Batch-normalization of cerebellar and medulloblastoma gene expression datasets utilizing empirically defined negative control genes.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:30715209", "kind": "science-record", "revision": 3, "content_hash": "sha256:612943c3d4c2f1b1075590ccc237d914599b9209eec3fb000a1199c61a8852a5", "created_at": "2026-11-01T15:40:41Z", "updated_at": "2026-11-01T21:21:57Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Batch-normalization of cerebellar and medulloblastoma gene expression datasets utilizing empirically defined negative control genes.", "doi": "10.1093/bioinformatics/btz066", "pmid": "30715209", "authors": ["Holger Weishaupt", "Patrik Johansson", "Anders Sundström", "Zelmina Lubovac-Pilav", "Björn Olsson", "Sven Nelander", "Fredrik J Swartling"], "journal": "Bioinformatics (Oxford, England)", "year": 2019, "abstract": "MOTIVATION: Medulloblastoma (MB) is a brain cancer predominantly arising in children. Roughly 70% of patients are cured today, but survivors often suffer from severe sequelae. MB has been extensively studied by molecular profiling, but often in small and scattered cohorts. To improve cure rates and reduce treatment side effects, accurate integration of such data to increase analytical power will be important, if not essential.\nRESULTS: We have integrated 23 transcription datasets, spanning 1350 MB and 291 normal brain samples. To remove batch effects, we combined the Removal of Unwanted Variation (RUV) method with a novel pipeline for determining empirical negative control genes and a panel of metrics to evaluate normalization performance. The documented approach enabled the removal of a majority of batch effects, producing a large-scale, integrative dataset of MB and cerebellar expression data. The proposed strategy will be broadly applicable for accurate integration of data and incorporation of normal reference samples for studies of various diseases. We hope that the integrated dataset will improve current research in the field of MB by allowing more large-scale gene expression analyses.\nAVAILABILITY AND IMPLEMENTATION: The RUV-normalized expression data is available through the Gene Expression Omnibus (GEO; https://www.ncbi.nlm.nih.gov/geo/) and can be accessed via the GSE series number GSE124814.\nSUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.", "claims": [{"id": "claim-method", "statement": "Batch effect correction was performed via the naiveRandRUV method (Jacob et al., 2016), employing the NCGs and a range of combinations of regularization parameters.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30715209", "locator": "sections[7] \"2.5 Batch effect removal\" paragraph 2", "quote": "Batch effect correction was performed via the naiveRandRUV method (Jacob et al., 2016), employing the NCGs and a range of combinations of regularization parameters."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The RUV-normalized expression data is available through the Gene Expression Omnibus (GEO; https://www.ncbi.nlm.nih.gov/geo/) and can be accessed via the GSE series number GSE124814. Supplementary data are available at Bioinformatics online.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30715209", "locator": "sections[0] \"Abstract\" paragraphs 1-4", "quote": "The RUV-normalized expression data is available through the Gene Expression Omnibus (GEO; https://www.ncbi.nlm.nih.gov/geo/) and can be accessed via the GSE series number GSE124814. Supplementary data are available at Bioinformatics online."}], "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:30715209"], "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:GSE124814"], "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:GSE124814"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:30715209", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/bioinformatics/btz066", "sha256": "sha256:3f718144c7193ae00eb9cccf5c76c6c516db0292661642d37cb76e0a0a997d1e", "bytes": 28680, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/bioinformatics/btz066", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6748729", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE124814", "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=GSE124814", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE124814", "version": null, "note": "The RUV-normalized expression data is available through the Gene Expression Omnibus (GEO; https://www.ncbi.nlm.nih.gov/geo/) and can be accessed via the GSE series number GSE124814. Supplementary data are available at Bioinformatics online.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The RUV-normalized expression data is available through the Gene Expression Omnibus (GEO; https://www.ncbi.nlm.nih.gov/geo/) and can be accessed via the GSE series number GSE124814. Supplementary data are available at Bioinformatics online.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": 0, "group_sizes": null, "group_sizes_basis": null, "platform": "", "taxon": "Homo sapiens", "title": "Batch-normalization of cerebellar and medulloblastoma gene expression datasets utilizing empirically defined negative control genes", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE124814 not downloaded", "asset:data:geo:GSE124814 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "Removal of Unwanted Variation (RUV), specifically the naiveRandRUV method", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Batch effect correction was performed via the naiveRandRUV method (Jacob et al., 2016), employing the NCGs and a range of combinations of regularization parameters."}}], "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 (Removal of Unwanted Variation (RUV), specifically the naiveRandRUV method), 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": ["GSE124814"], "resolved_accessions": ["GSE124814"], "statements": ["The RUV-normalized expression data is available through the Gene Expression Omnibus (GEO; https://www.ncbi.nlm.nih.gov/geo/) and can be accessed via the GSE series number GSE124814. Supplementary data are available at Bioinformatics online."], "basis": "The paper names GSE124814 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:30715209", "data:geo:GSE124814"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE124814"]}, "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": "2026-10-31T18:14:01Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 19809, "completion_tokens": 1881, "cached_tokens": 6664}}, "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:30715209", "type": "paper", "label": "pmid:30715209"}, {"id": "source:pmid:30715209", "type": "manuscript", "label": "PMID 30715209 full text"}, {"id": "data:geo:GSE124814", "type": "dataset", "label": "GEO GSE124814"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:30715209", "type": "paper", "label": "pmid:30715209"}, {"id": "source:pmid:30715209", "type": "manuscript", "label": "PMID 30715209 full text"}, {"id": "data:geo:GSE124814", "type": "dataset", "label": "GEO GSE124814"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-30715209", "type": "extraction", "used": ["source:pmid:30715209"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE124814", "type": "accession_resolution", "used": ["data:geo:GSE124814"], "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:30715209", "parent_hash": "sha256:21c3a988cb105cb626c5159b0c238feaae46b7cddf88d182030cf6fd8bb87526", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE124814 licence not read", "asset:data:geo:GSE124814 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"]}