This is a past event.
Chemical Engineering Seminar
Dr. Camille Bilodeau
Massachusetts Institute of Technology
Faculty Candidate Research
Molecular dynamics simulations are powerful tools capable of predicting important physical quantities ranging from the viscosity of liquids to the strength of drug binding while simultaneously yielding a full molecular picture of the phenomena of interest. In the past decade, the advent of GPU computing has resulted in dramatic improvements in the computational speed of MD simulations, making it possible to study and predict the behavior of larger, more complex systems. Concurrently, the field of deep learning has experienced a renaissance, with neural networks being successfully employed for a variety of problems including reading text, classifying images, and even recently folding proteins. In the first half of this seminar, I will describe how molecular dynamics simulations can be used to design new ligands for applications in protein chromatography. Specifically, we found that a series of commonly used, commercially available ligands self-assemble to form patterned surfaces when immobilized on a hydrophilic surface. In the second half of this seminar, I will illustrate how neural networks can be trained to discover new molecules with enhanced solubility. In particular, we developed a generative modeling framework that optimizes a set of starting molecules by training a Hierarchical Graph Neural Network (HGNN) to translate a given molecule into an improved one. In the future, these techniques can be combined to facilitate the rapid discovery of ligands that self-assemble into patterned surfaces with desirable properties.
Dr. Camille Bilodeau is a postdoc studying machine learning for molecular design in Klavs Jensen’s group in the Chemical Engineering department at MIT. She completed her PhD research at RPI with Shekhar Garde and Steve Cramer, where she used molecular simulation methods to study water-mediated, multi-modal interactions in the context of protein chromatography. During her PhD, she was granted the Lawrence Livermore Advanced Simulations and Computation Graduate Fellowship, through which she collaborated closely with researchers at Lawrence Livermore National Laboratory. She was also given awards for her research including the ACS Best in Biotechnology award, the Preparative Chromatography Symposium first place poster award, and the Gordon Conference on Water and Aqueous Solutions poster award.
0 people added