462 Data Mining and Machine Learning in Molecular Sciences I

Wednesday, November 11, 2015: 8:30 AM - 11:00 AM
255A (Salt Palace Convention Center)

Computational approaches to correlate, analyze, and understand large and complex data sets are playing increasingly important roles in the physical, chemical, and life sciences. This session solicits submissions pertaining to methodological advances and applications of data mining and machine learning methods, with particular emphasis on data-driven modeling and property prediction, statistical inference, big data, and informatics. Topics of interest include: algorithm development, inverse engineering, chemical property prediction, genomics/proteomics/metabolomics, (virtual) high-throughput screening, rational design, accelerated simulation, biomolecular folding, reaction networks, and quantum chemistry.

Computational Molecular Science and Engineering Forum
Andrew L. Ferguson Email: alf@illinois.edu
Johannes Hachmann Email: hachmann@buffalo.edu
- indicates paper has an Extended Abstract file available on CD.

9:00 AM
(462b) Detecting the True Dimensionality of Complex Dynamical Systems Using Nonlinear Manifold Learning
Carmeline Dsilva, Ronen Talmon, Ray M. Sehgal, Ronald Coifman and Ioannis G. Kevrekidis

9:15 AM

9:30 AM
(462d) Near Perfect Prediction of HIV-1 Coreceptor Usage Reveals the Interactions Driving Tropism
Chris A. Kieslich, Phanourios Tamamis, Yannis A. Guzman, Melis Yildirim and Christodoulos A. Floudas

9:45 AM

10:15 AM
(621du) Machine Learning Approaches to Design Catalysts for C1 Chemistry
Shane F. Carr, Zhuo Cheng, Eunmin Lee, Darrell L. Nelson, Tolutola Oyetunde and Cynthia S. Lo

10:30 AM
(462g) Qsars for Predicting Physicochemical and Biochemical Properties of Industrial Chemicals
Dimosthenis Sarigiannis, Krystalia Papadaki, Perklis Kontoroupis and Spyros Karakitsios