Data science for novel molecular materials: Applications to supramolecular chemistry and stem cell science

Over the last several years, machine learning and other data science techniques have made a profound impact on computational chemistry. On the one hand, data science techniques have significantly broadened the scope of molecular simulation , allowing us to study more complex materials over longer time scales. On the other, these techniques have allowed us to extract obscure structure function correlations from molecule databases, which can subsequently be used to design new functional materials.

In this presentation, I will illustrate these points by introducing two topics from our group's research. The first topic concerns the formation of supramolecular clusters via on surface molecular self assembly. By utilizing machine learned intermolecular potentials, we have developed new methodology for simulating the molecular self assembly process and predicting what kinds of supra molecular clusters will form. This simulation enables one to screen different types of molecules for the purposes of designing new supramolecular materials with novel functionality. The second topic concerns the generation of cardiac tissue from human stem cells. We have developed a machine learned model which can predict whether a particular organic compound will induce cardiac differentiation when applied to a stem cell, on the basis of molecule shape and hydrophilicity information extracted from a small chemical database. This talk is intended for general audiences who wish to know something about how data science can be applied in chemistry.