RNA-Seq data analysis reveals novel nonsense mutations in the NPR3 gene leading to the progression of intellectual disability disorder.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:38765165", "kind": "science-record", "revision": 5, "content_hash": "sha256:e6812738947521e75a4f8dfd38c7b7985f280314d74e53ff49df4b2d7cbb348f", "created_at": "2026-11-01T19:20:43Z", "updated_at": "2026-11-01T22:54:20Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "RNA-Seq data analysis reveals novel nonsense mutations in the NPR3 gene leading to the progression of intellectual disability disorder.", "doi": "10.1016/j.heliyon.2024.e30755", "pmid": "38765165", "authors": ["Prekshi Garg", "Farrukh Jamal", "Prachi Srivastava"], "journal": "Heliyon", "year": 2024, "abstract": "Intellectual disability (ID) is a progressive disorder that affects around 1-3% of the world's population. The heterogeneity of intellectual disability makes it difficult to diagnose as a complete disease. Genetic factors and major mutations play a noticeable role in the development and progression of ID. There is a high need to explore novel variants that may lead to new insights into the progressive aspects of ID. In the current course of study, 31 samples of ID from different studies available on GEO (GSE77742, GSE74263, GSE90682, GSE98476, GSE108887, GSE145710, and PRJEB21964) datasets were taken for the study. These datasets were analyzed for differential gene expression and single nucleotide polymorphism (SNPs). The SNPs of high impact were compared with the differentially expressed genes. Comparison leads to the identification of the priority gene ie NPR3 gene. The identified priority gene further was evaluated for the effect of the mutation using a Mutation Taster. Structure comparison analysis of the wild and mutated proteins of the NPR3 gene was further carried out by UCSF Chimera. Structural analysis reveals the anomalies in protein expression affecting the regulations of the NPR3 gene. These findings identified a novel nonsense mutation (E222*) in the downregulated NPR3 gene that leads to anomalies in the regulation of its protein expression. This missense mutation reveals a major role in causing ID. Our study concludes that the decrease in the expression of the NPR3 gene causes delayed sensory, motor, and physiological functions of the human brain leading to neurodevelopmental delay that causes ID.", "claims": [{"id": "claim-method", "statement": "The genes that were differentially expressed in the patient sample as compared to the control sample were analyzed using the DESeq2 [31] package of R Studio [32].", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:38765165", "locator": "sections[5] \"Differential gene expression analysis\" paragraph 2", "quote": "The genes that were differentially expressed in the patient sample as compared to the control sample were analyzed using the DESeq2 [31] package of R Studio [32]."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The data used in the present study is available in the BioProject and GEO database of NCBI (www.ncbi.nlm.nih.gov). The accession ID of the data used is provided in the result section of the manuscript.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:38765165", "locator": "sections[20] \"Data availability statement\" paragraph 2", "quote": "The data used in the present study is available in the BioProject and GEO database of NCBI (www.ncbi.nlm.nih.gov). The accession ID of the data used is provided in the result section of the manuscript."}], "state": "complete"}, {"id": "claim-target-result", "statement": "These findings identified a novel nonsense mutation (E222*) in the downregulated NPR3 gene that leads to anomalies in the regulation of its protein expression.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:38765165", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "These findings identified a novel nonsense mutation (E222*) in the downregulated NPR3 gene that leads to anomalies in the regulation of its protein expression."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "These findings identified a novel nonsense mutation (E222*) in the downregulated NPR3 gene that leads to anomalies in the regulation of its protein expression.", "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:38765165"], "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:GSE108887"], "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:GSE108887"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:38765165", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.heliyon.2024.e30755", "sha256": "sha256:7bf67eedaa5a5e4a380bf33dbfc787a364c6c3bcc5e5f564eff701c262d4bc17", "bytes": 42564, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.heliyon.2024.e30755", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC11101858", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE108887", "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=GSE108887", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE108887", "version": null, "note": "The data used in the present study is available in the BioProject and GEO database of NCBI (www.ncbi.nlm.nih.gov). The accession ID of the data used is provided in the result section of the manuscript.