Unraveling the reaction pathway of photoinduced reactions poses a great challenge owing to its complexity. Recently, graph theory-based machine learning combined with nonadiabatic molecular dynamics (NAMD) has been applied to obtain the global reaction coordinate of the photoisomerization of azobenzene. However, NAMD simulations are computationally expensive as they require calculating the nonadiabatic coupling vectors at each time step. Here, we showed that ab initio molecular dynamics (AIMD) can be used as an alternative to NAMD by choosing an appropriate initial condition for the simulation. We applied our methodology to determine a plausible global reaction coordinate of retinal photoisomerization, which is essential for human vision. On rank-ordering the internal coordinates, based on the mutual information (MI) between the internal coordinates and the HOMO energy, NAMD and AIMD give a similar trend. Our results demonstrate that our AIMD-based machine learning protocol for retinal is 1.5 times faster than that of NAMD to study reaction coordinates.
Generating drug candidates with desired protein–ligand interactions is a significant challenge in structure-based drug design. In this study, a new generative model, IEV2Mol, is proposed that incorporates interaction energy vectors (IEVs) between proteins and ligands obtained from docking simulations, which quantitatively capture the strength of each interaction type, such as hydrogen bonds, electrostatic interactions, and van der Waals forces. By integrating this IEV into an end-to-end variational autoencoder (VAE) framework that learns the chemical space from SMILES and minimizes the reconstruction error of the SMILES, the model can more accurately generate compounds with the desired interactions. To evaluate the effectiveness of IEV2Mol, we performed benchmark comparisons with randomly selected compounds, unconstrained VAE models (JT-VAE), and compounds generated by RNN models based on interaction fingerprints (IFP-RNN). The results show that the compounds generated by IEV2Mol retain a significantly greater percentage of the binding mode of the query structure than those of the other methods. Furthermore, IEV2Mol was able to generate compounds with interactions similar to those of the input compounds, regardless of structural similarity. The source code and trained models for IEV2Mol, JT-VAE, and IFP-RNN designed for generating compounds active against the DRD2, AA2AR, and AKT1, as well as the data sets (DM-QP-1M, active compounds to each protein, and ChEMBL33) utilized in this study, are released under the MIT License and available at https://github.com/sekijima-lab/IEV2Mol.
Renal secretion plays an important role in excretion of drug from the kidney. Two major transporters known to be highly involved in renal secretion are MATE1/2 K and OCT2, the former of which is highly related to drug–drug interactions. Among published in silico models for MATE inhibitors, a previous model obtained a ROC-AUC value of 0.78 using high throughput percentage inhibition data [J. Med. Chem. 2013, 56(3), 781–795] which we aimed to improve upon here using a combined fingerprint and physics-based approach. To this end, we collected 225 publicly available compounds with pIC50 values against MATE1. Subsequently, on the one hand, we performed a physics-based approach using an Alpha-Fold protein structure, from which we obtained MM–GB/SA scores for those compounds. On the other hand, we built Random Forest (RF) and message passing neural network models using extended-connectivity fingerprints with radius 4 (ECFP4) and chemical structures as graphs, respectively, which also included MM–GB/SA scores as input variables. In a five-fold cross-validation with a separate test set, we found that the best predictivity for the hold-out test was observed in the RF model (including ECFP4 and MM–GB/SA data) with an ROC-AUC of 0.833 ± 0.036; while that of the MM–GB/SA regression model was 0.742. However, the MM–GB/SA model did not show a dependency of the performance on the particular chemical space being predicted. Additionally, via structural interaction fingerprint analysis, we identified interacting residues with inhibitor as identical for those with noninhibitors, including substrates, such as Gln49, Trp274, Tyr277, Tyr299, Ile303, and Tyr306. The similar binding modes are consistent with the observed similar IC50 value inhibitor when using different substrates experimentally, and practically, this can release the experimental scientists from bothering of selecting substrates for MATE1. Hence, we were able to build highly predictive classification models for MATE1 inhibitory activity with both ECFP4 and MM–GB/SA score as input features, which is fit-for-purpose for use in the drug discovery process.
The occurrence of organophosphorus compounds, pesticides, and flame-retardants in wastes is an emerging ecological problem. Bacterial phosphotriesterases are capable of hydrolyzing some of them. We utilize modern molecular modeling tools to study the hydrolysis mechanism of organophosphorus compounds with good and poor leaving groups by phosphotriesterase from Pseudomonas diminuta (Pd-PTE). We compute Gibbs energy profiles for enzymes with different cations in the active site: native Zn2+cations and Co2+cations, which increase the steady-state rate constant. Hydrolysis occurs in two elementary steps via an associative mechanism and formation of the pentacoordinated intermediate. The first step, a nucleophilic attack, occurs with a low energy barrier independently of the substrate. The second step has a low energy barrier and considerable stabilization of products for substrates with good leaving groups. For substrates with poor leaving groups, the reaction products are destabilized relative to the ES complex that suppresses the reaction. The reaction proceeds with low energy barriers for substrates with good leaving groups with both Zn2+and Co2+cations in the active site; thus, the product release is likely to be a limiting step. Electron density and geometry analysis of the QM/MM MD trajectories of the intermediate states with all considered compounds allow us to discriminate substrates by their ability to be hydrolyzed by the Pd-PTE. For hydrolyzable substrates, the cleaving bond between a phosphorus atom and a leaving group is elongated, and electron density depletion is observed on the Laplacian of electron density maps.