ISMB 2026 programme, Washington, DC, USA

Monday, July 13

11:00  Automating subtype-specific cancer gene prioritization at the OncoTree ontology scale using large language models (LLMs) for exploration in cBioPortal. Suhasini Lulla (Baylor College of Medicine)

11:20  Constrained LLM-Assisted Alignment of HPO Terms to Phecodes. Chenjie Zeng (NHGRI)

11:40  BiomarkerKB: A Knowledgebase Supporting a Standardized Biomarker-Centric Knowledge and Data Integration. Raja Mazumder (George Washington University)

12:00  Do Mice Speak Human? Cross-Species Semantic Alignment of Disease Metadata. Yuzhang Fu (Smith College)

12:20  Signal Over Noise: Semi-Automated Relevancy Scoring for Biomedical Knowledge in Drug Repurposing. Shilpa Sundar (University of North Carolina at Chapel Hill)

12:40  Constraining Pathogenetic State Hypotheses in Synovial Sarcoma: A Neuro Symbolic Pipeline for SS18::SSX1 Characterization via TTT Linear and Z3 Based SMT Verification. George Anstey (Anstey Research Group)

14:20  Bridging classical and transcriptomic cell types at scale: agentic AI workflows for the Cell Ontology. David Osumi-Sutherland (Wellcome Sanger Institute)

14:40  Developing a Semantically Interoperable Knowledge Graph Schema to Support Single Cell Transcriptomics. Matthew Diller (National Institutes of Health)

15:00  The critical role of human validation in the era of AI-assisted biocuration: Extending competencies and reflecting career progression in current frameworks. Patricia Carvajal-Lpez (EMBL-EBI)

15:20  SomaModules: A Pathway Enrichment Approach Tailored to SomaScan Data. Julin Candia (National Institutes of Health)

15:40  Poster Madness

16:40  Keynote: AI and ontologies: The beginning of a beautiful friendship. Maryann Martone (UC San Diego)

17:40  Closing Day 1

Tuesday, July 14 (joint session with BOSC)

11:00  Welcome

11:05  MEDFORD in a Box: Demonstrating the Improvements and Future Directions for a Metadata Description Language. Noah Daniels (The University of Rhode Island)

11:05  Distributing standardized annotations of public transcriptomics samples and studies with MetaHQ and Meta2Onto. Parker Hicks (University of Colorado Anschutz)

11:20  KGXVal: Open-source quality control and curation support for biomedical knowledge graph harmonization. Daniel Korn (University of North Carolina at Chapel Hill)

11:40  KG-Registry: the open registry of knowledge graphs and their provenance. J. Harry Caufield (Lawrence Berkeley National Laboratory)

12:00  Scalable Representation of Categorical Genomic Variation Using Cat-VRS. Daniel Puthawala (Nationwide Children's Hospital)

12:20  Curating Gene Symbol Relationships for the Resolution of Gene Symbol Ambiguity. Anastasia Bratulin (Ohio State University / Nationwide Children's Hospital)

12:20  FAIRSCAPE: Pre-model AI-Readiness and Interpretability for Biomedical Data. Timothy Clark (University of Virginia School of Medicine)

12:20  A FAIR Framework for Structured Biomarker Representation, Discovery, and Hypothesis Generation. Maria Kim (George Washington University)

12:40  The OBO Foundry in 2026: Building Sustainable Ontology Infrastructure for Interoperable Life Science Data. James Balhoff (Renaissance Computing Institute)

Tuesday, July 14 (joint session with the Function COSI)

14:20  Keynote: In a genAI world, does structured knowledge still have a role in science? Karin Verspoor (RMIT University)

15:00  GO-CAM: thousands of curated pathways using GO, and new tools for using them. Paul Thomas (University of Southern California)

15:20  STAR-GO: Improving Protein Function Prediction by Learning to Hierarchically Integrate Ontology-Informed Semantic Embeddings. Gke Uludoan (Bogazici University)

15:40  GIMME: Graph Inference for Microbial Metabolism Exploration using Knowledge Graphs. Winston Anthony (Pacific Northwest National Laboratory)

Tuesday, July 14 (BOKR)

16:40  DGLink: automated knowledge graph construction from biomedical data repositories. Woodward Galbraith (Northeastern University)

17:00  Transforming PubChem BioAssay Data into Linked Open Data through the Resource Description Framework (RDF) and Standard Ontologies. Sunghwan Kim (National Library of Medicine, NIH)

17:20  ImmPort: A Foundational Data Repository Facilitating AI-Enabled Immunology Research. Sanchita Bhattacharya (UCSF Bakar Computational Health Sciences Institute)

17:40  Sage Brain: An AI-Powered Cross-Disease Knowledge Graph Connecting Neurodegenerative Research Communities. Orion Banks (Sage Bionetworks)

Posters

Enabling Researchers to Quickly Find Useful Controlled-Access Data through View-Only Data Access Requests (VODAR). Jonathan Lawson (Broad Institute of MIT and Harvard)

Streamlining Controlled-Access Data Governance with DUOS: An Ontology-Based Review and Oversight System. Jonathan Lawson (Broad Institute of MIT and Harvard)

