Development of a prognostic model for NSCLC based on differential genes in tumour stem cells.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:39251710", "kind": "science-record", "revision": 3, "content_hash": "sha256:2dd2a7dc193f2a200f1ac37e63ada2ca231e69f3f18e54c07db4fe13b027e472", "created_at": "2026-11-01T20:29:23Z", "updated_at": "2026-11-01T22:12:38Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Development of a prognostic model for NSCLC based on differential genes in tumour stem cells.", "doi": "10.1038/s41598-024-71317-2", "pmid": "39251710", "authors": ["Yuqi Ma", "Jiawei Li", "Chunping Xiong", "Xiaoluo Sun", "Tao Shen"], "journal": "Scientific reports", "year": 2024, "abstract": "Non-small cell lung cancer (NSCLC) constitutes a significant portion of lung cancers and cytotoxic drugs (e.g. cisplatin) are currently the first-line treatment. However, NSCLC has developed resistance to this drug, which limits the therapeutic effect and thus affects prognosis. NSCLC sc-RNA-seq data were downloaded from the GEO database and Ku Leuven Laboratory for Functional Epigenetics, and bulk RNA-seq data were obtained from the TCGA database. The \"Seurat\" package was employed for scRNA-seq data processing, and the uniform manifold approximation and projection (UMAP) were applied for downscaling and cluster identification. Use the FindAllMarkers function to find differential genes (DEGs) for tumor stem cells. Then, we performed univariate regression analyses on the DEGs to identify potential prognostic genes. We created a machine learning framework based on potential prognostic genes, which combines 10 machine learning methods and their 101 combinations to get the optimal prognostic risk model. The model was evaluated in the training set and validation set. A nomogram was developed to provide physicians with a quantitative tool for prognosis prediction. Finally, we evaluated the expression and functionality of SLC2A1. We discovered 22 cell clusters containing 218379 cells by examining single-cell RNA sequencing datasets (GSE148071, KU_lom, GSE131907, GSE136246, GSE127465). Tumour cells were isolated for subpopulation analysis and 162 differential genes from SOX2_cancer were obtained. After univariate Cox analysis, we found 23 genes with prognostic potential prognostic value and utilized them to develop 101‑combination machine learning computational framework. We eventually picked the best performing 'StepCox[both] + RSF', which includes 8 genes. The model has a relatively high prediction accuracy in both TCGA and GEO datasets. In in vitro investigations, targeted suppression of the SLC2A1 gene resulted in significant reductions in proliferation, invasion and migration in A549 cells. In addition, a significant reduction in cisplatin resistance was seen in A549/DDP cells. The outcomes demonstrated the precision and credibility of the prognostic model for NSCLC, highlighting its potential significance in the treatment and prognosis of individuals affected by this disease. SLC2A1 may become a promising prognostic marker and a potential therapeutic target, offering valuable insights to inform clinical treatment decisions.", "claims": [{"id": "claim-method", "statement": "We used ten machine learning methods—ridge regression, least absolute shrinkage and selection operator (Lasso) regression, stepwise Cox regression, CoxBoost, random survival forest (RSF), elastic network (Enet), plsRcox, supervised principal component (SuperPC), survival support vector machine (SVM) and gradient boosting machine (GBM) (The details of each method can be found in Attachment 4a). These methods were combined into 101 unique combinations for variable selection and model formulation. Finally, we evaluated the effectiveness of our models on the training and validation datasets using a consistency index (C-index) and then calculated the average scores.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39251710", "locator": "sections[5] \"Prognostic model construction and validation\" paragraph 2", "quote": "We used ten machine learning methods—ridge regression, least absolute shrinkage and selection operator (Lasso) regression, stepwise Cox regression, CoxBoost, random survival forest (RSF), elastic network (Enet), plsRcox, supervised principal component (SuperPC), survival support vector machine (SVM) and gradient boosting machine (GBM) (The details of each method can be found in Attachment 4a). These methods were combined into 101 unique combinations for variable selection and model formulation. Finally, we evaluated the effectiveness of our models on the training and validation datasets using a consistency index (C-index) and then calculated the average scores."