PLANEX: the plant co-expression database.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:23688397", "kind": "science-record", "revision": 6, "content_hash": "sha256:5e985f02e9bf9c1c0d7bb6743a2131d7837399af4a8889bba664c637504cfa99", "created_at": "2026-11-01T15:40:03Z", "updated_at": "2026-11-01T21:19:41Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "PLANEX: the plant co-expression database.", "doi": "10.1186/1471-2229-13-83", "pmid": "23688397", "authors": ["Won Cheol Yim", "Yongbin Yu", "Kitae Song", "Cheol Seong Jang", "Byung-Moo Lee"], "journal": "BMC plant biology", "year": 2013, "abstract": "BACKGROUND: The PLAnt co-EXpression database (PLANEX) is a new internet-based database for plant gene analysis. PLANEX (http://planex.plantbioinformatics.org) contains publicly available GeneChip data obtained from the Gene Expression Omnibus (GEO) of the National Center for Biotechnology Information (NCBI). PLANEX is a genome-wide co-expression database, which allows for the functional identification of genes from a wide variety of experimental designs. It can be used for the characterization of genes for functional identification and analysis of a gene's dependency among other genes. Gene co-expression databases have been developed for other species, but gene co-expression information for plants is currently limited.\nDESCRIPTION: We constructed PLANEX as a list of co-expressed genes and functional annotations for Arabidopsis thaliana, Glycine max, Hordeum vulgare, Oryza sativa, Solanum lycopersicum, Triticum aestivum, Vitis vinifera and Zea mays. PLANEX reports Pearson's correlation coefficients (PCCs; r-values) that distribute from a gene of interest for a given microarray platform set corresponding to a particular organism. To support PCCs, PLANEX performs an enrichment test of Gene Ontology terms and Cohen's Kappa value to compare functional similarity for all genes in the co-expression database. PLANEX draws a cluster network with co-expressed genes, which is estimated using the k-mean method. To construct PLANEX, a variety of datasets were interpreted by the IBM supercomputer Advanced Interactive eXecutive (AIX) in a supercomputing center.\nCONCLUSION: PLANEX provides a correlation database, a cluster network and an interpretation of enrichment test results for eight plant species. A typical co-expressed gene generates lists of co-expression data that contain hundreds of genes of interest for enrichment analysis. Also, co-expressed genes can be identified and cataloged in terms of comparative genomics by using the 'Co-expression gene compare' feature. This type of analysis will help interpret experimental data and determine whether there is a common term among genes of interest.", "claims": [{"id": "claim-method", "statement": "Cohen’s Kappa statistics were used to compare co-expression data between species [34].", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:23688397", "locator": "sections[8] \"Comparative analysis of co-expressed gene sets\" paragraph 2", "quote": "Cohen’s Kappa statistics were used to compare co-expression data between species [34]."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The serve is freely available athttp://planex.plantbioinformatics.org", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:23688397", "locator": "sections[14] \"Availability and requirements\" paragraph 7", "quote": "The serve is freely available athttp://planex.plantbioinformatics.org"}], "state": "complete"}, {"id": "claim-target-result", "statement": "PLANEX uses Pearson’s correlation coefficients to assess gene co-expression, with source data obtained from publicly available GeneChip datasets in GEO.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:23688397", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "PLANEX (http://planex.plantbioinformatics.org) contains publicly available GeneChip data obtained from the Gene Expression Omnibus (GEO) of the National Center for Biotechnology Information (NCBI)."}, {"asset": "source:pmid:23688397", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "PLANEX reports Pearson’s correlation coefficients (PCCs; r-values) that distribute from a gene of interest for a given microarray platform set corresponding to a particular organism."