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data used in the present study is available in the BioProject and GEO database of NCBI (www.ncbi.nlm.nih.gov). The accession ID of the data used is provided in the result section of the manuscript.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2915456", "GSM2915457", "GSM2915458", "GSM2915459", "GSM2915460", "GSM2915461", "GSM2915462", "GSM2915463", "GSM2915464", "GSM2915465", "GSM2915466", "GSM2915467"], "sample_count": 12, "group_sizes": null, "group_sizes_basis": null, "platform": "16791", "taxon": "Homo sapiens", "title": "Transcriptome analysis of intellectual disability patients with mutation in transcription factor genes", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE145710", "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=GSE145710", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE145710", "version": null, "note": "The data used in the present study is available in the BioProject and GEO database of NCBI (www.ncbi.nlm.nih.gov). The accession ID of the data used is provided in the result section of the manuscript.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data used in the present study is available in the BioProject and GEO database of NCBI (www.ncbi.nlm.nih.gov). The accession ID of the data used is provided in the result section of the manuscript.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4331435", "GSM4331436", "GSM4331437", "GSM4331438", "GSM4331439", "GSM4331440", "GSM4331441", "GSM4331442", "GSM4331443"], "sample_count": 9, "group_sizes": null, "group_sizes_basis": null, "platform": "20301", "taxon": "Homo sapiens", "title": "Mutations in FAM50A suggest that Armfield XLID syndrome is a spliceosomopathy (human)", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE74263", "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=GSE74263", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE74263", "version": null, "note": "The data used in the present study is available in the BioProject and GEO database of NCBI (www.ncbi.nlm.nih.gov). The accession ID of the data used is provided in the result section of the manuscript.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data used in the present study is available in the BioProject and GEO database of NCBI (www.ncbi.nlm.nih.gov). The accession ID of the data used is provided in the result section of the manuscript.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1915816", "GSM1915817", "GSM1915818", "GSM1915819"], "sample_count": 4, "group_sizes": null, "group_sizes_basis": null, "platform": "11154", "taxon": "Homo sapiens", "title": "Characterization of a novel mutation in O-GlcNAc transferase that segregates with disease in a family with X-linked intellectual disability", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE77742", "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=GSE77742", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE77742", "version": null, "note": "The data used in the present study is available in the BioProject and GEO database of NCBI (www.ncbi.nlm.nih.gov). The accession ID of the data used is provided in the result section of the manuscript.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data used in the present study is available in the BioProject and GEO database of NCBI (www.ncbi.nlm.nih.gov). The accession ID of the data used is provided in the result section of the manuscript.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2058388", "GSM2058389", "GSM2058390"], "sample_count": 3, "group_sizes": null, "group_sizes_basis": null, "platform": "11154", "taxon": "Homo sapiens", "title": "Complex Balanced Translocation Disrupting TCF4 and Altering TCF4 Isoform Expression Segregates as Mild Autosomal Dominant Intellectual Disability", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE90682", "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=GSE90682", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE90682", "version": null, "note": "The data used in the present study is available in the BioProject and GEO database of NCBI (www.ncbi.nlm.nih.gov). The accession ID of the data used is provided in the result section of the manuscript.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data used in the present study is available in the BioProject and GEO database of NCBI (www.ncbi.nlm.nih.gov). The accession ID of the data used is provided in the result section of the manuscript.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2410317", "GSM2410318", "GSM2410319", "GSM2410320", "GSM2410321", "GSM2410322", "GSM2410323", "GSM2410324", "GSM2410325", "GSM2410326", "GSM2410327", "GSM2410328", "GSM2410329", "GSM2410330", "GSM2410331", "GSM2410332"], "sample_count": 16, "group_sizes": null, "group_sizes_basis": null, "platform": "16791;18573", "taxon": "Homo sapiens", "title": "Mutations in EBF3 disturb transcriptional profiles and cause intellectual disability, ataxia and facial dysmorphism", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE98476", "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=GSE98476", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE98476", "version": null, "note": "The data used in the present study is available in the BioProject and GEO database of NCBI (www.ncbi.nlm.nih.gov). The accession ID of the data used is provided in the result section of the manuscript.