}], "state": "complete"}, {"id": "claim-data-access", "statement": "We thank the TCGA and GEO databases for providing data. Single-cell data can be obtained by searching the official website according to the data number(s).TCGA: https://portal.gdc.cancer.gov/, GEO: https://www.ncbi.nlm.nih.gov/geo/. The dataset named KU_loom is available at (https://gbiomed.kuleuven.be/scRNAseq-NSCLC). The raw data of the in vitro experiments and the code of the R software can be obtained by contacting the corresponding author.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39251710", "locator": "sections[34] \"notes\" paragraph 1", "quote": "We thank the TCGA and GEO databases for providing data. Single-cell data can be obtained by searching the official website according to the data number(s).TCGA: https://portal.gdc.cancer.gov/, GEO: https://www.ncbi.nlm.nih.gov/geo/. The dataset named KU_loom is available at (https://gbiomed.kuleuven.be/scRNAseq-NSCLC). The raw data of the in vitro experiments and the code of the R software can be obtained by contacting the corresponding author."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The optimal NSCLC prognostic model was StepCox[both] + RSF, which achieved the highest average C-index of 0.796.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:39251710", "locator": "sections[17] \"Validation of the prognostic model\" paragraph 2", "quote": "The results showed that the combination of ‘StepCox[both] + RSF’ had the highest average C-index (0.796) (Fig. 3a)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The optimal NSCLC prognostic model was StepCox[both] + RSF, which achieved the highest average C-index of 0.796.", "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:39251710"], "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:GSE127465"], "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:GSE127465"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:39251710", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1038/s41598-024-71317-2", "sha256": "sha256:72ffcf1dc7d98f3e030639459ace177b7395ebbe101be3dfcdbeb9d00d4752d4", "bytes": 30349, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1038/s41598-024-71317-2", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC11383933", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE127465", "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=GSE127465", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE127465", "version": null, "note": "We thank the TCGA and GEO databases for providing data. Single-cell data can be obtained by searching the official website according to the data number(s).TCGA: https://portal.gdc.cancer.gov/, GEO: https://www.ncbi.nlm.nih.gov/geo/. The dataset named KU_loom is available at (https://gbiomed.kuleuven.be/scRNAseq-NSCLC). The raw data of the in vitro experiments and the code of the R software can be obtained by contacting the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "We thank the TCGA and GEO databases for providing data. Single-cell data can be obtained by searching the official website according to the data number(s).TCGA: https://portal.gdc.cancer.gov/, GEO: https://www.ncbi.nlm.nih.gov/geo/. The dataset named KU_loom is available at (https://gbiomed.kuleuven.be/scRNAseq-NSCLC). The raw data of the in vitro experiments and the code of the R software can be obtained by contacting the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3635278", "GSM3635279", "GSM3635280", "GSM3635281", "GSM3635282", "GSM3635283", "GSM3635284", "GSM3635285", "GSM3635286", "GSM3635287", "GSM3635288", "GSM3635289", "GSM3635290", "GSM3635291", "GSM3635292", "GSM3635293", "GSM3635294", "GSM3635295", "GSM3635296", "GSM3635297", "GSM3635298", "GSM3635299", "GSM3635300", "GSM3635301", "GSM3635302", "GSM3635303", "GSM3635304", "GSM3635305", "GSM3635306", "GSM3635307", "GSM3635308", "GSM3635309", "GSM3635310", "GSM3635311", "GSM3635312", "GSM3635313", "GSM3635314", "GSM3635315", "GSM3635316", "GSM3635317"], "sample_count": 40, "group_sizes": null, "group_sizes_basis": null, "platform": "19057;18573", "taxon": "Mus musculus; Homo sapiens", "title": "Single cell transcriptomics of human and mouse lung cancers reveals conserved myeloid populations across individuals and species", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE131907", "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=GSE131907", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE131907", "version": null, "note": "We thank the TCGA and GEO databases for providing data. Single-cell data can be obtained by searching the official website according to the data number(s).TCGA: https://portal.gdc.cancer.gov/, GEO: https://www.ncbi.nlm.nih.gov/geo/. The dataset named KU_loom is available at (https://gbiomed.kuleuven.be/scRNAseq-NSCLC). The raw data of the in vitro experiments and the code of the R software can be obtained by contacting the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "We thank the TCGA and GEO databases for providing data. Single-cell data can be obtained by searching the official website according to the data number(s).TCGA: https://portal.gdc.cancer.gov/, GEO: https://www.ncbi.nlm.nih.gov/geo/. The dataset named KU_loom is available at (https://gbiomed.kuleuven.be/scRNAseq-NSCLC). The raw data of the in vitro experiments and the code of the R software can be obtained by contacting the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3827114", "GSM3827115", "GSM3827116", "GSM3827117", "GSM3827118", "GSM3827119", "GSM3827120", "GSM3827121", "GSM3827122", "GSM3827123", "GSM3827124", "GSM3827125", "GSM3827126", "GSM3827127", "GSM3827128", "GSM3827129", "GSM3827130", "GSM3827131", "GSM3827132", "GSM3827133", "GSM3827134", "GSM3827135", "GSM3827136", "GSM3827137", "GSM3827138", "GSM3827139", "GSM3827140", "GSM3827141", "GSM3827142", "GSM3827143", "GSM3827144", "GSM3827145", "GSM3827146", "GSM3827147", "GSM3827148", "GSM3827149", "GSM3827150", "GSM3827151", "GSM3827152", "GSM3827153", "GSM3827154", "GSM3827155", "GSM3827156", "GSM3827157", "GSM3827158", "GSM3827159", "GSM3827160", "GSM3827161", "GSM3827162", "GSM3827163", "GSM3827164", "GSM3827165", "GSM3827166", "GSM3827167", "GSM3827168", "GSM3827169", "GSM3827170", "GSM3827171"], "sample_count": 58, "group_sizes": null, "group_sizes_basis": null, "platform": "16791", "taxon": "Homo sapiens", "title": "Single cell RNA sequencing of lung adenocarcinoma", "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:GSE13213", "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=GSE13213", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE13213", "version": null, "note": "We thank the TCGA and GEO databases for providing data. Single-cell data can be obtained by searching the official website according to the data number(s).TCGA: https://portal.gdc.cancer.gov/, GEO: https://www.ncbi.nlm.nih.gov/geo/. The dataset named KU_loom is available at (https://gbiomed.kuleuven.be/scRNAseq-NSCLC). The raw data of the in vitro experiments and the code of the R software can be obtained by contacting the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "We thank the TCGA and GEO databases for providing data. Single-cell data can be obtained by searching the official website according to the data number(s).TCGA: https://portal.gdc.cancer.gov/, GEO: https://www.ncbi.nlm.nih.gov/geo/. The dataset named KU_loom is available at (https://gbiomed.kuleuven.be/scRNAseq-NSCLC). The raw data of the in vitro experiments and the code of the R software can be obtained by contacting the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM333673", "GSM333674", "GSM333675", "GSM333676", "GSM333677", "GSM333678", "GSM333679", "GSM333680", "GSM333681", "GSM333682", "GSM333683", "GSM333684", "GSM333685", "GSM333686", "GSM333687", "GSM333688", "GSM333689", "GSM333690", "GSM333691", "GSM333692", "GSM333693", "GSM333694", "GSM333695", "GSM333696", "GSM333697", "GSM333698", "GSM333699", "GSM333700", "GSM333701", "GSM333702", "GSM333703", "GSM333704", "GSM333705", "GSM333706", "GSM333707", "GSM333708", "GSM333709", "GSM333710", "GSM333711", "GSM333712", "GSM333713", "GSM333714", "GSM333715", "GSM333716", "GSM333717", "GSM333718", "GSM333719", "GSM333720", "GSM333721", "GSM333722", "GSM333723", "GSM333724", "GSM333725", "GSM333726", "GSM333727", "GSM333728", "GSM333729", "GSM333730", "GSM333731", "GSM333732", "GSM333733", "GSM333734", "GSM333735", "GSM333736", "GSM333737", "GSM333738", "GSM333739", "GSM333740", "GSM333741", "GSM333742", "GSM333743", "GSM333744", "GSM333745", "GSM333746", "GSM333747", "GSM333748", "GSM333749", "GSM333750", "GSM333751", "GSM333752", "GSM333753", "GSM333754", "GSM333755", "GSM333756", "GSM333757", "GSM333758", "GSM333759", "GSM333760", "GSM333761", "GSM333762", "GSM333763", "GSM333764", "GSM333765", "GSM333766", "GSM333767", "GSM333768", "GSM333769", "GSM333770", "GSM333771", "GSM333772", "GSM333773", "GSM333774", "GSM333775", "GSM333776", "GSM333777", "GSM333778", "GSM333779", "GSM333780", "GSM333781", "GSM333782", "GSM333783", "GSM333784", "GSM333785", "GSM333786", "GSM333787", "GSM333788", "GSM333789"], "sample_count": 