Your browser doesn't support javascript.
Mostrar: 20 | 50 | 100
Resultados 1 - 6 de 6
Mais filtros

Base de dados
Intervalo de ano de publicação
J Phys Chem Lett ; 13(22): 4924-4933, 2022 Jun 09.
Artigo em Inglês | MEDLINE | ID: mdl-35635003


Spectroscopy is the study of how matter interacts with electromagnetic radiation. The spectra of any molecule are highly information-rich, yet the inverse relation of spectra to the corresponding molecular structure is still an unsolved problem. Nuclear magnetic resonance (NMR) spectroscopy is one such critical technique in the scientists' toolkit to characterize molecules. In this work, a novel machine learning framework is proposed that attempts to solve this inverse problem by navigating the chemical space to find the correct structure given an NMR spectra. The proposed framework uses a combination of online Monte Carlo tree search (MCTS) and a set of graph convolution networks to build a molecule iteratively. Our method can predict the structure of the molecule ∼80% of the time in its top 3 guesses for molecules with <10 heavy atoms. We believe that the proposed framework is a significant step in solving the inverse design problem of NMR spectra.

Chem Sci ; 12(35): 11710-11721, 2021 Sep 15.
Artigo em Inglês | MEDLINE | ID: mdl-34659706


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.

J Chem Inf Model ; 61(2): 689-698, 2021 02 22.
Artigo em Inglês | MEDLINE | ID: mdl-33546556


Solvation free energy is a fundamental property that influences various chemical and biological processes, such as reaction rates, protein folding, drug binding, and bioavailability of drugs. In this work, we present a deep learning method based on graph networks to accurately predict solvation free energies of small organic molecules. The proposed model, comprising three phases, namely, message passing, interaction, and prediction, is able to predict solvation free energies in any generic organic solvent with a mean absolute error of 0.16 kcal/mol. In terms of accuracy, the current model outperforms all of the proposed machine learning-based models so far. The atomic interactions predicted in an unsupervised manner are able to explain the trends of free energies consistent with chemical wisdom. Further, the robustness of the machine learning-based model has been tested thoroughly, and its capability to interpret the predictions has been verified with several examples.

Modelos Químicos , Redes Neurais de Computação , Entropia , Solventes , Termodinâmica
Phys Chem Chem Phys ; 22(46): 26935-26943, 2020 Dec 07.
Artigo em Inglês | MEDLINE | ID: mdl-33205786


Recent years have witnessed utilization of modern machine learning approaches for predicting the properties of materials 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 on conditional variational autoencoders (CVAEs) and the predictor module consists of three deep neural networks trained for predicting the 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.

J Comput Chem ; 41(8): 790-799, 2020 Mar 30.
Artigo em Inglês | MEDLINE | ID: mdl-31845368


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.

Indian J Endocrinol Metab ; 21(5): 684-687, 2017.
Artigo em Inglês | MEDLINE | ID: mdl-28989874


AIMS AND OBJECTIVES: The aim of this study is to determine the prevalence of hypogonadism in human immunodeficiency virus (HIV)-infected males and to study its relation to age, CD4 count, body mass index (BMI), duration of highly active antiretroviral therapy (HAART), and metabolic status. METHODOLOGY: Eighty-one HIV positive cases and 82 healthy controls were included in this case-control study. Each case underwent a complete physical examination and serum fasting plasma glucose, A1c, lipid profile, total testosterone (TT), follicle-stimulating hormone (FSH), and luteinizing hormone (LH) levels were estimated. Serum TT level <300 ng/dl, or TT >300 ng/dl with high LH and FSH (compensatory hypogonadism) were taken as markers for hypogonadism, and it was correlated with age, CD4 count, duration of HAART, and metabolic status of the patient. RESULTS: Out of 81 cases, 21 (25.9%) were found to have hypogonadism as compared to 4 (4.9%) out of 82 controls. Of these 21, 14 cases had secondary hypogonadism, five had primary, and the remaining two had compensatory hypogonadism. The mean serum TT value among cases (371.7 ± 102.9 ng/dl) was significantly lower than that among controls (419.7 ± 71.5 ng/dl) (P = 0.007). Hypogonadism was found to be significantly associated with the age of the patient (P = 0.007), CD4 count (P = 0.002), and duration of HAART (P = 0.04) and was independent of the BMI (P = 0.9) and the waist circumference (P = 0.8). Dyslipidemia and dysglycemia were significantly more common among cases as compared to controls (P < 0.05) but were not associated with hypogonadism. CONCLUSION: The prevalence of hypogonadism is higher among HIV-infected males as compared to healthy individuals. Hypogonadism was significantly associated with age, CD4 count, and duration of HAART and was independent of BMI, glycemic status, and dyslipidemia.