On the Relevance of Sophisticated Structural Annotations for Disulfide Connectivity Pattern Prediction

Disulfide bridges strongly constrain the native structure of many proteins and predicting their formation is therefore a key sub-problem of protein structure and function inference. Most recently proposed approaches for this prediction problem adopt the following pipeline: first they enrich the primary sequence with structural annotations, second they apply a binary classifier to each candidate pair of cysteines to predict disulfide bonding probabilities and finally, they use a maximum weight graph matching algorithm to derive the predicted disulfide connectivity pattern of a protein. In this paper, we adopt this three step pipeline and propose an extensive study of the relevance of various structural annotations and feature encodings. In particular, we consider five kinds of structural annotations, among which three are novel in the context of disulfide bridge prediction. So as to be usable by machine learning algorithms, these annotations must be encoded into features. For this purpose, we propose four different feature encodings based on local windows and on different kinds of histograms. The combination of structural annotations with these possible encodings leads to a large number of possible feature functions. In order to identify a minimal subset of relevant feature functions among those, we propose an efficient and interpretable feature function selection scheme, designed so as to avoid any form of overfitting. We apply this scheme on top of three supervised learning algorithms: k-nearest neighbors, support vector machines and extremely randomized trees. Our results indicate that the use of only the PSSM (position-specific scoring matrix) together with the CSP (cysteine separation profile) are sufficient to construct a high performance disulfide pattern predictor and that extremely randomized trees reach a disulfide pattern prediction accuracy of on the benchmark dataset SPX, which corresponds to improvement over the state of the art. A web-application is available at http://m24.giga.ulg.ac.be:81/x3CysBridges.     

Exploiting SNP Correlations within Random Forest for Genome-Wide Association Studies

The primary goal of genome-wide association studies (GWAS) is to discover variants that could lead, in isolation or in combination, to a particular trait or disease. Standard approaches to GWAS, however, are usually based on univariate hypothesis tests and therefore can account neither for correlations due to linkage disequilibrium nor for combinations of several markers. To discover and leverage such potential multivariate interactions, we propose in this work an extension of the Random Forest algorithm tailored for structured GWAS data. In terms of risk prediction, we show empirically on several GWAS datasets that the proposed T-Trees method significantly outperforms both the original Random Forest algorithm and standard linear models, thereby suggesting the actual existence of multivariate non-linear effects due to the combinations of several SNPs. We also demonstrate that variable importances as derived from our method can help identify relevant loci. Finally, we highlight the strong impact that quality control procedures may have, both in terms of predictive power and loci identification. Variable importance results and T-Trees source code are all available at www.montefiore.ulg.ac.be/~botta/ttrees/ and github.com/0asa/TTree-source respectively.     

Continuous Distributed Representation of Biological Sequences for Deep Proteomics and Genomics

We introduce a new representation and feature extraction method for biological sequences. Named bio-vectors (BioVec) to refer to biological sequences in general with protein-vectors (ProtVec) for proteins (amino-acid sequences) and gene-vectors (GeneVec) for gene sequences, this representation can be widely used in applications of deep learning in proteomics and genomics. In the present paper, we focus on protein-vectors that can be utilized in a wide array of bioinformatics investigations such as family classification, protein visualization, structure prediction, disordered protein identification, and protein-protein interaction prediction. In this method, we adopt artificial neural network approaches and represent a protein sequence with a single dense n-dimensional vector. To evaluate this method, we apply it in classification of 324,018 protein sequences obtained from Swiss-Prot belonging to 7,027 protein families, where an average family classification accuracy of 93%±0.06% is obtained, outperforming existing family classification methods. In addition, we use ProtVec representation to predict disordered proteins from structured proteins. Two databases of disordered sequences are used: the DisProt database as well as a database featuring the disordered regions of nucleoporins rich with phenylalanine-glycine repeats (FG-Nups). Using support vector machine classifiers, FG-Nup sequences are distinguished from structured protein sequences found in Protein Data Bank (PDB) with a 99.8% accuracy, and unstructured DisProt sequences are differentiated from structured DisProt sequences with 100.0% accuracy. These results indicate that by only providing sequence data for various proteins into this model, accurate information about protein structure can be determined. Importantly, this model needs to be trained only once and can then be applied to extract a comprehensive set of information regarding proteins of interest. Moreover, this representation can be considered as pre-training for various applications of deep learning in bioinformatics. The related data is available at Life Language Processing Website: http://llp.berkeley.edu and Harvard Dataverse: http://dx.doi.org/10.7910/DVN/JMFHTN.     

16S Classifier: A Tool for Fast and Accurate Taxonomic Classification of 16S rRNA Hypervariable Regions in Metagenomic Datasets

The diversity of microbial species in a metagenomic study is commonly assessed using 16S rRNA gene sequencing. With the rapid developments in genome sequencing technologies, the focus has shifted towards the sequencing of hypervariable regions of 16S rRNA gene instead of full length gene sequencing. Therefore, 16S Classifier is developed using a machine learning method, Random Forest, for faster and accurate taxonomic classification of short hypervariable regions of 16S rRNA sequence. It displayed precision values of up to 0.91 on training datasets and the precision values of up to 0.98 on the test dataset. On real metagenomic datasets, it showed up to 99.7% accuracy at the phylum level and up to 99.0% accuracy at the genus level. 16S Classifier is available freely at http://metagenomics.iiserb.ac.in/16Sclassifier and http://metabiosys.iiserb.ac.in/16Sclassifier.     

