM475738", "GSM475739", "GSM475740", "GSM475741", "GSM475742", "GSM475743", "GSM475744", "GSM475745", "GSM475746", "GSM475747", "GSM475748", "GSM475749", "GSM475750", "GSM475751", "GSM475752", "GSM475753", "GSM475754", "GSM475755", "GSM475756", "GSM475757", "GSM475758", "GSM475759", "GSM475760", "GSM475761", "GSM475762", "GSM475763", "GSM475764", "GSM475765", "GSM475766", "GSM475767", "GSM475768", "GSM475769", "GSM475770", "GSM475771", "GSM475772", "GSM475773", "GSM475774", "GSM475775", "GSM475776", "GSM475777", "GSM475778", "GSM475779", "GSM475780", "GSM475781", "GSM475782", "GSM475783", "GSM475784", "GSM475785", "GSM475786", "GSM475787", "GSM475788", "GSM475789", "GSM475790", "GSM475791", "GSM475792", "GSM475793", "GSM475794", "GSM475795", "GSM475796", "GSM475797", "GSM475798", "GSM475799", "GSM475800", "GSM475801", "GSM475802", "GSM475803", "GSM475804", "GSM475805", "GSM475806", "GSM475807", "GSM475808", "GSM475809", "GSM475810", "GSM475811"], "sample_count": 156, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data for early stage NSCLC", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE49996", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE49996", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE49996", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1211448", "GSM1211449", "GSM1211450", "GSM1211451", "GSM1211452", "GSM1211453", "GSM1211454", "GSM1211455", "GSM1211456", "GSM1211457", "GSM1211458", "GSM1211459", "GSM1211460", "GSM1211461", "GSM1211462", "GSM1211463", "GSM1211464", "GSM1211465", "GSM1211466", "GSM1211467", "GSM1211468", "GSM1211469", "GSM1211470", "GSM1211471", "GSM1211472", "GSM1211473", "GSM1211474", "GSM1211475", "GSM1211476", "GSM1211477", "GSM1211478", "GSM1211479", "GSM1211480", "GSM1211481", "GSM1211482", "GSM1211483", "GSM1211484", "GSM1211485", "GSM1211486", "GSM1211487", "GSM1211488", "GSM1211489", "GSM1211490", "GSM1211491", "GSM1211492", "GSM1211493", "GSM1211494", "GSM1211495", "GSM1211496", "GSM1211497", "GSM1211498", "GSM1211499", "GSM1211500", "GSM1211501", "GSM1211502", "GSM1211503", "GSM1211504", "GSM1211505", "GSM1211506", "GSM1211507", "GSM1211508", "GSM1211509", "GSM1211510", "GSM1211511", "GSM1211512", "GSM1211513", "GSM1211514", "GSM1211515", "GSM1211516", "GSM1211517", "GSM1211518", "GSM1211519", "GSM1211520", "GSM1211521", "GSM1211522", "GSM1211523", "GSM1211524", "GSM1211525", "GSM1211526", "GSM1211527", "GSM1211528", "GSM1211529", "GSM1211530", "GSM1211531", "GSM1211532", "GSM1211533", "GSM1211534", "GSM1211535"], "sample_count": 88, "group_sizes": null, "group_sizes_basis": null, "platform": "8490", "taxon": "Homo sapiens", "title": "Methylation analysis of normal and adenocarcinoma lung tissues", "resolution_checked_at": "2026-11-01T18:06:44Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE139032 not downloaded", "asset:data:geo:GSE139032 licence not read", "asset:data:geo:GSE19188 not downloaded", "asset:data:geo:GSE19188 licence not read", "asset:data:geo:GSE49996 not downloaded", "asset:data:geo:GSE49996 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "survival_analysis", "specific": "kaplan_meier", "label": "Survival analysis", "dsl_operations": ["survival_km"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.7, "band": "medium", "quote": "Kaplan-Meier"}}, {"id": "method-2", "family": "differential_expression", "specific": "limma_voom", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 0.8, "band": "high", "quote": "limma"}}, {"id": "method-3", "family": "machine_learning", "specific": "random_forest", "label": "Machine learning", "dsl_operations": [], "missing_operations": ["machine_learning_random_forest"], "expressible": false, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "random forest"}}, {"id": "method-4", "family": "diagnostic_evaluation", "specific": "roc", "label": "Diagnostic test evaluation", "dsl_operations": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["reference_standard_and_test"], "evidence": {"score": 0.8, "band": "high", "quote": "AUROC"}}, {"id": "method-5", "family": null, "specific": null, "label": "five-fold cross validation", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Five-fold cross validation is also used to obtain the average values of accuracy and AUROC."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["survival_km"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: kaplan_meier."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R1", "reachable": true, "accessions": ["GSE19188", "GSE139032", "GSE49996"], "resolved_accessions": ["GSE19188", "GSE139032", "GSE49996"], "statements": ["The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material."], "basis": "The paper names GSE19188, GSE139032, GSE49996 in Comprehensive Gene Expression Omnibus of the National Center for Biotechnology Information and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["survival_km"], "assets": ["source:pmid:35846148", "data:geo:GSE139032"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE139032"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T17:55:46Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 12800, "completion_tokens": 1381, "cached_tokens": 256}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:35846148", "type": "paper", "label": "pmid:35846148"}, {"id": "source:pmid:35846148", "type": "manuscript", "label": "PMID 35846148 full text"}, {"id": "data:geo:GSE139032", "type": "dataset", "label": "GEO GSE139032"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:35846148", "type": "paper", "label": "pmid:35846148"}, {"id": "source:pmid:35846148", "type": "manuscript", "label": "PMID 35846148 full text"}, {"id": "data:geo:GSE139032", "type": "dataset", "label": "GEO GSE139032"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-35846148", "type": "extraction", "used": ["source:pmid:35846148"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE139032", "type": "accession_resolution", "used": ["data:geo:GSE139032"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}, {"id": "agent:minimax-reader", "type": "software", "label": "MiniMax literature reader"}], "source_run_id": "reading-sci-2026-11-01", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:35846148", "parent_hash": "sha256:4a0ebd6bf1ce8c0b9833eaf35d229ffc1d94a2933615a23ffd7add1f249659f5", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE139032 licence not read", "asset:data:geo:GSE139032 not downloaded", "asset:data:geo:GSE19188 licence not read", "asset:data:geo:GSE19188 not downloaded", "asset:data:geo:GSE49996 licence not read", "asset:data:geo:GSE49996 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["survival_km"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["Kaplan-Meier"], "order_basis": "analysis_only", "id": "assay:1"}]}