Lab members

Michael Keiser, PhD bio photo

Michael Keiser, PhD

Assistant Professor

pharm chem; bts; ichs; ind

Michael completed a bioinformatics Ph.D. in 2009 at UCSF as a NSF Fellow, where he developed techniques to relate drugs and proteins based on their ligands, such as the Similarity Ensemble Approach (SEA). He also holds B.Sc., B.A., and M.A. degrees from Stanford University. He subsequently co-founded a startup bringing these methods to pharma companies and the US FDA. Michael joined the faculty at UCSF in the Dept. of Pharmaceutical Chemistry and the Institute for Neurodegenerative Diseases in 2014, with joint appointments in the Dept. of Bioengineering and Therapeutic Sciences and the Institute for Computational Health Sciences (ICHS).

Email Google Scholar Google+ LinkedIn Github UCSF Profiles


Elena Caceres bio photo

Elena Caceres

Grad student; NSF Fellow; HHMI Gilliam Fellow

bioinformatics

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


Garrett Gaskins bio photo

Garrett Gaskins

Grad student; Genentech Fellow; Hillblom Fellow

bioinformatics

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

biophysics

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


Nick Mew, MS bio photo

Nick Mew, MS

Specialist

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


Cristina Melero, MS bio photo

Cristina Melero, MS

Alumn (Specialist)

I am examining chemical-genetic epistasis in mammalian cell lines to understand the underlying targets associated with therapeutically relevant compounds. By simultaneously inactivating multiple targets through chemical and genetic manipulation, we can begin to elucidate the phenotypic outputs underlying these therapeutic effects.

Email LinkedIn Github


Michael Mysinger, PhD bio photo

Michael Mysinger, PhD

Alumn (Specialist)

Principal Scientist, Atomwise

Email LinkedIn Github