Transcriptome data of peripheral white blood cells from beef heifers collected at the time of artificial insemination.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:29900224", "kind": "science-record", "revision": 5, "content_hash": "sha256:c57a830d0c0aa61a7385d6c5a44a66a54450337fb3dea95fc28812a7a0775740", "created_at": "2026-11-01T15:40:34Z", "updated_at": "2026-11-01T18:49:34Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Transcriptome data of peripheral white blood cells from beef heifers collected at the time of artificial insemination.", "doi": "10.1016/j.dib.2018.03.062", "pmid": "29900224", "authors": ["Sarah E Dickinson", "Fernando H Biase"], "journal": "Data in brief", "year": 2018, "abstract": "The reproductive performance of heifers within their first breeding season influences the success of beef cattle operations. Therefore, a means to identify infertile and late breeding heifers before the start of the breeding season holds great promise for the future of the beef industry. Pubertal beef heifers were subjected to estrous synchronization and fixed time artificial insemination (FTAI). We collected peripheral blood from the heifers at the time of artificial insemination (AI) and generated RNA sequencing data to characterize the transcriptome of peripheral white blood cells (PWBC). Following insemination, heifers were exposed to natural service for a defined breeding season, and pregnancy was evaluated to classify heifers into one of three groups: AI-pregnant, natural-bred (NB) pregnant, and non-pregnant. The raw transcriptome data of PWBC is available on the NCBI GEO repository (GSE103628) where the reader can also find raw read counts and normalized gene expression data. The normalized data on transcript coverage can be visualized as a genome browser at HeiferFertilityRNAseq.org.", "claims": [{"id": "claim-data-access", "statement": "Data accessibilityRaw data is in the public NCBI GEO repository (GSE103628,https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE103628). Normalized data on transcript coverage can be visualized as a genome browser at HeiferFertilityRNAseq.org (Fig. 1).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:29900224", "locator": "sections[1] \"p\" paragraph 1", "quote": "Data accessibilityRaw data is in the public NCBI GEO repository (GSE103628,https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE103628). Normalized data on transcript coverage can be visualized as a genome browser at HeiferFertilityRNAseq.org (Fig. 1)."}], "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:29900224"], "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:GSE103628"], "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:GSE103628"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:29900224", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2018.03.062", "sha256": "sha256:3f609bef5f4dfc456bc502ccd215393cb1a7d1499a190fa530c49b4195912a17", "bytes": 8122, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2018.03.062", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC5996294", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE103628", "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=GSE103628", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE103628", "version": null, "note": "Data accessibilityRaw data is in the public NCBI GEO repository (GSE103628,https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE103628). Normalized data on transcript coverage can be visualized as a genome browser at HeiferFertilityRNAseq.org (Fig. 1).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data accessibilityRaw data is in the public NCBI GEO repository (GSE103628,https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE103628). Normalized data on transcript coverage can be visualized as a genome browser at HeiferFertilityRNAseq.org (Fig. 1).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2776909", "GSM2776910", "GSM2776911", "GSM2776912", "GSM2776913", "GSM2776914", "GSM2776916", "GSM2776917", "GSM2776918", "GSM2776919", "GSM2776920", "GSM2776921", "GSM2776922", "GSM2776923", "GSM2776924", "GSM2776925", "GSM2776926", "GSM2776927", "GSM2776928", "GSM2776929", "GSM2776930", "GSM2776931", "GSM2776932"], "sample_count": 23, "group_sizes": null, "group_sizes_basis": null, "platform": "19172", "taxon": "Bos taurus", "title": "Transcriptome profiles in peripheral white blood cells at the time of artificial insemination discriminate beef heifers with different fertility potential", "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:29900224:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:54277def98e32f7221da386d41017b5d9f82e3bfa559f09fe8b6b800be4fd9ce", "bytes": 1286, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[1]#t0005", "version": null, "note": null, "structure": {"pmcid": "PMC5996294", "section_index": 1, "section_title": "p", "row_count": 9, "column_count": 2}, "table": {"label": null, "caption": null, "rows": [["Subject area", "Biology, Animal Sciences"], ["More specific subject area", "Reproductive Biology, Genomics"], ["Type of data", "mRNA sequencing data"], ["How data was acquired", "Next Generation Sequencing"], ["Data format", "High throughput sequencing short reads"], ["Experimental factors", "Samples were collected from heifers of three fertility classifications from two different locations."], ["Experimental features", "Blood was collected from crossbred, pubertal beef heifers (n=23) at the time of artificial insemination(AI). Heifers were then exposed to natural service for a defined breeding season. Pregnancy was evaluated, and heifers were categorized as AI-pregnant, NB-pregnant, or not pregnant. RNA was extracted from PWBC of each heifer and used as the template for cDNA libraries that were sequenced on an Illumina HiSeq. 