Visual analytics identifies key miRNAs for differentiating peripancreatic paraganglioma and pancreatic neuroendocrine tumors.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:37383401", "kind": "science-record", "revision": 4, "content_hash": "sha256:99cf08f9d7a5099b08ffb8e7029e4f96c30b33ce2518e226e4e1afc53370275d", "created_at": "2026-11-01T19:02:07Z", "updated_at": "2026-11-01T22:52:13Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Visual analytics identifies key miRNAs for differentiating peripancreatic paraganglioma and pancreatic neuroendocrine tumors.", "doi": "10.3389/fendo.2023.1162725", "pmid": "37383401", "authors": ["Jose María Enguita", "Ignacio Díaz", "Diego García", "Tamara Cubiella", "María-Dolores Chiara", "Nuria Valdés"], "journal": "Frontiers in endocrinology", "year": 2023, "abstract": "Introduction: Paragangliomas (PGL), a type of neuroendocrine tumor, pose a significant diagnostic challenge due to their potential for unpredictable locations and asymptomatic presentation. Misdiagnosis of peripancreatic PGLs, particularly as pancreatic neuroendocrine tumors (PANNETs), is a pressing issue as it can negatively impact both pre- and post-treatment decision-making. The aim of our study was to identify microRNA markers for the reliable differential diagnosis of peripancreatic PGLs and PANNETs, addressing a crucial unmet need in the field and advancing the standard of care for these patients.\nMethods: Morphing projections tool was used to analyze miRNA data from PGL and PANNET tumors present in the TCGA database. The findings were validated using two additional databases: GSE29742 and GSE73367.\nResults: Our research uncovered substantial differences in the miRNA expression profiles of PGL and PANNET, leading to the identification of 6 key miRNAs (miR-10b-3p, miR-10b-5p, and the miRNA families miR-200c/141 and miR-194/192) that can effectively differentiate between the two types of tumors.\nDiscussion: These miRNA levels hold potential as biomarkers for improved diagnosis, offering a solution to the diagnostic challenge posed by these tumors and potentially improving the standard of care for patients.", "claims": [{"id": "claim-method", "statement": "A logistic regression was conducted in each group to identify the most significant miRNAs, as explained in section 2.3, and ANOVA tests were performed to determine the statistical significance.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:37383401", "locator": "sections[6] \"Results\" paragraph 6", "quote": "A logistic regression was conducted in each group to identify the most significant miRNAs, as explained in section 2.3, and ANOVA tests were performed to determine the statistical significance."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Publicly available datasets were analyzed in this study. This data can be found here: https://portal.gdc.cancer.gov and in https://www.ncbi.nlm.nih.gov/ for the Gene Expression Omnibus: GSE29742 and GSE73367.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:37383401", "locator": "sections[10] \"Data availability statement\" paragraph 2", "quote": "Publicly available datasets were analyzed in this study. This data can be found here: https://portal.gdc.cancer.gov and in https://www.ncbi.nlm.nih.gov/ for the Gene Expression Omnibus: GSE29742 and GSE73367."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Six key miRNAs—miR-10b-3p, miR-10b-5p, miR-200c/141, and miR-194/192—effectively differentiate peripancreatic PGLs from PANNETs.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:37383401", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "Our research uncovered substantial differences in the miRNA expression profiles of PGL and PANNET, leading to the identification of 6 key miRNAs (miR-10b-3p, miR-10b-5p, and the miRNA families miR-200c/141 and miR-194/192) that can effectively differentiate between the two types of tumors."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "Six key miRNAs—miR-10b-3p, miR-10b-5p, miR-200c/141, and miR-194/192—effectively differentiate peripancreatic PGLs from PANNETs.", "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:37383401"], "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:GSE29742"], "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:GSE29742"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:37383401", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fendo.2023.1162725", "sha256": "sha256:13e6c84573cd14006fabbb95668ddc357cefeaf1f9197e5d10aa1448f4608d8f", "bytes": 31816, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fendo.2023.1162725", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC10299733", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE29742", "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=GSE29742", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE29742", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: https://portal.gdc.cancer.gov and in https://www.ncbi.nlm.nih.gov/ for the Gene Expression Omnibus: GSE29742 and GSE73367.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. This data can be found here: https://portal.gdc.cancer.gov and in https://www.ncbi.nlm.nih.gov/ for the Gene Expression Omnibus: GSE29742 and GSE73367.