117, "group_sizes": null, "group_sizes_basis": null, "platform": "6480", "taxon": "Homo sapiens", "title": "Relapse-related molecular signature in lung adenocarcinomas identifies patients with dismal prognosis", "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:GSE136246", "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=GSE136246", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE136246", "version": null, "note": "We thank the TCGA and GEO databases for providing data. Single-cell data can be obtained by searching the official website according to the data number(s).TCGA: https://portal.gdc.cancer.gov/, GEO: https://www.ncbi.nlm.nih.gov/geo/. The dataset named KU_loom is available at (https://gbiomed.kuleuven.be/scRNAseq-NSCLC). The raw data of the in vitro experiments and the code of the R software can be obtained by contacting the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "We thank the TCGA and GEO databases for providing data. Single-cell data can be obtained by searching the official website according to the data number(s).TCGA: https://portal.gdc.cancer.gov/, GEO: https://www.ncbi.nlm.nih.gov/geo/. The dataset named KU_loom is available at (https://gbiomed.kuleuven.be/scRNAseq-NSCLC). The raw data of the in vitro experiments and the code of the R software can be obtained by contacting the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4043230", "GSM4043231", "GSM4043232", "GSM4043233", "GSM4043234", "GSM4043235", "GSM4043236", "GSM4043237", "GSM4043238", "GSM4043239", "GSM4043240", "GSM4043241", "GSM4043242", "GSM4043243", "GSM4043244", "GSM4043245", "GSM4043246", "GSM4043247", "GSM4043248", "GSM4043249", "GSM4043250", "GSM4043251", "GSM4043252", "GSM4043253", "GSM4043254", "GSM4043255", "GSM4043256", "GSM4043257", "GSM4043258", "GSM4043259", "GSM4043260"], "sample_count": 31, "group_sizes": null, "group_sizes_basis": null, "platform": "24268;18573;27138", "taxon": "Homo sapiens; Mus musculus", "title": "Identification of a targetable KRAS-mutant epithelial population in non-small cell lung cancer", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE148071", "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=GSE148071", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE148071", "version": null, "note": "We thank the TCGA and GEO databases for providing data. Single-cell data can be obtained by searching the official website according to the data number(s).TCGA: https://portal.gdc.cancer.gov/, GEO: https://www.ncbi.nlm.nih.gov/geo/. The dataset named KU_loom is available at (https://gbiomed.kuleuven.be/scRNAseq-NSCLC). The raw data of the in vitro experiments and the code of the R software can be obtained by contacting the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "We thank the TCGA and GEO databases for providing data. Single-cell data can be obtained by searching the official website according to the data number(s).TCGA: https://portal.gdc.cancer.gov/, GEO: https://www.ncbi.nlm.nih.gov/geo/. The dataset named KU_loom is available at (https://gbiomed.kuleuven.be/scRNAseq-NSCLC). The raw data of the in vitro experiments and the code of the R software can be obtained by contacting the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4453576", "GSM4453577", "GSM4453578", "GSM4453579", "GSM4453580", "GSM4453581", "GSM4453582", "GSM4453583", "GSM4453584", "GSM4453585", "GSM4453586", "GSM4453587", "GSM4453588", "GSM4453589", "GSM4453590", "GSM4453591", "GSM4453592", "GSM4453593", "GSM4453594", "GSM4453595", "GSM4453596", "GSM4453597", "GSM4453598", "GSM4453599", "GSM4453600", "GSM4453601", "GSM4453602", "GSM4453603", "GSM4453604", "GSM4453605", "GSM4453606", "GSM4453607", "GSM4453608", "GSM4453609", "GSM4453610", "GSM4453611", "GSM4453612", "GSM4453613", "GSM4453614", "GSM4453615", "GSM4453616", "GSM4453617"], "sample_count": 42, "group_sizes": null, "group_sizes_basis": null, "platform": "20795", "taxon": "Homo sapiens", "title": "Comprehensive Profiling of Cancer Cells and Their Microenvironment in Advanced NSCLC", "resolution_checked_at": "2026-11-01T18:46:34Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE29016", "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=GSE29016", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE29016", "version": null, "note": "We