SchNetPack Hyperparameter Optimization for a More Reliable Top Docking Scores Prediction.

Options to improve the extrapolation power of the neural network designed using the SchNetPack package with respect to top docking scores prediction are presented. It is shown that hyperparameter tuning of the atomistic model representation (in the schnetpack.representation) improves the prediction of the top scoring compounds, which have characteristically a low incidence in randomized data sets for training of machine learning models. The prediction robustness is evaluated according to the mean square error (MSE) and the entropy of the average loss landscape decrease. Admittedly, the improvement of the top scoring compounds' prediction accuracy comes with the penalty of worsening the overall prediction power. It is revealed that the most impactful hyperparameter is the cutoff (5 Å is reported as the optimal choice). Other parameters (e.g., number of radial basis functions, number of interaction layers of the neural network, feature vector size or its batch size) are found to not affect the prediction robustness of the top scoring compounds in any comparable way relative to the cutoff. The MSE of the best docking score prediction (below -13 kcal/mol) improves from ca. 3.5 to 0.9 kcal/mol, while the prediction of less potent compounds (-13 to -11 kcal/mol) shows a lesser improvement, i.e., a decrease of MSE from 1.6 to 1.3 kcal/mol. Additionally, oversampling and undersampling of the training set with respect to the top scoring compounds' abundance is presented. The results indicate that the cutoff choice performs better than over- or undersampling of the training set, with undersampling performing better than oversampling.

Molecular docking and machine learning affinity prediction of compounds identified upon softwood bark extraction to the main protease of the SARS-CoV-2 virus.

Molecular docking of 234 unique compounds identified in the softwood bark (W set) is presented with a focus on their inhibition potential to the main protease of the SARS-CoV-2 virus 3CLpro (6WQF). The docking results are compared with the docking results of 866 COVID19-related compounds (S set). Furthermore, machine learning (ML) prediction of docking scores of the W set is presented using the S set trained TensorFlow, XGBoost, and SchNetPack ML approaches. Docking scores are evaluated with the Autodock 4.2.6 software. Four compounds in the W set achieve a docking score below -13 kcal/mol, with (+)-lariciresinol 9'-p-coumarate (CID 11497085) achieving the best docking score (-15 kcal/mol) within the W and S sets. In addition, 50% of W set docking scores are found below -8 kcal/mol and 25% below -10 kcal/mol. Therefore, the compounds identified in the softwood bark, show potential for antiviral activity upon extraction or further derivatization. The W set molecular docking studies are validated by means of molecular dynamics (five best compounds). The solubility (Log S, ESOL) and druglikeness of the best docking compounds in S and W sets are compared to evaluate the pharmacological potential of compounds identified in softwood bark.

Machine learning prediction of 3CLpro SARS-CoV-2 docking scores.

Molecular docking results of two training sets containing 866 and 8,696 compounds were used to train three different machine learning (ML) approaches. Neural network approaches according to Keras and TensorFlow libraries and the gradient boosted decision trees approach of XGBoost were used with DScribe's Smooth Overlap of Atomic Positions molecular descriptors. In addition, neural networks using the SchNetPack library and descriptors were used. The ML performance was tested on three different sets, including compounds for future organic synthesis. The final evaluation of the ML predicted docking scores was based on the ZINC in vivo set, from which 1,200 compounds were randomly selected with respect to their size. The results obtained showed a consistent ML prediction capability of docking scores, and even though compounds with more than 60 atoms were found slightly overestimated they remain valid for a subsequent evaluation of their drug repurposing suitability.

Formation and fragmentation of the tungsten clusters in gas phase.

We present a theoretical study of accumulation of clusters consisting of up to 100 tungsten atoms based on information extracted from molecular dynamics trajectory simulations. The description is based on the rates corresponding to the single W atom attachment to Wn clusters and their dissociation processes. The results display a strong Arrhenius dependence of the dissociation rate constant on temperature. The preferred products of dissociation of the clusters composed of more than ten atoms are single W atoms and fragments with six to nine atoms. On the other hand, the association rate constants depend weakly on temperature. The obtained rate constants are used to calculate the chemical equilibrium of the W clusters that results in significant traces of small clusters only at high initial W atoms concentrations.

Ab initio X(1)0(+) ground state potential curves of Pb···RG dimers (RG = He, Ne, Ar) including spin-orbit effects. Simulation of diffusion coefficients.

CCSD(T) ground state potential curves of Pb···RG systems (RG = He, Ne and Ar) are presented and the importance of the inclusion of spin-orbit effects is discussed. The closed-shell character of the Pb atom at the two-component relativistic level of relativistic theory leads to shallower potential energy curves compared to scalar relativistic open-shell calculations. The pressure-independent cross-diffusion coefficients pD12 have been simulated using the extrapolated two-component CCSD(T) ground state potential curves. The diffusion coefficients from scattering theory are compared with simulations based on molecular dynamics (MD) using the velocity autocorrelation function (VACF) and the Einstein equation. A correction for the proper assessment of the uncertainty in the VACF is proposed. The acceleration of the MD simulation of Pb in RG diffusion is proposed utilizing the RG in Pb diffusion. The dU[TQ]Z/CCSD(T) potential curve of Pb···He (De = 8.667 cm(-1), re = 4.683 Å) supports only one vibrational level. The anharmonicity of this potential is compared to the potential of He···He which also supports only one vibrational level. The comparison is based on the mean square separations of the vibrational wave function.

Specific O2⁻ generation in corona discharge for ion mobility spectrometry.

This study deals with O(2)(-) generation in corona discharge (CD) in point to plane geometry for single flow ion mobility spectrometry (IMS) with gas outlet located behind the ionization source. We have designed CD of special geometry in order to achieve the high O(2)(-) yield. Using this ion source we have achieved in zero air conditions that up to 74% all negative ions were O(2)(-) or O(2)(-)(H(2)O). It has been demonstrated that the non-electronegative nitrogen positively influences the efficiency of O(2)(-) generation in O(2)/N(2) mixtures. The reduced ion mobility of 2.27 cm(2)V(-1)s(-1) has been measured for O(2)(-)/O(2)(-)(H(2)O) ions in zero air. Additional ions detected in zero air (less than 200 ppb CO(2)) using the mass spectrometric and IMS technique were, NO(2)(-), N(2)O(2)(-) (2.37 cm(2)V(-1)s(-1)), NO(3)(-), N(2)O(3)(-) and N(2)O(3)(-)(H(2)O). The CO(3)(-) and CO(4)(-) ions have been detected after the introduction of 5 ppm CO(2) into zero air.