Machine-learning scoring functions have been found to outperform standard scoring functions for binding affinity prediction of protein-ligand complexes. A plethora of reports focus on the implementation of increasingly complex algorithms, while the chemical description of the system has not been fully exploited. Herein, we introduce Extended Connectivity Interaction Features (ECIF) to describe protein-ligand complexes and build machine-learning scoring functions with improved predictions of binding affinity. ECIF are a set of protein−ligand atom-type pair counts that take into account each atom’s connectivity to describe it and thus define the pair types. ECIF were used to build different machine-learning models to predict protein-ligand affinities (pKd / pKi). The models were evaluated in terms of “scoring power” on the Comparative Assessment of Scoring Functions 2016. The best models built on ECIF achieved Pearson correlation coefficients of 0.857 when used on its own, and 0.866 when used in combination with ligand descriptors, demonstrating ECIF descriptive power. Data and code to reproduce all the results are freely available at https://github.com/DIFACQUIM/ECIF. Supplementary data are available at Bioinformatics online.

Propolis is a natural resinous material produced by bees and has been used in folk medicines since ancient times. Due to it possessing a broad spectrum of biological activities, it has gained significant scientific and commercial interest over the last two decades. As a result of searching 122 publications reported up to the end of 2019, we assembled a unique compound database consisting of 578 components isolated from both honey bee propolis and stingless bee propolis, and analyzed the chemical space and chemical diversity of these compounds. The results demonstrated that both honey bee propolis and stingless bee propolis are valuable sources for pharmaceutical and nutraceutical development.

Open chemoinformatic servers facilitate analysis of chemical space and structure–activity relationships.

Naturally occurring small molecules include a large variety of natural products from different sources that have confirmed activity against epigenetic targets. In this work we review chemoinformatic, molecular modeling, and other computational approaches that have been used to uncover natural products as inhibitors of DNA methyltransferases, a major family of epigenetic targets with therapeutic interest. Examples of computational approaches surveyed in this work are docking, similarity-based virtual screening, and pharmacophore modeling. It is also discussed the chemoinformatic-guided exploration of the chemical space of naturally occurring compounds as epigenetic modulators which may have significant implications in epigenetic drug discovery and nutriepigenetics.