Development of a Four-mRNA Expression-Based Prognostic Signature for Cutaneous Melanoma.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34335689", "kind": "science-record", "revision": 6, "content_hash": "sha256:5b40d8b328770ae59b162bf484ddfd212f9d3730d850e5364da552ab31e1cc0d", "created_at": "2026-11-01T15:41:46Z", "updated_at": "2026-11-01T21:25:55Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Development of a Four-mRNA Expression-Based Prognostic Signature for Cutaneous Melanoma.", "doi": "10.3389/fgene.2021.680617", "pmid": "34335689", "authors": ["Haiya Bai", "Youliang Wang", "Huimin Liu", "Junyang Lu"], "journal": "Frontiers in genetics", "year": 2021, "abstract": "We aim to find a biomarker that can effectively predict the prognosis of patients with cutaneous melanoma (CM). The RNA sequencing data of CM was downloaded from The Cancer Genome Atlas (TCGA) database and randomly divided into training group and test group. Survival statistical analysis and machine-learning approaches were performed on the RNA sequencing data of CM to develop a prognostic signature. Using univariable Cox proportional hazards regression, random survival forest algorithm, and receiver operating characteristic (ROC) in the training group, the four-mRNA signature including CD276, UQCRFS1, HAPLN3, and PIP4P1 was screened out. The four-mRNA signature could divide patients into low-risk and high-risk groups with different survival outcomes (log-rank p < 0.001). The predictive efficacy of the four-mRNA signature was confirmed in the test group, the whole TCGA group, and the independent GSE65904 (log-rank p < 0.05). The independence of the four-mRNA signature in prognostic prediction was demonstrated by multivariate Cox analysis. ROC and timeROC analyses showed that the efficiency of the signature in survival prediction was better than other clinical variables such as melanoma Clark level and tumor stage. This study highlights that the four-mRNA model could be used as a prognostic signature for CM patients with potential clinical application value.", "claims": [{"id": "claim-method", "statement": "Univariable Cox analysis was applied to seek mRNAs significantly correlated with CM patients’ OS in the training group. Then, random survival forest (RSFVH, a machine learning approach) was performed. The clinical parameters and mRNA expression data of CM in The Cancer Genome Atlas (TCGA) database1 were from UCSC Xena2. The independent validation set (GSE65904) was obtained from Gene Expression Omnibus (GEO) database.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34335689", "locator": "sections[4] \"The Process of Developing Prognostic Models Through Statistics and Machine-Learning Methods\" paragraph 2", "quote": "Univariable Cox analysis was applied to seek mRNAs significantly correlated with CM patients’ OS in the training group."}, {"asset": "source:pmid:34335689", "locator": "sections[4] \"The Process of Developing Prognostic Models Through Statistics and Machine-Learning Methods\" paragraph 2", "quote": "Then, random survival forest (RSFVH, a machine learning approach) was performed."}, {"asset": "source:pmid:34335689", "locator": "sections[3] \"Expression Profile of CM Patients\" paragraph 2", "quote": "The clinical parameters and mRNA expression data of CM in The Cancer Genome Atlas (TCGA) database1 were from UCSC Xena2."}, {"asset": "source:pmid:34335689", "locator": "sections[3] \"Expression Profile of CM Patients\" paragraph 2", "quote": "The independent validation set (GSE65904) was obtained from Gene Expression Omnibus (GEO) database."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Publicly available datasets analyzed in this study can be found here: https://xenabrowser.net/datapages/?cohort=TCGA%20Melanoma%20(SKCM)&removeHub=https%3A%2F%2Fxena.treehouse.gi.ucsc.edu%3A443; https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE65904.