Abstract

Engineering proteins to have desired properties by mutating amino acids at specific sites is commonplace. Such engineered proteins must be stable to function. Experimental methods used to determine stability at throughputs required to scan the protein sequence space thoroughly are laborious. To this end, many machine learning based methods have been developed to predict thermodynamic stability changes upon mutation. These methods have been evaluated for symmetric consistency by testing with hypothetical reverse mutations. In this work, we propose transitive data augmentation, evaluating transitive consistency with our new Stransitive data set, and a new machine learning based method, the first of its kind, that incorporates both symmetric and transitive properties into the architecture. Our method, called SCONES, is an interpretable neural network that predicts small relative protein stability changes for missense mutations that do not significantly alter the structure. It estimates a residue’s contributions toward protein stability (ΔG) in its local structural environment, and the difference between independently predicted contributions of the reference and mutant residues is reported as ΔΔG. We show that this self-consistent machine learning architecture is immune to many common biases in data sets, relies less on data than existing methods, is robust to overfitting, and can explain a substantial portion of the variance in experimental data.

Abstract

Here we report the synthesis of an N-heterocyclic carbene (NHC)-stabilised phosphinidene oxide by the controlled oxygenation of a phosphinidene under ambient conditions. This compound can be further oxygenated to a phosphinidene dioxide. The stoichiometric reduction of a phosphinidene oxide with KC8 resembles the pinacol coupling reaction–the reduction of a carbonyl compound. We also looked at the stoichiometric oxidation of NHC-coordinated phosphinidene, phosphinidene oxide and phosphinidene dioxide with [NO][SbF6].

Abstract

In drug discovery applications, high throughput virtual screening exercises are routinely performed to determine an initial set of candidate molecules referred to as “hits”. In such an experiment, each molecule from a large small-molecule drug library is evaluated in terms of physical properties such as the docking score against a target receptor. In real-life drug discovery experiments, drug libraries are extremely large but still there is only a minor representation of the essentially infinite chemical space, and evaluation of physical properties for each molecule in the library is not computationally feasible. In the current study, a novel Machine learning framework for Enhanced MolEcular Screening (MEMES) based on Bayesian optimization is proposed for efficient sampling of the chemical space. The proposed framework is demonstrated to identify 90% of the top-1000 molecules from a molecular library of size about 100 million, while calculating the docking score only for about 6% of the complete library. We believe that such a framework would tremendously help to reduce the computational effort in not only drug-discovery but also areas that require such high-throughput experiments.

Abstract

The computationally expensive nature of ab initio molecular dynamics simulations severely limits its ability to simulate large system sizes and long time scales, both of which are necessary to imitate experimental conditions. In this work, we explore an approach to make use of the data obtained using the quantum mechanical density functional theory (DFT) on small systems and use deep learning to subsequently simulate large systems by taking liquid argon as a test case. A suitable vector representation was chosen to represent the surrounding environment of each Ar atom, and a -NetFF machine learning model where, the neural network was trained to predict the di↵erence in resultant forces obtained by DFT and classical force fields was introduced. Molecular dynamics simulations were then performed using forces from the neural network for various system sizes and time scales depending on the properties we calculated. A comparison of properties obtained from the classical force field and the neural network model was presented alongside available experimental data to validate the proposed method.

Abstract

Recent years have witnessed utilization of modern machine learning approaches for predicting properties of material using available datasets. However, to identify potential candidates for material discovery, one has to systematically scan through a large chemical space and subsequently calculate the properties of all such samples. On the other hand, generative methods are capable of efficiently sampling the chemical space and can generate molecules/materials with desired properties. In this study, we report a deep learning based inorganic material generator (DING) framework consisting of a generator module and a predictor module. The generator module is developed based upon conditional variational autoencoders (CVAE) and the predictor module consists of three deep neural networks trained for predicting enthalpy of formation, volume per atom and energy per atom chosen to demonstrate the proposed method. The predictor and generator modules have been developed using a one hot key representation of the material composition. A series of tests were done to examine the robustness of the predictor models, to demonstrate the continuity of the latent material space, and its ability to generate materials exhibiting target property values. The DING architecture proposed in this paper can be extended to other properties based on which the chemical space can be efficiently explored for interesting materials/molecules.

Abstract

Solubility of drug molecules is related to pharmacokinetic properties such as absorption and distribution, which affects the amount of drug that is available in the body for its action. Computational or experimental evaluation of solvation free energies of drug-like molecules/solute that quantify solubilities is an arduous task and hence development of reliable computationally tractable models is sought after in drug discovery tasks in pharmaceutical industry. Here, we report a novel method based on graph neural network to predict solvation free energies. Previous studies considered only the solute for solvation free energy prediction and ignored the nature of the solvent, limiting their practical applicability. The proposed model is an end-to-end framework comprising three phases namely, message passing, interaction and prediction phases. In the first phase, message passing neural network was used to compute inter-atomic interaction within both solute and solvent molecules represented as molecular graphs. In the interaction phase, features from the preceding step is used to calculate a solute-solvent interaction map, since the solvation free energy depends on how (un)favorable the solute and solvent molecules interact with each other. The calculated interaction map that captures the solute-solvent interactions along with the features from the message passing phase is used to predict the solvation free energies in the final phase. The model predicts solvation free energies involving a large number of solvents with high accuracy. We also show that the interaction map captures the electronic and steric factors that govern the solubility of drug-like molecules and hence is chemically interpretable.

