Identification of Candidate Therapeutic Target Genes and Profiling of Tumor-Infiltrating Immune Cells in Pancreatic Cancer via Integrated Transcriptomic Analysis.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:36061357", "kind": "science-record", "revision": 4, "content_hash": "sha256:e06ab0e94688981c68ed0659c23cc005dea35a027e328c0b293d458e241e52aa", "created_at": "2026-11-01T18:15:15Z", "updated_at": "2026-11-01T22:07:27Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of Candidate Therapeutic Target Genes and Profiling of Tumor-Infiltrating Immune Cells in Pancreatic Cancer via Integrated Transcriptomic Analysis.", "doi": "10.1155/2022/3839480", "pmid": "36061357", "authors": ["Wei Ding", "Yuxu Wang", "Yongbiao Ma", "Li Lin", "Manjiang Li"], "journal": "Disease markers", "year": 2022, "abstract": "Pancreatic cancer (PC) has a dismal prognosis despite advancing scientific and technological knowledge. The exploration of novel genes is critical to improving current therapeutic measures. This research is aimed at selecting hub genes that can act as candidate therapeutic target genes and as prognostic biomarkers in PC. Gene expression profiles of datasets GSE101448, GSE15471, and GSE62452 were extracted from the GEO database. The \"limma\" package was performed to select differentially expressed genes (DEGs) between PC and normal tissue samples in each dataset. Robust rank aggregation (RRA) algorithm was conducted to integrate multiple expression profiles and identify robust DEGs. GO analysis and KEGG analysis were conducted to identify the functional correlation of the DEGs. The CIBERSORT algorithm was conducted to estimate the immune cell composition of each tissue sample. STRING and Cytoscape were used to establish the protein-protein interaction (PPI) network. The cytoHubba plugin in Cytoscape was performed to identify hub genes. Survival analysis based on hub gene expression was performed with clinical information from TCGA database. 566 robust DEGs (338 upregulated genes and 226 downregulated genes) were identified. Tumor tissue had a higher infiltration of resting dendritic cells and tumor-associated macrophages (TAM), including M0, M1, and M2 macrophages, while infiltration levels of B memory cells, plasma cells, T cells CD8, T follicular helper cells, and NK cells in normal tissue were relatively higher. GO terms and KEGG pathway analysis results revealed enrichment in tumor-associated pathways, including the extracellular matrix organization, cell-substrate adhesion cytokine-cytokine receptor interaction, calcium signaling pathway, and glycine, serine, and threonine metabolism, to name a few. Finally, FN1, MSLN, PLAU, and VCAN were selected as hub genes. High expression of FN1, MSLN, PLAU, and VCAN in PC significantly correlated with poor prognosis. Integrated transcriptomic analysis was used to provide new insights into PC pathogenesis. FN1, MSLN, PLAU, and VCAN may be considered as novel biomarkers of PC.", "claims": [{"id": "claim-method", "statement": "The “robust rank aggregation” R package merged DEGs from three datasets to obtain robust DEGs.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:36061357", "locator": "sections[4] \"2.2. Identification of Robust DEGs\" paragraph 2", "quote": "The “robust rank aggregation” R package merged DEGs from three datasets to obtain robust DEGs."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets supporting the conclusion of this article are included within the article.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:36061357", "locator": "sections[21] \"Data Availability\" paragraph 2", "quote": "The datasets supporting the conclusion of this article are included within the article."}], "state": "complete"}, {"id": "claim-target-result", "statement": "566 robust DEGs (338 upregulated genes and 226 downregulated genes) were identified.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:36061357", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "566 robust DEGs (338 upregulated genes and 226 downregulated genes) were identified."