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34335689", "locator": "sections[13] \"Data Availability Statement\" paragraph 2", "quote": "Publicly available datasets analyzed in this study can be found here: https://xenabrowser.net/datapages/?cohort=TCGA%20Melanoma%20(SKCM)&removeHub=https%3A%2F%2Fxena.treehouse.gi.ucsc.edu%3A443; https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE65904."}], "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:34335689"], "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:GSE65904"], "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:GSE65904"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:34335689", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fgene.2021.680617", "sha256": "sha256:d6384a18545f20a8969504ad0df1a9e917903caa0a2fc877e18b79300d150681", "bytes": 20397, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fgene.2021.680617", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8320537", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE65904", "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=GSE65904", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE65904", "version": null, "note": "Publicly available datasets analyzed in this study can be found here: https://xenabrowser.net/datapages/?cohort=TCGA%20Melanoma%20(SKCM)&removeHub=https%3A%2F%2Fxena.treehouse.gi.ucsc.edu%3A443; https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE65904.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets analyzed in this study can be found here: https://xenabrowser.net/datapages/?cohort=TCGA%20Melanoma%20(SKCM)&removeHub=https%3A%2F%2Fxena.treehouse.gi.ucsc.edu%3A443; https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE65904.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1608593", "GSM1608594", "GSM1608595", "GSM1608596", "GSM1608597", "GSM1608598", "GSM1608599", "GSM1608600", "GSM1608601", "GSM1608602", "GSM1608603", "GSM1608604", "GSM1608605", "GSM1608606", "GSM1608607", "GSM1608608", "GSM1608609", "GSM1608610", "GSM1608611", "GSM1608612", "GSM1608613", "GSM1608614", "GSM1608615", "GSM1608616", "GSM1608617", "GSM1608618", "GSM1608619", "GSM1608620", "GSM1608621", "GSM1608622", "GSM1608623", "GSM1608624", "GSM1608625", "GSM1608626", "GSM1608627", "GSM1608628", "GSM1608629", "GSM1608630", "GSM1608631", "GSM1608632", "GSM1608633", "GSM1608634", "GSM1608635", "GSM1608636", "GSM1608637", "GSM1608638", "GSM1608639", "GSM1608640", "GSM1608641", "GSM1608642", "GSM1608643", "GSM1608644", "GSM1608645", "GSM1608646", "GSM1608647", "GSM1608648", "GSM1608649", "GSM1608650", "GSM1608651", "GSM1608652", "GSM1608653", "GSM1608654", "GSM1608655", "GSM1608656", "GSM1608657", "GSM1608658", "GSM1608659", "GSM1608660", "GSM1608661", "GSM1608662", "GSM1608663", "GSM1608664", "GSM1608665", "GSM1608666", "GSM1608667", "GSM1608668", "GSM1608669", "GSM1608670", "GSM1608671", "GSM1608672", "GSM1608673", "GSM1608674", "GSM1608675", "GSM1608676", "GSM1608677", "GSM1608678", "GSM1608679", "GSM1608680", "GSM1608681", "GSM1608682", "GSM1608683", "GSM1608684", "GSM1608685", "GSM1608686", "GSM1608687", "GSM1608688", "GSM1608689", "GSM1608690", "GSM1608691", "GSM1608692", "GSM1608693", "GSM1608694", "GSM1608695", "GSM1608696", "GSM1608697", "GSM1608698", "GSM1608699", "GSM1608700", "GSM1608701", "GSM1608702", "GSM1608703", "GSM1608704", "GSM1608705", "GSM1608706", "GSM1608707", "GSM1608708", "GSM1608709", "GSM1608710", "GSM1608711", "GSM1608712", "GSM1608713", "GSM1608714", "GSM1608715", "GSM1608716", "GSM1608717", "GSM1608718", "GSM1608719", "GSM1608720", "GSM1608721", "GSM1608722", "GSM1608723", "GSM1608724", "GSM1608725", "GSM1608726", "GSM1608727", "GSM1608728", "GSM1608729", "GSM1608730", "GSM1608731", "GSM1608732", "GSM1608733", "GSM1608734", "GSM1608735", "GSM1608736", "GSM1608737", "GSM1608738", "GSM1608739", "GSM1608740", "GSM1608741", "GSM1608742", "GSM1608743", "GSM1608744", "GSM1608745", "GSM1608746", "GSM1608747", "GSM1608748", "GSM1608749", "GSM1608750", "GSM1608751", "GSM1608752", "GSM1608753", "GSM1608754", "GSM1608755", "GSM1608756", "GSM1608757", "GSM1608758", "GSM1608759", "GSM1608760", "GSM1608761", "GSM1608762", "GSM1608763", "GSM1608764", "GSM1608765", "GSM1608766", "GSM1608767", "GSM1608768", "GSM1608769", "GSM1608770", "GSM1608771", "GSM1608772", "GSM1608773", "GSM1608774", "GSM1608775", "GSM1608776", "GSM1608777", "GSM1608778", "GSM1608779", "GSM1608780", "GSM1608781", "GSM1608782", "GSM1608783", "GSM1608784", "GSM1608785", "GSM1608786", "GSM1608787", "GSM1608788", "GSM1608789", "GSM1608790", "GSM1608791", "GSM1608792", "GSM1608793", "GSM1608794", "GSM1608795", "GSM1608796", "GSM1608797", "GSM1608798", "GSM1608799", "GSM1608800", "GSM1608801", "GSM1608802", "GSM1608803", "GSM1608804", "GSM1608805", "GSM1608806"], "sample_count": 