PROGmiR: a tool for identifying prognostic miRNA biomarkers in multiple cancers using publicly available data.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:23272654", "kind": "science-record", "revision": 4, "content_hash": "sha256:db74912377355e81e9fb8daa9400d6b4b9c9da55f684a3c97c223aaef4d5197b", "created_at": "2026-11-01T15:40:02Z", "updated_at": "2026-11-01T21:19:40Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "PROGmiR: a tool for identifying prognostic miRNA biomarkers in multiple cancers using publicly available data.", "doi": "10.1186/2043-9113-2-23", "pmid": "23272654", "authors": ["Chirayu Pankaj Goswami", "Harikrishna Nakshatri"], "journal": "Journal of clinical bioinformatics", "year": 2012, "abstract": "BACKGROUND: Identification of prognostic biomarkers is hallmark of cancer genomics. Since miRNAs regulate expression of multiple genes, they act as potent biomarkers in several cancers. Identification of miRNAs that are prognostically important has been done sporadically, but no resource is available till date that allows users to study prognostics of miRNAs of interest, utilizing the wealth of available data, in major cancer types.\nDESCRIPTION: In this paper, we present a web based tool that allows users to study prognostic properties of miRNAs in several cancer types, using publicly available data. We have compiled data from Gene Expression Omnibus (GEO), and recently developed \"The Cancer Genome Atlas (TCGA)\", to create this tool. The tool is called \"PROGmiR\" and it is available at http://www.compbio.iupui.edu/progmir. Currently, our tool can be used to study overall survival implications for approximately 1050 human miRNAs in 16 major cancer types.\nCONCLUSIONS: We believe this resource, as a hypothesis generation tool, will be helpful for researchers to link miRNA expression with cancer outcome and to design mechanistic studies. We studied performance of our tool using identified miRNA biomarkers from published studies. The prognostic plots created using our tool for specific miRNAs in specific cancer types corroborated with the findings in the studies.", "claims": [{"id": "claim-method", "statement": "Hazard ratio and p value are then calculated using function ‘coxph’ and prognostic plots are visualized using function ‘survfit’, both functions in library ‘survival’ for R.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:23272654", "locator": "sections[3] \"Workflow\" paragraph 4", "quote": "Hazard ratio and p value are then calculated using function ‘coxph’ and prognostic plots are visualized using function ‘survfit’, both functions in library ‘survival’ for R."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The database is available freely for non commercial and academic usage at http://www.compbio.iupui.edu/progmir.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:23272654", "locator": "sections[8] \"Availability and requirements\" paragraph 2", "quote": "The database is available freely for non commercial and academic usage at http://www.compbio.iupui.edu/progmir."}], "state": "complete"}, {"id": "claim-target-result", "statement": "PROGmiR uses miRNA expression data from GEO and TCGA to generate overall-survival Kaplan–Meier prognostic plots for approximately 1050 human miRNAs across 16 major cancer types.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:23272654", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "In this paper, we present a web based tool that allows users to study prognostic properties of miRNAs in several cancer types, using publicly available data."}, {"asset": "source:pmid:23272654", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "We have compiled data from Gene Expression Omnibus (GEO), and recently developed “The Cancer Genome Atlas (TCGA)”, to create this tool."}, {"asset": "source:pmid:23272654", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "Currently, our tool can be used to study overall survival implications for approximately 1050 human miRNAs in 16 major cancer types."}, {"asset": "source:pmid:23272654", "locator": "sections[1] \"Background\" paragraph 8", "quote": "PROGmiR allows users to study overall survival in form of prognostic plots using miRNA expression data from several publically available patient series. The data in our tool comes from Gene Expression Omnibus (GEO) and The Cancer Genome Atlas (TCGA) [51]."