SEARCH · PubMed Health

Results for “SHAP interpretability”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

23 records · Page 2Linked to original sources

PubMed2025

XPRS: a tool for interpretable and explainable polygenic risk score.

SUMMARY: The polygenic risk score (PRS) is an important method for assessing genetic susceptibility to diseases; however, its clinical utility is limited by a lack of interpretability tools. To address this problem, we introduce eXplainable PRS (XPRS), an interpretation and visualization tool that decomposes PRSs into genes/regions and single nucleotide polymorphism (SNP) contribution scores via Shapley additive explanations (SHAPs), which provide insights into specific genes and SNPs that significantly contribute to the PRS of an individual. This software features a multilevel visualization approach, including Manhattan plots, LocusZoom-like plots, and tables at the population and individual levels, to highlight important genes and SNPs. By implementing with a user-friendly web interface, XPRS allows for straightforward data input and interpretation. By bridging the gap between complex genetic data and actionable clinical insights, XPRS can improve communication between clinicians and patients. AVAILABILITY AND IMPLEMENTATION: The XPRS software is publicly available on GitHub at https://github.com/nayeonkim93/XPRS and can see the demo through our cloud-based web service at https://xprs.leelabsg.org/.

Software↗

PubMed2026

CircExor enables interpretable prediction of circRNA localization into extracellular vesicles.

Certain circular RNAs (circRNAs) are selectively enriched in extracellular vesicles (EVs), in which they contribute to intercellular communication and represent promising biomarkers, yet the sequence determinants of their sorting remain unclear. Existing computational predictors are optimized mainly for linear RNAs and rarely address circRNA localization into EVs. Here we introduce circExor, the first framework specifically designed for circRNA EV localization. We curate a dedicated benchmark data set of 2102 circRNAs and implement a variable-length end-to-end concatenation strategy together with k-mer frequency encoding to accommodate circular topology, long sequence length, and length heterogeneity. Using a tree-based classifier, circExor achieves superior performance compared with RNAlocate-v3 and ExoGRU, reaching an AUROC of 0.743 on the internal test set and an average AUROC of 0.680 on the held-out test set. SHAP-based analysis, sequence perturbation analysis, motif mapping, and cell-based experimental validation support the predicted EV tendency and identify YBX1, HNRNPK, HNRNPL, and NOVA2 as candidate RBPs potentially associated with circRNA sorting. CircExor therefore provides a predictive and interpretable framework that links in silico modeling to mechanistic hypotheses, and supports biomarker discovery and candidate prioritization for downstream studies of EV-associated circRNAs.

Journal Article↗

PubMed2026

From prediction to mechanism: Explainable AI uncovers plasma and CSF proteomic signatures of Alzheimer's disease.

Alzheimer's disease (AD) plasma and cerebrospinal fluid (CSF) proteomics can distinguish AD from cognitively normal controls, but the generalizability of machine learning performance and the recurrence of biological signals across datasets require cautious interpretation. We developed an explainable artificial intelligence framework spanning two fluids and four ADNI proteomic datasets, covering 2082 modality specific samples, all analysed internally within ADNI. Phase 1 analysed plasma using a 119 analyte NULISA and targeted UPENN panel (n = 727; 216 CE, 511 controls). Phase 2 extended the analysis to CSF using SOMAscan7k, TMT-MS and targeted SET2, with Elecsys Aβ42, Aβ40, total tau and p-tau181 as anchor biomarkers. Only SOMAscan was subject-independent relative to Phase 1 plasma; TMT-MS and SET2 overlapped with Phase 1 for 96.0% and 97.7% of subjects and therefore are not independent replication cohorts. Under subject-level splits with fold internal preprocessing, we compared Elastic Net, Explainable Boosting Machines and gradient boosted trees with SHAP-based explanations. Among the candidate pipelines, we selected the pipeline with the highest held-out test ROC AUC for each platform; the selected values were 0.927 in plasma and 0.954-0.973 across the three CSF datasets. Because the same held out test performance was used for pipeline selection and headline reporting, these are optimistically selected single-holdout estimates, not unbiased estimates of generalizable or clinical performance. Explanations identified five recurring biological axes within ADNI: cholinergic (ACHE), tau/14-3-3 (YWHAG, YWHAZ, YWHAB, YWHAE), neuro-axonal (NEFL, NEFH), microglial/complement (CHIT1, SMOC1, CHI3L1, C7, CFH) and synaptic (NPTXR, NPTX2, DLG4, SYT5, VSNL1, ELAVL2). CSF analyses showed synaptic vesicle-cycle enrichment (q = 2 × 10-6), and CSF YWHAG correlated strongly with total tau (ρ = 0.87). Cross-fluid directional concordance was modest overall (54-57%) but increased to 73-80% among mapped analyte/protein rows reaching q < 0.05 in CSF. These findings provide hypothesis-generating, internally supported evidence within ADNI. Independent external cohorts with locked pipelines are required to evaluate generalizable performance and biological reproducibility; the overlapping TMT-MS and SET2 analyses should not be interpreted as independent replication.

