Collaborative filtering on a family of biological targets.

Building a QSAR model of a new biological target for which few screening data are available is a statistical challenge. However, the new target may be part of a bigger family, for which we have more screening data. Collaborative filtering or, more generally, multi-task learning, is a machine learning approach that improves the generalization performance of an algorithm by using information from related tasks as an inductive bias. We use collaborative filtering techniques for building predictive models that link multiple targets to multiple examples. The more commonalities between the targets, the better the multi-target model that can be built. We show an example of a multi-target neural network that can use family information to produce a predictive model of an undersampled target. We evaluate JRank, a kernel-based method designed for collaborative filtering. We show their performance on compound prioritization for an HTS campaign and the underlying shared representation between targets. JRank outperformed the neural network both in the single- and multi-target models.

Biased fragment distribution in MC simulation of protein folding.

Monte Carlo (MC) methods play an important role in simulations of protein folding. These methods rely on a random sampling of moves on a potential energy surface. To improve the efficiency of the sampling, we propose a new selection of trial moves based on an empirical distribution of three-residue (triplet) conformations. This selection is compared to random combinations of the preferred conformations of the three amino acids, and it is shown that the new trial moves lead to finding structures closer to the native conformation.