Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing最新文献

{"title":"Integrating Polygenic Scores with Clinical, Lifestyle, and Social Risk Factors to Improve Heart Failure Risk Prediction.","authors":"Katie M Cardone, Dokyoon Kim, Marylyn D Ritchie","doi":"10.1142/9789819824755_0046","DOIUrl":"10.1142/9789819824755_0046","url":null,"abstract":"<p><p>Heart failure (HF) is highly prevalent, high-burden disorder with its prevalence expected to increase. Early detection of HF can reduce morbidity and mortality; therefore, novel early detection methods are needed. Polygenic scores (PGS) can combine common variants across the genome and provide phenotype-specific risk scores. However, there are also many well-known, non-genomic risk factors of HF, in the clinical, lifestyle, and social determinant of health (SDOH) domains, and it is not clear how genetic and non-genetic risk factors collectively contribute to HF risk. To address this question, we assessed whether combining HF PGS with clinical, lifestyle, and SDOH risk factors improves risk prediction. Leveraging data from the All of Us Research Program (n = 22,275), clinical risk factors were aggregated into a clinical risk score (CRS) while lifestyle and SDOH risk factors were aggregated into a polyexposure score (PXS). Feature selection was conducted with LASSO regression and statistical significance thresholding from logistic regression models (p < 0.05). Features were included in the model if they were statistically significant and important in ≥ 95% of 1000 iterations. To assess model performance, logistic regressions with HF case/control status were conducted with each risk score individually, as well as integrated models. The integrated model (PGS + CRS + PXS) performed better than individual risk scores (AUROC = 0.763, AUPRC = 0.047, F1 score = 0.062, balanced accuracy = 0.683). To assess the validity of the CRS and PXS, an integrated model with the PGS along with clinical and exposure risk factors as independent features was also evaluated. Based on AUPRC and F1 score, this integrated risk model (PGS + CRS risk factors + PXS risk factors) performed better than the combining the PGS with the CRS and PXS (AUROC = 0.738, AUPRC = 0.047, F1 score = 0.066, balanced accuracy = 0.657). These findings demonstrate that integration of risk factors across multiple domains can improve HF prediction. Knowing that PGS combined with clinical, lifestyle, and SDOH risk factors is predictive of HF risk provides greater opportunity for the identification of individuals at risk of HF prior to disease onset with the goal of prevention or early intervention.</p>","PeriodicalId":34954,"journal":{"name":"Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing","volume":"31 ","pages":"629-643"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12952681/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147310790","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Implicitly and Differentiably Representing Protein Surfaces and Interfaces.","authors":"Cory B Scott, Charlie Rothschild, Benjamin E Nye","doi":"10.1142/9789819824755_0030","DOIUrl":"10.1142/9789819824755_0030","url":null,"abstract":"<p><p>We introduce a pipeline for implicitly representing a protein, or protein complex, as the union of signed distance functions (SDFs) by representing each atom as a sphere with the appropriate van der Waals radius. While this idea has been used previously as a way to render images of proteins, it has not, to our knowledge, been widely adopted in a machine learning setting. Mirroring recent successful work applying SDFs to represent 3D geometry, we present a proof of concept that this representation of proteins could be useful in several biologically relevant applications. We also propose further experiments that are necessary to validate the proposed approach.</p>","PeriodicalId":34954,"journal":{"name":"Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing","volume":"31 ","pages":"425-437"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147310857","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"ColonCrafter: A Depth Estimation Model for Colonoscopy Videos Using Diffusion Priors.","authors":"Romain Hardy, Tyler M Berzin, Pranav Rajpurkar","doi":"10.1142/9789819824755_0003","DOIUrl":"10.1142/9789819824755_0003","url":null,"abstract":"<p><p>Three-dimensional (3D) scene understanding in colonoscopy presents significant challenges that necessitate automated methods for accurate depth estimation. However, existing depth estimation models for endoscopy struggle with temporal consistency across video sequences, limiting their applicability for 3D reconstruction.We present ColonCrafter, a diffusion-based depth