StCoExpNet: a global co-expression network analysis facilitates identifying genes underlying agronomic traits in potatoes.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:38622429", "kind": "science-record", "revision": 2, "content_hash": "sha256:3c21217844c401435e29a63257982e5793d85a9b56986a76ad56fb5256030dd3", "created_at": "2026-11-01T19:20:36Z", "updated_at": "2026-11-01T21:32:56Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "StCoExpNet: a global co-expression network analysis facilitates identifying genes underlying agronomic traits in potatoes.", "doi": "10.1007/s00299-024-03201-2", "pmid": "38622429", "authors": ["Venkata Suresh Bonthala", "Benjamin Stich"], "journal": "Plant cell reports", "year": 2024, "abstract": "KEY MESSAGE: We constructed a gene expression atlas and co-expression network for potatoes and identified several novel genes associated with various agronomic traits. This resource will accelerate potato genetics and genomics research. Potato (Solanum tuberosum L.) is the world's most crucial non-cereal food crop and ranks third in food production after wheat and rice. Despite the availability of several potato transcriptome datasets at public databases like NCBI SRA, an effort has yet to be put into developing a global transcriptome atlas and a co-expression network for potatoes. The objectives of our study were to construct a global expression atlas for potatoes using publicly available transcriptome datasets, identify housekeeping and tissue-specific genes, construct a global co-expression network and identify co-expression clusters, investigate the transcriptional complexity of genes involved in various essential biological processes related to agronomic traits, and provide a web server (StCoExpNet) to easily access the newly constructed expression atlas and co-expression network to investigate the expression and co-expression of genes of interest. In this study, we used data from 2299 publicly available potato transcriptome samples obtained from 15 different tissues to construct a global transcriptome atlas. We found that roughly 87% of the annotated genes exhibited detectable expression in at least one sample. Among these, we identified 281 genes with consistent and stable expression levels, indicating their role as housekeeping genes. Conversely, 308 genes exhibited marked tissue-specific expression patterns. We exemplarily linked some co-expression clusters to important agronomic traits of potatoes, such as self-incompatibility, anthocyanin biosynthesis, tuberization, and defense responses against multiple pathogens. The dataset compiled here constitutes a new resource (StCoExpNet), which can be accessed at https://stcoexpnet.julius-kuehn.de . This transcriptome atlas and the co-expression network will accelerate potato genetics and genomics research.", "claims": [{"id": "claim-method", "statement": "We constructed a Pearson correlation coefficient (PCC) based co-expression network for all genes expressed in at least one transcriptome library with a TPM of 1 using the pcc.py script of LSTrAP v1.3 (Goh and Mutwil 2021).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:38622429", "locator": "sections[11] \"Network reconstruction, module detection and gene ontology enrichment\" paragraph 2", "quote": "We constructed a Pearson correlation coefficient (PCC) based co-expression network for all genes expressed in at least one transcriptome library with a TPM of 1 using the pcc.py script of LSTrAP v1.3 (Goh and Mutwil 2021)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets analyzed during the current study are available in Supplementary Information. The interactive gene expression atlas and co-expression network are available at https://stcoexpnet.julius-kuehn.de.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:38622429", "locator": "sections[38] \"Data availability\" paragraph 2", "quote": "The datasets analyzed during the current study are available in Supplementary Information. The interactive gene expression atlas and co-expression network are available at https://stcoexpnet.julius-kuehn.de."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The study constructed a potato gene-expression atlas and co-expression network from 2,299 publicly available RNA-Seq samples spanning 15 tissues.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:38622429", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "In this study, we used data from 2299 publicly available potato transcriptome samples obtained from 15 different tissues to construct a global transcriptome atlas."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "The study constructed a potato gene-expression atlas and co-expression network from 2,299 publicly available RNA-Seq samples spanning 15 tissues.", "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:38622429"], "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:38622429", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1007/s00299-024-03201-2", "sha256": "sha256:376239a441f74e0cc778b3ebc5747d08deb9cfbb629ffd9415f5641e7cfa9405", "bytes": 95784, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1007/s00299-024-03201-2", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC11018665", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "complete", "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": 1.0, "band": "verbatim", "quote": "We constructed a Pearson correlation coefficient (PCC) based co-expression network for all genes expressed in at least one transcriptome library with a TPM of 1 using the pcc.py script of LSTrAP v1.3 (Goh and Mutwil 2021)."}}, {"id": "method-2", "family": "clustering", "specific": "hierarchical", "label": "Clustering", "dsl_operations": ["hierarchical_cluster"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["feature_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "hierarchical clustering"}}], "targets": [], "gaps": []}, "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 datasets analyzed during the current study are available in Supplementary Information. The interactive gene expression atlas and co-expression network are available at https://stcoexpnet.julius-kuehn.de."], "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:38622429"], "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": "2026-11-01T19:15:46Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 26637, "completion_tokens": 1701, "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:38622429", "type": "paper", "label": "pmid:38622429"}, {"id": "source:pmid:38622429", "type": "manuscript", "label": "PMID 38622429 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:38622429", "type": "paper", "label": "pmid:38622429"}, {"id": "source:pmid:38622429", "type": "manuscript", "label": "PMID 38622429 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-38622429", "type": "extraction", "used": ["source:pmid:38622429"], "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:38622429", "parent_hash": "sha256:7119437630cbb3470af947b1bb33394efa12a4b54887de60ef075acf2d0f6792", "fork_of": null, "generation": 1}, "gaps": ["execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"], "assays": [{"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": 1.0, "evidence": ["We constructed a Pearson correlation coefficient (PCC) based co-expression network for all genes expressed in at least one transcriptome library with a TPM of 1 using the pcc.py script of LSTrAP v1.3 (Goh and Mutwil 2021)."], "order_basis": "analysis_only", "id": "assay:1"}]}