Using principal component analysis and support vector machine to predict protein structural class for low-similarity sequences via PSSM

The accurate identification of protein structure class solely using extracted information from protein sequence is a complicated task in the current computational biology. Prediction of protein structural class for low-similarity sequences remains a challenging problem. In this study, the new computational method has been developed to predict protein structural class by fusing the sequence information and evolution information to represent a protein sample. To evaluate the performance of the proposed method, jackknife cross-validation tests are performed on two widely used benchmark data-sets, 1189 and 25PDB with sequence similarity lower than 40 and 25%, respectively. Comparison of our results with other methods shows that the proposed method by us is very promising and may provide a cost-effective alternative to predict protein structural class in particular for low-similarity data-sets.     

MemType-2L: a web server for predicting membrane proteins and their types by incorporating evolution information through Pse-PSSM

Given an uncharacterized protein sequence, how can we identify whether it is a membrane protein or not? If it is, which membrane protein type it belongs to? These questions are important because they are closely relevant to the biological function of the query protein and to its interaction process with other molecules in a biological system. Particularly, with the avalanche of protein sequences generated in the Post-Genomic Age and the relatively much slower progress in using biochemical experiments to determine their functions, it is highly desired to develop an automated method that can be used to help address these questions. In this study, a 2-layer predictor, called MemType-2L, has been developed: the 1st layer prediction engine is to identify a query protein as membrane or non-membrane; if it is a membrane protein, the process will be automatically continued with the 2nd-layer prediction engine to further identify its type among the following eight categories: (1) type I, (2) type II, (3) type III, (4) type IV, (5) multipass, (6) lipid-chain-anchored, (7) GPI-anchored, and (8) peripheral. MemType-2L is featured by incorporating the evolution information through representing the protein samples with the Pse-PSSM (Pseudo Position-Specific Score Matrix) vectors, and by containing an ensemble classifier formed by fusing many powerful individual OET-KNN (Optimized Evidence-Theoretic K-Nearest Neighbor) classifiers. The success rates obtained by MemType-2L on a new-constructed stringent dataset by both the jackknife test and the independent dataset test are quite high, indicating that MemType-2L may become a very useful high throughput tool. As a Web server, MemType-2L is freely accessible to the public at http://chou.med.harvard.edu/bioinf/MemType.     

Prediction of enzymes and non-enzymes from protein sequences based on sequence derived features and PSSM matrix using artificial neural network

The problem of predicting the enzymes and non-enzymes from the protein sequence information is still an open problem in bioinformatics. It is further becoming more important as the number of sequenced information grows exponentially over time. We describe a novel approach for predicting the enzymes and non-enzymes from its amino-acid sequence using artificial neural network (ANN). Using 61 sequence derived features alone we have been able to achieve 79 percent correct prediction of enzymes/non-enzymes (in the set of 660 proteins). For the complete set of 61 parameters using 5-fold cross-validated classification, ANN model reveal a superior model (accuracy = 78.79 plus or minus 6.86 percent, Q(pred) = 74.734 plus or minus 17.08 percent, sensitivity = 84.48 plus or minus 6.73 percent, specificity = 77.13 plus or minus 13.39 percent). The second module of ANN is based on PSSM matrix. Using the same 5-fold cross-validation set, this ANN model predicts enzymes/non-enzymes with more accuracy (accuracy = 80.37 plus or minus 6.59 percent, Q(pred) = 67.466 plus or minus 12.41 percent, sensitivity = 0.9070 plus or minus 3.37 percent, specificity = 74.66 plus or minus 7.17 percent).     

Predicting metal-binding site residues in low-resolution structural models

The accurate prediction of the biochemical function of a protein is becoming increasingly important, given the unprecedented growth of both structural and sequence databanks. Consequently, computational methods are required to analyse such data in an automated manner to ensure genomes are annotated accurately. Protein structure prediction methods, for example, are capable of generating approximate structural models on a genome-wide scale. However, the detection of functionally important regions in such crude models, as well as structural genomics targets, remains an extremely important problem. The method described in the current study, MetSite, represents a fully automatic approach for the detection of metal-binding residue clusters applicable to protein models of moderate quality. The method involves using sequence profile information in combination with approximate structural data. Several neural network classifiers are shown to be able to distinguish metal sites from non-sites with a mean accuracy of 94.5%. The method was demonstrated to identify metal-binding sites correctly in LiveBench targets where no obvious metal-binding sequence motifs were detectable using InterPro. Accurate detection of metal sites was shown to be feasible for low-resolution predicted structures generated using mGenTHREADER where no side-chain information was available. High-scoring predictions were observed for a recently solved hypothetical protein from Haemophilus influenzae, indicating a putative metal-binding site.     

