Identification of Key Genes and Potential Therapeutic Targets in Sepsis-Associated Acute Kidney Injury Using Transformer and Machine Learning Approaches.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40428155", "kind": "science-record", "revision": 4, "content_hash": "sha256:f22f592b649fcffe42c1f2a9b0b7d10fc88346430a89e123badded6ee2d8d628", "created_at": "2026-11-01T20:30:33Z", "updated_at": "2026-11-01T22:56:35Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of Key Genes and Potential Therapeutic Targets in Sepsis-Associated Acute Kidney Injury Using Transformer and Machine Learning Approaches.", "doi": "10.3390/bioengineering12050536", "pmid": "40428155", "authors": ["Zhendong Zhai", "JunZhe Peng", "Wenjun Zhong", "Jun Tao", "Yaqi Ao", "Bailin Niu", "Li Zhu"], "journal": "Bioengineering (Basel, Switzerland)", "year": 2025, "abstract": "Sepsis-associated acute kidney injury (SA-AKI) is a life-threatening complication of sepsis, characterized by high mortality and prolonged hospitalization. Early diagnosis and effective therapy remain difficult despite extensive investigation. To address this, we developed an AI-driven integrative framework that combines a Transformer-based deep learning model with established machine learning techniques (LASSO, SVM-RFE, Random Forest and neural networks) to uncover complex, nonlinear interactions among gene-expression biomarkers. Analysis of normalized microarray data from GEO (GSE95233 and GSE69063) identified differentially expressed genes (DEGs), and KEGG/GO enrichment via clusterProfiler revealed key pathways in immune response, protein synthesis, and antigen presentation. By integrating multiple transcriptomic cohorts, we pinpointed 617 SA-AKI-associated DEGs-21 of which overlapped between sepsis and AKI datasets. Our Transformer-based classifier ranked five genes (MYL12B, RPL10, PTBP1, PPIA, and TOMM7) as top diagnostic markers, with AUC values ranging from 0.9395 to 0.9996 (MYL12B yielding 0.9996). Drug-gene interaction mining using DGIdb (FDR < 0.05) nominated 19 candidate therapeutics for SA-AKI. Together, these findings demonstrate that melding deep learning with classical machine learning not only sharpens early SA-AKI detection but also systematically uncovers actionable drug targets, laying groundwork for precision intervention in critical care settings.", "claims": [{"id": "claim-method", "statement": "Differential expression analysis was performed using the limma package [27] in R (version 2024.12.1+563).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40428155", "locator": "sections[4] \"2.2. Sepsis and AKI-Related Gene Analysis\" paragraph 3", "quote": "Differential expression analysis was performed using the limma package [27] in R (version 2024.12.1+563)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "All data used in this study are publicly available from the GEO, GTEx, Malacards, Phenopedia, and DisGeNET databases.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40428155", "locator": "sections[24] \"notes\" paragraph 1", "quote": "All data used in this study are publicly available from the GEO, GTEx, Malacards, Phenopedia, and DisGeNET databases."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The Transformer-based classifier ranked five genes (MYL12B, RPL10, PTBP1, PPIA, and TOMM7) as top diagnostic markers, with AUC values ranging from 0.9395 to 0.9996 (MYL12B yielding 0.9996).", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:40428155", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Our Transformer-based classifier ranked five genes (MYL12B, RPL10, PTBP1, PPIA, and TOMM7) as top diagnostic markers, with AUC values ranging from 0.9395 to 0.9996 (MYL12B yielding 0.9996)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The Transformer-based classifier ranked five genes (MYL12B, RPL10, PTBP1, PPIA, and TOMM7) as top diagnostic markers, with AUC values ranging from 0.9395 to 0.9996 (MYL12B yielding 0.9996).", "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:40428155"], "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:GSE69063"], "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:GSE69063"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40428155", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3390/bioengineering12050536", "sha256": "sha256:c4174426114b758d4852c85ae1b1d384f363fea88e7717e73fffe25fbf30a5ed", "bytes": 31913, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3390/bioengineering12050536", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12108565", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE69063", "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=GSE69063", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE69063", "version": null, "note": "All data used in this study are publicly available from the GEO, GTEx, Malacards, Phenopedia, and DisGeNET databases.