NCSI: Machine Learning to Optimize Novel Drug Design

Status	Completed
Mentor Name	Gail L Rosen
Mentor's XSEDE Affiliation	Research Allocation
Mentor Has Been in XSEDE Community	4-5 years
Project Title	Machine Learning to Optimize Novel Drug Design
Summary	We are recruiting a student toadvance a novel deep learning (and other ML) framework for computational fragment-based drug design. We work with chemistry collaborators to develop and evaluate a reinforcement learning-based model using HPC to generate novel drug leads based on protein structure and computational docking analysis. The student will optimize and advance the modeling framework for clinically important drug targets.
Job Description	1) Study efficient reinforcement learning and particle swarm optimization HPC architectures, 2) Learn how to run architectures for drug targets, 3) and modify and optimize algorithms using the architectures to generate novel lead designs, which will be evaluated in conjunction with chemistry collaborators.
Computational Resources	We will use our existing allocation. Project: BIR190002 Title: Improving genomic sequence analysis by machine learning
Contribution to Community	This project will give the student the opportunity to experience working on a real scientific project. It will be hands on training for HPC. Students will learn GPU programming and distributed computing for ML implementations
Position Type	Apprentice
Training Plan	During the first couple of weeks students will be train on how to run python, AutoDockVina, and a reinforcement learner. The student will also study other techniques such as particle swarm optimization. We will start with simple batch jobs and move to running jobs on multiple CPU cores and multiple GPUs.
Student Prerequisites/Conditions/Qualifications	Fundamentals/Python and Unix/Bash knowledge is required. Basic machine learning knowledge, basic chemistry knowledge, and other programming languages is a plus.
Duration	Semester
Start Date	01/03/2022
End Date	04/22/2022