Gene expression profiling of NUAK kinase overexpression in Drosophila larval muscle development.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:35924094", "kind": "science-record", "revision": 5, "content_hash": "sha256:4a4574d89ec45800c1a89f34449adb91226ff96a402d37228960ee2be54be783", "created_at": "2026-11-01T18:15:01Z", "updated_at": "2026-11-01T22:49:42Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Gene expression profiling of NUAK kinase overexpression in Drosophila larval muscle development.", "doi": "10.1016/j.dib.2022.108482", "pmid": "35924094", "authors": ["David Brooks", "Erika R Geisbrecht"], "journal": "Data in brief", "year": 2022, "abstract": "Signal transduction pathways mediated by kinases control diverse biological outputs at the level of cells and tissues to regulate a diverse array of biological and developmental events. To gain insight into how muscle expression of the evolutionarily conserved NUAK kinase regulates the transcriptional landscape during Drosophila melanogaster development, we performed high-throughput sequencing of RNA from either whole larvae or dissected muscle fillets at the end of larval development. Raw data was generated using the Illumina HiSeq 4000 platform. After trimming and mapping to the Drosophila reference genome, differential gene expression and GO enrichment analysis were completed. Raw data are deposited in the NCBI Gene Expression Ominbus (GEO) repository under GEO accession GSE204894.", "claims": [{"id": "claim-method", "statement": "P-values and log2 fold changes were calculated using the Wald test.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:35924094", "locator": "sections[10] \"Differential gene expression and Gene ontology (GO) analysis\" paragraph 2", "quote": "P-values and log2 fold changes were calculated using the Wald test."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Gene expression profiling of NUAK kinase overexpression in Drosophila larval muscle development (Original data) (NCBI GEO).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:35924094", "locator": "sections[14] \"Data Availability\" paragraph 2", "quote": "Gene expression profiling of NUAK kinase overexpression in Drosophila larval muscle development (Original data) (NCBI GEO)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "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:35924094"], "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:GSE204894"], "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:GSE204894"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:35924094", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2022.108482", "sha256": "sha256:6dbce1941c9ee1ee630e663dcdb265f7d282df07b129eaecd033a7be1e32c381", "bytes": 14223, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2022.108482", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC9340529", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE204894", "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=GSE204894", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE204894", "version": null, "note": "Gene expression profiling of NUAK kinase overexpression in Drosophila larval muscle development (Original data) (NCBI GEO).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Gene expression profiling of NUAK kinase overexpression in Drosophila larval muscle development (Original data) (NCBI GEO).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM6199380", "GSM6199381", "GSM6199382", "GSM6199383", "GSM6199384", "GSM6199385", "GSM6199386", "GSM6199387", "GSM6199388", "GSM6199389", "GSM6199390", "GSM6199391", "GSM6199392", "GSM6199393", "GSM6199394", "GSM6199395", "GSM6199396", "GSM6199397"], "sample_count": 18, "group_sizes": null, "group_sizes_basis": null, "platform": "21306", "taxon": "Drosophila melanogaster", "title": "Gene expression profiling of NUAK kinase overexpression in Drosophila larval muscle development", "resolution_checked_at": "2026-11-01T18:06:43Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE204894 not downloaded", "asset:data:geo:GSE204894 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "deseq2", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "P-values and log2 fold changes were calculated using the Wald test."}}, {"id": "method-2", "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-3", "family": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "GO enrichment"}}], "targets": [], "gaps": ["method.reader_differs_from_extractor"]}, "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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: deseq2."}, "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": ["GSE204894"], "resolved_accessions": ["GSE204894"], "statements": ["Gene expression profiling of NUAK kinase overexpression in Drosophila larval muscle development (Original data) (NCBI GEO)."], "basis": "The paper names GSE204894 in NCBI GEO and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:35924094", "data:geo:GSE204894"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE204894"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T17:58:27Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 5415, "completion_tokens": 878, "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:35924094", "type": "paper", "label": "pmid:35924094"}, {"id": "source:pmid:35924094", "type": "manuscript", "label": "PMID 35924094 full text"}, {"id": "data:geo:GSE204894", "type": "dataset", "label": "GEO GSE204894"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:35924094", "type": "paper", "label": "pmid:35924094"}, {"id": "source:pmid:35924094", "type": "manuscript", "label": "PMID 35924094 full text"}, {"id": "data:geo:GSE204894", "type": "dataset", "label": "GEO GSE204894"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-35924094", "type": "extraction", "used": ["source:pmid:35924094"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE204894", "type": "accession_resolution", "used": ["data:geo:GSE204894"], "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:35924094", "parent_hash": "sha256:97f282e11482c1900dcb1b597190742aaae88abad5936060e182656cd4126e4a", "fork_of": null, "generation": 4}, "gaps": ["asset:data:geo:GSE204894 licence not read", "asset:data:geo:GSE204894 not downloaded", "execution.not_run", "method.reader_differs_from_extractor", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "rna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": [", raw data processing, and data analysis The RNA-seq libraries were sequenced using the Illumina"], "order_basis": "paper_text_order:946", "id": "assay:1"}, {"role": "analysis", "definition_id": "differential_expression", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["P-values and log2 fold changes were calculated using the Wald test."], "order_basis": "consumes_earlier_output", "id": "assay:2"}]}