<i>De novo</i> molecule design towards biased properties <i>via</i> a deep generative framework and iterative transfer learning

<p dir="ltr">This journal contribution is published Open Access by the publisher. Follow the DOI link to retrieve a copy of the full text. </p><p dir="ltr">Thanks for financial support by National Science Foundation (award number: 2154428) and U.S. Army Corps of Engineers, ERDC (grant number: W912HZ-21-2-0050). O. I. acknowledges the support from National Science Foundation (award number: 2154447). Part of the computation for this work was performed at the San Diego Supercomputer Center (SDSC) and the Pittsburgh Supercomputing Center (PSC) through allocation CHE200122 from the Advanced Cyberinfrastructure Coordination Ecosystem: Services & Support (ACCESS) program, which is supported by National Science Foundation grants #2138259, #2138286, #2138307, #2137603, and #2138296. Rest of the calculation was done on the high-performance computing infrastructure provided by Research Computing Support Services at the University of Missouri, Columbia MO, which is in part supported by National Science Foundation (Award number: CNS-1429294).</p>