Program

Annual International Conference on Critical Assessment of Massive Data Analysis
Washington, DC | July 12-16, 2026

Programme

The scientific program includes keynotes by leading researchers in the field (Prof Katherine Pollard and Prof Hoon Cho).

Schedule

Wednesday, 15 July 2026

11:00	CAMDA Welcome & Overview
11:10	CAMDA Keynote: Strain-resolved metagenomics enables detection of bacterial genes associated with human traits	Katherine Pollard, UCSF, U.S.A.
12:00	CAMDA Challenges - Introduction	Paweł Łabaj, MCB UJ, Poland
12:20	Differential Connectivity Analysis of Integrated Gut Microbiome Networks for Disease Prediction	Yulin Li, Univeristy of Florida, U.S.A.
13:00	Lunch
14:20	Metabolic Pathways as Ecological Niches: Topological Reorganization of Gut Microbiome Functional Networks Across Health and Disease	Nelly Selem, UNAM, Mexico
14:40	A Dual-Layer Network Framework Reveals Hidden Functional Drivers of Gut Microbiome Dysbiosis	Safa Bushnaq, Oxford Brookes University, U.K.
15:00	Knowledge Graph-Guided Interpretation of Disease-Specific Taxon-Taxon Interaction Networks in the Gut Microbiome	He Cheng, University of Colorado Anschutz Medical Campus, U.S.A.
15:20	Network-based optimal transport analysis of gut microbiome data in colorectal cancer	Jung Hun Oh, Memorial Sloan Kettering Cancer Center, U.S.A.
15:30	Metabolite-centric functional annotation with context-specific starting points	Ivory Blakley, UNC Charlotte, U.S.A.
15:40	Predicting Resistance with ALPAR	Alper Yurtseven, Helmholtz Institute for Pharmaceutical Research Saarland, Germany
16:00	Afternoon break
16:40	An Accurate Machine Learning Workflow for Inference of Antimicrobial Resistance from Bacterial Genomes	David Danko, Cornell University, U.S.A.
17:20	Quantifying uncertainty in protein representations across models and tasks	R. Prabakaran, Emory University, U.S.A.
18:00	Closing remarks

Thursday, 16 July 2026

08:40	CAMDA Welcome
08:50	CAMDA Keynote: Towards Privacy-Preserving Genomics: Understanding and Mitigating Risks	Hoon Cho, Yale, U.S.A.
09:40	A rigorous benchmarking of alignment-based HLA typing algorithms for RNA-seq data	Serghei Mangul, USC, U.S.A. / MCB UJ, Poland
10:00	Morning Break
11:00	The Health Privacy Challenge - Introduction	Hakime Öztürk, EMBL Germany
11:20	A Unified Weighted-Distance Framework for No-Box Membership Inference Attacks on Synthetic Gene Expression Data	Owen Tucker, Emory University, U.S.A.
11:40	Privacy Auditing of Synthetic Single-Cell RNA-seq Data	Steven Golob, University of Washington, Tacoma, U.S.A.
12:00	Does Synthetic Bulk RNA-seq Data Protect Donors? Privacy Auditing through Membership Inference Attacks	Charlene Jarrell, University of Washington, Tacoma, U.S.A.
12:20	Privacy-Preserving Synthetic Single-Cell RNA-seq via NMF-Compressed Truncated Vine Copulas	Andrew Wicks, DFKZ, Germany
12:40	From Graphical Models to Foundation Models: Synthetic Bulk RNA-seq Data Generation	Daniil Filienko, University of Washington, Tacoma, U.S.A.
12:50	Two-Stage P-PGM + Beta-CVAE Pipeline for Differentially Private Synthetic RNA-seq Generation	Eren Kotar, Boğaziçi University, Turkey
13:00	Lunch
14:20	Harmonization and Integration of Pharmacogenomics Screens	Nicole Mattson, University of California San Diego, U.S.A.
15:00	Adapting Mamba 2 For EHR Data Using Continual Learning	Mattia Prosperi, University of Florida, U.S.A.
15:20	CAMDA Invited: Insights from a Large Community Challenge Benchmark Applicable to AI/ML-based Complex Biomarkers	Wendell Jones, MAQC Society
15:50	CAMDA Trophy
18:00	Conference closing