Harmonizing Toxicology Data: An LLM-Driven Framework for Creating Machine Learning-Ready Resources. Joan Saurina-i-Ricos (EMBL-EBI)

AI Enablement for Biocuration: Evaluating Training Impact and Emerging Workflow Patterns in Biomedical Data Curation. Michelle Holko (Computercraft)

Standardizing Cross-Species Transcriptomics Experimental Metadata using OBI and spaCy. Moya Zouhon (Smith College)

ChEBI 2.0: A robust foundation for future development. Adnan Malik (EMBL-EBI)

Biomarker Knowledge Graph for Multi-Disease Biomarker Discovery and Translational Insights. Maria Kim (George Washington University)

CAMERA: A Centralized Public Resource for Validated Alternative Methods to Support Regulatory Decision-Making. Trey Saddler (Dynanet Corporation)

Navigating the NIH Data Ecosystem: A Landscape Analysis of the 105 NIH-Funded Data Resources and the Path Toward Federation. Bronwyn Walsh (Baylor College of Medicine)

Integrating Protein Knowledge Network (ProKN) into NSF Prototype Open Knowledge Network (Proto-OKN) for Cross-Domain Knowledge Discovery. Chuming Chen (University of Delaware)

A Generative AI-Extracted Mechanistic Knowledge Graph for mAb Stability: Construction, Analysis, and Prediction with mAb-GATED. Gyu Seong Lee (CHA University)

Multi-DWPC: A many-to-one pathfinding approach for subgraph extraction in biomedical knowledge graphs. Lucas Gillenwater (University of Colorado Anschutz Medical Campus)

Transforming Biomedical Literature into Structured Gene-Disease Knowledge Through Agentic AI. Dongyu Liu (Sanofi)

GlyGen: An Integrated Knowledgebase for Glycoscience Data Discovery and Data Sharing. Rene Ranzinger (University of Georgia)

LLM-Assisted Evaluation of Biomedical Ontologies using OntoClean. William Duncan (University of Florida)

Source: ISCB ISMB 2026 programme (BOKR track and poster listings).

Submission Types

The Bio-Ontologies and Knowledge Representation (BOKR) COSI (renamed from the "Bio-Ontologies" COSI, http://www.bio-ontologies.org.uk/) is an International Society for Computational Biology (ISCB) Community of Special Interest (COSI) focused on research related to building and using structured knowledge in bioinformatics. Topics include ontologies, knowledge graphs, knowledge-enhanced learning, knowledge extraction, and, in general, any aspect related to the organisation, presentation, dissemination, and use of knowledge in biology, biomedicine, and the life sciences. Bio-Ontologies and Knowledge Representation (BOKR) continues the tradition of the Bio-Ontologies COSI and will be in its 29th year at ISMB 2026 (https://www.iscb.org/ismb2026). ISMB 2026 will be held in-person between July 12-16, 2026 and will feature two days of exciting keynotes and cutting-edge research in the BOKR sessions. BOKR will share one session on 14 July with the Bioinformatics Open Source Conference (https://www.open-bio.org/events/bosc-2026/) and another with the Function COSI (https://www.biofunctionprediction.org/).

Submissions

We invite the submissions of proceedings papers (9 pages), abstracts (1 page) which will be reviewed and selected abstracts invited for oral or poster presentation.

The COSI covers these topics:

• New knowledge bases, knowledge graphs, and ontologies

• Methods that use knowledge bases, knowledge graphs, and ontologies

• Applications using knowledge bases, knowledge graphs, and ontologies

• Methods to improve knowledge bases, knowledge graphs, and ontologies

in bioinformatics, biomedical/life science research, health informatics, and healthcare

Examples include (but are not limited to):

• Novel knowledge bases, knowledge graphs, and ontologies in bioinformatics

• Ontologies and knowledge graphs in annotations, mapping applications, and metadata standards

• FAIR data systems and application of ontologies and other linked open data

• Bio-curation platforms

• Evaluation of knowledge graphs, ontologies, and knowledge bases

• Ontologies, knowledge representation, and reasoning

• Machine learning/artificial intelligence and knowledge representation

• Neuro-symbolic methods in bioinformatics

• Semantic Web-enabled applications

• Ontologies for biomedical/life science research, health informatics, and healthcare

Submissions can be made on the ISMB site (https://www.iscb.org/ismb2026/home). For proceedings, please follow the instructions provided on the ISMB site. For all other submissions, please prepare your submission using the Bio-Ontologies and Knowledge Representation templates (https://www.bio-ontologies.org.uk/2026-meeting).

All submissions are reviewed (review criteria provided on the Bio-Ontologies and Knowledge Representation website). Based on the review process, abstracts will be selected for oral or poster presentation at the Bio-Ontologies and Knowledge Representation COSI.

Accepted submissions require that one author register for the conference and present the work. The presenter should identify themselves as the corresponding author during the submission process.

If you have any questions please feel free to send us an email (bioontologies@gmail.com), direct message us on Slack (bioontologies.slack.com), or post a message on Twitter (@bioontologies) or our LinkedIn Group (https://www.linkedin.com/groups/13998260/).

Bio-Ontologies has been running since 1998, please use the ISMB Annual Meetings drop-down menu above to access content from prior meetings.