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM737370", "GSM737371", "GSM737372", "GSM737373", "GSM737374", "GSM737375", "GSM737376", "GSM737377", "GSM737378", "GSM737379", "GSM737380", "GSM737381", "GSM737382", "GSM737383", "GSM737384", "GSM737385", "GSM737386", "GSM737387", "GSM737388", "GSM737389", "GSM737390", "GSM737391", "GSM737392", "GSM737393", "GSM737394", "GSM737395", "GSM737396", "GSM737397", "GSM737398", "GSM737399", "GSM737400", "GSM737401", "GSM737402", "GSM737403", "GSM737404", "GSM737405", "GSM737406", "GSM737407", "GSM737408", "GSM737409", "GSM737410", "GSM737411", "GSM737412", "GSM737413", "GSM737414", "GSM737415", "GSM737416", "GSM737417", "GSM737418", "GSM737419", "GSM737420", "GSM737421", "GSM737422", "GSM737423"], "sample_count": 54, "group_sizes": null, "group_sizes_basis": null, "platform": "8227", "taxon": "Homo sapiens", "title": "MIRnome Profiling of Hereditary Pheochromocytoma and Paraganglioma Reveals Specific Signatures According to Primary Mutation: Possible Implications in the Differentiation Status of Tumor Cells", "resolution_checked_at": "2026-11-01T18:46:34Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE73367", "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=GSE73367", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE73367", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: https://portal.gdc.cancer.gov and in https://www.ncbi.nlm.nih.gov/ for the Gene Expression Omnibus: GSE29742 and GSE73367.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. This data can be found here: https://portal.gdc.cancer.gov and in https://www.ncbi.nlm.nih.gov/ for the Gene Expression Omnibus: GSE29742 and GSE73367.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1891904", "GSM1891905", "GSM1891906", "GSM1891907", "GSM1891908", "GSM1891909", "GSM1891910", "GSM1891911", "GSM1891912", "GSM1891913", "GSM1891914", "GSM1891915", "GSM1891916", "GSM1891917", "GSM1891918", "GSM1891919", "GSM1891920", "GSM1891921", "GSM1891922", "GSM1891923", "GSM1891924", "GSM1891925", "GSM1891926", "GSM1891927", "GSM1891928", "GSM1891929", "GSM1891930", "GSM1891931", "GSM1891932", "GSM1891933", "GSM1891934", "GSM1891935", "GSM1891936", "GSM1891937", "GSM1891938", "GSM1891939", "GSM1891940", "GSM1891941", "GSM1891942", "GSM1891943", "GSM1891944", "GSM1891945", "GSM1891946", "GSM1891947", "GSM1891948", "GSM1891949", "GSM1891950", "GSM1891951", "GSM1891952", "GSM1891953"], "sample_count": 50, "group_sizes": null, "group_sizes_basis": null, "platform": "16770", "taxon": "Homo sapiens", "title": "A cross species and multi-omics (including metabolomics) analysis in pancreatic neuroendocrine tumours (miRNA)", "resolution_checked_at": "2026-11-01T18:46:34Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE29742 not downloaded", "asset:data:geo:GSE29742 licence not read", "asset:data:geo:GSE73367 not downloaded", "asset:data:geo:GSE73367 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "group_comparison", "specific": "anova", "label": "Group comparison", "dsl_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "A logistic regression was conducted in each group to identify the most significant miRNAs, as explained in section 2.3, and ANOVA tests were performed to determine the statistical significance."}}, {"id": "method-2", "family": "regression_modelling", "specific": "logistic", "label": "Regression modelling", "dsl_operations": ["glm_logit_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["predictors_and_outcome"], "evidence": {"score": 0.8, "band": "high", "quote": "logistic regression"}}], "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": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: anova."}, "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": ["GSE29742", "GSE73367"], "resolved_accessions": ["GSE29742", "GSE73367"], "statements": ["Publicly available datasets were analyzed in this study. This data can be found here: https://portal.gdc.cancer.gov and in https://www.ncbi.nlm.nih.gov/ for the Gene Expression Omnibus: GSE29742 and GSE73367."], "basis": "The paper names GSE29742, GSE73367 in Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "assets": ["source:pmid:37383401", "data:geo:GSE29742"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE29742"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T18:45:13Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 9995, "completion_tokens": 1310, "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:37383401", "type": "paper", "label": "pmid:37383401"}, {"id": "source:pmid:37383401", "type": "manuscript", "label": "PMID 37383401 full text"}, {"id": "data:geo:GSE29742", "type": "dataset", "label": "GEO GSE29742"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:37383401", "type": "paper", "label": "pmid:37383401"}, {"id": "source:pmid:37383401", "type": "manuscript", "label": "PMID 37383401 full text"}, {"id": "data:geo:GSE29742", "type": "dataset", "label": "GEO GSE29742"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-37383401", "type": "extraction", "used": ["source:pmid:37383401"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE29742", "type": "accession_resolution", "used": ["data:geo:GSE29742"], "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:37383401", "parent_hash": "sha256:a88631f875204f60a3c625e2f7195c0367d1329ef74ee53f900ae69ec421226a", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE29742 licence not read", "asset:data:geo:GSE29742 not downloaded", "asset:data:geo:GSE73367 licence not read", "asset:data:geo:GSE73367 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["A logistic regression was conducted in each group to identify the most significant miRNAs, as explained in section 2.3, and ANOVA tests were performed to determine the statistical significance."], "order_basis": "analysis_only", "id": "assay:1"}]}