Expression profiling dataset of competing endogenous RNA in pre-eclampsia.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:31799347", "kind": "science-record", "revision": 4, "content_hash": "sha256:5584d93a1f0d32ac4c09e71ced093a29b07eaefde4419714d2fa4aac78694ed6", "created_at": "2026-11-01T15:40:52Z", "updated_at": "2026-11-01T21:22:41Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Expression profiling dataset of competing endogenous RNA in pre-eclampsia.", "doi": "10.1016/j.dib.2019.104795", "pmid": "31799347", "authors": ["Xiaopeng Hu", "Xinyue Li", "Geng G Tian", "Huijuan Zhang", "Weiwei Cheng", "Ji Wu"], "journal": "Data in brief", "year": 2019, "abstract": "This data descriptor is an extended version of the methodologies which have been described in a related paper [1]; its purpose is to disseminate the raw data and analyzed data produced in this experiment. For more insight please see the research article, \"competing endogenous RNA expression profiling in pre-eclampsia identifies hsa_circ_0036877 as a potential novel blood biomarker for early pre-eclampsia\" (Xiaopeng Hu and Junping Ao, 2018) [1]. Using microarray analysis, we investigated competing endogenous RNA (ceRNA) expression profiles in placentas of women with severe pre-eclampsia (SPE) and normal pregnancies. Competing endogenous RNA (ceRNA) refer to RNA transcripts, such as messenger RNA (mRNA), long noncoding RNA (lncRNA), and circular RNA (circRNA) that can regulate each other by competing for the same pool of miRNAs. CircRNAs, lncRNAs, and mRNAs differentially expressed between human normal and SPE placentas were obtained in the study. Metadata files were submitted to the Gene Expression Omnibus repository (GEO), with GEO accession number GSE102897. These data are potential useful for further study on the pathogenesis of PE and early prediction of PE onset.", "claims": [{"id": "claim-method", "statement": "The p-value was calculated by a right-sided hypergeometric test.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31799347", "locator": "sections[9] \"Microarray analysis\" paragraph 4", "quote": "The p-value was calculated by a right-sided hypergeometric test."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Data was submitted to the Gene Expression Omnibus repository (GEO) (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE102897), with GEO accession number GSE102897.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31799347", "locator": "sections[1] \"p\" paragraph 1", "quote": "Data was submitted to the Gene Expression Omnibus repository (GEO) (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE102897), with GEO accession number GSE102897."}], "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:31799347"], "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:GSE102897"], "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:GSE102897"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:31799347", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2019.104795", "sha256": "sha256:d0575678648dd253966ec12443da83168461a6f4a47021c2d2b77091b50ed065", "bytes": 14745, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2019.104795", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6881654", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE102897", "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=GSE102897", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE102897", "version": null, "note": "Data was submitted to the Gene Expression Omnibus repository (GEO) (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE102897), with GEO accession number GSE102897.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data was submitted to the Gene Expression Omnibus repository (GEO) (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE102897), with GEO accession number GSE102897.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2747897", "GSM2747898", "GSM2747899", "GSM2747900", "GSM2747901", "GSM2747902"], "sample_count": 6, "group_sizes": null, "group_sizes_basis": null, "platform": "22120", "taxon": "Homo sapiens", "title": "Competing endogenous RNA expression dataset from placenta tissues of normal human and  patients with severe preeclampsia.", "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:31799347:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:12b9bec530d640d23acd9f4a4289ee7b77e06c28dd9df589541783e884458c4a", "bytes": 1199, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[1]#undtbl1", "version": null, "note": "Specifications Table", "structure": {"pmcid": "PMC6881654", "section_index": 1, "section_title": "p", "row_count": 10, "column_count": 2}, "table": {"label": null, "caption": "Specifications Table", "rows": [["Subject area", "Medicine"], ["More specific subject area", "Pre-eclampsia (PE)"], ["Type of data", "Table and figure"], ["How data was acquired", "Microarray"], ["Data format", "Raw and analyzed data"], ["Parameters for data collection", "The human placentas of controls and SPE were randomly devided into 3 groups respectively."], ["Description of data collection", "Total RNA were extracted from the placental tissue for analysis of their circRNA, lncRNA, and mRNA profiles using Agilent Human (4 × 180K) GeneChip circRNA and lncRNA arrays."], ["Data source location", "Shanghai, china"], ["Data accessibility", "Data was submitted to the Gene Expression Omnibus repository (GEO) (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE102897), with GEO accession number GSE102897."], ["Related research article", "Hu X, Ao J, Li X, Zhang H, Wu J, Cheng W. Competing endogenous RNA expression profiling in pre-eclampsia identifies hsa_circ_0036877 as a potential novel blood biomarker for early pre-eclampsia. Clinical epigenetics 2018, 10: 