The current COVID-19 pandemic caused by a novel coronavirus SARS-CoV-2 urgently calls for a working therapeutic. Here, we report a computation-based workflow for efficiently selecting a subset of FDA-approved drugs that can potentially bind to the SARS-CoV-2 main protease M PRO . The workflow started with docking (using Autodock Vina) each of 1615 FDA-approved drugs to the M PRO active site. This step selected 62 candidates with docking energies lower than −8.5 kcal/mol. Then, the 62 docked protein–drug complexes were subjected to 100 ns of molecular dynamics (MD) simulations in a molecular mechanics (MM) force field (CHARMM36). This step reduced the candidate pool to 26, based on the root-mean-square-deviations (RMSDs) of the drug molecules in the trajectories. Finally, we modeled the 26 drug molecules by a pseudoquantum mechanical (ANI) force field and ran 5 ns hybrid ANI/MM MD simulations of the 26 protein–drug complexes. ANI was trained by neural network models on quantum mechanical density functional theory (wB97X/6-31G(d)) data points. An RMSD cutoff winnowed down the pool to 12, and free energy analysis (MM/PBSA) produced the final selection of 9 drugs: dihydroergotamine, midostaurin, ziprasidone, etoposide, apixaban, fluorescein, tadalafil, rolapitant, and palbociclib. Of these, three are found to be active in literature reports of experimental studies. To provide physical insight into their mechanism of action, the interactions of the drug molecules with the protein are presented as 2D-interaction maps. These findings and mappings of drug–protein interactions may be potentially used to guide rational drug discovery against COVID-19.

Artificial intelligence recently achieved the breakthrough of predicting the three-dimensional structures of proteins. The next frontier is presented by intrinsically disordered proteins (IDPs), which, representing 30% to 50% of proteomes, readily access vast conformational space. Molecular dynamics (MD) simulations are promising in sampling IDP conformations, but only at extremely high computational cost. Here, we developed generative autoencoders that learn from short MD simulations and generate full conformational ensembles. An encoder represents IDP conformations as vectors in a reduced-dimensional latent space. The mean vector and covariance matrix of the training dataset are calculated to define a multivariate Gaussian distribution, from which vectors are sampled and fed to a decoder to generate new conformations. The ensembles of generated conformations cover those sampled by long MD simulations and are validated by small-angle X-ray scattering profile and NMR chemical shifts. This work illustrates the vast potential of artificial intelligence in conformational mining of IDPs.

Virtual screening is receiving renewed attention in drug discovery, but progress is hampered by challenges on two fronts: handling the ever-increasing sizes of libraries of drug-like compounds and separating true positives from false positives. Here, we developed a machine learningenabled pipeline for large-scale virtual screening that promises breakthroughs on both fronts. By clustering compounds according to molecular properties and limited docking against a drug target, the full library was trimmed by 10-fold; the remaining compounds were then screened individually by docking; and finally, a dense neural network was trained to classify the hits into true and false positives. As illustration, we screened for inhibitors against RPN11, the deubiquitinase subunit of the proteasome, and a drug target for breast cancer.

Search and rescue missions and surveillance require finding targets in a large area. These tasks often use unmanned aerial vehicles (UAVs) with cameras to detect and move towards a target. However, common UAV approaches make two simplifying assumptions. First, they assume that observations made from different heights are deterministically correct. In practice, observations are noisy, with the noise increasing as the height used for observations increases. Second, they assume that a motion command executes correctly, which may not happen due to wind and other environmental factors. To address these, we propose a sequential algorithm that determines actions in real time based on observations, using partially observable Markov decision processes (POMDPs). Our formulation handles both observations and motion uncertainty and errors. We run offline simulations and learn a policy. This policy is run on a UAV to find the target efficiently. We employ a novel compact formulation to represent the coordinates of the drone relative to the target coordinates. Our POMDP policy finds the target up to 3.4 times faster when compared to a heuristic policy.

<div> <p> </p><div> <div> <div> <p> </p><div> <div> <div> <p> </p><div> <div> <div> <p>With the current pandemic situation caused by a novel coronavirus disease (COVID-19), there is an urgent call to develop a working therapeutic against it. Efficient computations aid to minimize the efforts by identifying a subset of drugs that can potentially bind to COVID-19 main protease or target protein (M^PRO). The results of computations are always accompanied by their accuracy which depends on the details described by the model used. Machine learning models trained on millions of points and with unmatched accuracies are the best bet to employ in the process. In this work, I first identified and described the interaction sites of M^PRO protein using a geometric deep learning model. Secondly, I conducted virtual screening (at one of the sites identified) on FDA approved drugs and picked 91 drugs having the highest binding affinity (below -8.0 kcal/mol). Then, I carried out 10 ns of molecular dynamics (MD) simulations using classical force fields and classified 37 drugs to be binding (includes drugs like Lopinavir, Saquinavir, Indinavir etc.) based on RMSD between MD-binding trajectories. To drastically improve the dynamics profile of selected 37 drugs, I brought in the highly accurate neural network force field (ANI) trained on coupled-cluster methods (CCSD(T)/CBS) data points and performed 1 ns of binding dynamics of each drug with protein. With the accurate approach, 19 drugs were qualified based on their RMSD cutoffs, and again with their free energy (ANI/MM/PBSA) computations another 7 drugs were rejected. The final selection of 12 drugs was validated based on MD trajectory clustering approach where 11 of 12 drugs (Targretin, Eltrombopag, Rifaximin, Deflazacort, Ergotamine, Doxazosin, Lastacaft, Rifampicin, Victrelis, Trajenta, Toposar, and Indinavir) were confirmed to be binding. Further investigations were made to study their interactions with the protein and an accurate 2D- interaction map was generated. These findings and mapping of drug-protein interactions are highly accurate and could be potentially used to guide rational drug discovery against the COVID-19. </p> </div> </div> </div> </div> </div> </div> </div> </div> </div> </div>