Establishment of a SVM classifier to predict recurrence of ovarian cancer.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:30106117", "kind": "science-record", "revision": 8, "content_hash": "sha256:70cc9e689dcebc2621b751cac36b796b045dea74ec4f0a117c7cd901f80b6d42", "created_at": "2026-11-01T15:40:36Z", "updated_at": "2026-11-01T22:43:29Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Establishment of a SVM classifier to predict recurrence of ovarian cancer.", "doi": "10.3892/mmr.2018.9362", "pmid": "30106117", "authors": ["Jinting Zhou", "Lin Li", "Liling Wang", "Xiaofang Li", "Hui Xing", "Li Cheng"], "journal": "Molecular medicine reports", "year": 2018, "abstract": "Gene expression data using retrieved ovarian cancer (OC) samples were used to identify genes of interest and a support vector machine (SVM) classifier was subsequently established to predict the recurrence of OC. Three datasets (GSE17260, GSE44104 and GSE51088) investigating OC gene expression were downloaded from the Gene Expression Omnibus. Differentially expressed genes (DEGs) in samples from patients with non‑recurrent and recurrent OC were revealed via a homogeneity test and quality control analysis. A protein‑protein interaction (PPI) network was subsequently established for the DEGs using data from Biological General Repository for Interaction Datasets, Human Protein Reference Database and Database of Interacting Proteins. Degrees of interaction and betweenness centrality (BC) scores were calculated for each node in the PPI network. The top 100 genes ranked by BC scores were selected to identify feature genes via recursive feature elimination using the GSE17260 dataset. Following this, a SVM classifier was constructed and further validated using the GSE44104 and GSE51088 datasets and independent gene expression data obtained from the Cancer Genome Atlas (TCGA). A total of 639 DEGs were identified from the three gene expression datasets, and a PPI network including 249 nodes and 354 edges was constructed. A SVM classifier consisting of 39 feature genes (including cullin 3, mouse double minute 2 homolog, aurora kinase A, WW domain containing oxidoreducatase, large tumor suppressor kinase 2, sirtuin 6, staphylococcal nuclease and tudor domain containing 1, leucine rich repeats and immunoglobulin like domains 1 and aurora kinase 1 interacting protein 1) was subsequently constructed. The prediction accuracies of the SVM classifier for GSE17260, GSE44104 and GSE51088 datasets as well as data downloaded from TCGA were revealed to be 92.7, 93.3, 96.6 and 90.4%, respectively. Furthermore, the results of the present study revealed that patients with predicted non‑recurrent OC survived significantly longer compared with the patients with predicted recurrent OC (P=6.598x10‑6). A SVM classifier consisting of 39 feature genes was established for predicting the recurrence and prognosis of OC. Therefore, the results of the present study suggested that the 39 feature genes may serve important roles in the development of OC and may represent therapeutic biomarkers of OC.", "claims": [{"id": "claim-method", "statement": "The SVM classifier was subsequently established to predict OC recurrence based on the expression levels of the screened feature genes.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30106117", "locator": "sections[7] \"Construction of the SVM classifier\" paragraph 5", "quote": "The SVM classifier was subsequently established to predict OC recurrence based on the expression levels of the screened feature genes."