48."]], "row_count": 10, "column_count": 2, "numeric_cells": 4, "header_rows": 0, "locator": "section[1]/table-wrap[1]#undtbl1"}}, {"id": "asset:table:pmid:31799347:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:42c538afec3f76d9d297d8e113926a8632c58dbcebddca0dd1c49bd25322c90a", "bytes": 1014, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[2]#undtbl2", "version": null, "note": null, "structure": {"pmcid": "PMC6881654", "section_index": 1, "section_title": "p", "row_count": 1, "column_count": 1}, "table": {"label": null, "caption": null, "rows": [["Value of the Data•The circRNA, lncRNA and mRNA expression profiling were performed simultaneously, which is generally believed to be one of the major advantages of this research. It is believed that this data is useful for more precise investigation of the interaction between ceRNAs in the process of PE onset.•It could also help PE researchers to resolve the issue of how ceRNAs are involved in the pathogenesis of PE.•The data could be used to analyse predicted targets associated to treatment of PE as it concerns maternal and child health, as well as to identify ceRNAs as early clinical biomarkers of PE.•After bioinformatics analysis, this dataset shows all differentially expressed ceRNAs between human normal and SPE placentas in tables. This dataset also shows all items of functional enrichment and prediction of ceRNAs interaction in tables."]], "row_count": 1, "column_count": 1, "numeric_cells": 0, "header_rows": 0, "locator": "section[1]/table-wrap[2]#undtbl2"}}, {"id": "asset:table:pmid:31799347:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:3f6ea6b4d3927c772ca7d0e69b46340f439eef7b81f0f8514b3db0dcc91f40a8", "bytes": 1057, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[2]/table-wrap[1]#tbl1", "version": null, "note": "Sample description for ceRNAs expression array.", "structure": {"pmcid": "PMC6881654", "section_index": 2, "section_title": "Data", "row_count": 7, "column_count": 8}, "table": {"label": "Table 1", "caption": "Sample description for ceRNAs expression array.", "rows": [["Sample name", "Source", "Organism", "Tissue", "Age", "Protocol 1", "Protocol 2", "Data"], ["SPE_1", "Severe Preeclampsia", "Homo sapiens", "Placenta", "25-35y", "RNA extraction", "circRNA arrayIncRNA and mRNA array", "GSM2747897"], ["SPE_2", "Severe Preeclampsia", "Homo sapiens", "Placenta", "25-35y", "RNA extraction", "circRNA arrayIncRNA and mRNA array", "GSM2747898"], ["SPE_3", "Severe Preeclampsia", "Homo sapiens", "Placenta", "25-35y", "RNA extraction", "circRNA arrayIncRNA and mRNA array", "GSM2747899"], ["N_1", "Normal human", "Homo sapiens", "Placenta", "25-35y", "RNA extraction", "circRNA arrayIncRNA and mRNA array", "GSM2747900"], ["N_2", "Normal human", "Homo sapiens", "Placenta", "25-35y", "RNA extraction", "circRNA arrayIncRNA and mRNA array", "GSM2747901"], ["N_3", "Normal human", "Homo sapiens", "Placenta", "25-35y", "RNA extraction", "circRNA arrayIncRNA and mRNA array", "GSM2747902"]], "row_count": 7, "column_count": 8, "numeric_cells": 20, "header_rows": 1, "locator": "section[2]/table-wrap[1]#tbl1"}}], "gaps": ["asset:data:geo:GSE102897 not downloaded", "asset:data:geo:GSE102897 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "Right-sided hypergeometric test", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The p-value was calculated by a right-sided hypergeometric test."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "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": "method", "blocked_on": "method:not_determinable", "axes": {"method": {"tier": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (Right-sided hypergeometric test), 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": "R1", "reachable": true, "accessions": ["GSE102897"], "resolved_accessions": ["GSE102897"], "statements": ["Data was submitted to the Gene Expression Omnibus repository (GEO) (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE102897), with GEO accession number GSE102897."], "basis": "The paper names GSE102897 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": [], "assets": ["source:pmid:31799347", "data:geo:GSE102897", "asset:table:pmid:31799347:1", "asset:table:pmid:31799347:2", "asset:table:pmid:31799347:3"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE102897"]}, "gaps": ["method:not_determinable"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:17:12Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 12425, "completion_tokens": 870, "cached_tokens": 4352}}, "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:31799347", "type": "paper", "label": "pmid:31799347"}, {"id": "source:pmid:31799347", "type": "manuscript", "label": "PMID 31799347 full text"}, {"id": "data:geo:GSE102897", "type": "dataset", "label": "GEO GSE102897"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:31799347", "type": "paper", "label": "pmid:31799347"}, {"id": "source:pmid:31799347", "type": "manuscript", "label": "PMID 31799347 full text"}, {"id": "data:geo:GSE102897", "type": "dataset", "label": "GEO GSE102897"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-31799347", "type": "extraction", "used": ["source:pmid:31799347"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE102897", "type": "accession_resolution", "used": ["data:geo:GSE102897"], "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:31799347", "parent_hash": "sha256:5e4c501dce0bf639ca4366f1f6e7fd1aef4513f50cc23a59c100b545dcc9ce1d", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE102897 licence not read", "asset:data:geo:GSE102897 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["Xiaopeng Hu and Junping Ao, 2018) [1]. Using microarray analysis, we investigated competing endogeno"], "order_basis": "paper_text_order:485", "id": "assay:1"}]}