214, "group_sizes": null, "group_sizes_basis": null, "platform": "10558", "taxon": "Homo sapiens", "title": "Whole-genome expression analysis of melanoma tumor biopsies from a population-based cohort.", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:34335689:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:36969c4e31d4583aa6da9c426f26b6b3f7e8ab661d4aa1ff3c77d8af4a6fbb22", "bytes": 465, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[7]/table-wrap[1]#T1", "version": null, "note": "Survival analysis of the messenger RNAs (mRNAs) in the prognostic signature.", "structure": {"pmcid": "PMC8320537", "section_index": 7, "section_title": "Development of the Prognostic Four-mRNA Signature", "row_count": 5, "column_count": 6}, "table": {"label": "TABLE 1", "caption": "Survival analysis of the messenger RNAs (mRNAs) in the prognostic signature.", "rows": [["geneID", "HR", "Right", "Left", "COX P", "KM P"], ["CD276", "1.42", "1.07", "1.88", "0.01", "0.03"], ["HAPLN3", "0.66", "0.55", "0.81", "<0.001", "<0.001"], ["PIP4P1", "0.47", "0.30", "0.74", "<0.001", "<0.001"], ["UQCRFS1", "2.13", "1.43", "3.16", "<0.001", "<0.001"]], "row_count": 5, "column_count": 6, "numeric_cells": 21, "header_rows": 1, "locator": "section[7]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:34335689:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:016c4c0f4f1cf35056699ffc4b472a71e62b1680f43298ba39b10379d42fd93c", "bytes": 2101, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#T2", "version": null, "note": "Association of the messenger RNA (mRNA) signature with clinical characteristics in cutaneous melanoma (CM) patients.", "structure": {"pmcid": "PMC8320537", "section_index": 9, "section_title": "Independent Prognostic Value of the Four-mRNA Signature", "row_count": 36, "column_count": 10}, "table": {"label": "TABLE 2", "caption": "Association of the messenger RNA (mRNA) signature with clinical characteristics in cutaneous melanoma (CM) patients.", "rows": [["Variables", "Training group", "p", "Test group", "p", "TCGA group", "p"], ["", "Low risk*", "High risk*", "", "Low risk*", "High risk*", "", "Low risk*", "High risk*", ""], ["Age (years)", "", "", "0.89", "", "", "0.27", "", "", "0.57"], ["≤ 58", "48", "46", "", "38", "47", "", "86", "93", ""], [">58", "48", "50", "", "58", "50", "", "106", "100", ""], ["Gender", "", "", "0.38", "", "", "1.00", "", "", "0.50"], ["Female", "43", "36", "", "33", "33", "", "76", "69", ""], ["Male", "53", "60", "", "63", "64", "", "116", "124", ""], ["Radiotherapy", "", "", "<0.001", "", "", "0.13", "", "", "<0.001"], ["Unknown", "25", "50", "", "29", "41", "", "54", "91", ""], ["No", "63", "42", "", "57", "51", "", "120", "93", ""], ["Yes", "8", "4", "", "10", "5", "", "18", "9", ""], ["Pathological M", "", "", "0.33", "", "", "0.52", "", "", "0.21"], ["M0", "84", "89", "", "82", "86", "", "166", "175", ""], ["M1", "6", "5", "", "5", "6", "", "11", "11", ""], ["Pathological N", "", "", "0.56", "", "", "0.31", "", "", "0.19"], ["N0", "48", "44", "", "42", "37", "", "90", "81", ""], ["N1", "14", "19", "", "19", "16", "", "33", "35", ""], ["N2", "11", "9", "", "12", "12", "", "23", "21", ""], ["N3", "11", "16", "", "10", "18", "", "21", "34", ""], ["Pathological T", "", "", "0.17", "", "", "0.31", "", "", "0.27"], ["T0", "5", "1", "", "6", "7", "", "11", "8", ""], ["T1", "12", "9", "", "8", "1", "", "20", "10", ""], ["T2", "16", "17", "", "12", "14", "", "28", "31", ""], ["T3", "16", "25", "", "17", "17", "", "33", "42", ""], ["T4", "30", "37", "", "35", "41", "", "65", "78", ""], ["Tumor