miRmine: a database of human miRNA expression profiles.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:28108447", "kind": "science-record", "revision": 2, "content_hash": "sha256:1d87e71a91c87deab3fc203440566ea7e74e391e8ef5d360bfeaaecfaa41ab85", "created_at": "2026-11-01T15:40:22Z", "updated_at": "2026-11-01T18:48:31Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "miRmine: a database of human miRNA expression profiles.", "doi": "10.1093/bioinformatics/btx019", "pmid": "28108447", "authors": ["Bharat Panwar", "Gilbert S Omenn", "Yuanfang Guan"], "journal": "Bioinformatics (Oxford, England)", "year": 2017, "abstract": "MOTIVATION: MicroRNAs (miRNAs) are small non-coding RNAs that are involved in post-transcriptional regulation of gene expression. In this high-throughput sequencing era, a tremendous amount of RNA-seq data is accumulating, and full utilization of publicly available miRNA data is an important challenge. These data are useful to determine expression values for each miRNA, but quantification pipelines are in a primitive stage and still evolving; there are many factors that affect expression values significantly.\nRESULTS: We used 304 high-quality microRNA sequencing (miRNA-seq) datasets from NCBI-SRA and calculated expression profiles for different tissues and cell-lines. In each miRNA-seq dataset, we found an average of more than 500 miRNAs with higher than 5x coverage, and we explored the top five highly expressed miRNAs in each tissue and cell-line. This user-friendly miRmine database has options to retrieve expression profiles of single or multiple miRNAs for a specific tissue or cell-line, either normal or with disease information. Results can be displayed in multiple interactive, graphical and downloadable formats.\nAVAILABILITY AND IMPLEMENTATION: http://guanlab.ccmb.med.umich.edu/mirmine.\nCONTACT: bharatpa@umich.edu.\nSUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.", "claims": [{"id": "claim-target-result", "statement": "The study analyzed 304 high-quality miRNA-seq datasets from NCBI-SRA and found an average of more than 500 miRNAs with greater than 5× coverage in each dataset, yielding the miRmine expression-profile database.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:28108447", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "We used 304 high-quality microRNA sequencing (miRNA-seq) datasets from NCBI-SRA and calculated expression profiles for different tissues and cell-lines."}, {"asset": "source:pmid:28108447", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "In each miRNA-seq dataset, we found an average of more than 500 miRNAs with higher than 5x coverage, and we explored the top five highly expressed miRNAs in each tissue and cell-line."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "The study analyzed 304 high-quality miRNA-seq datasets from NCBI-SRA and found an average of more than 500 miRNAs with greater than 5× coverage in each dataset, yielding the miRmine expression-profile database.", "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:28108447"], "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:28108447", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/bioinformatics/btx019", "sha256": "sha256:40c10013d32619cd744bc6b304d8ce50ce9e44fe9ca521ba476c67b69972a80f", "bytes": 1227, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/bioinformatics/btx019", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6044334", "source": "ncbi_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "absent", "methods": [], "targets": [], "gaps": ["method", "operations"]}, "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": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (not named), but the corpus's method extractor could not map it onto a DSL operation, so the method is published but not expressible."}, "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": [], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:28108447"], "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": "2026-10-31T18:30:19Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": null}, "calls": 2, "usage": {"prompt_tokens": 1482, "completion_tokens": 429, "cached_tokens": 520}}, "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:28108447", "type": "paper", "label": "pmid:28108447"}, {"id": "source:pmid:28108447", "type": "manuscript", "label": "PMID 28108447 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:28108447", "type": "paper", "label": "pmid:28108447"}, {"id": "source:pmid:28108447", "type": "manuscript", "label": "PMID 28108447 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-28108447", "type": "extraction", "used": ["source:pmid:28108447"], "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:28108447", "parent_hash": "sha256:11627bcbd5b1279729e2e59f2099a1c94dd8f4586ba51eff0cb8ca591bbd5b49", "fork_of": null, "generation": 1}, "gaps": ["execution.not_run", "method", "operations", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"], "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": 0.93, "evidence": ["ghput sequencing era, a tremendous amount of RNA-seq data is accumulating, and full utilization o"], "order_basis": "paper_text_order:204", "id": "assay:1"}]}