thank the TCGA and GEO databases for providing data. Single-cell data can be obtained by searching the official website according to the data number(s).TCGA: https://portal.gdc.cancer.gov/, GEO: https://www.ncbi.nlm.nih.gov/geo/. The dataset named KU_loom is available at (https://gbiomed.kuleuven.be/scRNAseq-NSCLC). The raw data of the in vitro experiments and the code of the R software can be obtained by contacting the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "We thank the TCGA and GEO databases for providing data. Single-cell data can be obtained by searching the official website according to the data number(s).TCGA: https://portal.gdc.cancer.gov/, GEO: https://www.ncbi.nlm.nih.gov/geo/. The dataset named KU_loom is available at (https://gbiomed.kuleuven.be/scRNAseq-NSCLC). The raw data of the in vitro experiments and the code of the R software can be obtained by contacting the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM718902", "GSM718903", "GSM718904", "GSM718905", "GSM718906", "GSM718907", "GSM718908", "GSM718909", "GSM718910", "GSM718911", "GSM718912", "GSM718913", "GSM718914", "GSM718915", "GSM718916", "GSM718917", "GSM718918", "GSM718919", "GSM718920", "GSM718921", "GSM718922", "GSM718923", "GSM718924", "GSM718925", "GSM718926", "GSM718927", "GSM718928", "GSM718929", "GSM718930", "GSM718931", "GSM718932", "GSM718933", "GSM718934", "GSM718935", "GSM718936", "GSM718937", "GSM718938", "GSM718939", "GSM718940", "GSM718941", "GSM718942", "GSM718943", "GSM718944", "GSM718945", "GSM718946", "GSM718947", "GSM718948", "GSM718949", "GSM718950", "GSM718951", "GSM718952", "GSM718953", "GSM718954", "GSM718955", "GSM718956", "GSM718957", "GSM718958", "GSM718959", "GSM718960", "GSM718961", "GSM718962", "GSM718963", "GSM718964", "GSM718965", "GSM718966", "GSM718967", "GSM718968", "GSM718969", "GSM718970", "GSM718971", "GSM718972", "GSM718973"], "sample_count": 72, "group_sizes": null, "group_sizes_basis": null, "platform": "6947", "taxon": "Homo sapiens", "title": "Relation between smoking history and gene expression profiles in lung adenocarcinomas", "resolution_checked_at": "2026-11-01T19:09:46Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE127465 not downloaded", "asset:data:geo:GSE127465 licence not read", "asset:data:geo:GSE131907 not downloaded", "asset:data:geo:GSE131907 licence not read", "asset:data:geo:GSE13213 not downloaded", "asset:data:geo:GSE13213 licence not read", "asset:data:geo:GSE136246 not downloaded", "asset:data:geo:GSE136246 licence not read", "asset:data:geo:GSE148071 not downloaded", "asset:data:geo:GSE148071 licence not read", "asset:data:geo:GSE29016 not downloaded", "asset:data:geo:GSE29016 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "survival_analysis", "specific": "cox_proportional_hazards", "label": "Survival analysis", "dsl_operations": ["cox_ph"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "We used ten machine learning methods—ridge regression, least absolute shrinkage and selection operator (Lasso) regression, stepwise Cox regression, CoxBoost, random survival forest (RSF), elastic network (Enet), plsRcox, supervised principal component (SuperPC), survival support vector machine (SVM) and gradient boosting machine (GBM) (The details of each method can be found in Attachment 4a). These methods were combined into 101 unique combinations for variable selection and model formulation. Finally, we evaluated the effectiveness of our models on the training and validation datasets using a consistency index (C-index) and then calculated the average scores."}}, {"id": "method-2", "family": "machine_learning", "specific": "support_vector_machine", "label": "Machine learning", "dsl_operations": ["train_classifier", "cross_validate", "roc_auc"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "support vector machine"}}, {"id": "method-3", "family": "machine_learning", "specific": "gradient_boosting", "label": "Machine learning", "dsl_operations": ["train_classifier", "cross_validate", "roc_auc"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "gradient boosting"}}], "targets": [], "gaps": []}, "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": ["cox_ph"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: cox_proportional_hazards."