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "566 robust DEGs (338 upregulated genes and 226 downregulated genes) were identified.", "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:36061357"], "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:GSE101448"], "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:GSE101448"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:36061357", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1155/2022/3839480", "sha256": "sha256:babb622c8494c9bfbeeba2a61b4cb11cce199a925d6b80d3ad1855b59ff64d68", "bytes": 21715, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1155/2022/3839480", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC9428685", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE101448", "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=GSE101448", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE101448", "version": null, "note": "The datasets supporting the conclusion of this article are included within the article.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets supporting the conclusion of this article are included within the article.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2703750", "GSM2703751", "GSM2703752", "GSM2703753", "GSM2703754", "GSM2703755", "GSM2703756", "GSM2703757", "GSM2703758", "GSM2703759", "GSM2703760", "GSM2703761", "GSM2703762", "GSM2703763", "GSM2703764", "GSM2703765", "GSM2703766", "GSM2703767", "GSM2703768", "GSM2703769", "GSM2703770", "GSM2703771", "GSM2703772", "GSM2703773", "GSM2703774", "GSM2703775", "GSM2703776", "GSM2703777", "GSM2703778", "GSM2703779", "GSM2703780", "GSM2703781", "GSM2703782", "GSM2703783", "GSM2703784", "GSM2703785", "GSM2703786", "GSM2703787", "GSM2703788", "GSM2703789", "GSM2703790", "GSM2703791", "GSM2703792"], "sample_count": 43, "group_sizes": null, "group_sizes_basis": null, "platform": "10558", "taxon": "Homo sapiens", "title": "Microarray gene-expression data to identify a robust biomarker signature in PDAC and validate it in formalin-fixed paraffin-embedded tissue material.", "resolution_checked_at": "2026-11-01T18:06:43Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE15471", "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=GSE15471", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE15471", "version": null, "note": "The datasets supporting the conclusion of this article are included within the article.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets supporting the conclusion of this article are included within the article.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM388076", "GSM388077", "GSM388078", "GSM388079", "GSM388080", "GSM388081", "GSM388082", "GSM388083", "GSM388084", "GSM388085", "GSM388086", "GSM388087", "GSM388088", "GSM388089", "GSM388090", "GSM388091", "GSM388092", "GSM388093", "GSM388094", "GSM388095", "GSM388096", "GSM388097", "GSM388098", "GSM388099", "GSM388100", "GSM388101", "GSM388102", "GSM388103", "GSM388104", "GSM388105", "GSM388106", "GSM388107", "GSM388108", "GSM388109", "GSM388110", "GSM388111", "GSM388112", "GSM388113", "GSM388114", "GSM388115", "GSM388116", "GSM388117", "GSM388118", "GSM388119", "GSM388120", "GSM388121", "GSM388122", "GSM388123", "GSM388124", "GSM388125", "GSM388126", "GSM388127", "GSM388128", "GSM388129", "GSM388130", "GSM388131", "GSM388132", "GSM388133", "GSM388134", "GSM388135", "GSM388136", "GSM388137", "GSM388138", "GSM388139", "GSM388140", "GSM388141", "GSM388142", "GSM388143", "GSM388144", "GSM388145", "GSM388146", "GSM388147", "GSM388148", "GSM388149", "GSM388150", "GSM388151", "GSM388152", "GSM388153"], "sample_count": 78, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Whole-Tissue Gene Expression Study of Pancreatic Ductal Adenocarcinoma", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE62452", "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=GSE62452", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE62452", "version": null, "note": "The datasets supporting the conclusion of this article are included within the article.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets supporting the conclusion of this article are included within the article.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1527105", "GSM1527106", "GSM1527107", "GSM1527108", "GSM1527109", "GSM1527110", "GSM1527111", "GSM1527112", "GSM1527113", "GSM1527114", "GSM1527115", "GSM1527116", "GSM1527117", "GSM1527118", "GSM1527119", "GSM1527120", "GSM1527121", "GSM1527122", "GSM1527123", "GSM1527124", "GSM1527125", "GSM1527126", "GSM1527127", "GSM1527128", "GSM1527129", "GSM1527130", "GSM1527131", "GSM1527132", "GSM1527133", "GSM1527134", "GSM1527135", "GSM1527136", "GSM1527137", "GSM1527138", "GSM1527139", "GSM1527140", "GSM1527141", "GSM1527142", "GSM1527143", "GSM1527144", "GSM1527145", "GSM1527146", "GSM1527147", "GSM1527148", "GSM1527149", "GSM1527150", "GSM1527151