Proteins
Schmidt Center researchers are developing methods to decipher the structure of particularly large or disordered proteins — and accurately predict protein binding.
Advances in biomedical technologies have resulted in an explosion of data. Yet, self-driving cars, advertising, and recommender systems are the key drivers of advances in machine learning today. These systems require machine learning tools that optimize prediction accuracy.
This is insufficient for biological problems where we seek to understand the genetic circuits of cells and the root causes of disease.
While biology and machine learning have so far largely developed in parallel, our goal is to foster a two-way street between the disciplines. We envision that biomedical problems will fuel foundational advances in machine learning — and that machine learning will drive what kinds of biological data scientists generate.
Such a two-way street between the disciplines holds the potential to create a new era of biology, yielding a deeper understanding of basic biological processes and improvements in human health.
Schmidt Center researchers are developing methods to decipher the structure of particularly large or disordered proteins — and accurately predict protein binding.
Our researchers develop strategies to iteratively identify the best modifications, or “perturbations,” to change cells from one state to another.
Our researchers build machine-learning methods that integrate gene expression, cell location, and other data modalities to uncover how tissues are organized in health and disease.
Our researchers create methods to integrate genetic, cellular, and tissue-level data to better characterize diseases — and predict who will respond best to what therapies.