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30106117", "locator": "sections[18] \"Availability of data and materials\" paragraph 2", "quote": "The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The paper used a 39-feature-gene SVM classifier, trained using GSE17260 and validated with GSE44104, GSE51088, and independent TCGA gene-expression data; the classifier achieved 90.4% accuracy and an AUROC of 0.981 in the TCGA validation.", "kind": "quantitative", "target": {"value": 90.4, "unit": "per cent", "tolerance": null, "source": "Prediction accuracy of independent gene expression data downloaded from TCGA was revealed to be 90.4% [357 out of 395 samples (138 samples from patients with non-recurrent OC and 219 samples from patients with recurrent OC)], with an AUROC value of 0.981 (Table VI, Fig. 6A)."}, "evidence": [{"asset": "source:pmid:30106117", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Following this, a SVM classifier was constructed and further validated using the GSE44104 and GSE51088 datasets and independent gene expression data obtained from the Cancer Genome Atlas (TCGA)."}, {"asset": "source:pmid:30106117", "locator": "sections[14] \"Results of validation\" paragraph 2", "quote": "Prediction accuracy of independent gene expression data downloaded from TCGA was revealed to be 90.4% [357 out of 395 samples (138 samples from patients with non-recurrent OC and 219 samples from patients with recurrent OC)], with an AUROC value of 0.981 (Table VI, Fig. 6A)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The paper used a 39-feature-gene SVM classifier, trained using GSE17260 and validated with GSE44104, GSE51088, and independent TCGA gene-expression data; the classifier achieved 90.4% accuracy and an AUROC of 0.981 in the TCGA validation.", "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:30106117"], "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:GSE17260"], "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:GSE17260"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:30106117", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3892/mmr.2018.9362", "sha256": "sha256:17062f87404694cb59b5ad4e129cd35c5650afd1f7f059c7984009b109c974ec", "bytes": 36696, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3892/mmr.2018.9362", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6131358", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE17260", "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=GSE17260", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE17260", "version": null, "note": "The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM432220", "GSM432221", "GSM432222", "GSM432223", "GSM432224", "GSM432225", "GSM432226", "GSM432227", "GSM432228", "GSM432229", "GSM432230", "GSM432231", "GSM432232", "GSM432233", "GSM432234", "GSM432235", "GSM432236", "GSM432237", "GSM432238", "GSM432239", "GSM432240", "GSM432242", "GSM432243", "GSM432244", "GSM432245", "GSM432246", "GSM432247", "GSM432248", "GSM432249", "GSM432250", "GSM432251", "GSM432252", "GSM432253", "GSM432254", "GSM432255", "GSM432256", "GSM432257", "GSM432258", "GSM432259", "GSM432260", "GSM432261", "GSM432262", "GSM432263", "GSM432264", "GSM432265", "GSM432266", "GSM432267", "GSM432268", "GSM432269", "GSM432270", "GSM432271", "GSM432272", "GSM432273", "GSM432274", "GSM432275", "GSM432276", "GSM432277", "GSM432278", "GSM432279", "GSM432280", "GSM432281", "GSM432282", "GSM432283", "GSM432284", "GSM432285", "GSM432286", "GSM432287", "GSM432288", "GSM432289", "GSM432290", "GSM432291", "GSM432292", "GSM432293", "GSM432294", "GSM432295", "GSM432296", "GSM432297", "GSM432298", "GSM432299", "GSM432300", "GSM432301", "GSM432302", "GSM432303", "GSM432304", "GSM432305", "GSM432306", "GSM432307", "GSM432308", "GSM432309", "GSM432310", "GSM432311", "GSM432312", "GSM432313", "GSM432314", "GSM432315", "GSM432316", "GSM432317", "GSM432318", "GSM432319", "GSM432320", "GSM432321", "GSM432322", "GSM432323", "GSM432324", "GSM432325", "GSM432326", "GSM432327", "GSM432328", "GSM432329", "GSM432330"], "sample_count": 110, "group_sizes": null, "group_sizes_basis": null, "platform": "6480", "taxon": "Homo sapiens", "title": "Prediction of progression-free survival in patients