On the impact of batch effect correction in TCGA isomiR expression data.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34316700", "kind": "science-record", "revision": 6, "content_hash": "sha256:92348a2adc8108a383b2397390f290ce7062063ff0cd056f391071857624e0ee", "created_at": "2026-11-01T15:41:45Z", "updated_at": "2026-11-01T21:25:52Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "On the impact of batch effect correction in TCGA isomiR expression data.", "doi": "10.1093/narcan/zcab007", "pmid": "34316700", "authors": ["Susanne Ibing", "Birgitta E Michels", "Moritz Mosdzien", "Helen R Meyer", "Lars Feuerbach", "Cindy Körner"], "journal": "NAR cancer", "year": 2021, "abstract": "MicroRNAs (miRNAs) are small non-coding RNAs with diverse functions in post-transcriptional regulation of gene expression. Sequence and length variants of miRNAs are called isomiRs and can exert different functions compared to their canonical counterparts. The Cancer Genome Atlas (TCGA) provides isomiR-level expression data for patients of various cancer entities collected in a multi-center approach over several years. However, the impact of batch effects within individual cohorts has not been systematically investigated and corrected for before. Therefore, the aim of this study was to identify relevant cohort-specific batch variables and generate batch-corrected isomiR expression data for 16 TCGA cohorts. The main batch variables included sequencing platform, plate, sample purity and sequencing depth. Platform bias was related to certain length and sequence features of individual recurrently affected isomiRs. Furthermore, significant downregulation of reported tumor suppressive isomiRs in lung tumor tissue compared to normal samples was only observed after batch correction, highlighting the importance of working with corrected data. Batch-corrected datasets for all cohorts including quality control are provided as supplement. In summary, this study reveals that batch effects present in the TCGA dataset might mask biologically relevant effects and provides a valuable resource for research on isomiRs in cancer (accessible through GEO: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE164767).", "claims": [{"id": "claim-method", "statement": "To assess the effect of the batch correction on differential expression between the platforms statistically, two-sided t-tests were performed comparing log2 transformed isomiR expression values for each isomiR on the two platforms. P-values were FDR corrected for multiple testing.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34316700", "locator": "sections[7] \"Assessment of systematic sequencing bias introduced by different sequencing platforms\" paragraph 3", "quote": "To assess the effect of the batch correction on differential expression between the platforms statistically, two-sided t-tests were performed comparing log2 transformed isomiR expression values for each isomiR on the two platforms. P-values were FDR corrected for multiple testing."}], "state": "complete"}, {"id": "claim-data-access", "statement": "All data are publicly available and accessible as described in the ‘Data download and pre-processing’ section. The batch corrected data have been deposited in NCBI’s Gene Expression Omnibus (57) and are accessible through GEO Series accession number GSE164767 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE164767). R code for data download, pre-processing, annotation and batch correction as well as for the implementation of described analyses and main figures are publicly available on GitHub (https://github.com/susibing/BatchCor_TCGAisomiR).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34316700", "locator": "sections[19] \"DATA AVAILABILITY\" paragraph 2", "quote": "All data are publicly available and accessible as described in the ‘Data download and pre-processing’ section. The batch corrected data have been deposited in NCBI’s Gene Expression Omnibus (57) and are accessible through GEO Series accession number GSE164767 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE164767). R code for data download, pre-processing, annotation and batch correction as well as for the implementation of described analyses and main figures are publicly available on GitHub (https://github.com/susibing/BatchCor_TCGAisomiR)."}], "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:34316700"], "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:GSE164767"], "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:GSE164767"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:34316700", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/narcan/zcab007", "sha256": "sha256:0dfb15383200a8006ade7f29ffc2436e600ba7b493f8e943e74dc7d5c46dc40c", "bytes": 78255, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/narcan/zcab007", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8210273", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE164767", "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=GSE164767", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE164767", "version": null, "note": "All data are publicly available and accessible as described in the ‘Data download and pre-processing’ section. The batch corrected data have been deposited in NCBI’s Gene Expression Omnibus (57) and are accessible through GEO Series accession number GSE164767 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE164767). R code for data download, pre-processing, annotation and batch correction as well as for the implementation of described analyses and main figures are publicly available on GitHub (https://github.com/susibing/BatchCor_TCGAisomiR).