Keynotes

Dr. Katherine S. Pollard

Director of the Gladstone Institute of Data Science & Biotechnology

Investigator at the Chan Zuckerberg Biohub

Professor of Bioinformatics at UCSF

Keynote Title: Strain-resolved metagenomics enables detection of bacterial genes associated with human traits

Abstract:

Metagenomic data holds great promise for characterizing human-associated microbes at the strain level. However, a deeply sequenced tree of life poses many challenges for traditional bioinformatics approaches, ranging from computational complexity to alignment errors and blurred species boundaries. This talk will explore these issues and some emerging solutions that enable strain-level and gene-level characterization of microbiomes. These tools make it possible to link microbiome genotypes with human traits at biobank scale. A mixed modeling approach will be presented along with some examples for how it can be used to generate testable causal hypotheses.

About the speaker:

Dr. Katherine S. Pollard is Director of the Gladstone Institute of Data Science & Biotechnology, Investigator at the Chan Zuckerberg Biohub, and Professor of Bioinformatics at UCSF. Her lab develops machine learning models and open-source bioinformatics software for predictive understanding and AI-guided experimentation with an emphasize on human genetics and genomics. Previously, Dr. Pollard was an assistant professor in the University of California, Davis Genome Center and Department of Statistics. She earned her PhD in Biostatistics from the University of California, Berkeley and was a comparative genomics postdoctoral fellow at the University of California, Santa Cruz. She was awarded the Thomas J. Watson Fellowship, the Sloan Research Fellowship, and the Alumna of the Year from UC Berkeley. She is a member of the National Academy of Medicine and a Fellow of the American Association for the Advancement of Science, International Society for Computational Biology, American Institute for Medical and Biological Engineering, and California Academy of Sciences.

Hyunghoon (Hoon) Cho, PhD

Assistant Professor of Biomedical Informatics & Data Science and of Computer Science at Yale

Director of Graduate Admissions for the Human Genome Sciences PhD Program at Yale

Keynote Title: Towards Privacy-Preserving Genomics: Understanding and Mitigating Risks

Abstract:

As genomic datasets continue to expand in scale, diversity, and modality, the privacy implications of sharing massive amounts of human data are becoming increasingly urgent. I will discuss how principled mathematical frameworks for quantifying privacy risk can deepen our understanding of genomic privacy while guiding the development of practical methods for privacy-preserving data sharing and analysis. I will highlight recent work on vulnerabilities in genome imputation services, linkage risks in transcriptomic data, and formal approaches for genetic association studies with privacy guarantees. I will conclude with an outlook on how community-driven efforts can accelerate progress in this area, enabling the scientific community to maximize the value of data sharing while safeguarding the individuals who make such research possible.

About the speaker:

Hyunghoon (Hoon) Cho, PhD, is an Assistant Professor of Biomedical Informatics & Data Science and of Computer Science at Yale. He also serves as Director of Graduate Admissions for the Human Genome Sciences PhD Program at Yale. He received his PhD in Electrical Engineering and Computer Science from MIT in 2019 and previously earned his MS and BS with Honors in Computer Science from Stanford University. Prior to joining Yale, he was a Schmidt Fellow and Principal Investigator at the Broad Institute of MIT and Harvard. His research focuses on overcoming key computational challenges in analyzing massive and distributed biomedical data, creating modern tools based on applied cryptography and machine learning. He is particularly interested in developing privacy-preserving, scalable AI methods and mathematical models for extracting insights from complex genomic data to advance human health. He is a recipient of the NIH Director’s Early Independence Award.