estimation model that generates temporally consistent depth maps from monocular colonoscopy videos. Our approach learns robust geometric priors from synthetic colonoscopy sequences, enabling reliable depth estimation across frames. We also introduce a style transfer technique that preserves geometric structure while adapting realistic clinical videos to match our synthetic training domain. ColonCrafter achieves state-of-the-art zero-shot performance on the C3VD dataset, outperforming both general-purpose and endoscopyspecific approaches. Although full trajectory 3D reconstruction remains a challenge, we demonstrate clinically relevant applications of ColonCrafter, including 3D point cloud generation and surface coverage assessment. Our code will be made publicly available at https://github.com/rajpurkarlab/ColonCrafter.</p>","PeriodicalId":34954,"journal":{"name":"Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing","volume":"31 ","pages":"27-41"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147310768","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Clinician-Guided Framework for Endoscopic AI: Developing PanEndoAtlas and Benchmarking Foundation Models Across the Full GI Spectrum.","authors":"Shreya Johri, Luyang Luo, Hong-Yu Zhou, Todd Brenner, Sami Elamin, Mark Enrik Geissler, Tyler M Berzin, Pranav Rajpurkar","doi":"10.1142/9789819824755_0004","DOIUrl":"10.1142/9789819824755_0004","url":null,"abstract":"<p><p>Endoscopic procedures play a central role in the diagnosis and management of gastrointestinal (GI) diseases, yet the field lacks large-scale, clinically diverse benchmarks and unified datasets to evaluate vision foundation models. We introduce PanEndoSuite, the first unified ecosystem for endoscopic AI, developed through systematic collaboration between AI researchers and practicing gastroenterologists. PanEndoSuite consists of three complementary components: PanEndoAtlas, PanEndoX, and PanEndoFM. PanEndoAtlas is a harmonized dataset of over 420,000 labeled images from 30 public endoscopy datasets across 13 countries and 26 hospitals, creating a clinically-grounded hierarchical taxonomy that mirrors diagnostic reasoning patterns across 111 GI diseases. PanEndoX is a benchmark of 10 clinically grounded tasks, including hierarchical GI-tree classification, Barrett's esophagus grading, ulcerative colitis scoring, polyp subtyping, Boston Bowel Preparation Scale assessment, multi-organ disease classification, and anatomical landmark identification-designed to probe generalization across anatomical regions, disease presentations, and annotation granularities. PanEndoFM is a foundation model pretrained on a 10 million-image corpus curated from public data sources, spanning the entire GI tract. We benchmark PanEndoFM against two endoscopy-specific foundation models (EndoFM-LV, EndoSSL) and two general-purpose vision models (ViT-B/16, ResNet-50). PanEndoFM achieves the highest macro-AUC on 6 of 10 tasks, demonstrating broad clinical generalization; EndoFM-LV performs best on colon-focused tasks, EndoSSL excels in polyp subtyping, and ViT-B/16 shows strengths on small-intestine conditions. Together, PanEndoSuite establishes a foundation for building robust, generalist AI systems in gastrointestinal endoscopy that bridge current AI capabilities and clinical practice.</p>","PeriodicalId":34954,"journal":{"name":"Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing","volume":"31 ","pages":"42-56"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147311062","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The Intention-Execution Disconnect in Medical AI: The ReXecution Framework for Evaluating Real-World Clinical Performance.","authors":"Oishi Banerjee, Lucas Bijnens, Subathra Adithan, Pranav Rajpurkar","doi":"10.1142/9789819824755_0021","DOIUrl":"10.1142/9789819824755_0021","url":null,"abstract":"<p><p>We present the ReXecution framework for conducting clinician-centered assessments of medical AI assistants, providing detailed insights into their reliability in realistic clinical settings. Using this framework, we assessed AI assistants for chest X-ray (CXR) interpretation, exploring the gap between current model capabilities and real-world radiological needs. Unlike prior benchmarks that rely on automatically generated questions with limited clinical relevance, our dataset consists of 100 expert-curated tasks that radiologists might realistically present to an AI assistant in their day-to-day workflow. Through detailed manual review by a radiologist, we evaluated two leading foundation models, ChatGPTo3 and MedGemma, on our tasks. While both models demonstrated considerable medical knowledge and reasoning capabilities on our tasks, they frequently struggled to interpret images and execute tasks accurately, producing correct outputs in only 5-10% of cases. Our detailed manual evaluation highlights a critical mismatch: models often abstractly understand radiology concepts but cannot reliably execute their plans when interpreting specific medical images. This work identifies key gaps in current models' ability to serve as comprehensive radiology assistants and provides insights into how the development and evaluation of models can better align with real-world clinician needs, enabling seamless clinician-AI collaboration.