Neural networks as robust tools in drug lead discovery and development

Empirical methods for building predictive models of the relationships between molecular structure and useful properties are becoming increasingly important. This has arisen because drug discovery and development have become more complex. A large amount of biological target information is becoming available though molecular biology. Automation of chemical synthesis and pharmacological screening has also provided a vast amount of experimental data. Tools for designing libraries and extracting information from molecular databases and high-throughput screening (HTS) experiments robustly and quickly enable leads to be discovered more effectively. As drug leads progress down the development pipeline, the ability to predict physicochemical, pharmacokinetic, and toxicological properties of these leads is becoming increasingly important in reducing the number of expensive, late-development failures. Neural network methods have much to offer in these areas. This review introduces the concepts behind neural networks applied to quantitative structure-activity relationships (QSARs), points out problems that may be encountered, suggests ways of avoiding the pitfalls, and introduces several exciting new neural network methods discovered during the last decade.     

Structure-activity relationships for a class of selective inhibitors of the major cysteine protease from Trypanosoma cruzi

Chagas' disease is a parasitic infection widely distributed throughout Latin America, with devastating consequences in terms of human morbidity and mortality. Cruzain, the major cysteine protease from Trypanosoma cruzi, is an attractive target for antitrypanosomal chemotherapy. In the present work, classical two-dimensional quantitative structure-activity relationships (2D QSAR) and hologram QSAR (HQSAR) studies were performed on a training set of 45 thiosemicarbazone and semicarbazone derivatives as inhibitors of T. cruzi cruzain. Significant statistical models (HQSAR, q² = 0.75 and r² = 0.96; classical QSAR, q² = 0.72 and r² = 0.83) were obtained, indicating their consistency for untested compounds. The models were then used to evaluate an external test set containing 10 compounds which were not included in the training set, and the predicted values were in good agreement with the experimental results (HQSAR, = 0.95; classical QSAR, = 0.91), indicating the existence of complementary between the two ligand-based drug design techniques.     

Novel virtual lead identification in the discovery of hematopoietic cell kinase (HCK) inhibitors: application of 3D QSAR and molecular dynamics simulation

High level of hematopoietic cell kinase (Hck) is associated with drug resistance in chronic myeloid leukemia. Additionally, Hck activity has also been connected with the pathogenesis of HIV-1 and chronic obstructive pulmonary disease. In this study, three-dimensional (3D) QSAR pharmacophore models were generated for Hck based on experimentally known inhibitors. A best pharmacophore model, Hypo1, was developed with high correlation coefficient (0.975), Low RMS deviation (0.60) and large cost difference (49.31), containing three ring aromatic and one hydrophobic aliphatic feature. It was further validated by the test set (r?=?0.96) and Fisher’s randomization method (95%). Hypo 1 was used as a 3D query for screening the chemical databases, and the hits were further screened by applying Lipinski’s rule of five and ADMET properties. Selected hit compounds were subjected to molecular docking to identify binding conformations in the active site. Finally, the appropriate binding modes of final hit compounds were revealed by molecular dynamics (MD) simulations and free energy calculation studies. Hence, we propose the final three hit compounds as virtual candidates for Hck inhibitors.     

Novel computational biology methods and their applications to drug discovery

Computational biology methods are now firmly entrenched in the drug discovery process. These methods focus on modeling and simulations of biological systems to complement and direct conventional experimental approaches. Two important branches of computational biology include protein homology modeling and the computational biophysics method of molecular dynamics. Protein modeling methods attempt to accurately predict three-dimensional (3D) structures of uncrystallized proteins for subsequent structure-based drug design applications. Molecular dynamics methods aim to elucidate the molecular motions of the static representations of crystallized protein structures. In this review we highlight recent novel methodologies in the field of homology modeling and molecular dynamics. Selected drug discovery applications using these methods conclude the review.     

木聚糖酶氨基酸组成与其最适pH的神经网络模型

籍均匀设计（UD）方法,构建了G/11家族木聚糖酶氨基酸组成和最适pH的神经网络（NNs）模型。当学习速率为0.09、动态参数为0.4、Sigmoid参数为0.98,隐含层结点数为10时,该模型对最适pH的拟合和预测平均绝对百分比误差可分别达到3.02%和4.06%,均方根误差均为0.19个pH单位,平均绝对误差分别为0.11和0.19个pH单位。该结果比文献报道的用逐步回归方法好。     

Molecular mechanisms and design principles for promiscuous inhibitors to avoid drug resistance: Lessons learned from HIV‐1 protease inhibition

