Machine Learning and Disease Treatments

 'Transformational' Approach to ML Could Accelerate Search for Disease Treatments

University of Cambridge (U.K.), in CACM.November 29, 2021

The transformational machine learning (TML) approach developed by U.K., Swedish, Indian, and Dutch researchers can learn from multiple problems, improving its performance in the process. Ross King at the U.K.'s University of Cambridge said the system "learns information from previous problems it has encountered in order to better learn new problems." He said the approach outperforms current machine learning (ML)-based drug design methods by checking what other ML models determine about a particular molecule, which could speed up the search for new disease therapies. "It's better at choosing drugs than humans are—and without the best science, we won't get the best results," King said.