hCoCena: horizontal integration and analysis of transcriptomics datasets.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:36018233", "kind": "science-record", "revision": 3, "content_hash": "sha256:46b5235df47b5e5d70f3e675c4390904b05215f253b47904b25d1cf8e75f6cc8", "created_at": "2026-11-01T18:15:10Z", "updated_at": "2026-11-01T21:28:43Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "hCoCena: horizontal integration and analysis of transcriptomics datasets.", "doi": "10.1093/bioinformatics/btac589", "pmid": "36018233", "authors": ["Marie Oestreich", "Lisa Holsten", "Shobhit Agrawal", "Kilian Dahm", "Philipp Koch", "Han Jin", "Matthias Becker", "Thomas Ulas"], "journal": "Bioinformatics (Oxford, England)", "year": 2022, "abstract": "MOTIVATION: Transcriptome-based gene co-expression analysis has become a standard procedure for structured and contextualized understanding and comparison of different conditions and phenotypes. Since large study designs with a broad variety of conditions are costly and laborious, extensive comparisons are hindered when utilizing only a single dataset. Thus, there is an increased need for tools that allow the integration of multiple transcriptomic datasets with subsequent joint analysis, which can provide a more systematic understanding of gene co-expression and co-functionality within and across conditions. To make such an integrative analysis accessible to a wide spectrum of users with differing levels of programming expertise it is essential to provide user-friendliness and customizability as well as thorough documentation.\nRESULTS: This article introduces horizontal CoCena (hCoCena: horizontal construction of co-expression networks and analysis), an R-package for network-based co-expression analysis that allows the analysis of a single transcriptomic dataset as well as the joint analysis of multiple datasets. With hCoCena, we provide a freely available, user-friendly and adaptable tool for integrative multi-study or single-study transcriptomics analyses alongside extensive comparisons to other existing tools.\nAVAILABILITY AND IMPLEMENTATION: The hCoCena R-package is provided together with R Markdowns that implement an exemplary analysis workflow including extensive documentation and detailed descriptions of data structures and objects. Such efforts not only make the tool easy to use but also enable the seamless integration of user-written scripts and functions into the workflow, creating a tool that provides a clear design while remaining flexible and highly customizable. The package and additional information including an extensive Wiki are freely available on GitHub: https://github.com/MarieOestreich/hCoCena. The version at the time of writing has been added to Zenodo under the following link: https://doi.org/10.5281/zenodo.6911782.\nSUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.", "claims": [{"id": "claim-method", "statement": "Spearman’s Rank Correlation was used to calculate the pair-wise co-expression values and the cut-off statistics were calculated for 50 cut-off values in the range 0.9 to 1.0 and visualized in the cut-off selection guides (Fig. 2B, Supplementary Fig. S1B).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:36018233", "locator": "sections[9] \"3.1 Integration strategy showcase\" paragraph 3", "quote": "Spearman’s Rank Correlation was used to calculate the pair-wise co-expression values and the cut-off statistics were calculated for 50 cut-off values in the range 0.9 to 1.0 and visualized in the cut-off selection guides (Fig. 2B, Supplementary Fig. S1B)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Supplementary data are available at Bioinformatics online.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:36018233", "locator": "sections[0] \"Abstract\" paragraph 4", "quote": "Supplementary data are available at Bioinformatics online."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "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:36018233"], "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": "blocked", "blocked_on": "data:accession_absent", "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": [], "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": [], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:36018233", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/bioinformatics/btac589", "sha256": "sha256:c3c0e0053da16f5e117ab12721e36a62616054b3a4c8a5fddbbb173be6d04f64", "bytes": 35072, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/bioinformatics/btac589", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC9563699", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "Spearman’s Rank Correlation", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Spearman’s Rank Correlation was used to calculate the pair-wise co-expression values and the cut-off statistics were calculated for 50 cut-off values in the range 0.9 to 1.0 and visualized in the cut-off selection guides (Fig. 2B, Supplementary Fig. S1B)."}}], "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": "data", "blocked_on": "data:accession_absent", "axes": {"method": {"tier": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (Spearman’s Rank Correlation), 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": "R4", "reachable": false, "accessions": [], "resolved_accessions": [], "statements": ["Supplementary data are available at Bioinformatics online."], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:36018233"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:None"]}, "gaps": ["data:accession_absent"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T18:01:45Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 9058, "completion_tokens": 852, "cached_tokens": 256}}, "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:36018233", "type": "paper", "label": "pmid:36018233"}, {"id": "source:pmid:36018233", "type": "manuscript", "label": "PMID 36018233 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:36018233", "type": "paper", "label": "pmid:36018233"}, {"id": "source:pmid:36018233", "type": "manuscript", "label": "PMID 36018233 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-36018233", "type": "extraction", "used": ["source:pmid:36018233"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-None", "type": "accession_resolution", "used": ["data:geo:None"], "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:36018233", "parent_hash": "sha256:2fca517aaa68992511556b1370d960cfc0e39641d3afcce8f0b52ab93733f01b", "fork_of": null, "generation": 2}, "gaps": ["execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"]}