", "GSM1527152", "GSM1527153", "GSM1527154", "GSM1527155", "GSM1527156", "GSM1527157", "GSM1527158", "GSM1527159", "GSM1527160", "GSM1527161", "GSM1527162", "GSM1527163", "GSM1527164", "GSM1527165", "GSM1527166", "GSM1527167", "GSM1527168", "GSM1527169", "GSM1527170", "GSM1527171", "GSM1527172", "GSM1527173", "GSM1527174", "GSM1527175", "GSM1527176", "GSM1527177", "GSM1527178", "GSM1527179", "GSM1527180", "GSM1527181", "GSM1527182", "GSM1527183", "GSM1527184", "GSM1527185", "GSM1527186", "GSM1527187", "GSM1527188", "GSM1527189", "GSM1527190", "GSM1527191", "GSM1527192", "GSM1527193", "GSM1527194", "GSM1527195", "GSM1527196", "GSM1527197", "GSM1527198", "GSM1527199", "GSM1527200", "GSM1527201", "GSM1527202", "GSM1527203", "GSM1527204", "GSM1527205", "GSM1527206", "GSM1527207", "GSM1527208", "GSM1527209", "GSM1527210", "GSM1527211", "GSM1527212", "GSM1527213", "GSM1527214", "GSM1527215", "GSM1527216", "GSM1527217", "GSM1527218", "GSM1527219", "GSM1527220", "GSM1527221", "GSM1527222", "GSM1527223", "GSM1527224", "GSM1527225", "GSM1527226", "GSM1527227", "GSM1527228", "GSM1527229", "GSM1527230", "GSM1527231", "GSM1527232", "GSM1527233", "GSM1527234"], "sample_count": 130, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "Microarray gene-expression profiles of 69 pancreatic tumors and 61 adjacent non-tumor tissue from patients with pancreatic ductal adenocarcinoma", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE101448 not downloaded", "asset:data:geo:GSE101448 licence not read", "asset:data:geo:GSE15471 not downloaded", "asset:data:geo:GSE15471 licence not read", "asset:data:geo:GSE62452 not downloaded", "asset:data:geo:GSE62452 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "limma_voom", "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": "limma"}}, {"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": 0.8, "band": "high", "quote": "GO enrichment"}}, {"id": "method-4", "family": null, "specific": null, "label": "robust rank aggregation (RRA)", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The “robust rank aggregation” R package merged DEGs from three datasets to obtain robust DEGs."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "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: limma_voom."}, "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": ["GSE101448", "GSE15471", "GSE62452"], "resolved_accessions": ["GSE101448", "GSE15471", "GSE62452"], "statements": ["The datasets supporting the conclusion of this article are included within the article."], "basis": "The paper names GSE101448, GSE15471, GSE62452 in GEO database 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:36061357", "data:geo:GSE101448"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE101448"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T18:03:43Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 7025, "completion_tokens": 1487, "cached_tokens": 128}}, "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:36061357", "type": "paper", "label": "pmid:36061357"}, {"id": "source:pmid:36061357", "type": "manuscript", "label": "PMID 36061357 full text"}, {"id": "data:geo:GSE101448", "type": "dataset", "label": "GEO GSE101448"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:36061357", "type": "paper", "label": "pmid:36061357"}, {"id": "source:pmid:36061357", "type": "manuscript", "label": "PMID 36061357 full text"}, {"id": "data:geo:GSE101448", "type": "dataset", "label": "GEO GSE101448"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-36061357", "type": "extraction", "used": ["source:pmid:36061357"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE101448", "type": "accession_resolution", "used": ["data:geo:GSE101448"], "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:36061357", "parent_hash": "sha256:6dea73f36071eacdbc822fc471bfd6fa7f0fb6194b3b8c8b0a130db7e5fbb77e", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE101448 licence not read", "asset:data:geo:GSE101448 not downloaded", "asset:data:geo:GSE15471 licence not read", "asset:data:geo:GSE15471 not downloaded", "asset:data:geo:GSE62452 licence not read", "asset:data:geo:GSE62452 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["datasets. Perl language was used to map the microarray probe data to gene symbols. “limma” software"], "order_basis": "paper_text_order:2947", "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": 0.7, "evidence": ["limma"], "order_basis": "consumes_earlier_output", "id": "assay:2"}]}