Abstract

Recent advances in artificial intelligence along with the development of large data sets of energies calculated using quantum mechanical (QM)/density functional theory (DFT) methods have enabled prediction of accurate molecular energies at reasonably low computational cost. However, machine learning models that have been reported so far require the atomic positions obtained from geometry optimizations using high‐level QM/DFT methods as input in order to predict the energies and do not allow for geometry optimization. In this study, a transferable and molecule size‐independent machine learning model bonds (B), angles (A), nonbonded (N) interactions, and dihedrals (D) neural network (BAND NN) based on a chemically intuitive representation inspired by molecular mechanics force fields is presented. The model predicts the atomization energies of equilibrium and nonequilibrium structures as sum of energy contributions from bonds (B), angles (A), nonbonds (N), and dihedrals (D) at remarkable accuracy. The robustness of the proposed model is further validated by calculations that span over the conformational, configurational, and reaction space. The transferability of this model on systems larger than the ones in the data set is demonstrated by performing calculations on selected large molecules. Importantly, employing the BAND NN model, it is possible to perform geometry optimizations starting from nonequilibrium structures along with predicting their energies. © 2019 Wiley Periodicals, Inc.

Abstract

The fifty–year proposal of nondissociative racemization reaction of a tetracoordinated tetrahedral center from one enantiomer to another via a planar transition state by Hoffmann and coworkers has been explored by many research groups during the past five decades. A number of stable molecules with planar tetracoordinate and higher-coordinate centers have been designed and experimentally realized; however, there has not been a single example of molecular system that can possibly undergo such racemization. Here we show examples of molecular species that undergo inversion of stereochemistry around tetrahedral centers (Si, Al− and P+) either via a planar transition state or an intermediate state using quantum mechanical, ab initio quasi-classical dynamics calculations, and Born-Oppenheimer molecular dynamics (BOMD) simulations. This work is expected to provide potential leads for future studies on this fundamental phenomenon in chemistry.

Abstract

Noncovalent interactions are key determinants in both chemical and biological processes. Among such processes, the hydrophobic interactions play an eminent role in folding of proteins, nucleic acids, formation of membranes, protein-ligand recognition, etc.. Though this interaction is mediated through the aqueous solvent, the stability of the above biomolecules can be highly sensitive to any small external perturbations, such as temperature, pressure, pH, or even cosolvent additives, like, urea-a highly soluble small organic molecule utilized by various living organisms to regulate osmotic pressure. A plethora of detailed studies exist covering both experimental and theoretical regimes, to understand how urea modulates the stability of biological macromolecules. While experimentalists have been primarily focusing on the thermodynamic and kinetic aspects, theoretical modeling predominantly involves mechanistic information at the molecular level, calculating atomistic details applying the force field approach to the high level electronic details using the quantum mechanical methods. The review focuses mainly on examples with biological relevance, such as (1) urea-assisted protein unfolding, (2) urea-assisted RNA unfolding, (3) urea lesion interaction within damaged DNA, (4) urea conduction through membrane proteins, and (5) protein-ligand interactions those explicitly address the vitality of hydrophobic interactions involving exclusively the urea-aromatic moiety.

Abstract

The optical activity of a metal nanocluster (NC) is induced either by an asymmetric arrangement of constituents or by a dissymmetric field of a chiral ligand layer. Herein, we unveil the origin of chirality in Ag29 NCs, which is attributed to the intrinsically chiral atomic arrangement. The X-ray crystal structure of a Ag29(BDT)12(TPP)4 NC (BDT: 1,3-benzenedithiol; TPP: triphenylphosphine) manifested the presence of intrinsic chirality in the outer shell capping the icosahedral achiral Ag13 core. The enantiomers of the Ag29(BDT)12(TPP)4 NC are separated by high-performance liquid chromatography (HPLC) using a chiral column for the first time, showing mirror-image circular dichroism (CD) spectra. The CD spectra are reproduced by time-dependent density functional theory (TDDFT) calculations based on enantiomeric Ag29 models with achiral 1,3-propanedithiolate ligands. The mechanism of chiral induction in the synthesis of Ag29(DHLA)12 (DHLA: a-dihydrolipoic acid) NCs with a chiral ligand system is further discussed with the aid of DFT calculations. The use of the enantiomeric DHLA ligand preferentially leads to a one-handed atomic arrangement which is more stable than the opposite one, inducing the enantiomeric excess in the population of intrinsically chiral Ag29 NCs with CD activity