David Ryan Koes, PhD

Removing barriers to computational drug discovery one bit at a time



About

I am an Associate Professor in the Department of Computational and Systems Biology at the University of Pittsburgh and am an Associate Director of the Joint Carnegie Mellon-University of Pittsburgh Ph.D. Program in Computational Biology (CPCB). I am also affiliated with the Integrative Systems Biology, Intelligent Systems Program, and Computational Biomedicine & Biotechnology graduate programs.

I develop novel computational algorithms and build full-scale systems to support rapid and inexpensive drug discovery while simultaneously applying these methods to develop novel therapeutics. I seek to unlock the power of computation and machine learning to solve challenging, real world problems and am a staunch advocate of open source software and open science.

I use a light-themed IDE.

Undergraduate Research Application

Contact

748 Murdoch Building
Department of Computational & Systems Biology
School of Medicine, University of Pittsburgh
3420 Forbes Ave
Pittsburgh, PA 15213-3203

(412) 383-5745

   

Publications

Google Scholar NCBI

Presentations and Data

People

Graduate Students

Ian Dunn, Daniel Penaherrera, Rishal Aggarwal, Emma Flynn, Jacky Chen, Fareeda Abu-Juam (co-advised), Ben Krummenacher (co-advised), Tyler Katz (CMU CompBio MS), Justin Shao (CMU CompBio MS), Sumeet Kothare (CMU CompBio MS), Pratham Lotia (CMU Biotech MS), Yao Wang (COBB), Nate Odonkor (CMU CompBio MS), Liv Toft (CMU CompBio MS) Drew McNutt, Andrew Lutsky (CMU QuantBio MS), Minhyek Jeon (CMU CompBio MS), Rosalie Nolen (PittMed), Vratin Srivastava (CMU CompBio MS), Zoey Yang (CMU CompBio MS), Yanjing Li (CMU CompBio MS), William Hsu (CMU CompBio MS), Sitong Liu (CMU CompBio MS), Jackie Vo (CMU CompBio MS), Jonathan King, Paul Francoeur, Jocelyn Sunseri, Dillon Gavlock (COBB)

Research Fellows and PostDocs

Somayeh Pirhadi, Dakota Folmsbee, Matthew Ragoza, Rishal Aggarwal, Tomohide Masuda

Former

Teaching

MSCBIO2066: Scalable Machine Learning for Big Data Biology

Distributed and cloud computing meets machine learning meets computational biology.
The focus is on applications rather than theory. Co-taught with Maria Chikina
Spring Semester (2016-2024)

COBB2060: Machine Learning for Biomedical Applications

Successor to Scalable. Less distributed and cloud computing.
The focus remains on applications rather than theory. Co-taught with Maria Chikina
Spring Semester (2025-)

MSCBIO2025: Introduction to Bioinformatics Programming in Python

An graduate-level introductory programming course with a focus on analyzing biological data.
Fall Semester (2013-2023)

MSCBIO2030: Introduction to Computational Structural Biology

An introduction into the physical, chemical, and algorithmic underpinnings of computational structural biology.
Fall 2022, Spring 2025

CompBio Academy (formerly DiscoBio)

The Computational Biology Summer Academy at UPMC Hillman Cancer Center.
An experiential summer academy for rising high school juniors and seniors.
Co-Director 2013-2023

Software (GitHub)

libmolgrid
Python library for CUDA accelerated molecular gridding

gnina
Deep learning for molecular docking

pharmit
Interactive exploration of chemical space

3Dmol.js
Molecular visualization with WebGL

qsar-tools
Collection of scripts for creating and visualizing 2D QSAR models

SolTranNet Molecule attention transformer for aqueous solubility prediction.

smina*
Scoring and Minimization with AutoDock Vina

AnchorQuery*
Specialized pharmacophore search for targeting protein-protein interactions with multicomponent reaction chemistry.

Pharmer*
General pharmacophore search open-source software.

ZINCPharmer*
Free online pharmacophore search engine for the ZINC database.

PocketQuery*
Identify PPI inhibitor starting points from PPI structure.

ShapeDB*
Indexed search of molecular shapes

*Developed in collaboration with the Camacho Lab

Funding

I am currently funded through R35GM140753 from the National Institute of General Medical Sciences. I have previously received funding from CHE-2102474 from the National Science Foundation (with Geoff Hutchison), R21EY032632 from the National Eye Institute (with Partha Roy, Donna Huryn, and Andrew VanDemark), R01GM108340 from the National Institute of General Medical Sciences, CHE-1800435 from the National Science Foundation (with Geoff Hutchison), R21NS107785 from the National Institute of Neurological Disorders and Stroke (with Sam Poloyac and Lee McDermott), Relay Therapeutics, the Samuel and Emma Winters Foundation, the CTSI Biomedical Modeling Pilot Award, and aigrant.org, as well as hardware and software support from NVIDIA and Google Cloud Platform.