with advanced-stage serous ovarian cancer", "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:GSE44104", "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=GSE44104", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE44104", "version": null, "note": "The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1078972", "GSM1078973", "GSM1078974", "GSM1078975", "GSM1078976", "GSM1078977", "GSM1078978", "GSM1078979", "GSM1078980", "GSM1078981", "GSM1078982", "GSM1078983", "GSM1078984", "GSM1078985", "GSM1078986", "GSM1078987", "GSM1078988", "GSM1078989", "GSM1078990", "GSM1078991", "GSM1078992", "GSM1078993", "GSM1078994", "GSM1078995", "GSM1078996", "GSM1078997", "GSM1078998", "GSM1078999", "GSM1079000", "GSM1079001", "GSM1079002", "GSM1079003", "GSM1079004", "GSM1079005", "GSM1079006", "GSM1079007", "GSM1079008", "GSM1079009", "GSM1079010", "GSM1079011", "GSM1079012", "GSM1079013", "GSM1079014", "GSM1079015", "GSM1079016", "GSM1079017", "GSM1079018", "GSM1079019", "GSM1079020", "GSM1079021", "GSM1079022", "GSM1079023", "GSM1079024", "GSM1079025", "GSM1079026", "GSM1079027", "GSM1079028", "GSM1079029", "GSM1079030", "GSM1079031"], "sample_count": 60, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "COL11A1 promotes tumor progression and predicts poor clinical outcome in ovarian cancer.", "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:GSE51088", "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=GSE51088", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE51088", "version": null, "note": "The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1238145", "GSM1238146", "GSM1238147", "GSM1238148", "GSM1238149", "GSM1238150", "GSM1238151", "GSM1238152", "GSM1238153", "GSM1238154", "GSM1238155", "GSM1238156", "GSM1238157", "GSM1238158", "GSM1238159", "GSM1238160", "GSM1238161", "GSM1238162", "GSM1238163", "GSM1238164", "GSM1238165", "GSM1238166", "GSM1238167", "GSM1238168", "GSM1238169", "GSM1238170", "GSM1238171", "GSM1238172", "GSM1238173", "GSM1238174", "GSM1238175", "GSM1238176", "GSM1238177", "GSM1238178", "GSM1238179", "GSM1238180", "GSM1238181", "GSM1238182", "GSM1238183", "GSM1238184", "GSM1238185", "GSM1238186", "GSM1238187", "GSM1238188", "GSM1238189", "GSM1238190", "GSM1238191", "GSM1238192", "GSM1238193", "GSM1238194", "GSM1238195", "GSM1238196", "GSM1238197", "GSM1238198", "GSM1238199", "GSM1238200", "GSM1238201", "GSM1238202", "GSM1238203", "GSM1238204", "GSM1238205", "GSM1238206", "GSM1238207", "GSM1238208", "GSM1238209", "GSM1238210", "GSM1238211", "GSM1238212", "GSM1238213", "GSM1238214", "GSM1238215", "GSM1238216", "GSM1238217", "GSM1238218", "GSM1238219", "GSM1238220", "GSM1238221", "GSM1238222", "GSM1238223", "GSM1238224", "GSM1238225", "GSM1238226", "GSM1238227", "GSM1238228", "GSM1238229", "GSM1238230", "GSM1238231", "GSM1238232", "GSM1238233", "GSM1238234", "GSM1238235", "GSM1238236", "GSM1238237", "GSM1238238", "GSM1238239", "GSM1238240", "GSM1238241", "GSM1238242", "GSM1238243", "GSM1238244", "GSM1238245", "GSM1238246", "GSM1238247", "GSM1238248", "GSM1238249", "GSM1238250", "GSM1238251", "GSM1238252", "GSM1238253", "GSM1238254", "GSM1238255", "GSM1238256", "GSM1238257", "GSM1238258", "GSM1238259", "GSM1238260", "GSM1238261", "GSM1238262", "GSM1238263", "GSM1238264", "GSM1238265", "GSM1238266", "GSM1238267", "GSM1238268", "GSM1238269", "GSM1238270", "GSM1238271", "GSM1238272", "GSM1238273", "GSM1238274", "GSM1238275", "GSM1238276", "GSM1238277", "GSM1238278", "GSM1238279", "GSM1238280", "GSM1238281", "GSM1238282", "GSM1238283", "GSM1238284", "GSM1238285", "GSM1238286", "GSM1238287", "GSM1238288", "GSM1238289", "GSM1238290", "GSM1238291", "GSM1238292", "GSM1238293", "GSM1238294", "GSM1238295", "GSM1238296", "GSM1238297", "GSM1238298", "GSM1238299", "GSM1238300", "GSM1238301", "GSM1238302", "GSM1238303", "GSM1238304", "GSM1238305", "GSM1238306", "GSM1238307", "GSM1238308", "GSM1238309", "GSM1238310", "GSM1238311", "GSM1238312", "GSM1238313", "GSM1238314", "GSM1238315", "GSM1238316"], "sample_count": 