GeneFriends: gene co-expression databases and tools for humans and model organisms.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:36454018", "kind": "science-record", "revision": 3, "content_hash": "sha256:d337166038903d9ef4b73c314f19c57c019a547e3f43aca9c95c8685b49fdfb2", "created_at": "2026-11-01T19:00:56Z", "updated_at": "2026-11-01T22:08:13Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "GeneFriends: gene co-expression databases and tools for humans and model organisms.", "doi": "10.1093/nar/gkac1031", "pmid": "36454018", "authors": ["Priyanka Raina", "Rodrigo Guinea", "Kasit Chatsirisupachai", "Inês Lopes", "Zoya Farooq", "Cristina Guinea", "Csaba-Attila Solyom", "João Pedro de Magalhães"], "journal": "Nucleic acids research", "year": 2023, "abstract": "Gene co-expression analysis has emerged as a powerful method to provide insights into gene function and regulation. The rapid growth of publicly available RNA-sequencing (RNA-seq) data has created opportunities for researchers to employ this abundant data to help decipher the complexity and biology of genomes. Co-expression networks have proven effective for inferring the relationship between the genes, for gene prioritization and for assigning function to poorly annotated genes based on their co-expressed partners. To facilitate such analyses we created previously an online co-expression tool for humans and mice entitled GeneFriends. To continue providing a valuable tool to the scientific community, we have now updated the GeneFriends database and website. Here, we present the new version of GeneFriends, which includes gene and transcript co-expression networks based on RNA-seq data from 46 475 human and 34 322 mouse samples. The new database also encompasses tissue-specific gene co-expression networks for 20 human and 21 mouse tissues, dataset-specific gene co-expression maps based on TCGA and GTEx projects and gene co-expression networks for additional seven model organisms (fruit fly, zebrafish, worm, rat, yeast, cow and chicken). GeneFriends is freely available at http://www.genefriends.org/.", "claims": [{"id": "claim-method", "statement": "We compared the number of cancer driver genes presented in the top 5% co-expressed genes of each cancer driver gene between GTEx and TCGA using a two-sided Wilcoxon rank-sum test.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:36454018", "locator": "sections[20] \"Comparison of GTEx and TCGA database\" paragraph 2", "quote": "We compared the number of cancer driver genes presented in the top 5% co-expressed genes of each cancer driver gene between GTEx and TCGA using a two-sided Wilcoxon rank-sum test."}], "state": "complete"}, {"id": "claim-data-access", "statement": "All gene and transcript co-expression maps are available for download at http://www.genefriends.org (https://www.dropbox.com/sh/jz0z3z8fuhx70fx/AACt3CUvyro2cEETVBoWwIrNa?dl=0). Additionally, the code can be found in GitHub (https://github.com/maglab/genefriends_v5).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:36454018", "locator": "sections[24] \"DATA AVAILABILITY\" paragraph 2", "quote": "All gene and transcript co-expression maps are available for download at http://www.genefriends.org (https://www.dropbox.com/sh/jz0z3z8fuhx70fx/AACt3CUvyro2cEETVBoWwIrNa?dl=0). Additionally, the code can be found in GitHub (https://github.com/maglab/genefriends_v5)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The updated GeneFriends database provides gene and transcript co-expression networks based on 46 475 human and 34 322 mouse RNA-seq samples, together with tissue-, dataset-, and species-specific networks.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:36454018", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Here, we present the new version of GeneFriends, which includes gene and transcript co-expression networks based on RNA-seq data from 46 475 human and 34 322 mouse samples."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "The updated GeneFriends database provides gene and transcript co-expression networks based on 46 475 human and 34 322 mouse RNA-seq samples, together with tissue-, dataset-, and species-specific networks.", "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:36454018"], "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": "blocked", "blocked_on": "method:group_comparison_wilcoxon", "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:run_analysis blocked on method:group_comparison_wilcoxon", "step:obtain_source_data blocked on data:accession_absent"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:36454018", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/nar/gkac1031", "sha256": "sha256:7fdbe7b21c1e367cac9a015f8e543ce4a933e3d3855cf16235fc166ded8c32a1", "bytes": 55310, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/nar/gkac1031", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC9825523", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "group_comparison", "specific": "wilcoxon", "label": "Group comparison", "dsl_operations": [], "missing_operations": ["group_comparison_wilcoxon"], "expressible": false, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "We compared the number of cancer driver genes presented in the top 5% co-expressed genes of each cancer driver gene between GTEx and TCGA using a two-sided Wilcoxon rank-sum test."}}, {"id": "method-2", "family": "contingency_analysis", "specific": "fisher_exact", "label": "Categorical (contingency table) analysis", "dsl_operations": ["contingency_table", "chi_square_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["categorical_cross_tabulation"], "evidence": {"score": 0.8, "band": "high", "quote": "Fisher's exact"}}], "targets": [], "gaps": ["method.group_comparison_wilcoxon"]}, "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": "R1", "expressible": false, "required_operations": [], "missing_operations": ["group_comparison_wilcoxon"], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: wilcoxon."}, "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": ["All gene and transcript co-expression maps are available for download at http://www.genefriends.org (https://www.dropbox.com/sh/jz0z3z8fuhx70fx/AACt3CUvyro2cEETVBoWwIrNa?dl=0). Additionally, the code can be found in GitHub (https://github.com/maglab/genefriends_v5)."], "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:36454018"], "steps": []}, "must_build": {"dsl_operations": [{"operation": "group_comparison_wilcoxon", "unlocks_papers": null, "priority": null}], "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": "2026-11-01T18:17:47Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 15756, "completion_tokens": 2266, "cached_tokens": 264}}, "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:36454018", "type": "paper", "label": "pmid:36454018"}, {"id": "source:pmid:36454018", "type": "manuscript", "label": "PMID 36454018 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:36454018", "type": "paper", "label": "pmid:36454018"}, {"id": "source:pmid:36454018", "type": "manuscript", "label": "PMID 36454018 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-36454018", "type": "extraction", "used": ["source:pmid:36454018"], "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:36454018", "parent_hash": "sha256:9c119236c00314a4744b2dfb4d50d7ff54b93c8a9b507d9b5d847b2bb1972777", "fork_of": null, "generation": 2}, "gaps": ["execution.not_run", "method.group_comparison_wilcoxon", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent", "step:run_analysis blocked on method:group_comparison_wilcoxon"], "assays": [{"role": "data_generation", "definition_id": "animal_model", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["on RNA-seq data from 46 475 human and 34 322 mouse samples. The new database also encompasses t", "e co-expression networks for 20 human and 21 mouse tissues, dataset-specific gene co-expression", "model organisms (fruit fly, zebrafish, worm, rat, yeast, cow and chicken). GeneFriends is fre", "bution of dN/dS scores between the human and mouse co-expression database. The median and inter"], "order_basis": "paper_text_order:965", "id": "assay:1"}, {"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["We compared the number of cancer driver genes presented in the top 5% co-expressed genes of each cancer driver gene between GTEx and TCGA using a two-sided Wilcoxon rank-sum test."], "order_basis": "consumes_earlier_output", "id": "assay:2"}]}