stage", "", "", "0.31", "", "", "0.87", "", "", "0.38"], ["Stage 0", "0", "1", "", "1", "0", "", "1", "1", ""], ["Stage I", "20", "14", "", "11", "9", "", "31", "23", ""], ["I/II Nos", "2", "0", "", "1", "0", "", "3", "0", ""], ["Stage II", "29", "31", "", "29", "31", "", "58", "62", ""], ["Stage III", "32", "42", "", "41", "44", "", "73", "86", ""], ["Stage IV", "6", "5", "", "5", "6", "", "11", "11", ""], ["Race demographic", "", "", "0.22", "", "", "0.03", "", "", "0.51"], ["Asian", "3", "3", "", "2", "4", "", "5", "7", ""], ["White", "93", "90", "", "88", "93", "", "181", "183", ""]], "row_count": 36, "column_count": 10, "numeric_cells": 183, "header_rows": 2, "locator": "section[9]/table-wrap[1]#T2"}}, {"id": "asset:table:pmid:34335689:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:1f3f08a8ffd883f2d50da340253ea6eb1868067ca230068645198bd2df2eb2f2", "bytes": 2229, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[2]#T3", "version": null, "note": "Cox regression analysis of the signature with the survival of cutaneous melanoma (CM).", "structure": {"pmcid": "PMC8320537", "section_index": 9, "section_title": "Independent Prognostic Value of the Four-mRNA Signature", "row_count": 26, "column_count": 10}, "table": {"label": "TABLE 3", "caption": "Cox regression analysis of the signature with the survival of cutaneous melanoma (CM).", "rows": [["", "", "Univariable analysis", "Multivariable analysis"], ["Variables", "", "HR", "95% CI of HR", "P", "HR", "95% CI of HR", "p"], ["", "", "", "lower", "upper", "", "", "lower", "upper", ""], ["The training group"], ["Age", ">58 vs. ≤58", "1.47", "0.98", "2.22", "0.07", "1.24", "0.77", "2.01", "0.38"], ["Gender", "Male vs. female", "0.79", "0.52", "1.20", "0.27", "1.03", "0.64", "1.67", "0.89"], ["Tumor stage", "III, IV vs. I, II", "1.01", "0.98", "1.03", "0.60", "1.03", "0.97", "1.08", "0.36"], ["Melanoma Clark level", "IV, V vs. I, II, III", "1.87", "1.16", "3.02", "0.01", "1.40", "1.01", "1.94", "0.04"], ["Signature", "High risk vs. low risk", "3.53", "2.25", "5.53", "< 0.001", "3.00", "1.77", "5.06", "< 0.001"], ["The test group"], ["Age", ">58 vs. ≤58", "0.87", "0.58", "1.31", "0.51", "0.85", "0.51", "1.41", "0.52"], ["Gender", "Male vs. female", "1.01", "0.65", "1.58", "0.96", "0.75", "0.43", "1.31", "0.31"], ["Tumor stage", "III, IV vs. I, II", "0.99", "0.97", "1.02", "0.56", "0.98", "0.94", "1.01", "0.24"], ["Melanoma Clark level", "IV, V vs. I, II, III", "1.35", "0.86", "2.11", "0.20", "1.33", "0.94", "1.89", "0.11"], ["Signature", "High risk vs. low risk", "1.93", "1.27", "2.93", "<0.001", "1.72", "1.02", "2.90", "0.04"], ["The TCGA dataset"], ["Age", ">58 vs. ≤58", "1.13", "0.85", "1.50", "0.40", "0.90", "0.50", "1.64", "0.74"], ["Gender", "Male vs. female", "0.90", "0.67", "1.22", "0.51", "0.98", "0.52", "1.85", "0.95"], ["Tumor stage", "III, IV vs. I, II", "1.00", "0.98", "1.01", "0.80", "1.04", "0.99", "1.10", "0.14"], ["Melanoma Clark level", "IV,V vs. I, II,III", "1.55", "1.13", "2.13", "0.01", "1.88", "1.19", "2.96", "0.01"], ["Radiation therapy", "Yes vs. no", "0.74", "0.35", "1.55", "0.42", "0.68", "0.23", "2.06", "0.50"], ["Signature", "High risk vs. low risk", "2.54", "1.88", "3.44", "<0.001", "2.00", "1.08", "3.69", "0.03"], ["The GSE65904 dataset"], ["Age", ">58 vs. ≤58", "1.61", "0.91", "2.85", "0.10", "1.52", "1.00", "2.29", "0.05"], ["Gender", "Male vs. female", "2.56", "1.36", "4.85", "<0.001", "0.95", "0.62", "1.45", "0.82"], ["Signature", "High risk vs. low risk", "1.89", "1.11", "3.23", "0.02", "3.55", "2.25", "5.58", "< 0.001"]], "row_count": 26, "column_count": 10, "numeric_cells": 159, "header_rows": 3, "locator": "section[9]/table-wrap[2]#T3"}}], "gaps": ["asset:data:geo:GSE65904 not downloaded", "asset:data:geo:GSE65904 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": "reordered", "quote": "Univariable Cox analysis was applied to seek mRNAs significantly correlated with CM patients’ OS in the training group. Then, random survival forest (RSFVH, a machine learning approach) was performed. The clinical parameters and mRNA expression data of CM in The Cancer Genome Atlas (TCGA) database1 were from UCSC Xena2. The independent validation set (GSE65904) was obtained from Gene Expression Omnibus (GEO) database."