Alzheimer Disease↗

PubMed2025

Integrating explainable AI with multiomics systems biology and EHR data mining for personalized drug repurposing in Alzheimer's disease.

Alzheimer's disease (AD) is characterized by region- and patient-specific molecular heterogeneity, which hinders therapeutic design. In this study, we introduce PRISM-ML (PRecision-medicine using Interpretable Systems and Multiomics with Machine Learning), an open-source integrated analysis pipeline that combines interpretable machine learning with systems biology and electronic health record (EHR) data mining to elucidate the molecular diversity of AD and predict promising drug repurposing opportunities. First, we integrated and harmonized transcriptomic (bulk RNA-seq) and genomic (genome-wide association study) data from 2105 brain samples, each with matched data from the same individual (1363 AD patients, 742 controls; nine tissues), sourced from three independent studies. Random forest classifiers with SHapley Additive exPlanations (SHAP) identified patient-specific biomarkers; unsupervised clustering resolved 36 molecularly distinct "subtissues" (clusters of samples); and gene-gene co-expression networks prioritized 262 high-centrality bottleneck genes as putative regulators of dysregulated pathways. Next, knowledge graph-based drug repurposing predicted six FDA-approved drugs that simultaneously target multiple bottleneck genes and multiple AD-relevant pathways. Notably, in a large U.S. de-identified insurance-claims database (n = 364733), exposure to promethazine, one of the candidate drugs, was associated with a 57-62 % lower incidence of AD versus an active antihistamine comparator (adjusted hazard ratio 0.38; inverse-probability weighted 0.43; both p < 0.001), providing real-world support for its repurposing potential. In summary, PRISM-ML, as an explainable multi-omics analysis pipeline, is readily transferable to other complex diseases, advancing precision medicine.

Computational Biology↗

PubMed2025

HallmarkGraph: a cancer hallmark informed graph neural network for classifying hierarchical tumor subtypes.

MOTIVATION: Accurate tumor subtype diagnosis is crucial for precision oncology, yet current methodologies face significant challenges. These include balancing model accuracy with interpretability and the high costs of generating multi-omics data in clinical settings. Moreover, there is a lack of validated models capable of classifying hierarchical tumor subtypes across a comprehensive pan-cancer cohort. RESULTS: We present a graph neural network, HallmarkGraph, the first biologically informed model developed to classify hierarchical tumor subtypes in human cancer. Inspired by cancer hallmarks, the model's architecture integrates transcriptome profiles and gene regulatory interactions to perform multi-label classification. We evaluate the model on a comprehensive pan-cancer cohort comprising 11 476 samples from 26 primary cancers with 405 subtypes up to eight levels. The model demonstrates exceptional performance, achieving 5-fold cross-validation accuracy between 85% and 99% for tumor subtypes labeled with increasing details of genomic information. It also shows good generalizability on a validation dataset of 887 samples, assessed using three metrics that consider tumor subtypes at individual, combined, and sample levels. Benchmarking and ablation experiments show that hallmark-based embeddings slightly influence model performance, while the integrated multilayer perceptron plays a significant role in determining classifier accuracy. Additionally, we use the SHAP method to link cancer hallmarks with genes, identifying key features that influence model decisions. Our findings present a biologically informed machine learning framework capable of tracking tumor transcriptomic trajectories and distinguishing inter- and intra-tumor heterogeneity in pan-cancer. This approach holds promise for enhancing cancer diagnostics. AVAILABILITY AND IMPLEMENTATION: HallmarkGraph is accessible at https://github.com/laixn/HallmarkGraph.

Humans↗