</p>","PeriodicalId":34954,"journal":{"name":"Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing","volume":"31 ","pages":"294-308"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147310749","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MedAgentBench v2: Improving Medical LLM Agent Design.","authors":"Eric Chen, Sam Postelnik, Kameron Black, Yixing Jiang, Jonathan H Chen","doi":"10.1142/9789819824755_0025","DOIUrl":"10.1142/9789819824755_0025","url":null,"abstract":"<p><p>MedAgentBench is the first benchmark for evaluating LLM agents on clinical tasks in a FHIR-compliant EHR. In this paper, we present significant prompt engineering and tool design improvements over the original agent implementation and introduce a memory component that enables the agent to learn from prior failures. We added new tools for the agent to properly format its output for tasks, interact with an EHR without constructing explicit HTTP requests, which were prone to syntax errors, and make math calculations. We also wrote a new system prompt that asked the agent to outline its plan before making any tool calls and think step by step using chain of thought reasoning, and provided few shot examples of good vs. bad outputs. Using GPT-4.1 as the base model, our agent achieved a success rate of 91.0% without memory and 98.0% with memory. A surprising consequence is that the agent performed better on a different task that had no associated memory entry, possibly demonstrating that LLMs can adapt to the style of tasks presented by users. To contribute to the benchmark and evaluate the generalization of our agent, we developed 300 new multi-step clinically-driven tasks in collaboration with a physician. Lastly, we show the current limitations of these benchmarks and highlight the necessary next steps and challenges for the responsible deployment of AI agents in real-world healthcare settings. We hope that this paper leads to further development of EHR agents and benchmarks.</p>","PeriodicalId":34954,"journal":{"name":"Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing","volume":"31 ","pages":"354-371"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147310818","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"PertSpectra: Interpretable Matrix Factorization for Predicting Functional Impact of Genetic Perturbation Experiments.","authors":"Seowon Chang, Anna Shcherbina, Tal Ashuach, Shahin Mohammadi, Stephanie See, Ninad Ranadive, Emily Fox, Navpreet Ranu","doi":"10.1142/9789819824755_0033","DOIUrl":"10.1142/9789819824755_0033","url":null,"abstract":"<p><p>In drug discovery, measuring the effects of genetic perturbations is a powerful tool for studying unknown disease mechanisms, but biological interpretation of these effects, especially with the advent of screens involving combinatorial perturbations, remains challenging. To address limitations in current methodology we introduce PertSpectra, a guided triple matrix factorization that incorporates perturbation information and regularizes the model using a known gene-gene interaction graph prior to generate sparse, biologically relevant latent factors that capture perturbational effects. We evaluate PertSpectra on three single-cell RNAseq datasets with both single and combinatorial genetic perturbations, measuring latent space interpretability, predictive ability on unseen combinations of observed perturbations, and stratification of functionally similar perturbations. We show that PertSpectra provides an integrated modeling approach to understanding combinatorial perturbation data in the context of drug discovery.