Badri Adhikari

CONFOLD: Residue‐residue contact‐guided ab initio protein folding

Predicted protein residue–residue contacts can be used to build three‐dimensional models and consequently to predict protein folds from scratch. A considerable amount of effort is currently being spent to improve contact prediction accuracy, whereas few methods are available to construct protein tertiary structures from predicted contacts. Here, we present an ab initio protein folding method to build three‐dimensional models using predicted contacts and secondary structures. Our method first translates contacts and secondary structures into distance, dihedral angle, and hydrogen bond restraints according to a set of new conversion rules, and then provides these restraints as input for a distance geometry algorithm to build tertiary structure models. The initially reconstructed models are used to regenerate a set of physically realistic contact restraints and detect secondary structure patterns, which are then used to reconstruct final structural models. This unique two‐stage modeling approach of integrating contacts and secondary structures improves the quality and accuracy of structural models and in particular generates better β‐sheets than other algorithms. We validate our method on two standard benchmark datasets using true contacts and secondary structures. Our method improves TM‐score of reconstructed protein models by 45% and 42% over the existing method on the two datasets, respectively. On the dataset for benchmarking reconstructions methods with predicted contacts and secondary structures, the average TM‐score of best models reconstructed by our method is 0.59, 5.5% higher than the existing method. The CONFOLD web server is available at http://protein.rnet.missouri.edu/confold/. Proteins 2015; 83:1436–1449.

Large-scale model quality assessment for improving protein tertiary structure prediction.

Motivation: Sampling structural models and ranking them are the two major challenges of protein structure prediction. Traditional protein structure prediction methods generally use one or a few quality assessment (QA) methods to select the best-predicted models, which cannot consistently select relatively better models and rank a large number of models well. Results: Here, we develop a novel large-scale model QA method in conjunction with model clustering to rank and select protein structural models. It unprecedentedly applied 14 model QA methods to generate consensus model rankings, followed by model refinement based on model combination (i.e. averaging). Our experiment demonstrates that the large-scale model QA approach is more consistent and robust in selecting models of better quality than any individual QA method. Our method was blindly tested during the 11th Critical Assessment of Techniques for Protein Structure Prediction (CASP11) as MULTICOM group. It was officially ranked third out of all 143 human and server predictors according to the total scores of the first models predicted for 78 CASP11 protein domains and second according to the total scores of the best of the five models predicted for these domains. MULTICOM’s outstanding performance in the extremely competitive 2014 CASP11 experiment proves that our large-scale QA approach together with model clustering is a promising solution to one of the two major problems in protein structure modeling. Availability and implementation: The web server is available at: http://sysbio.rnet.missouri.edu/multicom_cluster/human/. Contact: chengji@missouri.edu

QAcon: single model quality assessment using protein structural and contact information with machine learning techniques

Motivation: Protein model quality assessment (QA) plays a very important role in protein structure prediction. It can be divided into two groups of methods: single model and consensus QA method. The consensus QA methods may fail when there is a large portion of low quality models in the model pool. Results: In this paper, we develop a novel single‐model quality assessment method QAcon utilizing structural features, physicochemical properties, and residue contact predictions. We apply residue‐residue contact information predicted by two protein contact prediction methods PSICOV and DNcon to generate a new score as feature for quality assessment. This novel feature and other 11 features are used as input to train a two‐layer neural network on CASP9 datasets to predict the quality of a single protein model. We blindly benchmarked our method QAcon on CASP11 dataset as the MULTICOM‐CLUSTER server. Based on the evaluation, our method is ranked as one of the top single model QA methods. The good performance of the features based on contact prediction illustrates the value of using contact information in protein quality assessment. Availability and Implementation: The web server and the source code of QAcon are freely available at: http://cactus.rnet.missouri.edu/QAcon Contact: chengji@missouri.edu Supplementary information: Supplementary data are available at Bioinformatics online.