}}, {"id": "method-2", "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": 0.8, "band": "high", "quote": "KM"}}, {"id": "method-3", "family": "survival_analysis", "specific": "log_rank_test", "label": "Survival analysis", "dsl_operations": ["logrank_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.7, "band": "medium", "quote": "log-rank"}}, {"id": "method-4", "family": "correlation_analysis", "specific": "pearson", "label": "Correlation analysis", "dsl_operations": ["pearson_r"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["paired_numeric_columns"], "evidence": {"score": 0.8, "band": "high", "quote": "Pearson correlation"}}, {"id": "method-5", "family": "contingency_analysis", "specific": "chi_square", "label": "Categorical (contingency table) analysis", "dsl_operations": ["chi_square_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["categorical_cross_tabulation"], "evidence": {"score": 0.8, "band": "high", "quote": "Chi-square"}}], "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": ["GSE65904"], "resolved_accessions": ["GSE65904"], "statements": ["Publicly available datasets analyzed in this study can be found here: https://xenabrowser.net/datapages/?cohort=TCGA%20Melanoma%20(SKCM)&removeHub=https%3A%2F%2Fxena.treehouse.gi.ucsc.edu%3A443; https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE65904."], "basis": "The paper names GSE65904 in Gene Expression Omnibus (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:34335689", "data:geo:GSE65904", "asset:table:pmid:34335689:1", "asset:table:pmid:34335689:2", "asset:table:pmid:34335689:3"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE65904"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:33:03Z", "independence": "single_reader"}, "evidence_check": {"method": "reordered", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 16011, "completion_tokens": 1815, "cached_tokens": 784}}, "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:34335689", "type": "paper", "label": "pmid:34335689"}, {"id": "source:pmid:34335689", "type": "manuscript", "label": "PMID 34335689 full text"}, {"id": "data:geo:GSE65904", "type": "dataset", "label": "GEO GSE65904"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34335689", "type": "paper", "label": "pmid:34335689"}, {"id": "source:pmid:34335689", "type": "manuscript", "label": "PMID 34335689 full text"}, {"id": "data:geo:GSE65904", "type": "dataset", "label": "GEO GSE65904"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34335689", "type": "extraction", "used": ["source:pmid:34335689"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE65904", "type": "accession_resolution", "used": ["data:geo:GSE65904"], "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:34335689", "parent_hash": "sha256:af39fa820645bdbaced2e5b386e20395abc2b5ea1d72b64d7078d2ab120afcf2", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:GSE65904 licence not read", "asset:data:geo:GSE65904 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": ["f patients with cutaneous melanoma (CM). The RNA sequencing data of CM was downloaded from The Cancer Ge", "ne-learning approaches were performed on the RNA sequencing data of CM to develop a prognostic signature"], "order_basis": "paper_text_order:160", "id": "assay:1"}, {"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": ["Univariable Cox analysis was applied to seek mRNAs significantly correlated with CM patients’ OS in the training group. Then, random survival forest (RSFVH, a machine learning approach) was performed. The clinical parameters and mRNA expression data of CM in The Cancer Genome Atlas (TCGA) database1 were from UCSC Xena2. The independent validation set (GSE65904) was obtained from Gene Expression Omnibus (GEO) database."], "order_basis": "consumes_earlier_output", "id": "assay:2"}]}