172, "group_sizes": null, "group_sizes_basis": null, "platform": "7264", "taxon": "Homo sapiens", "title": "Ovarian Tumor Samples: mixed reference of 106 pooled ovarian samples vs.  individual patient ovarian sample", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:30106117:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:8b6ef5a7cb0994e797b89b64bbd20b9efdb6c2a0f5cb222bc7ea389144ade484", "bytes": 445, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[4]/table-wrap[1]#tI-mmr-18-04-3589", "version": null, "note": "Summary of gene expression datasets used in the present study.", "structure": {"pmcid": "PMC6131358", "section_index": 4, "section_title": "Gene expression data", "row_count": 4, "column_count": 5}, "table": {"label": "Table I.", "caption": "Summary of gene expression datasets used in the present study.", "rows": [["Accession number", "Platform", "Recurrence samples", "Non-recurrence samples", "Total number of samples"], ["GSE17260", "GPL6480", "76", "34", "110"], ["GSE44104", "GPL570", "20", "40", "60"], ["GSE51088", "GPL7264", "17", "130", "147"]], "row_count": 4, "column_count": 5, "numeric_cells": 15, "header_rows": 1, "locator": "section[4]/table-wrap[1]#tI-mmr-18-04-3589"}}, {"id": "asset:table:pmid:30106117:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:deae089ae2acd355408a730550a349564f975f9314e7af7bf3ec519c117615cd", "bytes": 567, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#tII-mmr-18-04-3589", "version": null, "note": "Results of quality control measures and standardized mean rank test from data included in GSE17260, GSE44104 and GSE51088 datasets.", "structure": {"pmcid": "PMC6131358", "section_index": 11, "section_title": "DEGs", "row_count": 4, "column_count": 8}, "table": {"label": "Table II.", "caption": "Results of quality control measures and standardized mean rank test from data included in GSE17260, GSE44104 and GSE51088 datasets.", "rows": [["Accession number", "IQC", "EQC", "CQCg", "CQCp", "AQCg", "AQCp", "SMR"], ["GSE17260", "5.48", "3.36", "110.95", "165.26", "34.03", "94.54", "1.69"], ["GSE44104", "4.55", "3.29", "66.72", "152.42", "27.52", "100.64", "2.51"], ["GSE51088", "6.33", "1.14", "105.17", "118.9", "20.32", "30.64", "4.08"]], "row_count": 4, "column_count": 8, "numeric_cells": 24, "header_rows": 1, "locator": "section[11]/table-wrap[1]#tII-mmr-18-04-3589"}}, {"id": "asset:table:pmid:30106117:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:2c3fe3ce95a62446d7e5bfff1689503a6382f96347cc3316074bc8a00cb183ed", "bytes": 1330, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#tIII-mmr-18-04-3589", "version": null, "note": "Gene Ontology biological process terms significantly associated with the genes included in the protein-protein interaction network.", "structure": {"pmcid": "PMC6131358", "section_index": 12, "section_title": "PPI network", "row_count": 15, "column_count": 4}, "table": {"label": "Table III.", "caption": "Gene Ontology biological process terms significantly associated with the genes included in the protein-protein interaction network.", "rows": [["Term", "Count", "P-value", "FDR"], ["GO:0022403, cell cycle phase", "33", "8.56×10−15", "1.40×10−11"], ["GO:0000279, M phase", "29", "4.41×10−14", "7.23×10−11"], ["GO:0000278, mitotic cell cycle", "30", "1.24×10-13", "2.04×10−10"], ["GO:0022402, cell cycle process", "36", "3.14×10−13", "5.15×10−10"], ["GO:0007067, mitosis", "23", "1.12×10−12", "1.83×10−9"], ["GO:0000280, nuclear division", "23", "1.12×10−12", "1.83×10−9"], ["GO:0000087, M phase of mitotic cell cycle", "23", "1.61×10−12", "2.64×10−9"], ["GO:0007049, cell cycle", "41", "1.90×10−12", "3.12×10−9"], ["GO:0048285, organelle fission", "23", "2.52×10−12", "4.13×10−9"], ["GO:0051301, cell division", "24", "5.77×10−11", "9.47×10−8"], ["GO:0000226, microtubule