Massive integration of diverse protein quality assessment methods to improve template based modeling in CASP11

Model evaluation and selection is an important step and a big challenge in template‐based protein structure prediction. Individual model quality assessment methods designed for recognizing some specific properties of protein structures often fail to consistently select good models from a model pool because of their limitations. Therefore, combining multiple complimentary quality assessment methods is useful for improving model ranking and consequently tertiary structure prediction. Here, we report the performance and analysis of our human tertiary structure predictor (MULTICOM) based on the massive integration of 14 diverse complementary quality assessment methods that was successfully benchmarked in the 11th Critical Assessment of Techniques of Protein Structure prediction (CASP11). The predictions of MULTICOM for 39 template‐based domains were rigorously assessed by six scoring metrics covering global topology of Cα trace, local all‐atom fitness, side chain quality, and physical reasonableness of the model. The results show that the massive integration of complementary, diverse single‐model and multi‐model quality assessment methods can effectively leverage the strength of single‐model methods in distinguishing quality variation among similar good models and the advantage of multi‐model quality assessment methods of identifying reasonable average‐quality models. The overall excellent performance of the MULTICOM predictor demonstrates that integrating a large number of model quality assessment methods in conjunction with model clustering is a useful approach to improve the accuracy, diversity, and consequently robustness of template‐based protein structure prediction. Proteins 2016; 84(Suppl 1):247–259.

ConEVA: a toolbox for comprehensive assessment of protein contacts

BackgroundIn recent years, successful contact prediction methods and contact-guided ab initio protein structure prediction methods have highlighted the importance of incorporating contact information into protein structure prediction methods. It is also observed that for almost all globular proteins, the quality of contact prediction dictates the accuracy of structure prediction. Hence, like many existing evaluation measures for evaluating 3D protein models, various measures are currently used to evaluate predicted contacts, with the most popular ones being precision, coverage and distance distribution score (Xd).ResultsWe have built a web application and a downloadable tool, ConEVA, for comprehensive assessment and detailed comparison of predicted contacts. Besides implementing existing measures for contact evaluation we have implemented new and useful methods of contact visualization using chord diagrams and comparison using Jaccard similarity computations. For a set (or sets) of predicted contacts, the web application runs even when a native structure is not available, visualizing the contact coverage and similarity between predicted contacts. We applied the tool on various contact prediction data sets and present our findings and insights we obtained from the evaluation of effective contact assessments. ConEVA is publicly available at http://cactus.rnet.missouri.edu/coneva/.ConclusionConEVA is useful for a range of contact related analysis and evaluations including predicted contact comparison, investigation of individual protein folding using predicted contacts, and analysis of contacts in a structure of interest.

DeepSF: deep convolutional neural network for mapping protein sequences to folds

Motivation Protein fold recognition is an important problem in structural bioinformatics. Almost all traditional fold recognition methods use sequence (homology) comparison to indirectly predict the fold of a target protein based on the fold of a template protein with known structure, which cannot explain the relationship between sequence and fold. Only a few methods had been developed to classify protein sequences into a small number of folds due to methodological limitations, which are not generally useful in practice. Results We develop a deep 1D‐convolution neural network (DeepSF) to directly classify any protein sequence into one of 1195 known folds, which is useful for both fold recognition and the study of sequence‐structure relationship. Different from traditional sequence alignment (comparison) based methods, our method automatically extracts fold‐related features from a protein sequence of any length and maps it to the fold space. We train and test our method on the datasets curated from SCOP1.75, yielding an average classification accuracy of 75.3%. On the independent testing dataset curated from SCOP2.06, the classification accuracy is 73.0%. We compare our method with a top profile‐profile alignment method—HHSearch on hard template‐based and template‐free modeling targets of CASP9‐12 in terms of fold recognition accuracy. The accuracy of our method is 12.63‐26.32% higher than HHSearch on template‐free modeling targets and 3.39‐17.09% higher on hard template‐based modeling targets for top 1, 5 and 10 predicted folds. The hidden features extracted from sequence by our method is robust against sequence mutation, insertion, deletion and truncation, and can be used for other protein pattern recognition problems such as protein clustering, comparison and ranking. Availability and implementation The DeepSF server is publicly available at: http://iris.rnet.missouri.edu/DeepSF/. Supplementary information Supplementary data are available at Bioinformatics online.

The MULTICOM Protein Tertiary Structure Prediction System

With the expansion of genomics and proteomics data aided by the rapid progress of next-generation sequencing technologies, computational prediction of protein three-dimensional structure is an essential part of modern structural genomics initiatives. Prediction of protein structure through understanding of the theories behind protein sequence-structure relationship, however, remains one of the most challenging problems in contemporary life sciences. Here, we describe MULTICOM, a multi-level combination technique, intended to predict moderate- to high-resolution structure of a protein through a novel approach of combining multiple sources of complementary information derived from the experimentally solved protein structures in the Protein Data Bank. The MULTICOM web server is freely available at http://sysbio.rnet.missouri.edu/multicom_toolbox/.