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data used in the present study is available in the BioProject and GEO database of NCBI (www.ncbi.nlm.nih.gov). The accession ID of the data used is provided in the result section of the manuscript.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2597186", "GSM2597187", "GSM2597188", "GSM2597189", "GSM2597190", "GSM2597191", "GSM2597192", "GSM2597193", "GSM2597194", "GSM2597195", "GSM2597196", "GSM2597197", "GSM2597198", "GSM2597199", "GSM2597200", "GSM2597201", "GSM2597202", "GSM2597203"], "sample_count": 18, "group_sizes": null, "group_sizes_basis": null, "platform": "11154", "taxon": "Homo sapiens", "title": "YY1 haploinsufficiency causes an intellectual disability syndrome featuring transcriptional and chromatin dysfunction [RNA-seq]", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:PRJEB21964", "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=PRJEB21964", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PRJEB21964", "version": null, "note": "The data used in the present study is available in the BioProject and GEO database of NCBI (www.ncbi.nlm.nih.gov). The accession ID of the data used is provided in the result section of the manuscript.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data used in the present study is available in the BioProject and GEO database of NCBI (www.ncbi.nlm.nih.gov). The accession ID of the data used is provided in the result section of the manuscript.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": null, "resolution_checked_at": "2026-11-01T20:16:20Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE108887 not downloaded", "asset:data:geo:GSE108887 licence not read", "asset:data:geo:GSE145710 not downloaded", "asset:data:geo:GSE145710 licence not read", "asset:data:geo:GSE74263 not downloaded", "asset:data:geo:GSE74263 licence not read", "asset:data:geo:GSE77742 not downloaded", "asset:data:geo:GSE77742 licence not read", "asset:data:geo:GSE90682 not downloaded", "asset:data:geo:GSE90682 licence not read", "asset:data:geo:GSE98476 not downloaded", "asset:data:geo:GSE98476 licence not read", "asset:data:geo:PRJEB21964 not downloaded", "asset:data:geo:PRJEB21964 licence not read"]}, "analysis": {"state": "complete", "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": "The genes that were differentially expressed in the patient sample as compared to the control sample were analyzed using the DESeq2 [31] package of R Studio [32]."}}], "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": "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": ["GSE77742", "GSE74263", "GSE90682", "GSE98476", "GSE108887", "GSE145710", "PRJEB21964"], "resolved_accessions": ["GSE77742", "GSE74263", "GSE90682", "GSE98476", "GSE108887", "GSE145710"], "statements": ["The data used in the present study is available in the BioProject and GEO database of NCBI (www.ncbi.nlm.nih.gov). The accession ID of the data used is provided in the result section of the manuscript."], "basis": "The paper names GSE77742, GSE74263, GSE90682, GSE98476, GSE108887, GSE145710 in 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:38765165", "data:geo:GSE108887"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE108887"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:18:46Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 13022, "completion_tokens": 2244, "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:38765165", "type": "paper", "label": "pmid:38765165"}, {"id": "source:pmid:38765165", "type": "manuscript", "label": "PMID 38765165 full text"}, {"id": "data:geo:GSE108887", "type": "dataset", "label": "GEO GSE108887"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:38765165", "type": "paper", "label": "pmid:38765165"}, {"id": "source:pmid:38765165", "type": "manuscript", "label": "PMID 38765165 full text"}, {"id": "data:geo:GSE108887", "type": "dataset", "label": "GEO GSE108887"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-38765165", "type": "extraction", "used": ["source:pmid:38765165"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE108887", "type": "accession_resolution", "used": ["data:geo:GSE108887"], "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:38765165", "parent_hash": "sha256:55a2ff6c9cc2774b6e89cd1cbc5001820e15dc01afe74c70695dde9b1445601c", "fork_of": null, "generation": 4}, "gaps": ["asset:data:geo:GSE108887 licence not read", "asset:data:geo:GSE108887 not downloaded", "asset:data:geo:GSE145710 licence not read", "asset:data:geo:GSE145710 not downloaded", "asset:data:geo:GSE74263 licence not read", "asset:data:geo:GSE74263 not downloaded", "asset:data:geo:GSE77742 licence not read", "asset:data:geo:GSE77742 not downloaded", "asset:data:geo:GSE90682 licence not read", "asset:data:geo:GSE90682 not downloaded", "asset:data:geo:GSE98476 licence not read", "asset:data:geo:GSE98476 not downloaded", "asset:data:geo:PRJEB21964 licence not read", "asset:data:geo:PRJEB21964 not downloaded", "execution.not_run", "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": ["RNA-Seq data analysis reveals novel nonsense mutatio"], "order_basis": "paper_text_order:0", "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": ["The genes that were differentially expressed in the patient sample as compared to the control sample were analyzed using the DESeq2 [31] package of R Studio [32]."], "order_basis": "consumes_earlier_output", "id": "assay:2"}]}