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data are publicly available and accessible as described in the ‘Data download and pre-processing’ section. The batch corrected data have been deposited in NCBI’s Gene Expression Omnibus (57) and are accessible through GEO Series accession number GSE164767 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE164767). R code for data download, pre-processing, annotation and batch correction as well as for the implementation of described analyses and main figures are publicly available on GitHub (https://github.com/susibing/BatchCor_TCGAisomiR).", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": 0, "group_sizes": null, "group_sizes_basis": null, "platform": "", "taxon": "Homo sapiens", "title": "Annotation- and Batch Effect Correction in TCGA IsomiR Expression Data [Third-party re-analysis]", "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:34316700:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:380903cda2fa7a8d77fc7c9bc35431d717e435bbbe4f599d5ca26d6192f172f1", "bytes": 1798, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#tbl1", "version": null, "note": "Isoform expression quantification data from 16 different TCGA projects", "structure": {"pmcid": "PMC8210273", "section_index": 3, "section_title": "Data download and pre-processing", "row_count": 17, "column_count": 10}, "table": {"label": "Table 1.", "caption": "Isoform expression quantification data from 16 different TCGA projects", "rows": [["Project", "Abbrev.", "Primary solid tumor", "Recurrent/addit. tumor", "Metastatic tumor", "Solid tissue normal", "Solid tissue normal (same plate as matched tumor sample)", "Batch cor. tumor samples", "Batch cor. tumor + normal samples", "Expression comparison between sequencing platforms"], ["Urothelial bladder carcinoma", "BLCA", "417", "0", "1", "19", "19", "x", "x", ""], ["Breast invasive carcinoma", "BRCA", "1096 (1051)", "0", "7", "104 (103)", "86", "x", "x", "x"], ["Cervical squamous cell carcinoma and endocervical adenocarcinoma", "CESC", "307", "0", "2", "3", "3", "x", "", ""], ["Colon adenocarcinoma", "COAD", "455 (404)", "1", "1", "8 (0)", "0", "x", "", "x"], ["Head-neck squamous cell carcinoma", "HNSC", "523 (517)", "0", "2", "44", "42", "x", "x", "x"], ["Kidney renal clear cell carcinoma", "KIRC", "544 (535)", "1", "0", "71", "68", "x", "x", "x"], ["Cervical kidney renal papillary cell carcinoma", "KIRP", "291", "0", "0", "34", "33", "x", "x", ""], ["Low grade glioma", "LGG", "512 (510)", "18", "0", "0", "0", "x", "", ""], ["Liver hepatocellular carcinoma", "LIHC", "372 (371)", "3", "0", "50", "48", "x", "x", ""], ["Lung adenocarcinoma", "LUAD", "519 (506)", "2", "0", "46 (40)", "26", "x", "x", "x"], ["Lung squamous cell carcinoma", "LUSC", "478 (456)", "0", "0", "45", "36", "x", "x", "x"], ["Ovarian cancer", "OV", "491 (452)", "8 (7)", "0", "0", "0", "x", "", ""], ["Prostate adenocarcinoma", "PRAD", "498", "0", "1", "52", "51", "x", "x", ""], ["Stomach adenocarcinoma", "STAD", "446 (432)", "0", "0", "45", "41", "x", "x", "x"], ["Thyroid cancer", "THCA", "506 (504)", "0", "8", "59", "59", "x", "x", ""], ["Uterine corpus endometrial carcinoma", "UCEC", "545 (512)", "1", "0", "33", "18", "x", "x", "x"]], "row_count": 17, "column_count": 10, "numeric_cells": 80, "header_rows": 1, "locator": "section[3]/table-wrap[1]#tbl1"}}], "gaps": ["asset:data:geo:GSE164767 not downloaded", "asset:data:geo:GSE164767 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "principal_component_analysis", "specific": "pca", "label": "Principal component analysis", "dsl_operations": ["pca_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["wide_numeric_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "PCA"}}, {"id": "method-2", "family": null, "specific": null, "label": "Two-sided t-tests with false discovery rate (FDR) correction for multiple testing", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "To assess the effect of the batch correction on differential expression between the platforms statistically, two-sided t-tests were performed comparing log2 transformed isomiR expression values for each isomiR on the two platforms. P-values were FDR corrected for multiple testing."}}], "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": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["pca_fit"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: pca."}, "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": ["GSE164767"], "resolved_accessions": ["GSE164767"], "statements": ["All data are publicly available and accessible as described in the ‘Data download and pre-processing’ section. The batch corrected data have been deposited in NCBI’s Gene Expression Omnibus (57) and are accessible through GEO Series accession number GSE164767 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE164767). R code for data download, pre-processing, annotation and batch correction as well as for the implementation of described analyses and main figures are publicly available on GitHub (https://github.com/susibing/BatchCor_TCGAisomiR)."], "basis": "The paper names GSE164767 in NCBI Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["pca_fit"], "assets": ["source:pmid:34316700", "data:geo:GSE164767", "asset:table:pmid:34316700:1"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE164767"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:32:51Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 54409, "completion_tokens": 1866, "cached_tokens": 793}}, "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:34316700", "type": "paper", "label": "pmid:34316700"}, {"id": "source:pmid:34316700", "type": "manuscript", "label": "PMID 34316700 full text"}, {"id": "data:geo:GSE164767", "type": "dataset", "label": "GEO GSE164767"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34316700", "type": "paper", "label": "pmid:34316700"}, {"id": "source:pmid:34316700", "type": "manuscript", "label": "PMID 34316700 full text"}, {"id": "data:geo:GSE164767", "type": "dataset", "label": "GEO GSE164767"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34316700", "type": "extraction", "used": ["source:pmid:34316700"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE164767", "type": "accession_resolution", "used": ["data:geo:GSE164767"], "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:34316700", "parent_hash": "sha256:179a9290da6c6fa3ca39af3ec3a9f44b951600d82972dce67bd2268a0d94eaf1", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:GSE164767 licence not read", "asset:data:geo:GSE164767 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "principal_component_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["pca_fit"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["PCA"], "order_basis": "analysis_only", "id": "assay:1"}]}