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "PLANEX uses Pearson’s correlation coefficients to assess gene co-expression, with source data obtained from publicly available GeneChip datasets in GEO.", "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:23688397"], "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:23688397", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/1471-2229-13-83", "sha256": "sha256:19ee2fdac170dde3cf933745f082552e22d26971ac43f58e270fa28f77f97793", "bytes": 23772, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/1471-2229-13-83", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC3663717", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "asset:table:pmid:23688397:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:3102210024eeeeb56812a4760a166f640ae4b5de9ee029f64890fb667b8c1b1c", "bytes": 770, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#T1", "version": null, "note": "Co-expression data information contained in PLANEX", "structure": {"pmcid": "PMC3663717", "section_index": 3, "section_title": "Expression data", "row_count": 9, "column_count": 5}, "table": {"label": "Table 1", "caption": "Co-expression data information contained in PLANEX", "rows": [["Species", "Affymetrix GeneChip", "Number of microarray slides", "Micorarray platform", "Source database of coding sequence"], ["Arabidopsis thaliana", "ATH1", "5502", "GPL198", "Phytozome1"], ["Glycine max", "Soybean", "3080", "GPL4592", "Phytozome"], ["Hordeum vulgare", "Barley1", "738", "GPL1340", "DFCI2"], ["Oryza sativa", "Rice", "884", "GPL2025", "Phytozome"], ["Solanum lycopersicum", "Tomato", "253", "GPL4741", "Phytozome"], ["Triticum aestivum", "Wheat", "451", "GPL3802", "DFCI"], ["Vitis vinifera", "Vitis vinifera", "738", "GPL1320", "Phytozome"], ["Zea mays", "Maize", "379", "GPL4032", "Phytozome"]], "row_count": 9, "column_count": 5, "numeric_cells": 16, "header_rows": 1, "locator": "section[3]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:23688397:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c3189ea120150f160cf17e55fd032800a249bd514b144eb0b93d3e7a53176234", "bytes": 618, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[4]/table-wrap[1]#T2", "version": null, "note": "The thresholds for co-expression values", "structure": {"pmcid": "PMC3663717", "section_index": 4, "section_title": "Implementation", "row_count": 9, "column_count": 4}, "table": {"label": "Table 2", "caption": "The thresholds for co-expression values", "rows": [["Species", "No. of probes", "Positive1", "Negative2"], ["Arabidopsis thaliana", "22,810", "0.585", "−0.465"], ["Hordeum vulgare", "22,840", "0.68", "−0.625"], ["Oryza sativa", "57,381", "0.646", "−0.535"], ["Triticum aestivum", "61,290", "0.686", "−0.635"], ["Zea mays", "17,734", "0.835", "−0.775"], ["Glycine max", "61,170", "0.645", "−0.505"], ["Vitis vinifera", "16,602", "0.715", "−0.715"], ["Solanum lycopersicum", "10,209", "0.775", "−0.705"]], "row_count": 9, "column_count": 4, "numeric_cells": 24, "header_rows": 1, "locator": "section[4]/table-wrap[1]#T2"}}], "gaps": []}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "correlation_analysis", "specific": "pearson", "label": "Correlation analysis", "dsl_operations": ["pearson_r"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["paired_numeric_columns"], "evidence": {"score": 0.7, "band": "medium", "quote": "Pearson's correlation"}}, {"id": "method-2", "family": null, "specific": null, "label": "Cohen’s Kappa statistics", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Cohen’s Kappa statistics were used to compare co-expression data between species [34]."}}], "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": "R1", "expressible": true, "required_operations": ["pearson_r"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: pearson."}, "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": ["The serve is freely available athttp://planex.plantbioinformatics.org"], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": ["pearson_r"], "assets": ["source:pmid:23688397", "asset:table:pmid:23688397:1", "asset:table:pmid:23688397:2"], "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": "2026-10-31T18:21:23Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 45104, "completion_tokens": 6543, "cached_tokens": 34374}}, "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:23688397", "type": "paper", "label": "pmid:23688397"}, {"id": "source:pmid:23688397", "type": "manuscript", "label": "PMID 23688397 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:23688397", "type": "paper", "label": "pmid:23688397"}, {"id": "source:pmid:23688397", "type": "manuscript", "label": "PMID 23688397 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-23688397", "type": "extraction", "used": ["source:pmid:23688397"], "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:23688397", "parent_hash": "sha256:11239ac6c5862ee2c528ef574fe6ee3917c91b5f4758118f91e95322c3826820", "fork_of": null, "generation": 5}, "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"], "assays": [{"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["stribute from a gene of interest for a given microarray platform set corresponding to a particular o", "y Material Additional file 1: Table S1Public microarray data information in PLANEX.Click here for fi"], "order_basis": "paper_text_order:1079", "id": "assay:1"}, {"role": "analysis", "definition_id": "correlation_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["pearson_r"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["Pearson's correlation"], "order_basis": "consumes_earlier_output", "id": "assay:2"}]}