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data used in this study are publicly available from the GEO, GTEx, Malacards, Phenopedia, and DisGeNET databases.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1691688", "GSM1691689", "GSM1691690", "GSM1691691", "GSM1691692", "GSM1691693", "GSM1691694", "GSM1691695", "GSM1691696", "GSM1691697", "GSM1691698", "GSM1691699", "GSM1691700", "GSM1691701", "GSM1691702", "GSM1691703", "GSM1691704", "GSM1691705", "GSM1691706", "GSM1691707", "GSM1691708", "GSM1691709", "GSM1691710", "GSM1691711", "GSM1691712", "GSM1691713", "GSM1691714", "GSM1691715", "GSM1691716", "GSM1691717", "GSM1691718", "GSM1691719", "GSM1691720", "GSM1691721", "GSM1691722", "GSM1691723", "GSM1691724", "GSM1691725", "GSM1691726", "GSM1691727", "GSM1691728", "GSM1691729", "GSM1691730", "GSM1691731", "GSM1691732", "GSM1691733", "GSM1691734", "GSM1691735", "GSM1691736", "GSM1691737", "GSM1691738", "GSM1691739", "GSM1691740", "GSM1691741", "GSM1691742", "GSM1691743", "GSM1691744", "GSM1691745", "GSM1691746", "GSM1691747", "GSM1691748", "GSM1691749", "GSM1691750", "GSM1691751", "GSM1691752", "GSM1691753", "GSM1691754", "GSM1691755", "GSM1691756", "GSM1691757", "GSM1691758", "GSM1691759", "GSM1691760", "GSM1691761", "GSM1691762", "GSM1691763", "GSM1691764", "GSM1691765", "GSM1691766", "GSM1691767", "GSM1691768", "GSM1691769", "GSM1691770", "GSM1691771", "GSM1691772", "GSM1691773", "GSM1691774", "GSM1691775", "GSM1691776", "GSM1691777", "GSM1691778", "GSM1691779", "GSM1691780", "GSM1691781", "GSM1691782", "GSM1691783", "GSM1691784", "GSM1691785", "GSM1691786", "GSM1691787", "GSM1691788", "GSM1691789", "GSM1691790", "GSM1691791", "GSM1691792", "GSM1691793", "GSM1691794", "GSM1691795", "GSM1691796", "GSM1691797", "GSM1691798", "GSM1691799", "GSM1691800", "GSM1691801", "GSM1691802", "GSM1691803", "GSM1691804", "GSM1691805", "GSM1691806", "GSM1691807", "GSM1691808", "GSM1691809", "GSM1691810", "GSM1691811", "GSM1691812", "GSM1691813", "GSM1691814", "GSM1691815", "GSM1691816", "GSM1691817", "GSM1691818", "GSM1691819", "GSM1691820", "GSM1691821", "GSM1691822", "GSM1691823", "GSM1691824", "GSM1691825", "GSM1691826", "GSM1691827", "GSM1691828", "GSM1691829", "GSM1691830", "GSM1691831", "GSM1691832", "GSM1691833", "GSM1691834", "GSM1691835", "GSM1691836", "GSM1691837", "GSM1691838", "GSM1691839", "GSM1691840"], "sample_count": 153, "group_sizes": null, "group_sizes_basis": null, "platform": "19983", "taxon": "Homo sapiens", "title": "Gene expression patterns in blood during human anaphylaxis, trauma, and sepsis", "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:GSE95233", "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=GSE95233", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE95233", "version": null, "note": "All data used in this study are publicly available from the GEO, GTEx, Malacards, Phenopedia, and DisGeNET databases.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data used in this study are publicly available from the GEO, GTEx, Malacards, Phenopedia, and DisGeNET databases.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2500349", "GSM2500350", "GSM2500351", "GSM2500352", "GSM2500353", "GSM2500354", "GSM2500355", "GSM2500356", "GSM2500357", "GSM2500358", "GSM2500359", "GSM2500360", "GSM2500361", "GSM2500362", "GSM2500363", "GSM2500364", "GSM2500365", "GSM2500366", "GSM2500367", "GSM2500368", "GSM2500369", "GSM2500370", "GSM2500371", "GSM2500372", "GSM2500373", "GSM2500374", "GSM2500375", "GSM2500376", "GSM2500377", "GSM2500378", "GSM2500379", "GSM2500380", "GSM2500381", "GSM2500382", "GSM2500383", "GSM2500384", "GSM2500385", "GSM2500386", "GSM2500387", "GSM2500388", "GSM2500389", "GSM2500390", "GSM2500391", "GSM2500392", "GSM2500393", "GSM2500394", "GSM2500395", "GSM2500396", "GSM2500397", "GSM2500398", "GSM2500399", "GSM2500400", "GSM2500401", "GSM2500402", "GSM2500403", "GSM2500404", "GSM2500405", "GSM2500406", "GSM2500407", "GSM2500408", "GSM2500409", "GSM2