Leili Zhang1, Giacomo Domeniconi2, Ruhong Zhou3, Guojing Cong4, Chih-Chieh Yang5, Seung-Gu Kang5. 1. IBM Thomas J. Watson Research Center, 1101 Kitchawan Rd, 10598, Yorktown Heights, NY, USA. zhangle@us.ibm.com. 2. IBM Thomas J. Watson Research Center, 1101 Kitchawan Rd, 10598, Yorktown Heights, NY, USA. gdomeniconi@ibm.com. 3. ZheJiang University, 688 Yuhangtang Road, Hangzhou, 310027, China. 4. Oak Ridge national laboratory, 1 Bethel Valley Rd, 37830, Oak Ridge, TN, USA. 5. IBM Thomas J. Watson Research Center, 1101 Kitchawan Rd, 10598, Yorktown Heights, NY, USA.
Abstract
BACKGROUND: Drug discovery is a multi-stage process that comprises two costly major steps: pre-clinical research and clinical trials. Among its stages, lead optimization easily consumes more than half of the pre-clinical budget. We propose a combined machine learning and molecular modeling approach that partially automates lead optimization workflow in silico, providing suggestions for modification hot spots. RESULTS: The initial data collection is achieved with physics-based molecular dynamics simulation. Contact matrices are calculated as the preliminary features extracted from the simulations. To take advantage of the temporal information from the simulations, we enhanced contact matrices data with temporal dynamism representation, which are then modeled with unsupervised convolutional variational autoencoder (CVAE). Finally, conventional and CVAE-based clustering methods are compared with metrics to rank the submolecular structures and propose potential candidates for lead optimization. CONCLUSION: With no need for extensive structure-activity data, our method provides new hints for drug modification hotspots which can be used to improve drug potency and reduce the lead optimization time. It can potentially become a valuable tool for medicinal chemists.
BACKGROUND: Drug discovery is a multi-stage process that comprises two costly major steps: pre-clinical research and clinical trials. Among its stages, lead optimization easily consumes more than half of the pre-clinical budget. We propose a combined machine learning and molecular modeling approach that partially automates lead optimization workflow in silico, providing suggestions for modification hot spots. RESULTS: The initial data collection is achieved with physics-based molecular dynamics simulation. Contact matrices are calculated as the preliminary features extracted from the simulations. To take advantage of the temporal information from the simulations, we enhanced contact matrices data with temporal dynamism representation, which are then modeled with unsupervised convolutional variational autoencoder (CVAE). Finally, conventional and CVAE-based clustering methods are compared with metrics to rank the submolecular structures and propose potential candidates for lead optimization. CONCLUSION: With no need for extensive structure-activity data, our method provides new hints for drug modification hotspots which can be used to improve drug potency and reduce the lead optimization time. It can potentially become a valuable tool for medicinal chemists.
Entities:
Keywords:
Clustering; Drug discovery; Lead optimization; Machine learning; Molecular dynamics simulation; Variational autoencoder
Authors: Ricardo Macarron; Martyn N Banks; Dejan Bojanic; David J Burns; Dragan A Cirovic; Tina Garyantes; Darren V S Green; Robert P Hertzberg; William P Janzen; Jeff W Paslay; Ulrich Schopfer; G Sitta Sittampalam Journal: Nat Rev Drug Discov Date: 2011-03 Impact factor: 84.694