Filling-in Void and Sparse Regions in Protein Sequence Space by Protein-Like Artificial Sequences Enables Remarkable Enhancement in Remote Homology Detection Capability

Protein functional annotation relies on the identification of accurate relationships, sequence divergence being a key factor. This is especially evident when distant protein relationships are demonstrated only with three-dimensional structures. To address this challenge, we describe a computational approach to purposefully bridge gaps between related protein families through directed design of protein-like “linker” sequences. For this, we represented SCOP domain families, integrated with sequence homologues, as multiple profiles and performed HMM-HMM alignments between related domain families. Where convincing alignments were achieved, we applied a roulette wheel-based method to design 3,611,010 protein-like sequences corresponding to 374 SCOP folds. To analyze their ability to link proteins in homology searches, we used 3024 queries to search two databases, one containing only natural sequences and another one additionally containing designed sequences. Our results showed that augmented database searches showed up to 30% improvement in fold coverage for over 74% of the folds, with 52 folds achieving all theoretically possible connections. Although sequences could not be designed between some families, the availability of designed sequences between other families within the fold established the sequence continuum to demonstrate 373 difficult relationships. Ultimately, as a practical and realistic extension, we demonstrate that such protein-like sequences can be “plugged-into” routine and generic sequence database searches to empower not only remote homology detection but also fold recognition. Our richly statistically supported findings show that complementary searches in both databases will increase the effectiveness of sequence-based searches in recognizing all homologues sharing a common fold.     

自动编码器方法的蛋白质二级结构预测

蛋白质二级结构预测是进行蛋白质三级结构研究的重要基础,氨基酸的编码方式对二级结构预测有一定的影响。本文应用了一种新的组合编码方式,即将基团编码与位置特异性打分矩阵(PSSM)进行组合的编码方式。本文中提出的基团编码是针对氨基酸的一种新的编码方式,基团编码是根据氨基酸内部组成来进行编码的,由42位属性组成。本文选取位置特异性打分矩阵(PSSM)中的Blosum62进化矩阵和新的基团编码进行组合,形成新的编码方式。然后对CB513和25pdb两组数据分别进行实验。本文中将采用贝叶斯分类器与自动编码器两种方法来对这种新的编码方式进行实验,然后比较这两种方法得到的两组数据的结果。可以很明显的发现采用自动编码器的实验结果要比使用贝叶斯分类器的结果要高出1.65%。在本文的实验中,可以提取特征的自动编码器的预测准确率更好。     

Prediction of zinc binding sites in proteins using sequence derived information

Zinc is one the most abundant catalytic cofactor and also an important structural component of a large number of metallo-proteins. Hence prediction of zinc metal binding sites in proteins can be a significant step in annotation of molecular function of a large number of proteins. Majority of existing methods for zinc-binding site predictions are based on a data-set of proteins, which has been compiled nearly a decade ago. Hence there is a need to develop zinc-binding site prediction system using the current updated data to include recently added proteins. Herein, we propose a support vector machine-based method, named as ZincBinder, for prediction of zinc metal-binding site in a protein using sequence profile information. The predictor was trained using fivefold cross validation approach and achieved 85.37% sensitivity with 86.20% specificity during training. Benchmarking on an independent non-redundant data-set, which was not used during training, showed better performance of ZincBinder vis-à-vis existing methods. Executable versions, source code, sample datasets, and usage instructions are available at http://proteininformatics.org/mkumar/znbinder/     

NAGbinder: An approach for identifying N‐acetylglucosamine interacting residues of a protein from its primary sequence

