Inferring Principles of Cell Cycle Regulation from Lineage Correlations in Cancer Cells



Shaon Chakrabarti, National Centre for Biological Research at the Tata Institute of Fundamental Research, India


2020.10.27 10:45-11:45


Room 306, No. 5, Science Building


In this talk, we will see how a seamless integration of molecular modeling (ML), machine learning (MM), and high-performance computing (HPC) pushes the limit of molecular simulation with ab initio accuracy and addresses issues that would be computationally inaccessible otherwise. In the first part, using examples at scales of electrons, molecules, and coarse-grained particles, we introduce a list of machine learning-based models that help overcome the conventional accuracy-vs-efficiency dilemma in multi-scale molecular modeling problems. In the second part, we present our efforts on developing related software packages and HPC schemes. In particular, we will discuss special optimization techniques and corresponding implications in this new ML+MM+HPC paradigm.


Linfeng Zhang is temporarily working as a research scientist at the Beijing Institute of Big Data Research. In the May of 2020, he graduated from the Program in Applied and Computational Mathematics (PACM), Princeton University, working with Profs. Roberto Car and Weinan E. Linfeng has been focusing on developing machine learning based physical models for electronic structures, molecular dynamics, as well as enhanced sampling. He is one of the main developers of DeePMD-kit, a very popular deep learning based open-source software for molecular simulation in physics, chemistry, and materials science.