2500."], ["Data source location", "Auburn, Alabama"], ["Data accessibility", "Raw data is in the public NCBI GEO repository (GSE103628,https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE103628). Normalized data on transcript coverage can be visualized as a genome browser at HeiferFertilityRNAseq.org (Fig. 1)."]], "row_count": 9, "column_count": 2, "numeric_cells": 2, "header_rows": 0, "locator": "section[1]/table-wrap[1]#t0005"}}, {"id": "asset:table:pmid:29900224:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:54277def98e32f7221da386d41017b5d9f82e3bfa559f09fe8b6b800be4fd9ce", "bytes": 1286, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[1]#t0005", "version": null, "note": null, "structure": {"pmcid": "PMC5996294", "section_index": 2, "section_title": "p", "row_count": 9, "column_count": 2}, "table": {"label": null, "caption": null, "rows": [["Subject area", "Biology, Animal Sciences"], ["More specific subject area", "Reproductive Biology, Genomics"], ["Type of data", "mRNA sequencing data"], ["How data was acquired", "Next Generation Sequencing"], ["Data format", "High throughput sequencing short reads"], ["Experimental factors", "Samples were collected from heifers of three fertility classifications from two different locations."], ["Experimental features", "Blood was collected from crossbred, pubertal beef heifers (n=23) at the time of artificial insemination(AI). Heifers were then exposed to natural service for a defined breeding season. Pregnancy was evaluated, and heifers were categorized as AI-pregnant, NB-pregnant, or not pregnant. RNA was extracted from PWBC of each heifer and used as the template for cDNA libraries that were sequenced on an Illumina HiSeq. 2500."], ["Data source location", "Auburn, Alabama"], ["Data accessibility", "Raw data is in the public NCBI GEO repository (GSE103628,https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE103628). Normalized data on transcript coverage can be visualized as a genome browser at HeiferFertilityRNAseq.org (Fig. 1)."]], "row_count": 9, "column_count": 2, "numeric_cells": 2, "header_rows": 0, "locator": "section[1]/table-wrap[1]#t0005"}}], "gaps": ["asset:data:geo:GSE103628 not downloaded", "asset:data:geo:GSE103628 licence not read"]}, "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": "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 (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": "R1", "reachable": true, "accessions": ["GSE103628"], "resolved_accessions": ["GSE103628"], "statements": ["Data accessibilityRaw data is in the public NCBI GEO repository (GSE103628,https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE103628). Normalized data on transcript coverage can be visualized as a genome browser at HeiferFertilityRNAseq.org (Fig. 1)."], "basis": "The paper names GSE103628 in NCBI GEO and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:29900224", "data:geo:GSE103628", "asset:table:pmid:29900224:1", "asset:table:pmid:29900224:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE103628"]}, "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": "2026-10-31T18:34:47Z", "independence": "same_provider"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 20027, "completion_tokens": 2236, "cached_tokens": 2088}}, "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:29900224", "type": "paper", "label": "pmid:29900224"}, {"id": "source:pmid:29900224", "type": "manuscript", "label": "PMID 29900224 full text"}, {"id": "data:geo:GSE103628", "type": "dataset", "label": "GEO GSE103628"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:29900224", "type": "paper", "label": "pmid:29900224"}, {"id": "source:pmid:29900224", "type": "manuscript", "label": "PMID 29900224 full text"}, {"id": "data:geo:GSE103628", "type": "dataset", "label": "GEO GSE103628"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-29900224", "type": "extraction", "used": ["source:pmid:29900224"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE103628", "type": "accession_resolution", "used": ["data:geo:GSE103628"], "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:29900224", "parent_hash": "sha256:3989eb0b4d9bb151c3d079a4469030aca5b82bc58ce68604e30d6de4e30fdbc9", "fork_of": null, "generation": 4}, "gaps": ["asset:data:geo:GSE103628 licence not read", "asset:data:geo:GSE103628 not downloaded", "execution.not_run", "method", "operations", "review.human_critique", "review.independent_reader", "review.machine_critique"], "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": 0.99, "evidence": ["Transcriptome data of peripheral white blood cells from be", "ated RNA sequencing data to characterize the transcriptome of peripheral white blood cells (PWBC). Foll", "red (NB) pregnant, and non-pregnant. The raw transcriptome data of PWBC is available on the NCBI GEO re", "f artificial insemination (AI) and generated RNA sequencing data to characterize the transcriptome of pe"], "order_basis": "paper_text_order:0", "id": "assay:1"}]}