N‐acetylglucosamine (NAG) belongs to the eight essential saccharides that are required to maintain the optimal health and precise functioning of systems ranging from bacteria to human. In the present study, we have developed a method, NAGbinder, which predicts the NAG‐interacting residues in a protein from its primary sequence information. We extracted 231 NAG‐interacting nonredundant protein chains from Protein Data Bank, where no two sequences share more than 40% sequence identity. All prediction models were trained, validated, and evaluated on these 231 protein chains. At first, prediction models were developed on balanced data consisting of 1,335 NAG‐interacting and noninteracting residues, using various window size. The model developed by implementing Random Forest using binary profiles as the main principle for identifying NAG‐interacting residue with window size 9, performed best among other models. It achieved highest Matthews Correlation Coefficient (MCC) of 0.31 and 0.25, and Area Under Receiver Operating Curve (AUROC) of 0.73 and 0.70 on training and validation data set, respectively. We also developed prediction models on realistic data set (1,335 NAG‐interacting and 47,198 noninteracting residues) using the same principle, where the model achieved MCC of 0.26 and 0.27, and AUROC of 0.70 and 0.71, on training and validation data set, respectively. The success of our method can be appraised by the fact that, if a sequence of 1,000 amino acids is analyzed with our approach, 10 residues will be predicted as NAG‐interacting, out of which five are correct. Best models were incorporated in the standalone version and in the webserver available at https://webs.iiitd.edu.in/raghava/nagbinder/     

WEDeepT3: predicting type III secreted effectors based on word embedding and deep learning

Background: The type III secreted effectors (T3SEs) are one of the indispensable proteins in the growth and reproduction of Gram-negative bacteria. In particular, the pathogenesis of Gram-negative bacteria depends on the type III secreted effectors, and by injecting T3SEs into a host cell, the host cell’s immunity can be destroyed. The high diversity of T3SE sequences and the lack of defined secretion signals make it difficult to identify and predict. Moreover, the related study of the pathological system associated with T3SE remains a hot topic in bioinformatics. Some computational tools have been developed to meet the growing demand for the recognition of T3SEs and the studies of type III secretion systems (T3SS). Although these tools can help biological experiments in certain procedures, there is still room for improvement, even for the current best model, as the existing methods adopt hand-designed feature and traditional machine learning methods. Methods: In this study, we propose a powerful predictor based on deep learning methods, called WEDeepT3. Our work consists mainly of three key steps. First, we train word embedding vectors for protein sequences in a large-scale amino acid sequence database. Second, we combine the word vectors with traditional features extracted from protein sequences, like PSSM, to construct a more comprehensive feature representation. Finally, we construct a deep neural network model in the prediction of type III secreted effectors. Results: The feature representation of WEDeepT3 consists of both word embedding and position-specific features. Working together with convolutional neural networks, the new model achieves superior performance to the state-of-the-art methods, demonstrating the effectiveness of the new feature representation and the powerful learning ability of deep models. Conclusion: WEDeepT3 exploits both semantic information of k-mer fragments and evolutional information of protein sequences to accurately differentiate between T3SEs and non-T3SEs. WEDeepT3 is available at bcmi.sjtu.edu.cn/~yangyang/WEDeepT3.html.     

Determinants of BH3 Binding Specificity for Mcl-1 versus Bcl-xL

Interactions among Bcl-2 family proteins are important for regulating apoptosis. Prosurvival members of the family interact with proapoptotic BH3 (Bcl-2-homology-3)-only members, inhibiting execution of cell death through the mitochondrial pathway. Structurally, this interaction is mediated by binding of the α-helical BH3 region of the proapoptotic proteins to a conserved hydrophobic groove on the prosurvival proteins. Native BH3-only proteins exhibit selectivity in binding prosurvival members, as do small molecules that block these interactions. Understanding the sequence and structural basis of interaction specificity in this family is important, as it may allow the prediction of new Bcl-2 family associations and/or the design of new classes of selective inhibitors to serve as reagents or therapeutics. In this work, we used two complementary techniques—yeast surface display screening from combinatorial peptide libraries and SPOT peptide array analysis—to elucidate specificity determinants for binding to Bcl-x_Lversus Mcl-1, two prominent prosurvival proteins. We screened a randomized library and identified BH3 peptides that bound to either Mcl-1 or Bcl-x_L selectively or to both with high affinity. The peptides competed with native ligands for binding into the conserved hydrophobic groove, as illustrated in detail by a crystal structure of a specific peptide bound to Mcl-1. Mcl-1-selective peptides from the screen were highly specific for binding Mcl-1 in preference to Bcl-x_L, Bcl-2, Bcl-w, and Bfl-1, whereas Bcl-x_L-selective peptides showed some cross-interaction with related proteins Bcl-2 and Bcl-w. Mutational analyses using SPOT arrays revealed the effects of 170 point mutations made in the background of a peptide derived from the BH3 region of Bim, and a simple predictive model constructed using these data explained much of the specificity observed in our Mcl-1 versus Bcl-x_L binders.