Search

Motivation: X-ray crystallography has facilitated the majority of protein structures determined to date. Sequence-based predictors that can accurately estimate protein crystallization propensities would be highly beneficial to overcome the high expenditure, large attrition rate, and to reduce the trial-and-error settings required for crystallization., Results: In this study, we present a novel model, BCrystal, which uses an optimized gradient boosting machine (XGBoost) on sequence, structural and physio-chemical features extracted from the proteins of interest. BCrystal also provides explanations, highlighting the most important features for the predicted crystallization propensity of an individual protein using the SHAP algorithm. On three independent test sets, BCrystal outperforms state-of-the-art sequence-based methods by more than 12.5% in accuracy, 18% in recall and 0.253 in Matthew's correlation coefficient, with an average accuracy of 93.7%, recall of 96.63% and Matthew's correlation coefficient of 0.868. For relative solvent accessibility of exposed residues, we observed higher values to associate positively with protein crystallizability and the number of disordered regions, fraction of coils and tripeptide stretches that contain multiple histidines associate negatively with crystallizability. The higher accuracy of BCrystal enables it to accurately screen for sequence variants with enhanced crystallizability., Availability and Implementation: Our BCrystal webserver is at https://machinelearning-protein.qcri.org/ and source code is available at https://github.com/raghvendra5688/BCrystal., Supplementary Information: Supplementary data are available at Bioinformatics online., (© The Author(s) 2019. Published by Oxford University Press. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.)

Advances in X-ray crystallography have streamlined the process of determining high-resolution three-dimensional macromolecular structures. However, a rate-limiting step in this process continues to be the generation of crystals that are of sufficient size and quality for subsequent diffraction experiments. Here, iterative screen optimization (ISO), a highly automated process in which the precipitant concentrations of each condition in a crystallization screen are modified based on the results of a prior crystallization experiment, is described. After designing a novel high-throughput crystallization screen to take full advantage of this method, the value of ISO is demonstrated by using it to successfully crystallize a panel of six diverse proteins. The results suggest that ISO is an effective method to obtain macromolecular crystals, particularly for proteins that crystallize under a narrow range of precipitant concentrations., (open access.)

Recent studies have shown that the yield, antigenicity, and immunogenicity of an immunogen can be enhanced by stabilizing it into a specific conformation. Such stabilization often involves the engineering of proline mutations at residue positions where a proline is structurally compatible with the target conformation but not with an alternative conformation. However, there is no publicly available tool that can design proline mutations for this purpose automatically. Here we implemented an automated tool, CRISPro, that inputs structural coordinates of the target conformation and/or an alternative conformation and outputs a list of residue positions where proline mutations are predicted to stabilize the target conformation based on compatibility of phi-psi angles, secondary structure, and steric constraints. Thus, CRISPro can be used to engineer immunogens into specific conformation and to design serologic probes, capable of isolating antibodies that recognize a target shape.

Motivation: Protein solubility plays a vital role in pharmaceutical research and production yield. For a given protein, the extent of its solubility can represent the quality of its function, and is ultimately defined by its sequence. Thus, it is imperative to develop novel, highly accurate in silico sequence-based protein solubility predictors. In this work we propose, DeepSol, a novel Deep Learning-based protein solubility predictor. The backbone of our framework is a convolutional neural network that exploits k-mer structure and additional sequence and structural features extracted from the protein sequence., Results: DeepSol outperformed all known sequence-based state-of-the-art solubility prediction methods and attained an accuracy of 0.77 and Matthew's correlation coefficient of 0.55. The superior prediction accuracy of DeepSol allows to screen for sequences with enhanced production capacity and can more reliably predict solubility of novel proteins., Availability and Implementation: DeepSol's best performing models and results are publicly deposited at https://doi.org/10.5281/zenodo.1162886 (Khurana and Mall, 2018)., Supplementary Information: Supplementary data are available at Bioinformatics online.

Motivation: Protein solubility can be a decisive factor in both research and production efficiency, and in silico sequence-based predictors that can accurately estimate solubility outcomes are highly sought., Results: In this study, we present a novel approach termed PRotein SolubIlity Predictor (PaRSnIP), which uses a gradient boosting machine algorithm as well as an approximation of sequence and structural features of the protein of interest. Based on an independent test set, PaRSnIP outperformed other state-of-the-art sequence-based methods by more than 9% in accuracy and 0.17 in Matthew's correlation coefficient, with an overall accuracy of 74% and Matthew's correlation coefficient of 0.48. Additionally, PaRSnIP provides importance scores for all features used in training. We observed higher fractions of exposed residues to associate positively with protein solubility and tripeptide stretches with multiple histidines to associate negatively with solubility. The improved prediction accuracy of PaRSnIP should enable it to predict protein solubility with greater reliability and to screen for sequence variants with enhanced manufacturability., Availability and Implementation: PaRSnIP software is available for download under GitHub (https://github.com/RedaRawi/PaRSnIP)., Contact: gwo-yu.chuang@nih.gov., Supplementary Information: Supplementary data are available at Bioinformatics online.