cytoskeleton organization", "13", "1.65×10−6", "2.71×10−3"], ["GO:0007051, spindle organization", "8", "3.67×10−6", "6.02×10−3"], ["GO:0007017, microtubule-based process", "16", "4.71×10−6", "7.72×10−3"], ["GO:0007010, cytoskeleton organization", "21", "6.25×10−6", "1.03×10−2"]], "row_count": 15, "column_count": 4, "numeric_cells": 56, "header_rows": 1, "locator": "section[12]/table-wrap[1]#tIII-mmr-18-04-3589"}}, {"id": "asset:table:pmid:30106117:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:83120377d5661a36d10c0c0526c6c8dc5ba4f80807c1fa0f14b08e81d024d7aa", "bytes": 768, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[2]#tIV-mmr-18-04-3589", "version": null, "note": "Significantly enriched Kyoto Encyclopedia of Genes and Genomes pathways for genes in the protein-protein interaction network.", "structure": {"pmcid": "PMC6131358", "section_index": 12, "section_title": "PPI network", "row_count": 6, "column_count": 4}, "table": {"label": "Table IV.", "caption": "Significantly enriched Kyoto Encyclopedia of Genes and Genomes pathways for genes in the protein-protein interaction network.", "rows": [["Term", "Count", "P-value", "Genes"], ["hsa04110:Cell cycle", "7", "6.62×10−3", "RAD21, BUB1B, MDM2, TTK, CDC20, PTTG1, MCM5"], ["hsa03440:Homologous recombination", "3", "5.47×10−3", "POLD1, BRCA2, RAD51"], ["hsa00230:Purine metabolism", "6", "3.57×10−2", "POLR2G, GDA, POLD1, AK2, AMPD3, GMPS"], ["hsa05200:Pathways in cancer", "9", "4.44×10−2", "CTBP2, RALBP1, PIK3CD, TFG, MDM2, BRCA2, BIRC5, CDH1, RAD51"], ["hsa03030:DNA replication", "3", "4.51×10−2", "POLD1, RNASEH2A, MCM5"]], "row_count": 6, "column_count": 4, "numeric_cells": 18, "header_rows": 1, "locator": "section[12]/table-wrap[2]#tIV-mmr-18-04-3589"}}, {"id": "asset:table:pmid:30106117:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:ac3677719ea29aa28f2d97f334a3aabc614ce967bb24e211eb71e88cc8195707", "bytes": 3671, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#tV-mmr-18-04-3589", "version": null, "note": "Screened feature genes used for construction of support vector machine classifier as determined by recursive feature elimination.", "structure": {"pmcid": "PMC6131358", "section_index": 13, "section_title": "SVM classifier", "row_count": 40, "column_count": 9}, "table": {"label": "Table V.", "caption": "Screened feature genes used for construction of support vector machine classifier as determined by recursive feature elimination.", "rows": [["Gene", "BC", "Degree", "P-value", "FDR", "Q value", "Cochran's Q value", "tau2", "Log fold change"], ["CUL3", "0.759895", "41", "0.009775", "0.02304", "0.198586", "0.905478", "0", "−3.08977"], ["MDM2", "0.694803", "25", "0.014685", "0.034611", "0.513419", "0.773593", "0", "−1.09727"], ["AURKA", "0.558121", "19", "0.001087", "0.002561", "1.286947", "0.525464", "0", "1.42154"], ["HNRNPK", "0.50414", "13", "0.011236", "0.026482", "1.021909", "0.599923", "0", "−0.96217"], ["RAD21", "0.490358", "12", "0.014482", "0.034133", "0.386617", "0.824228", "0", "2.596818"], ["WWOX", "0.458579", "10", "0.013516", "0.031857", "0.857721", "0.651251", "0", "−3.74564"], ["IGBP1", "0.449997", "7", "0.011454", "0.026997", "0.47506", "0.788573", "0", "0.321061"], ["IPO7", "0.442128", "5", "0.002717", "0.006405", "1.598947", "0.449566", "0", "−1.03747"], ["RAD23A", "0.441265", "8", "0.012419", "0.02927", "0.900161", "0.637577", "0", "1.194153"], ["TSTA3", "0.436658", "5", "0.010425", "0.02457", "0.358922", "0.835721", "0", "2.936405"], ["BRCA2", "0.435695", "5", "0.003583", "0.008444", "0.100529", "0.950978", "0", "1.948855"], ["FHL3", "0.433658", "6", "0.001257", "0.002963", "0.279246", "0.869686", "0", "0.987126"], ["LATS2", "0.430752", "4", "0.011053", "0.026051", "0.09771", "0.952319", "0", "0.4797"], ["NOC2L", "0.430291", "4", "0.013451", "0.031703", "0.014566", "0.992743", "0", "1.077813"], ["CD2AP", "0.42926", "4", "0.018901", "0.044548", "0.026358", "0.986908", "0", "−1.79036"], ["TPM4", "0.428095", "7", "0.013303", "0.031355", "1.621492", "0.444526", "0", "2.932572"], ["MCM5", "0.427881", "7", "0.006661", "0.0157", "0.397359", "0.819813", "0", "0.44911"], ["CTBP2", "0.427047", "5", "0.013728", "0.032356", "1.715255", "0.424167", "0", "0.877948"], ["SIRT6", "0.426042", "6", "0.009524", "0.022448", "0.145688", "0.929746", "0", "−0.81214"], ["RALBP1", "0.42506", "3", "0.008046", "0.018964", "1.608012", "0.447533", "0", "1.788163"], ["DBN1", "0.422172", "9", "0.001295", "0.003052", "1.479727", "0.477179", "0", "1.499493"], ["FAF1", "0.420131", "4", "0.014442", "0.034039", "1.184726", "0.553019", "0", "1.782133"], ["SMC4", "0.416491", "5", "0.005295", "0.01248", "0.238612", "0.887536", "0", "1.769396"], ["SND1", "0.41646", "3", "0.003913", "0.009222", "0.920509", "0.631123", "0", "1.238259"], ["TEAD4", "0.414377", "2", "0.008077", "0.019037", "1.729928", "0.421067", "0", "0.992568"], ["BANP", "0.411436", "3", "0.004271", "0.010067", "0.305887", "0.858178", "0", "0.759078"], ["SART1", "0.409053", "3", "0.01088", "0.025643", "0.068045", "0.96655", "0", "1.254434"], ["INPPL1", "0.408929", "2", "9.41E-05", "0.000222", "1.3698", "0.504141", "0", "2.084808"], ["LRIG1", "0.408929", "2", "0.018088", "0.042633", "1.901966", "0.386361", "0", "−1.42735"], ["LRRC49", "0.408929", "2", "0.011943", "0.028148", "0.263645", "0.876497", "0", "−1.66365"], ["PCSK9", "0.408929", "2", "0.000332", "0.000782", "0.045994", "0.977266", "0", "−5.13551"], ["PHPT1", "0.408929", "2", "0.009973", "0.023507", "0.52427", "0.769407", "0", "−1.60935"], ["POLR2G", "0.408929", "2", "0.010377", "0.024458", "0.509447", "0.775131", "0", "1.450648"], ["PPA2", "0.408929", "2", "0.002415", "0.005691", "0.983689", "0.611498", "0", "−0.77017"], ["USP47", "0.408929", "2", "0.016431", "0.038727", "1.485343", "0.475841", "0", "−2.70658"], ["TTK", "0.408856", "3", "0.019272", "0.045422", "0.154504", "0.925656", "0", "−0.23932"], ["ARFIP1", "0.408051", "3", "5.30E-06", "1.25E-05", "1.795171", "0.407552", "0", "−2.91913"], ["FTL", "0.407729", "2", "0.00145", "0.003417", "1.83461", "0.399595", "0", "2.012816"], ["AURKAIP1", "0.407431", "2", "0.006809", "0.016048", "0.532797", "0.766134", "0", "0.828771"]], "row_count": 40, "column_count": 9, "numeric_cells": 316, "header_rows": 1, "locator": "section[13]/table-wrap[1]#tV-mmr-18-04-3589"}}, {"id": "asset:table:pmid:30106117:6", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:1760c390fdc67d64341efc74906d1c1863efc5aad45f7b99115079d03c7ebcae", "bytes": 682, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[2]#tVI-mmr-18-04-3589", "version": null, "note": "Prediction results of the support vector machine classifier using sample data from GSE17260, GSE44104 and GSE51088.", "structure": {"pmcid": "PMC6131358", "section_index": 13, "section_title": "SVM classifier", "row_count": 5, "column_count": 9}, "table": {"label": "Table VI.", "caption": "Prediction results of the support vector machine classifier using sample data from GSE17260, GSE44104 and GSE51088.", "rows": [["Datasets", "Number of samples", "Correct samples", "Correct rate", "Sensitivity", "Specificity", "PPV", "NPV", "AUROC"], ["GSE17260", "110", "102", "0.927", "0.894", "0.987", "0.964", "0.915", "0.988"], ["GSE44104", "60", "56", "0.933", "1.000", "0.800", "0.909", "1.000", "0.970"], ["GSE51088", "147", "142", "0.966", "0.969", "0.941", "0.992", "0.800", "0.967"], ["TCGA", "395", "357", "0.9038", "0.987", "0.801", "0.862", "0.979", "0.981"]], "row_count": 5, "column_count": 9, "numeric_cells": 35, "header_rows": 1, "locator": "section[13]/table-wrap[2]#tVI-mmr-18-04-3589"}}], "gaps": ["asset:data:geo:GSE17260 not downloaded", "asset:data:geo:GSE17260 licence not read", "asset:data:geo:GSE44104 not downloaded", "asset:data:geo:GSE44104 licence not read", "asset:data:geo:GSE51088 not downloaded", "asset:data:geo:GSE51088 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "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": 1.0, "band": "verbatim", "quote": "The SVM classifier was subsequently established to predict OC recurrence based on the expression levels of the screened feature genes."