Ensemble docking has provided an inexpensive method to account for receptor flexibility in molecular docking for virtual screening. Unfortunately, as there is no rigorous theory to connect the docking scores from multiple structures to measured activity, researchers have not yet come up with effective ways to use these scores to classify compounds into actives and inactives. This shortcoming has led to the decrease, rather than an increase in the performance of classifying compounds when more structures are added to the ensemble. Previously, we suggested machine learning, implemented in the form of a naïve Bayesian model could alleviate this problem. However, the naïve Bayesian model assumed that the probabilities of observing the docking scores to different structures to be independent. This approximation might prevent it from achieving even higher performance. In the work presented in this paper, we have relaxed this approximation when using several other machine learning methods—k nearest neighbor, logistic regression, support vector machine, and random forest—to improve ensemble docking. We found significant improvement.

No abstract

A new program, ECEP2D, for simulating the one-dimensional (1D) and two-dimensional (2D) patterns of the gel electrophoresis of a protein after it has been digested by one or more enzymes is introduced. With ECEP2D, students can gain deeper insights into gel electrophoresis by performing hands-on simulations. For example, students can visualize how 2D gel electrophoresis can improve resolution over 1D by comparing them side-by-side. Students can watch how different enzymes cut a protein into different fragments, giving rise to different gel patterns; some patterns are less congested than the others. Students can recognize how enzyme digestion can enhance gel electrophoresis to distinguish proteins. For students not having the chance to take biochemistry laboratories, ECEP2D provides a useful simulated learning environment. Instructors can also complement wet-lab experiments with simulations by ECEP2D to introduce more concepts with fewer laboratory hours. ECEP2D is available for free at .