Identification of candidate biomarkers and pathways associated with type 1 diabetes mellitus using bioinformatics analysis.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:35650387", "kind": "science-record", "revision": 4, "content_hash": "sha256:fad852b585ed936d7604adda7873cfa64b7829269c1b1f37ca80e7196e4a9221", "created_at": "2026-11-01T18:14:35Z", "updated_at": "2026-11-01T22:06:39Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of candidate biomarkers and pathways associated with type 1 diabetes mellitus using bioinformatics analysis.", "doi": "10.1038/s41598-022-13291-1", "pmid": "35650387", "authors": ["Madhu Pujar", "Basavaraj Vastrad", "Satish Kavatagimath", "Chanabasayya Vastrad", "Shivakumar Kotturshetti"], "journal": "Scientific reports", "year": 2022, "abstract": "Type 1 diabetes mellitus (T1DM) is a metabolic disorder for which the underlying molecular mechanisms remain largely unclear. This investigation aimed to elucidate essential candidate genes and pathways in T1DM by integrated bioinformatics analysis. In this study, differentially expressed genes (DEGs) were analyzed using DESeq2 of R package from GSE162689 of the Gene Expression Omnibus (GEO). Gene ontology (GO) enrichment analysis, REACTOME pathway enrichment analysis, and construction and analysis of protein-protein interaction (PPI) network, modules, miRNA-hub gene regulatory network and TF-hub gene regulatory network, and validation of hub genes were performed. A total of 952 DEGs (477 up regulated and 475 down regulated genes) were identified in T1DM. GO and REACTOME enrichment result results showed that DEGs mainly enriched in multicellular organism development, detection of stimulus, diseases of signal transduction by growth factor receptors and second messengers, and olfactory signaling pathway. The top hub genes such as MYC, EGFR, LNX1, YBX1, HSP90AA1, ESR1, FN1, TK1, ANLN and SMAD9 were screened out as the critical genes among the DEGs from the PPI network, modules, miRNA-hub gene regulatory network and TF-hub gene regulatory network. Receiver operating characteristic curve (ROC) analysis confirmed that these genes were significantly associated with T1DM. In conclusion, the identified DEGs, particularly the hub genes, strengthen the understanding of the advancement and progression of T1DM, and certain genes might be used as candidate target molecules to diagnose, monitor and treat T1DM.", "claims": [{"id": "claim-data-access", "statement": "The datasets supporting the conclusions of this article are available in the GEO (Gene Expression Omnibus) (https://www.ncbi.nlm.nih.gov/geo/) repository. [(GSE162689) (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE162689].", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:35650387", "locator": "sections[24] \"Data availability\" paragraph 2", "quote": "The datasets supporting the conclusions of this article are available in the GEO (Gene Expression Omnibus) (https://www.ncbi.nlm.nih.gov/geo/) repository. [(GSE162689) (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE162689]."}], "state": "complete"}, {"id": "claim-target-result", "statement": "A total of 952 DEGs (477 up regulated and 475 down regulated genes) were identified in T1DM.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:35650387", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "A total of 952 DEGs (477 up regulated and 475 down regulated genes) were identified in T1DM."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "A total of 952 DEGs (477 up regulated and 475 down regulated genes) were identified in T1DM.", "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:35650387"], "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:GSE162689"], "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:GSE162689"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:35650387", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1038/s41598-022-13291-1", "sha256": "sha256:9717cda540654eb612d9a800024b222547aff596e476ac04796fdffc4715a845", "bytes": 100239, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1038/s41598-022-13291-1", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC9160069", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE162689", "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=GSE162689", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE162689", "version": null, "note": "The datasets supporting the conclusions of this article are available in the GEO (Gene Expression Omnibus) (https://www.ncbi.nlm.nih.gov/geo/) repository. [(GSE162689) (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE162689].", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets supporting the conclusions of this article are available in the GEO (Gene Expression Omnibus) (https://www.ncbi.nlm.nih.gov/geo/) repository. [(GSE162689) (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE162689].", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4957182", "GSM4957183", "GSM4957184", "GSM4957185", "GSM4957186", "GSM4957187", "GSM4957188", "GSM4957189", "GSM4957190", "GSM4957191", "GSM4957192", "GSM4957193", "GSM4957194", "GSM4957195", "GSM4957196", "GSM4957197", "GSM4957198", "GSM4957199", "GSM4957200", "GSM4957201", "GSM4957202", "GSM4957203", "GSM4957204", "GSM4957205", "GSM4957206", "GSM4957207", "GSM4957208", "GSM4957209", "GSM4957210", "GSM4957211", "GSM4957212", "GSM4957213", "GSM4957214", "GSM4957215", "GSM4957216", "GSM4957217", "GSM4957218", "GSM4957219", "GSM4957220", "GSM4957221", "GSM4957222", "GSM4957223", "GSM4957224", "GSM4957225", "GSM4957226", "GSM4957227", "GSM4957228", "GSM4957229", "GSM4957230", "GSM4957231", "GSM4957232", "GSM4957233", "GSM4957234", "GSM4957235", "GSM4957236", "GSM4957237", "GSM4957238", "GSM4957239", "GSM4957240"], "sample_count": 59, "group_sizes": null, "group_sizes_basis": null, "platform": "24014", "taxon": "Homo sapiens", "title": "A histological and transcriptional characterization of the pancreatic acinar tissue in type 1 diabetes", "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:GSE162689 not downloaded", "asset:data:geo:GSE162689 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": 0.7, "band": "medium", "quote": "DESeq2"}}, {"id": "method-2", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "protein-protein interaction"}}, {"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": "pathway enrichment"}}], "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": ["GSE162689"], "resolved_accessions": ["GSE162689"], "statements": ["The datasets supporting the conclusions of this article are available in the GEO (Gene Expression Omnibus) (https://www.ncbi.nlm.nih.gov/geo/) repository. [(GSE162689) (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE162689]."], "basis": "The paper names GSE162689 in GEO (Gene Expression Omnibus) 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:35650387", "data:geo:GSE162689"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE162689"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T17:48:23Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 33983, "completion_tokens": 878, "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:35650387", "type": "paper", "label": "pmid:35650387"}, {"id": "source:pmid:35650387", "type": "manuscript", "label": "PMID 35650387 full text"}, {"id": "data:geo:GSE162689", "type": "dataset", "label": "GEO GSE162689"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:35650387", "type": "paper", "label": "pmid:35650387"}, {"id": "source:pmid:35650387", "type": "manuscript", "label": "PMID 35650387 full text"}, {"id": "data:geo:GSE162689", "type": "dataset", "label": "GEO GSE162689"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-35650387", "type": "extraction", "used": ["source:pmid:35650387"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE162689", "type": "accession_resolution", "used": ["data:geo:GSE162689"], "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:35650387", "parent_hash": "sha256:091d8da07884a2634df23f131ce018b086910b93cb4d4ab38ea63e3e0b02079f", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE162689 licence not read", "asset:data:geo:GSE162689 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"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": 0.7, "evidence": ["DESeq2"], "order_basis": "analysis_only", "id": "assay:1"}]}