An Improved Integration of Template-Based and Template-Free Protein Structure Modeling Methods and its Assessment in CASP11

Most computational protein structure prediction methods are designed for either template based or template-free (ab initio) structure prediction. The approaches that integrate the prediction capabilities of both template-based modeling and template-free modeling are needed to synergistically combine the two kinds of methods to improve protein structure prediction. In this work, we develop a new method to integrate several protein structure prediction methods including our template-based MULTICOM server, our ab initio contact-based protein structure prediction method CONFOLD, our multi-template-based model generation tool MTMG, and locally installed external Rosetta, I-TASSER and RaptorX protein structure prediction tools to improve protein structure prediction of a fullspectrum difficulty ranging from easy, to medium and to hard. Our method participated in the 11(th) community-wide Critical Assessment of Techniques for Protein Structure Prediction (CASP11) in 2014 as MULTICOM-NOVEL server. It was ranked among top 10 methods for protein tertiary structure prediction according to the official CASP11 assessment, which demonstrates that integrating complementary modeling methods is useful for advancing protein structure prediction.

Deep learning methods for protein torsion angle prediction

BackgroundDeep learning is one of the most powerful machine learning methods that has achieved the state-of-the-art performance in many domains. Since deep learning was introduced to the field of bioinformatics in 2012, it has achieved success in a number of areas such as protein residue-residue contact prediction, secondary structure prediction, and fold recognition. In this work, we developed deep learning methods to improve the prediction of torsion (dihedral) angles of proteins.ResultsWe design four different deep learning architectures to predict protein torsion angles. The architectures including deep neural network (DNN) and deep restricted Boltzmann machine (DRBN), deep recurrent neural network (DRNN) and deep recurrent restricted Boltzmann machine (DReRBM) since the protein torsion angle prediction is a sequence related problem. In addition to existing protein features, two new features (predicted residue contact number and the error distribution of torsion angles extracted from sequence fragments) are used as input to each of the four deep learning architectures to predict phi and psi angles of protein backbone. The mean absolute error (MAE) of phi and psi angles predicted by DRNN, DReRBM, DRBM and DNN is about 20–21° and 29–30° on an independent dataset. The MAE of phi angle is comparable to the existing methods, but the MAE of psi angle is 29°, 2° lower than the existing methods. On the latest CASP12 targets, our methods also achieved the performance better than or comparable to a state-of-the art method.ConclusionsOur experiment demonstrates that deep learning is a valuable method for predicting protein torsion angles. The deep recurrent network architecture performs slightly better than deep feed-forward architecture, and the predicted residue contact number and the error distribution of torsion angles extracted from sequence fragments are useful features for improving prediction accuracy.

A novel variant in CMAH is associated with blood type AB in Ragdoll cats

The enzyme cytidine monophospho-N-acetylneuraminic acid hydroxylase is associated with the production of sialic acids on cat red blood cells. The cat has one major blood group with three serotypes; the most common blood type A being dominant to type B. A third rare blood type is known as AB and has an unclear mode of inheritance. Cat blood type antigens are defined, with N-glycolylneuraminic acid being associated with type A and N-acetylneuraminic acid with type B. Blood type AB is serologically characterized by agglutination using typing reagents directed against both A and B epitopes. While a genetic characterization of blood type B has been achieved, the rare type AB serotype remains genetically uncharacterized. A genome-wide association study in Ragdoll cats (22 cases and 15 controls) detected a significant association between blood type AB and SNPs on cat chromosome B2, with the most highly associated SNP being at position 4,487,432 near the candidate gene cytidine monophospho-N-acetylneuraminic acid hydroxylase. A novel variant, c.364C>T, was identified that is highly associated with blood type AB in Ragdoll cats and, to a lesser degree, with type AB in random bred cats. The newly identified variant is probably linked with blood type AB in Ragdoll cats, and is associated with the expression of both antigens (N-glycolylneuraminic acid and N-acetylneuraminic acid) on the red blood cell membrane. Other variants, not identified by this work, are likely to be associated with blood type AB in other breeds of cat.