BIOKDD is among the longest-running workshops at the ACM SIGKDD Conference and the longest-running one devoted to biomedical data mining — from the first sequence-motif algorithms of 2001 to the digital twins of 2026. Every year, the field's evolving frontier has been tested, debated, and published here.
Welcome to BIOKDD's 25-year retrospective. What started in 2001 as a small workshop at ACM SIGKDD has grown into the longest-running forum where data mining and biology meet — a place where new methods test themselves against new biology, where students share a session with department chairs, and where the next year's frontier is often visible eighteen months before the journals confirm it.
If you are a returning author, thank you for shaping this community. If you are new, you are very welcome here. Browse the 25-year archive below, plan to join us in August for BIOKDD 2026 on Digital Twins, and consider joining our LinkedIn group to stay in touch between editions.
BIOKDD was founded in 2001 to give biomedical data-mining research a permanent home inside the world's flagship knowledge-discovery conference. Twenty-four editions later, it has tracked — and often led — every major wave of biomedical informatics: sequence motifs, microarrays, networks, NGS, deep learning, multi-omics, large language models, and now digital twins.
Across 25 years, four distinct research phases emerge from the workshop's program. Each phase reflects what biology was producing — and what data-mining methods were ready to absorb.
The first eight years brought sequence motifs, microarray clustering, biclustering, frequent-pattern mining, classification of expression profiles, and the earliest gene/protein interaction studies into SIGKDD.
NGS reshaped the data, and networks reshaped the methods. Pathway mining, network medicine, disease-gene prediction, and the first wave of structured biomedical big-data made BIOKDD a meeting point for systems and computational biologists.
Deep neural nets, single-cell omics, knowledge graphs, biomedical imaging, and electronic health records arrived together. BIOKDD became the place where the data-mining and biomedical-AI communities began to share a methodological vocabulary — culminating in the COVID-19 themed 2020 edition.
The current era opens with AlphaFold and closes with patient digital twins. Workshop themes track the frontier in real time — AI in medicine (2021), large-scale ML (2023), LLMs in bioinformatics (2024), generative biomolecular design (2025), digital twins (2026).
Twenty-five years of programs, keynotes, organisers and proceedings. Click any year to open its workshop page at biokdd.org/biokddXX/.
BIOKDD has been organised by a continuous chain of program and general chairs since 2001, with broad scientific program committees drawn from across academia, industry and government labs.
Joined as program co-chair in 2007 and has been in a chair or steering role every year since. Brought the biology and systems-biology community into BIOKDD — broadening the workshop from a pure data-mining venue into a meeting point for biomedical informaticians, and the principal force behind the workshop's sustained scientific impact across its second and third decades.
AIMed Lab · aimed-lab.orgJoined as program co-chair in 2017 and has run the workshop's program every year since. Established the IEEE/ACM TCBB Special Issue as a recurring BIOKDD tradition, ensuring that selected workshop papers are routed each year to a peer-reviewed journal venue — the workhorse behind the workshop's annual programmatic execution.
Faculty profile · luddy.indiana.eduFounded BIOKDD in 2001 and shaped its character through the workshop's foundational phases — the SIGKDD partnership, the open call for biological data-mining research, and the original program-committee network from which today's community grew. Has remained on the steering committee every year since, giving BIOKDD its continuous 25-year institutional memory.
Faculty profile · cs.rpi.edu/~zakiSubmissions are closed and the program is being finalized. We now invite the broader community to attend the workshop: a full day of peer-reviewed talks, an invited keynote, abstract spotlights and a late-breaking research session — all framed around digital twins for biology and medicine.
Register & attend BIOKDD 2026 →Across 25 editions, more than 1,800 researchers have been part of BIOKDD as authors, reviewers, program-committee members, keynote speakers, and attendees. Our LinkedIn group is the smaller, active online hub where this community stays in touch between editions.