Motivation: An effective docking algorithm for antibody-protein antigen complex prediction is an important first step toward design of biologics and vaccines. We have recently developed a new class of knowledge-based interaction potentials called Decoys as the Reference State (DARS) and incorporated DARS into the docking program PIPER based on the fast Fourier transform correlation approach. Although PIPER was the best performer in the latest rounds of the CAPRI protein docking experiment, it is much less accurate for docking antibody-protein antigen pairs than other types of complexes, in spite of incorporating sequence-based information on the location of the paratope. Analysis of antibody-protein antigen complexes has revealed an inherent asymmetry within these interfaces. Specifically, phenylalanine, tryptophan and tyrosine residues highly populate the paratope of the antibody but not the epitope of the antigen., Results: Since this asymmetry cannot be adequately modeled using a symmetric pairwise potential, we have removed the usual assumption of symmetry. Interaction statistics were extracted from antibody-protein complexes under the assumption that a particular atom on the antibody is different from the same atom on the antigen protein. The use of the new potential significantly improves the performance of docking for antibody-protein antigen complexes, even without any sequence information on the location of the paratope. We note that the asymmetric potential captures the effects of the multi-body interactions inherent to the complex environment in the antibody-protein antigen interface., Availability: The method is implemented in the ClusPro protein docking server, available at http://cluspro.bu.edu.

Motivation: N-linked glycosylation occurs predominantly at the N-X-T/S motif, where X is any amino acid except proline. Not all N-X-T/S sequons are glycosylated, and a number of web servers for predicting N-linked glycan occupancy using sequence and/or residue pattern information have been developed. None of the currently available servers, however, utilizes protein structural information for the prediction of N-glycan occupancy., Results: Here, we describe a novel classifier algorithm, NGlycPred, for the prediction of glycan occupancy at the N-X-T/S sequons. The algorithm utilizes both structural as well as residue pattern information and was trained on a set of glycosylated protein structures using the Random Forest algorithm. The best predictor achieved a balanced accuracy of 0.687 under 10-fold cross-validation on a curated dataset of 479 N-X-T/S sequons and outperformed sequence-based predictors when evaluated on the same dataset. The incorporation of structural information, including local contact order, surface accessibility/composition and secondary structure thus improves the prediction accuracy of glycan occupancy at the N-X-T/S consensus sequon., Availability and Implementation: NGlycPred is freely available to non-commercial users as a web-based server at http://exon.niaid.nih.gov/nglycpred/.

Despite the growing number of examples of small-molecule inhibitors that disrupt protein-protein interactions (PPIs), the origin of druggability of such targets is poorly understood. To identify druggable sites in protein-protein interfaces we combine computational solvent mapping, which explores the protein surface using a variety of small "probe" molecules, with a conformer generator to account for side-chain flexibility. Applications to unliganded structures of 15 PPI target proteins show that the druggable sites comprise a cluster of binding hot spots, distinguishable from other regions of the protein due to their concave topology combined with a pattern of hydrophobic and polar functionality. This combination of properties confers on the hot spots a tendency to bind organic species possessing some polar groups decorating largely hydrophobic scaffolds. Thus, druggable sites at PPI are not simply sites that are complementary to particular organic functionality, but rather possess a general tendency to bind organic compounds with a variety of structures, including key side chains of the partner protein. Results also highlight the importance of conformational adaptivity at the binding site to allow the hot spots to expand to accommodate a ligand of drug-like dimensions. The critical components of this adaptivity are largely local, involving primarily low energy side-chain motions within 6 Å of a hot spot. The structural and physicochemical signature of druggable sites at PPI interfaces is sufficiently robust to be detectable from the structure of the unliganded protein, even when substantial conformational adaptation is required for optimal ligand binding.

Motivation: The binding sites of proteins generally contain smaller regions that provide major contributions to the binding free energy and hence are the prime targets in drug design. Screening libraries of fragment-sized compounds by NMR or X-ray crystallography demonstrates that such 'hot spot' regions bind a large variety of small organic molecules, and that a relatively high 'hit rate' is predictive of target sites that are likely to bind drug-like ligands with high affinity. Our goal is to determine the 'hot spots' computationally rather than experimentally., Results: We have developed the FTMAP algorithm that performs global search of the entire protein surface for regions that bind a number of small organic probe molecules. The search is based on the extremely efficient fast Fourier transform (FFT) correlation approach which can sample billions of probe positions on dense translational and rotational grids, but can use only sums of correlation functions for scoring and hence is generally restricted to very simple energy expressions. The novelty of FTMAP is that we were able to incorporate and represent on grids a detailed energy expression, resulting in a very accurate identification of low-energy probe clusters. Overlapping clusters of different probes are defined as consensus sites (CSs). We show that the largest CS is generally located at the most important subsite of the protein binding site, and the nearby smaller CSs identify other important subsites. Mapping results are presented for elastase whose structure has been solved in aqueous solutions of eight organic solvents, and we show that FTMAP provides very similar information. The second application is to renin, a long-standing pharmaceutical target for the treatment of hypertension, and we show that the major CSs trace out the shape of the first approved renin inhibitor, aliskiren., Availability: FTMAP is available as a server at http://ftmap.bu.edu/.