}, "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": ["GSE148071", "GSE131907", "GSE136246", "GSE127465", "GSE29016", "GSE13213"], "resolved_accessions": ["GSE148071", "GSE131907", "GSE136246", "GSE127465", "GSE29016", "GSE13213"], "statements": ["We thank the TCGA and GEO databases for providing data. Single-cell data can be obtained by searching the official website according to the data number(s).TCGA: https://portal.gdc.cancer.gov/, GEO: https://www.ncbi.nlm.nih.gov/geo/. The dataset named KU_loom is available at (https://gbiomed.kuleuven.be/scRNAseq-NSCLC). The raw data of the in vitro experiments and the code of the R software can be obtained by contacting the corresponding author."], "basis": "The paper names GSE148071, GSE131907, GSE136246, GSE127465, GSE29016, GSE13213 in GEO and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["cox_ph"], "assets": ["source:pmid:39251710", "data:geo:GSE127465"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE127465"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:30:45Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 8771, "completion_tokens": 2338, "cached_tokens": 264}}, "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:39251710", "type": "paper", "label": "pmid:39251710"}, {"id": "source:pmid:39251710", "type": "manuscript", "label": "PMID 39251710 full text"}, {"id": "data:geo:GSE127465", "type": "dataset", "label": "GEO GSE127465"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:39251710", "type": "paper", "label": "pmid:39251710"}, {"id": "source:pmid:39251710", "type": "manuscript", "label": "PMID 39251710 full text"}, {"id": "data:geo:GSE127465", "type": "dataset", "label": "GEO GSE127465"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-39251710", "type": "extraction", "used": ["source:pmid:39251710"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE127465", "type": "accession_resolution", "used": ["data:geo:GSE127465"], "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:39251710", "parent_hash": "sha256:4bf03817e9e2eb907506bc2825771631f440ba26b7d955bc52c6c1c26e6a10b6", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE127465 licence not read", "asset:data:geo:GSE127465 not downloaded", "asset:data:geo:GSE131907 licence not read", "asset:data:geo:GSE131907 not downloaded", "asset:data:geo:GSE13213 licence not read", "asset:data:geo:GSE13213 not downloaded", "asset:data:geo:GSE136246 licence not read", "asset:data:geo:GSE136246 not downloaded", "asset:data:geo:GSE148071 licence not read", "asset:data:geo:GSE148071 not downloaded", "asset:data:geo:GSE29016 licence not read", "asset:data:geo:GSE29016 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "rna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["effect and thus affects prognosis. NSCLC sc-RNA-seq data were downloaded from the GEO database a", "oratory for Functional Epigenetics, and bulk RNA-seq data were obtained from the TCGA database. T", "aining 218379 cells by examining single-cell RNA sequencing datasets (GSE148071, KU_lom, GSE131907, GSE1"], "order_basis": "paper_text_order:339", "id": "assay:1"}, {"role": "data_generation", "definition_id": "scrna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "unsupported", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["lusters containing 218379 cells by examining single-cell RNA sequencing datasets (GSE148071, KU_lom, GSE131907, GSE1", "abase. The \"Seurat\" package was employed for scRNA-seq data processing, and the uniform manifold ap"], "order_basis": "paper_text_order:540", "id": "assay:2"}, {"role": "data_generation", "definition_id": "cell_culture", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["in proliferation, invasion and migration in A549 cells. In addition, a significant reduction", "eduction in cisplatin resistance was seen in A549/DDP cells. The outcomes demonstrated the pre"], "order_basis": "paper_text_order:2061", "id": "assay:3"}, {"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["cox_ph"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["We used ten machine learning methods—ridge regression, least absolute shrinkage and selection operator (Lasso) regression, stepwise Cox regression, CoxBoost, random survival forest (RSF), elastic network (Enet), plsRcox, supervised principal component (SuperPC), survival support vector machine (SVM) and gradient boosting machine (GBM) (The details of each method can be found in Attachment 4a). These methods were combined into 101 unique combinations for variable selection and model formulation. Finally, we evaluated the effectiveness of our models on the training and validation datasets using a consistency index (C-index) and then calculated the average scores."], "order_basis": "consumes_earlier_output", "id": "assay:4"}]}