Molecular recognition is central to biology and ranges from highly selective to broadly promiscuous. The ability to modulate specificity at will is particularly important for drug development, and discovery of mechanisms contributing to binding specificity is crucial for our basic understanding of biology and for applications in health care. In this study, we used computational molecular design to create a large dataset of diverse small molecules with a range of binding specificities. We then performed structural, energetic, and statistical analysis on the dataset to study molecular mechanisms of achieving specificity goals. The work was done in the context of HIV‐1 protease inhibition and the molecular designs targeted a panel of wild‐type and drug‐resistant mutant HIV‐1 protease structures. The analysis focused on mechanisms for promiscuous binding to bind robustly even to resistance mutants. Broadly binding inhibitors tended to be smaller in size, more flexible in chemical structure, and more hydrophobic in nature compared to highly selective ones. Furthermore, structural and energetic analyses illustrated mechanisms by which flexible inhibitors achieved binding; we found ligand conformational adaptation near mutation sites and structural plasticity in targets through torsional flips of asymmetric functional groups to form alternative, compensatory packing interactions or hydrogen bonds. As no inhibitor bound to all variants, we designed small cocktails of inhibitors to do so and discovered that they often jointly covered the target set through mechanistic complementarity. Furthermore, using structural plasticity observed in experiments, and potentially in simulations, is suggested to be a viable means of designing adaptive inhibitors that are promiscuous binders. Proteins 2015; 83:351–372. © 2014 Wiley Periodicals, Inc.     

Identification and evaluation of inhibitors of the EhGEF1 protein from Entamoeba histolytica

The Dbl family of guanine nucleotide exchange factors (GEFs) is made up of a vast array of members that participate in the activation of the Rho family of small GTPases. Dbl-family proteins promote the exchange of guanosine diphosphate/guanosine triphosphate (GDP/GTP) in their target molecules, resulting in the activation of a variety of signaling pathways involved in diverse cellular events, such as actin-cytoskeleton remodeling, cellular invasion, cell movement, and other functions. It has been reported that members of the Dbl family have important roles in several cellular events in Entamoeba histolytica. These include activation of the actin cytoskeleton, cytokinesis, capping, uroid formation, cellular proliferation, erythrophagocytosis, cell migration, and chemotaxis. Here, we report the identification and testing of inhibitors of the E. histolytica guanine nucleotide exchange factor 1 (EhGEF1) protein (the research compounds 2BYRF, 2BY05, 2BYT6, 2BYLX, and 2BYPD), which decreased the in vitro ability of the protein to exchange GDP/GTP at its target GTPases, EhRacG and EhRho1, by 14.9-85.2%. Interestingly, the drug 1,1'-(1,2-phenylene)-bis-(1H-pyrrole-2,5-dione), which completely inhibits the GEF activity of the Trio protein in human cells, decreases the GEF activity of the EhGEF1 protein on the EhRacG and EhRho1 GTPases by 55.7% and 3.2%, respectively. The identification and evaluation of such inhibitors opens up the possibility of obtaining a new pharmacological tool to study the function of amoeba GEF proteins, their roles in various Rho GTPase-mediated signaling pathways, and the repercussions of modulating their activities with respect to several mechanisms related to E. histolytica pathogenesis.     

Binding hotspots on K‐ras: Consensus ligand binding sites and other reactive regions from probe‐based molecular dynamics analysis

We have used probe‐based molecular dynamics (pMD) simulations to search for interaction hotspots on the surface of the therapeutically highly relevant oncogenic K‐Ras G12D. Combining the probe‐based query with an ensemble‐based pocket identification scheme and an analysis of existing Ras‐ligand complexes, we show that (i) pMD is a robust and cost‐effective strategy for binding site identification, (ii) all four of the previously reported ligand binding sites are suitable for structure‐based ligand design, and (iii) in some cases probe binding and expanded sampling of configurational space enable pocket expansion and increase the likelihood of site identification. Furthermore, by comparing the distribution of hotspots in nonpocket‐like regions with known protein‐ and membrane‐interacting interfaces, we propose that pMD has the potential to predict surface patches responsible for protein‐biomolecule interactions. These observations have important implications for future drug design efforts and will facilitate the search for potential interfaces responsible for the proposed transient oligomerization or interaction of Ras with other biomolecules in the cellular milieu. Proteins 2015; 83:898–909. © 2015 Wiley Periodicals, Inc.     

Rational Design of Novel Phosphoinositide 3‐Kinase Gamma (PI3Kγ) Selective Inhibitors: A Computational Investigation Integrating 3D‐QSAR,Molecular Docking and Molecular Dynamics Simulation

Phosphoinositide 3‐kinase gamma (PI3Kγ) draws an increasing attention due to its link with deadly cancer, chronic inflammation and allergy. But the development of PI3Kγ selective inhibitors is still a challenging endeavor because of the high sequence homology with the other PI3K isoforms. In order to acquire valuable information about the interaction mechanism between potent inhibitors and PI3Kγ, a series of PI3Kγ isoform‐selective inhibitors were analyzed by a systematic computational method, combining 3D‐QSAR, molecular docking, molecular dynamic (MD) simulations, free energy calculations and decomposition. The general structure–activity relationships were revealed and some key residues relating to selectivity and high activity were highlighted. It provides precious guidance for rational virtual screening, modification and design of selective PI3Kγ inhibitors. Finally, ten novel inhibitors were optimized and P10 showed satisfactory predicted bioactivity, demonstrating the feasibility to develop potent PI3Kγ inhibitors through this computational modeling and optimization.