}, {"asset": "source:pmid:23272654", "locator": "sections[1] \"Background\" paragraph 8", "quote": "Our tool uses miRNA expression data from these datasets to create overall survival Kaplan-Meier (K-M) plots."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "PROGmiR uses miRNA expression data from GEO and TCGA to generate overall-survival Kaplan–Meier prognostic plots for approximately 1050 human miRNAs across 16 major cancer types.", "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:23272654"], "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": "blocked", "blocked_on": "data:accession_absent", "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": [], "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": [], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:23272654", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/2043-9113-2-23", "sha256": "sha256:292b5b65364f3b114aad1aee04868c83fe5b5400f87c54a2698f65494e97e15c", "bytes": 21959, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/2043-9113-2-23", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC3564827", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "asset:table:pmid:23272654:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e03e13d3aa0407e4a66fb4bd5396d966c1286c928ce0b7f96d60ef0d1d74e3e8", "bytes": 1831, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[1]#T1", "version": null, "note": "Description of various data sources included in progmir database", "structure": {"pmcid": "PMC3564827", "section_index": 1, "section_title": "Background", "row_count": 17, "column_count": 8}, "table": {"label": "Table 1", "caption": "Description of various data sources included in progmir database", "rows": [["", "Cancer type", "Dataset", "Source", "Platform", "No of samples", "No of miRNAs*", "Reference"], ["1", "Adrenocortial Carcinoma", "GSE22816", "GEO", "Agilent-025987 Human miRNA Microarray Release 14.0", "22", "200", "[52]"], ["2", "Acute Myeloid Leukemia", "LAML", "TCGA", "Illumina GA miRNA Seq", "164", "704", "[51]"], ["3", "Brain Lower Grade Glioma", "LGG", "TCGA", "Illumina HISeq miRNA Seq", "29", "1046", "[51]"], ["4", "Glioblastoma multiforme", "GBM", "TCGA", "UNC miRNA 8X15K", "487", "470", "[51]"], ["5", "Breast Invasive Carcinoma", "BRCA", "TCGA", "Illumina GA and HISeq", "727", "1046", "[51]"], ["6", "Non-small-cell Lung Cancer", "GSE16025", "GEO", "mirVANA miRNA Bioarray V2", "60", "328", "[53]"], ["7", "Small Cell Lung Cancer", "GSE27435", "GEO", "Capitalbio mammal microRNA V3.0", "42", "1638", "[54]"], ["8", "Lung Adenocarcinoma", "LUAD", "TCGA", "Illumina GA and HISeq", "79", "1046", "[51]"], ["9", "Lung Squamous Cell Carcinoma", "LUSC", "TCGA", "Illumina GA and HISeq", "185", "1046", "[51]"], ["10", "Hepatocellular Carcinoma", "GSE31384", "GEO", "CapitalBio custom Human microRNA array", "166", "682", "[55]"], ["11", "Head and Neck Squamous Cell Carcinoma", "HNSC", "TCGA", "Illumina GA and HISeq", "89", "1046", "[51]"], ["12", "Ovarian Cystadenocarcinoma", "OV", "TCGA", "UNC miRNA 8X15K", "46", "705", "[51]"], ["13", "Rectal Adenocarcinoma", "READ", "TCGA", "Illumina GA miRNA Seq", "38", "705", "[51]"], ["14", "Renal Clear Cell Carcinoma", "KIRC", "TCGA", "Illumina GA and HISeq", "546", "1046", "[51]"], ["15", "Stomach Ademocarcinoma", "STAD", "TCGA", "Illumina GA and HISeq", "79", "1046", "[51]"], ["16", "Uterine Corpus Endometroid Carcinoma", "UCEC", "TCGA", "Illumina GA and HISeq", "358", "1046", "[51]"]], "row_count": 17, "column_count": 8, "numeric_cells": 72, "header_rows": 1, "locator": "section[1]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:23272654:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:51589efb5aab6138654af723adeb48724d6e0a97b5d6f0a86d8bf041b0e43185", "bytes": 1910, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[6]/table-wrap[1]#T2", "version": null, "note": "Global statistics on survival related variables for the datasets available in PROGmiR", "structure": {"pmcid": "PMC3564827", "section_index": 6, "section_title": "Utility and discussion", "row_count": 18, "column_count": 8}, "table": {"label": "Table 2", "caption": "Global