Computational prediction of Protein-Ligand Interaction (PLI) is an important step in the modern drug discovery pipeline as it mitigates the cost, time, and resources required to screen novel therapeutics. Deep Neural Networks (DNN) have recently shown excellent performance in PLI prediction. However, the performance is highly dependent on protein and ligand features utilized for the DNN model. Moreover, in current models, the deciphering of how protein features determine the underlying principles that govern PLI is not trivial. In this work, we developed a DNN framework named SSnet that utilizes secondary structure information of proteins extracted as the curvature and torsion of the protein backbone to predict PLI. We demonstrate the performance of SSnet by comparing against a variety of currently popular machine and non-Machine Learning (ML) models using various metrics. We visualize the intermediate layers of SSnet to show a potential latent space for proteins, in particular to extract structural elements in a protein that the model finds influential for ligand binding, which is one of the key features of SSnet. We observed in our study that SSnet learns information about locations in a protein where a ligand can bind, including binding sites, allosteric sites and cryptic sites, regardless of the conformation used. We further observed that SSnet is not biased to any specific molecular interaction and extracts the protein fold information critical for PLI prediction. Our work forms an important gateway to the general exploration of secondary structure-based Deep Learning (DL), which is not just confined to protein-ligand interactions, and as such will have a large impact on protein research, while being readily accessible for de novo drug designers as a standalone package.

Severe Acute Respiratory Syndrome Corona Virus 2 has altered life on a global scale. A concerted effort from research labs around the world resulted in the identification of potential pharmaceutical treatments for CoVID-19 using existing drugs, as well as the discovery of multiple vaccines. During an urgent crisis, rapidly identifying potential new treatments requires global and cross-discipline cooperation, together with an enhanced open-access research model to distribute new ideas and leads. Herein, we introduce an application of a deep neural network based drug screening method, validating it using a docking algorithm on approved drugs for drug repurposing efforts, and extending the screen to a large library of 750,000 compounds for de novo drug discovery effort. The results of large library screens are incorporated into an open-access web interface to allow researchers from diverse fields to target molecules of interest. Our combined approach allows for both the identification of existing drugs that may be able to be repurposed and de novo design of ACE2-regulatory compounds. Through these efforts we demonstrate the utility of a new machine learning algorithm for drug discovery, SSnet, that can function as a tool to triage large molecular libraries to identify classes of molecules with possible efficacy.

With the increasing popularity of machine learning (ML) applications, the demand for explainable artificial intelligence techniques to explain ML models developed for computational chemistry has also emerged. In this study, we present the development of the Boltzmann-weighted cumulative integrated gradients (BCIG) approach for effective explanation of mechanistic insights into ML models trained on high-level quantum mechanical and molecular mechanical (QM/MM) minimum energy pathways. Using the acylation reactions of the Toho-1 beta-lactamase and two antibiotics (ampicillin and cefalexin) as the model systems, we show that the BCIG approach could quantitatively attribute the energetic contribution in one system and the relative reactivity of individual steps across different systems to specific chemical processes such as the bond making/breaking and proton transfers. The proposed BCIG contribution attribution method quantifies chemistry-interpretable insights in terms of contributions from each elementary chemical process, which is in agreement with the validating QM/MM calculations and our intuitive mechanistic understandings of the model reactions.

The analysis of molecular dynamics simulation of the angiotensin-converting enzyme 2 peptidase domain via targeted machine learning and REDAN model revealed how the functional motions of this protein can be allosterically controlled.

In Arabidopsis thaliana, the Light-Oxygen-Voltage (LOV) domain containing protein ZEITLUPE (ZTL) integrates light quality, intensity, and duration into regulation of the circadian clock. Recent structural and biochemical studies of ZTL indicate that the protein diverges from other members of the LOV superfamily in its allosteric mechanism, and that the divergent allosteric mechanism hinges upon conservation of two signaling residues G46 and V48 that alter dynamic motions of a Gln residue implicated in signal transduction in all LOV proteins. Here, we delineate the allosteric mechanism of ZTL via an integrated computational approach that employs atomistic simulations of wild type and allosteric variants of ZTL in the functional dark and light states, together with Markov state and supervised machine learning classification models. This approach has unveiled key factors of the ZTL allosteric mechanisms, and identified specific interactions and residues implicated in functional allosteric changes. The final results reveal atomic level insights into allosteric mechanisms of ZTL function that operate via a non-trivial combination of population-shift and dynamics-driven allosteric pathways.