</p>","PeriodicalId":34954,"journal":{"name":"Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing","volume":"31 ","pages":"465-479"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147310794","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Gene-R1: Reasoning with Data-Augmented Lightweight LLMs for Gene Set Analysis.","authors":"Zhizheng Wang, Yifan Yang, Qiao Jin, Zhiyong Lu","doi":"10.1142/9789819824755_0035","DOIUrl":"10.1142/9789819824755_0035","url":null,"abstract":"<p><p>The gene set analysis (GSA) is a foundational approach for uncovering the molecular functions associated with a group of genes. Recently, LLM-powered methods have emerged to annotate gene sets with biological functions together with coherent explanatory insights. However, existing studies primarily focus on proprietary models, which have been shown to outperform their open-source counterparts despite concerns over cost and data privacy. Furthermore, no research has investigated the application of advanced reasoning strategies to the GSA task. To address this gap, we introduce Gene-R1, a data-augmented learning framework that equips lightweight and open-source LLMs with step-by-step reasoning capabilities tailored to GSA. Experiments on 1,508 in-distribution gene sets demonstrate that Gene-R1 achieves substantial performance gains, matching commercial LLMs. On 106 out-of-distribution gene sets, Gene-R1 performs comparably to both commercial and large-scale LLMs, exhibiting robust generalizability across diverse gene sources.</p>","PeriodicalId":34954,"journal":{"name":"Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing","volume":"31 ","pages":"494-507"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147310739","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Discovery of Disease Relationships via Transcriptomic Signature Analysis Powered by Agentic AI.","authors":"Ke Chen, Haohan Wang","doi":"10.1142/9789819824755_0058","DOIUrl":"10.1142/9789819824755_0058","url":null,"abstract":"<p><p>Modern disease classification often overlooks molecular commonalities hidden beneath divergent clinical presentations. This study introduces a transcriptomics-driven framework for discovering disease relationships by analyzing over 1,300 disease-condition pairs using GenoMAS, a fully automated agentic AI system. Beyond identifying robust gene-level overlaps, we develop a novel pathway-based similarity framework that integrates multi-database enrichment analysis to quantify functional convergence across diseases. The resulting disease similarity network reveals both known comorbidities and previously undocumented crosscategory links. By examining shared biological pathways, we explore potential molecular mechanisms underlying these connections-offering functional hypotheses that go beyond symptom-based taxonomies. We further show how background conditions such as obesity and hypertension modulate transcriptomic similarity, and identify therapeutic repurposing opportunities for rare diseases like autism spectrum disorder based on their molecular proximity to better-characterized conditions. In addition, this work demonstrates how biologically grounded agentic AI can scale transcriptomic analysis while enabling mechanistic interpretation across complex disease landscapes. All results are publicly accessible at https://github.com/KeeeeChen/Pathway_Similarity_Network.</p>","PeriodicalId":34954,"journal":{"name":"Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing","volume":"31 ","pages":"799-814"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147310696","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Session Introduction: Precision Medicine: Integrating Large-Scale Data and Intermediate Phenotypes for Understanding Health and Treating Disease.","authors":"Steven E Brenner, Nilah M Ioannidis, Tayo Obafemi-Ajayi, Anne O'Donnell-Luria","doi":"10.1142/9789819824755_0043","DOIUrl":"10.1142/9789819824755_0043","url":null,"abstract":"<p><p>The field of precision medicine has undergone rapid development over the past three decades, driven by advances in high-throughput molecular profiling, large-scale electronic health data, and computational modeling. The central objective is to refine disease risk prediction, diagnosis, and treatment strategies by incorporating genetic, molecular, environmental, and clinical information into individualized care. However, the effective integration of these heterogeneous data sources presents substantial analytical challenges. The 2026 Precision Medicine session of the Pacific Symposium on Biocomputing (PSB) highlights computational methods that bridge large-scale biological data and intermediate phenotypes, emphasizing approaches that advance mechanistic understanding, risk prediction, and clinical utility. The contributions span multi-modal risk modeling, biomarker discovery, and causal inference frameworks, demonstrating the breadth and depth of research in computational precision medicine.</p>","PeriodicalId":34954,"journal":{"name":"Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing","volume":"31 ","pages":"596-599"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147310251","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}