Lab members

Michael Keiser, PhD bio photo

Michael Keiser, PhD

Assistant Professor

pharm chem; bts; ichs; ind

Michael joined the UCSF faculty in the Dept. of Pharmaceutical Chemistry and the Institute for Neurodegenerative Diseases as an Assistant Professor in 2014, with joint appointments in the Dept. of Bioengineering & Therapeutic Sciences and the Institute for Computational Health Sciences. Before this, he co-founded a startup bringing systems pharmacology methods to pharma and the US FDA. During his bioinformatics Ph.D. at UCSF as a NSF Fellow, Michael developed techniques to relate drugs and proteins from the statistical similarity of their ligands, such as the Similarity Ensemble Approach (SEA). He also holds B.Sc., B.A., and M.A. degrees from Stanford University.

Email Google Scholar LinkedIn Github UCSF Profiles

Elena Caceres bio photo

Elena Caceres

Grad Student; NSF Fellow; HHMI Gilliam Fellow


Elena graduated from UCSD with a B.Sc. in molecular biology and a minor in mathematics. As of 2014, she is a graduate student in the Bioinformatics program as part of the iPQB program at UCSF. She is interested in applying techniques from statistics and machine learning to better understand and predict features underlying drug-target interactions.

Email Github

Kangway Chuang, PhD bio photo

Kangway Chuang, PhD

Postdoctoral Scholar

Email LinkedIn Github

Edward Elhauge, MPH bio photo

Edward Elhauge, MPH


Email LinkedIn Github

Garrett Gaskins bio photo

Garrett Gaskins

Grad Student; Genentech Fellow; Hillblom Fellow


High-content screening across varied cells, conditions, and chemical libraries has emerged as a key method for identifying novel compounds capable of systematically perturbing a biological network to induce a phenotype. The molecular targets (proteins, receptors, etc.) through which these compounds act to achieve their phenotype(s) are typically unknown. I am currently developing a chemoinformatic approach using aspects of image processing, machine learning, and SEA to identify the targets of novel compounds via their phenotypic signature.

Email Github

Leo Gendelev bio photo

Leo Gendelev

Grad Student; Fletcher Jones Fellow


Traditional approaches for ligand similarity, such as neighborhood or path based fingerprints, are based on molecular patterns, containing little information about the physics underlying protein-ligand recognition events. I am using a combined cheminformatics and structural bioinformatics approach to construct a thesaurus for ligand-based scaffolds, related via their interaction patterns with proteins from high-resolution x-ray crystals. This thesaurus will then be used to construct 3D interaction fingerprints for use in SEA (Similarity Ensemble Approach), for constraining or filtering virtual screening experiments, and for designing ligand-binding proteins. In developing these interaction fingerprints, we differ philosophically from previous fingerprinting approaches in that we strive to capture statistically enriched many-body interactions instead of painting yet another unsatisfying pairwise landscape.

Email Github

Amanda Li, PhD bio photo

Amanda Li, PhD

Postdoctoral Scholar

Email LinkedIn Github

Nick Mew, MS bio photo

Nick Mew, MS


Coming from a software engineering and computer science background, I’m focused on creating research tools that combine the state of the art in machine learning, statistics and data visualization. My current research involves training artificial neural networks to answer questions related to drugs, targets and their interactions. I also work on creating interactive visualizations that help human neural networks answer similar questions.

Email Github

Ziqi Tang bio photo

Ziqi Tang

Visiting Research Scholar

Tsinghua University

Ziqi is an undergraduate student from Tsinghua University School of Pharmaceutical Sciences, participating in the UCSF-Tsinghua University Joint Student Education Program. His interests are in polypharmacology and machine learning.


Lab alumni

Cristina Melero, MS bio photo

Cristina Melero, MS

Email LinkedIn Github

Michael Mysinger, PhD bio photo

Michael Mysinger, PhD

Principal Scientist, Atomwise

Email LinkedIn Github