statistics on survival related variables for the datasets available in PROGmiR", "rows": [["", "", "", "", "Survival event", "No event"], ["", "Cancer type", "Dataset", "Total no of samples", "No of samples", "Median survival§ (range)", "No of samples", "Median survival§* (range)"], ["1", "Adrenocortial Carcinoma", "GSE22816", "22", "6", "600 (120-4860)", "16", "885 (60-4980)"], ["2", "Acute Myeloid Leukemia", "LAML", "164", "100", "303 (28-1706)", "64", "699 (28-2861)"], ["3", "Brain Lower Grade Glioma", "LGG", "29", "23", "788 (96-1915)", "6", "1317 (242-6423)"], ["4", "Glioblastoma multiforme", "GBM", "487", "383", "377 (3-3880)", "104", "266 (3-2817)"], ["5", "Breast Invasive Carcinoma", "BRCA", "727", "91", "1563 (157-4456)", "636", "466 (1-6795)"], ["6", "Non-small-cell Lung Cancer", "GSE16025", "60", "26", "1980 (210-2490)", "34", "1500 (120-2580)"], ["7", "Small Cell Lung Cancer", "GSE27435", "42", "18", "743 (234-2400)", "24", "1314 (426 -2490)"], ["8", "Lung Adenocarcinoma", "LUAD", "79", "27", "701 (22-1318)", "52", "400 (1-2161)"], ["9", "Lung Squamous Cell Carcinoma", "LUSC", "185", "77", "544 (12-5296)", "108", "640 (3-4299)"], ["10", "Hepatocellular Carcinoma", "GSE31384", "166", "73", "450 (30 – 2280)", "93", "1320 (420-2430)"], ["11", "Head and Neck Squamous Cell Carcinoma", "HNSC", "89", "27", "395 (128 – 2318)", "62", "359 (45 – 4115)"], ["12", "Ovarian Cystadenocarcinoma", "OV", "46", "21", "887 (9-1756)", "25", "912 (141 – 2099)"], ["13", "Rectal Adenocarcinoma", "READ", "38", "3", "316 (59 – 1184)", "35", "183 (28 – 2192)"], ["14", "Renal Clear Cell Carcinoma", "KIRC", "546", "173", "722 (2-2830)", "373", "1307 (4 – 3377)"], ["15", "Stomach Adenocarcinoma", "STAD", "79", "14", "258 (19 – 881)", "65", "109 (2 – 2131)"], ["16", "Uterine Corpus Endometroid Carcinoma", "UCEC", "358", "27", "413 (58 – 3251)", "331", "527 (1 – 5690)"]], "row_count": 18, "column_count": 8, "numeric_cells": 100, "header_rows": 2, "locator": "section[6]/table-wrap[1]#T2"}}], "gaps": []}, "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": "Hazard ratio and p value are then calculated using function ‘coxph’ and prognostic plots are visualized using function ‘survfit’, both functions in library ‘survival’ for R."}}], "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": "blocked", "tier": "R4", "blocking_axis": "data", "blocked_on": "data:accession_absent", "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": "R4", "reachable": false, "accessions": [], "resolved_accessions": [], "statements": ["The database is available freely for non commercial and academic usage at http://www.compbio.iupui.edu/progmir."], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": ["cox_ph"], "assets": ["source:pmid:23272654", "asset:table:pmid:23272654:1", "asset:table:pmid:23272654:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:None"]}, "gaps": ["data:accession_absent"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:21:15Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 41817, "completion_tokens": 2484, "cached_tokens": 31790}}, "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:23272654", "type": "paper", "label": "pmid:23272654"}, {"id": "source:pmid:23272654", "type": "manuscript", "label": "PMID 23272654 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:23272654", "type": "paper", "label": "pmid:23272654"}, {"id": "source:pmid:23272654", "type": "manuscript", "label": "PMID 23272654 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-23272654", "type": "extraction", "used": ["source:pmid:23272654"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-None", "type": "accession_resolution", "used": ["data:geo:None"], "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:23272654", "parent_hash": "sha256:87b9b331348978d5bdcfe64c6f70a1065571f44cab1c51ae545df0e7ea78193b", "fork_of": null, "generation": 3}, "gaps": ["execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"], "assays": [{"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": ["Hazard ratio and p value are then calculated using function ‘coxph’ and prognostic plots are visualized using function ‘survfit’, both functions in library ‘survival’ for R."], "order_basis": "analysis_only", "id": "assay:1"}]}