Dataset for miRNA expression analysis in the peripheral white blood cells of beef heifers at weaning.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:37680347", "kind": "science-record", "revision": 5, "content_hash": "sha256:88086c685c36b3d3a11891a2405825ccc239645c42f03ac1c5c9dae015323530", "created_at": "2026-11-01T19:02:28Z", "updated_at": "2026-11-01T22:52:39Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Dataset for miRNA expression analysis in the peripheral white blood cells of beef heifers at weaning.", "doi": "10.1016/j.dib.2023.109515", "pmid": "37680347", "authors": ["Priyanka Banerjee", "Wellison J S Diniz", "Paul W Dyce"], "journal": "Data in brief", "year": 2023, "abstract": "Subfertility in beef heifers leads to a substantial economic loss for producers and beef industry. To overcome this problem, producers require an efficient system to discriminate beef heifers with varying reproductive potential as early as possible. MicroRNAs are short non-coding RNAs that post-transcriptionally regulate gene expression. Herein, we profiled the miRNAs in peripheral white blood cells (PWBC) of beef heifers at weaning to investigate the differences in the beef heifers with varying reproductive outcomes. Blood samples from Angus-Simmental crossbred heifers were collected at weaning. The blood was processed to extract the PWBC pellet and was stored at -80 °C until further processing. After the synchronization of estrus and breeding protocol (artificial insemination (AI) followed by natural bull service) and pregnancy diagnosis, the heifers were categorized as fertile (pregnant to AI) or subfertile (not pregnant to AI or bull exposure). Total RNA was extracted from PWBC collected at the time of weaning from the fertile and subfertile heifers. After quality assessment, the total RNA was used to prepare libraries. The quality-checked libraries (n = 14; 7 samples per fertile and subfertile group) were pooled and sequenced (single-end 50 bp) using a NextSeq 500 platform. The raw sequence reads were analyzed using a bioinformatics workflow utilizing FastQC and MultiQC for quality control, Cutadapt for adapter trimming, miRDeep2 for alignment, and DESeq2 for differential expression analysis. The raw and normalized miRNA counts were deposited and made publicly available on the gene expression omnibus database (GEO; GSE225854). This is the first dataset investigating the miRNA expression level in PWBC at weaning in beef heifers to predict the future reproductive outcome. The results from the data presented here are reported in the research article titled \"miRNA expression profiles of peripheral white blood cells from beef heifers with varying reproductive potential\" [1].", "claims": [{"id": "claim-method", "statement": "For the differential expression analysis, the filtered raw counts were used in DESeq2 v1.26.0 [7].", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:37680347", "locator": "sections[10] \"Data Analysis\" paragraph 2", "quote": "For the differential expression analysis, the filtered raw counts were used in DESeq2 v1.26.0 [7]."}], "state": "complete"}, {"id": "claim-data-access", "statement": "miRNA profiling from peripheral white blood cells in fertile and subfertile beef heifers at weaning (Original data) (NCBI GEO).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:37680347", "locator": "sections[16] \"Data Availability\" paragraph 2", "quote": "miRNA profiling from peripheral white blood cells in fertile and subfertile beef heifers at weaning (Original data) (NCBI GEO)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "", "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:37680347"], "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:GSE225854"], "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:GSE225854"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:37680347", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2023.109515", "sha256": "sha256:0fc837e68a78f4df16319b971f104e1b987fdbffd0681f64bb9b667c61b10585", "bytes": 16493, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2023.109515", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC10481169", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE225854", "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=GSE225854", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE225854", "version": null, "note": "miRNA profiling from peripheral white blood cells in fertile and subfertile beef heifers at weaning (Original data) (NCBI GEO).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "miRNA profiling from peripheral white blood cells in fertile and subfertile beef heifers at weaning (Original data) (NCBI GEO).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM7058355", "GSM7058356", "GSM7058357", "GSM7058358", "GSM7058359", "GSM7058360", "GSM7058361", "GSM7058362", "GSM7058363", "GSM7058364", "GSM7058365", "GSM7058366", "GSM7058367", "GSM7058368"], "sample_count": 14, "group_sizes": null, "group_sizes_basis": null, "platform": "23055", "taxon": "Bos taurus", "title": "miRNA profiling from peripheral white blood cells in fertile and subfertile beef heifers at weaning", "resolution_checked_at": "2026-11-01T19:09:46Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE225854 not downloaded", "asset:data:geo:GSE225854 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "deseq2", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "For the differential expression analysis, the filtered raw counts were used in DESeq2 v1.26.0 [7]."}}], "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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: deseq2."}, "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": ["GSE225854"], "resolved_accessions": ["GSE225854"], "statements": ["miRNA profiling from peripheral white blood cells in fertile and subfertile beef heifers at weaning (Original data) (NCBI GEO)."], "basis": "The paper names GSE225854 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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:37680347", "data:geo:GSE225854"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE225854"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T18:52:38Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 5762, "completion_tokens": 1167, "cached_tokens": 128}}, "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:37680347", "type": "paper", "label": "pmid:37680347"}, {"id": "source:pmid:37680347", "type": "manuscript", "label": "PMID 37680347 full text"}, {"id": "data:geo:GSE225854", "type": "dataset", "label": "GEO GSE225854"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:37680347", "type": "paper", "label": "pmid:37680347"}, {"id": "source:pmid:37680347", "type": "manuscript", "label": "PMID 37680347 full text"}, {"id": "data:geo:GSE225854", "type": "dataset", "label": "GEO GSE225854"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-37680347", "type": "extraction", "used": ["source:pmid:37680347"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE225854", "type": "accession_resolution", "used": ["data:geo:GSE225854"], "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:37680347", "parent_hash": "sha256:055e68baa59101351c2b83e269b4e946d8c1a3f832b14436c4311d48c5bf94d8", "fork_of": null, "generation": 4}, "gaps": ["asset:data:geo:GSE225854 licence not read", "asset:data:geo:GSE225854 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "clinical_cohort", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.77, "evidence": ["heifers with varying reproductive outcomes. Blood samples from Angus-Simmental crossbred heifers were colle"], "order_basis": "paper_text_order:582", "id": "assay:1"}, {"role": "analysis", "definition_id": "differential_expression", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["For the differential expression analysis, the filtered raw counts were used in DESeq2 v1.26.0 [7]."], "order_basis": "consumes_earlier_output", "id": "assay:2"}]}