Protein Secondary Structure Prediction with Partially Recurrent Neural Networks

Abstract

Partially recurrent neural networks with different topologies are applied for secondary structure prediction of proteins. The state of some activations in the network is available after a pattern presentation via feedback connections as additional input during the processing of the next pattern in a sequence. A reference data set containing 91 proteins in the training set and 15 non-homologous proteins in the test set is used for training and testing a network with a modified, hierarchical Elman architecture. The network predicts the secondary structures α-helix, β-sheet, and “coil” for each amino acid. The percentage of correctly classified amino acids is 67.83% on the training set and 63.98% on the test set. The best performance of a three-layer feedforward network is 62.7% on the same test set. A cascaded network, where the outputs of the recurrent network are processed by a second net with 13 × 3 inputs, four hidden and three output units has a predictive performance of 64.49%. The best corresponding feedforward net has a performance of 64.3%.     

Knowledge-Based Expert Systems for Toxicity and Metabolism Prediction: DEREK,StAR and METEOR

Abstract

It has long been recognised that the ability to predict the metabolic fate of a chemical substance and the potential toxicity of either the parent compound or its metabolites are important in novel drug design. The popularity of using computer models as an aid in this area has grown considerably in recent years.

LHASA Limited has been developing knowledge-based expert systems for toxicity and metabolism prediction in collaboration with industry and regulatory authorities. These systems, DEREK, StAR and METEOR, use rules to describe the relationship between chemical structure and either toxicity in the case of DEREK and StAR, or metabolic fate in the case of METEOR.

The rule refinement process for DEREK often involves assessing the predictions for a novel set of compounds and comparing them to their biological assay results as a measure of the system's performance. For example, 266 non-congeneric chemicals from the National Toxicology Program database have been processed through the DEREK mutagenicity knowledge base and the predictions compared to their Salmonella typhimurium mutagenicity data. Initially, 81 of 114 mutagens (71%) and 117 of 152 non-mutagens (77%) were correctly identified. Following further knowledge base development, the number of correctly identified mutagens has increased to 96 (84%). Further work on improving the predictive capabilities of DEREK, StAR and METEOR is in progress.     

Prediction of CL-20 chemical degradation pathways,theoretical and experimental evidence for dependence on competing modes of reaction

Highest occupied and lowest unoccupied molecular orbital energies, formation energies, bond lengths and FTIR spectra all suggest competing CL-20 degradation mechanisms. This second of two studies investigates recalcitrant, toxic, aromatic CL-20 intermediates that absorb from 370 to 430?nm. Our earlier study (Struct. Chem., 15, 2004) revealed that these intermediates were formed at high OH^? concentrations via the chemically preferred pathway of breaking the C–C bond between the two cyclopentanes, thereby eliminating nitro groups, forming conjugated π bonds, and resulting in a pyrazine three-ring aromatic intermediate. In attempting to find and make dominant a more benign CL-20 transformation pathway, this current research validates hydroxylation results from both studies and examines CL-20 transformations via photo-induced free radical reactions. This article discusses CL-20 competing modes of degradation revealed through: computational calculation; UV/VIS and SF spectroscopy following alkaline hydrolysis; and photochemical irradiation to degrade CL-20 and its byproducts at their respective wavelengths of maximum absorption.     

Gas chromatographic retention of alkyl phosphates on ionic liquid stationary phases

Retention behaviors of alkyl phosophates were studied on a series of ionic liquid gas chromatography columns. The selectivity of the IL columns for alkyl phosphates were compared with a 5% phenyl column as a route to evaluating the potential use of IL columns in the analysis of alkyl phosphates in petroleum samples in both one- and multi-dimensional GC. Most interestingly, we demonstrate for the first time the dependence of elution order on separation temperature for members of a homologous series of compounds. At low temperatures it was found that trihexyl phosphate eluted before trioctyl phosphate, while at higher temperatures this pattern was reversed.     

Two‐dimensional replica‐exchange method for predicting protein–ligand binding structures

We have developed a two‐dimensional replica‐exchange method for the prediction of protein–ligand binding structures. The first dimension is the umbrella sampling along the reaction coordinate, which is the distance between a protein binding pocket and a ligand. The second dimension is the solute tempering, in which the interaction between a ligand and a protein and water is weakened. The second dimension is introduced to make a ligand follow the umbrella potential more easily and enhance the binding events, which should improve the sampling efficiency. As test cases, we applied our method to two protein‐ligand complex systems (MDM2 and HSP 90‐alpha). Starting from the configuration in which the protein and the ligand are far away from each other in each system, our method predicted the ligand binding structures in excellent agreement with the experimental data from Protein Data Bank much faster with the improved sampling efficiency than the replica‐exchange umbrella sampling method that we have previously developed. © 2013 Wiley Periodicals, Inc.     

Membrane protein native state discrimination by implicit membrane models

Four implicit membrane models [IMM1, generalized Born (GB)‐surface area‐implicit membrane (GBSAIM), GB with a simple switching (GBSW), and heterogeneous dielectric GB (HDGB)] were tested for their ability to discriminate the native conformation of five membrane proteins from 450 decoys generated by the Rosetta‐Membrane program. The energy ranking of the native state and Z‐scores were used to assess the performance of the models. The effect of membrane thickness was examined and was found to be substantial. Quite satisfactory discrimination was achieved with the all‐atom IMM1 and GBSW models at 25.4 Å thickness and with the HDGB model at 28.5 Å thickness. The energy components by themselves were not discriminative. Both van der Waals and electrostatic interactions contributed to native state discrimination, to a different extent in each model. Computational efficiency of the models decreased in the order: extended‐atom IMM1 > all‐atom IMM1 > GBSAIM > GBSW > HDGB. These results encourage the further development and use of implicit membrane models for membrane protein structure prediction. © 2012 Wiley Periodicals, Inc.     

Water PMF for predicting the properties of water molecules in protein binding site

Water is an important component in living systems and deserves better understanding in chemistry and biology. However, due to the difficulty of investigating the water functions in protein structures, it is usually ignored in computational modeling, especially in the field of computer‐aided drug design. Here, using the potential of mean forces (PMFs) approach, we constructed a water PMF (wPMF) based on 3946 non‐redundant high resolution crystal structures. The extracted wPMF potential was first used to investigate the structure pattern of water and analyze the residue hydrophilicity. Then, the relationship between wPMF score and the B factor value of crystal waters was studied. It was found that wPMF agrees well with some previously reported experimental observations. In addition, the wPMF score was also tested in parallel with 3D‐RISM to measure the ability of retrieving experimentally observed waters, and showed comparable performance but with much less computational cost. In the end, we proposed a grid‐based clustering scheme together with a distance weighted wPMF score to further extend wPMF to predict the potential hydration sites of protein structure. From the test, this approach can predict the hydration site at the accuracy about 80% when the calculated score lower than ?4.0. It also allows the assessment of whether or not a given water molecule should be targeted for displacement in ligand design. Overall, the wPMF presented here provides an optional solution to many water related computational modeling problems, some of which can be highly valuable as part of a rational drug design strategy. © 2012 Wiley Periodicals, Inc.