500410", "GSM2500411", "GSM2500412", "GSM2500413", "GSM2500414", "GSM2500415", "GSM2500416", "GSM2500417", "GSM2500418", "GSM2500419", "GSM2500420", "GSM2500421", "GSM2500422", "GSM2500423", "GSM2500424", "GSM2500425", "GSM2500426", "GSM2500427", "GSM2500428", "GSM2500429", "GSM2500430", "GSM2500431", "GSM2500432", "GSM2500433", "GSM2500434", "GSM2500435", "GSM2500436", "GSM2500437", "GSM2500438", "GSM2500439", "GSM2500440", "GSM2500441", "GSM2500442", "GSM2500443", "GSM2500444", "GSM2500445", "GSM2500446", "GSM2500447", "GSM2500448", "GSM2500449", "GSM2500450", "GSM2500451", "GSM2500452", "GSM2500453", "GSM2500454", "GSM2500455", "GSM2500456", "GSM2500457", "GSM2500458", "GSM2500459", "GSM2500460", "GSM2500461", "GSM2500462", "GSM2500463", "GSM2500464", "GSM2500465", "GSM2500466", "GSM2500467", "GSM2500468", "GSM2500469", "GSM2500470", "GSM2500471", "GSM2500472"], "sample_count": 124, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Fractalkine receptor CX3CR1 and leukocyte Ig-like receptor B2 LILRB2 are prognostic biomarkers in septic shock", "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:GSE69063 not downloaded", "asset:data:geo:GSE69063 licence not read", "asset:data:geo:GSE95233 not downloaded", "asset:data:geo:GSE95233 licence not read"]}, "analysis": {"state": "complete", "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": 1.0, "band": "verbatim", "quote": "Differential expression analysis was performed using the limma package [27] in R (version 2024.12.1+563)."}}, {"id": "method-2", "family": "machine_learning", "specific": "random_forest", "label": "Machine learning", "dsl_operations": [], "missing_operations": ["machine_learning_random_forest"], "expressible": false, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "Random Forest"}}, {"id": "method-3", "family": "machine_learning", "specific": "support_vector_machine", "label": "Machine learning", "dsl_operations": ["train_classifier", "cross_validate", "roc_auc"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "SVM"}}, {"id": "method-4", "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": "PPI"}}, {"id": "method-5", "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": []}, "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": ["GSE95233", "GSE69063"], "resolved_accessions": ["GSE95233", "GSE69063"], "statements": ["All data used in this study are publicly available from the GEO, GTEx, Malacards, Phenopedia, and DisGeNET databases."], "basis": "The paper names GSE95233, GSE69063 in NCBI Gene Expression Omnibus (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:40428155", "data:geo:GSE69063"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE69063"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:53:14Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 8902, "completion_tokens": 2302, "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:40428155", "type": "paper", "label": "pmid:40428155"}, {"id": "source:pmid:40428155", "type": "manuscript", "label": "PMID 40428155 full text"}, {"id": "data:geo:GSE69063", "type": "dataset", "label": "GEO GSE69063"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:40428155", "type": "paper", "label": "pmid:40428155"}, {"id": "source:pmid:40428155", "type": "manuscript", "label": "PMID 40428155 full text"}, {"id": "data:geo:GSE69063", "type": "dataset", "label": "GEO GSE69063"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-40428155", "type": "extraction", "used": ["source:pmid:40428155"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE69063", "type": "accession_resolution", "used": ["data:geo:GSE69063"], "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:40428155", "parent_hash": "sha256:8b32d67341b8f2bb7f6a3b25853ef916c41833b4fb873f7a17785f8b342290f9", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE69063 licence not read", "asset:data:geo:GSE69063 not downloaded", "asset:data:geo:GSE95233 licence not read", "asset:data:geo:GSE95233 not downloaded", "execution.not_run", "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": ["xpression biomarkers. Analysis of normalized microarray data from GEO (GSE95233 and GSE69063) identi"], "order_basis": "paper_text_order:669", "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": ["Differential expression analysis was performed using the limma package [27] in R (version 2024.12.1+563)."], "order_basis": "consumes_earlier_output", "id": "assay:2"}]}