}}, {"id": "method-2", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "PPI"}}, {"id": "method-3", "family": "network_analysis", "specific": "centrality", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "centrality"}}], "targets": [{"id": "target-published-estimate", "claim_id": "claim-target-result", "operation": "build_graph", "expected_value": 90.4, "unit": "per cent", "tolerance": null, "state": "complete", "note": "The published estimate as the reader quoted it from the paper. No tolerance is published because the paper states none."}], "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": ["train_classifier", "cross_validate", "roc_auc"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: support_vector_machine."}, "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": ["GSE17260", "GSE44104", "GSE51088"], "resolved_accessions": ["GSE17260", "GSE44104", "GSE51088"], "statements": ["The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request."], "basis": "The paper names GSE17260, GSE44104, GSE51088 in Gene Expression Omnibus and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["train_classifier", "cross_validate", "roc_auc"], "assets": ["source:pmid:30106117", "data:geo:GSE17260", "asset:table:pmid:30106117:1", "asset:table:pmid:30106117:2", "asset:table:pmid:30106117:3", "asset:table:pmid:30106117:4", "asset:table:pmid:30106117:5", "asset:table:pmid:30106117:6"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE17260"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:35:22Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 78377, "completion_tokens": 5104, "cached_tokens": 1568}}, "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:30106117", "type": "paper", "label": "pmid:30106117"}, {"id": "source:pmid:30106117", "type": "manuscript", "label": "PMID 30106117 full text"}, {"id": "data:geo:GSE17260", "type": "dataset", "label": "GEO GSE17260"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:30106117", "type": "paper", "label": "pmid:30106117"}, {"id": "source:pmid:30106117", "type": "manuscript", "label": "PMID 30106117 full text"}, {"id": "data:geo:GSE17260", "type": "dataset", "label": "GEO GSE17260"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-30106117", "type": "extraction", "used": ["source:pmid:30106117"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE17260", "type": "accession_resolution", "used": ["data:geo:GSE17260"], "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:30106117", "parent_hash": "sha256:7a0865e7904d3f7e1dec5337440ea1ea009c71e24b2ab98191f28dd50b983447", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE17260 licence not read", "asset:data:geo:GSE17260 not downloaded", "asset:data:geo:GSE44104 licence not read", "asset:data:geo:GSE44104 not downloaded", "asset:data:geo:GSE51088 licence not read", "asset:data:geo:GSE51088 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "animal_model", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.69, "evidence": ["ing of 39 feature genes (including cullin 3, mouse double minute 2 homolog, aurora kinase A, WW"], "order_basis": "paper_text_order:1432", "id": "assay:1"}, {"role": "analysis", "definition_id": "machine_learning", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["train_classifier", "cross_validate", "roc_auc"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["The SVM classifier was subsequently established to predict OC recurrence based on the expression levels of the screened feature genes."], "order_basis": "consumes_earlier_output", "id": "assay:2"}]}