High-throughput prediction of RNA,DNA and protein binding regions mediated by intrinsic disorder

Intrinsically disordered proteins and regions (IDPs and IDRs) lack stable 3D structure under physiological conditions in-vitro, are common in eukaryotes, and facilitate interactions with RNA, DNA and proteins. Current methods for prediction of IDPs and IDRs do not provide insights into their functions, except for a handful of methods that address predictions of protein-binding regions. We report first-of-its-kind computational method DisoRDPbind for high-throughput prediction of RNA, DNA and protein binding residues located in IDRs from protein sequences. DisoRDPbind is implemented using a runtime-efficient multi-layered design that utilizes information extracted from physiochemical properties of amino acids, sequence complexity, putative secondary structure and disorder and sequence alignment. Empirical tests demonstrate that it provides accurate predictions that are competitive with other predictors of disorder-mediated protein binding regions and complementary to the methods that predict RNA- and DNA-binding residues annotated based on crystal structures. Application in Homo sapiens, Mus musculus, Caenorhabditis elegans and Drosophila melanogaster proteomes reveals that RNA- and DNA-binding proteins predicted by DisoRDPbind complement and overlap with the corresponding known binding proteins collected from several sources. Also, the number of the putative protein-binding regions predicted with DisoRDPbind correlates with the promiscuity of proteins in the corresponding protein–protein interaction networks. Webserver: http://biomine.ece.ualberta.ca/DisoRDPbind/     

PIPE-CLIP: a comprehensive online tool for CLIP-seq data analysis

CLIP-seq is widely used to study genome-wide interactions between RNA-binding proteins and RNAs. However, there are few tools available to analyze CLIP-seq data, thus creating a bottleneck to the implementation of this methodology. Here, we present PIPE-CLIP, a Galaxy framework-based comprehensive online pipeline for reliable analysis of data generated by three types of CLIP-seq protocol: HITS-CLIP, PAR-CLIP and iCLIP. PIPE-CLIP provides both data processing and statistical analysis to determine candidate cross-linking regions, which are comparable to those regions identified from the original studies or using existing computational tools. PIPE-CLIP is available at http://pipeclip.qbrc.org/.     

Assessing and enhancing foldability in designed proteins

Recent advances in protein‐design methodology have led to a dramatic increase in reliability and scale. With these advances, dozens and even thousands of designed proteins are automatically generated and screened. Nevertheless, the success rate, particularly in design of functional proteins, is low and fundamental goals such as reliable de novo design of efficient enzymes remain beyond reach. Experimental analyses have consistently indicated that a major reason for design failure is inaccuracy and misfolding relative to the design conception. To address this challenge, we describe complementary methods to diagnose and ameliorate suboptimal regions in designed proteins: first, we develop a Rosetta atomistic computational mutation scanning approach to detect energetically suboptimal positions in designs (available on a web server https://pSUFER.weizmann.ac.il); second, we demonstrate that AlphaFold2 ab initio structure prediction flags regions that may misfold in designed enzymes and binders; and third, we focus FuncLib design calculations on suboptimal positions in a previously designed low‐efficiency enzyme, improving its catalytic efficiency by 330‐fold. Furthermore, applied to a de novo designed protein that exhibited limited stability, the same approach markedly improved stability and expressibility. Thus, foldability analysis and enhancement may dramatically increase the success rate in design of functional proteins.     

DisoMCS: Accurately Predicting Protein Intrinsically Disordered Regions Using a Multi-Class Conservative Score Approach

The precise prediction of protein intrinsically disordered regions, which play a crucial role in biological procedures, is a necessary prerequisite to further the understanding of the principles and mechanisms of protein function. Here, we propose a novel predictor, DisoMCS, which is a more accurate predictor of protein intrinsically disordered regions. The DisoMCS bases on an original multi-class conservative score (MCS) obtained by sequence-order/disorder alignment. Initially, near-disorder regions are defined on fragments located at both the terminus of an ordered region connecting a disordered region. Then the multi-class conservative score is generated by sequence alignment against a known structure database and represented as order, near-disorder and disorder conservative scores. The MCS of each amino acid has three elements: order, near-disorder and disorder profiles. Finally, the MCS is exploited as features to identify disordered regions in sequences. DisoMCS utilizes a non-redundant data set as the training set, MCS and predicted secondary structure as features, and a conditional random field as the classification algorithm. In predicted near-disorder regions a residue is determined as an order or a disorder according to the optimized decision threshold. DisoMCS was evaluated by cross-validation, large-scale prediction, independent tests and CASP (Critical Assessment of Techniques for Protein Structure Prediction) tests. All results confirmed that DisoMCS was very competitive in terms of accuracy of prediction when compared with well-established publicly available disordered region predictors. It also indicated our approach was more accurate when a query has higher homologous with the knowledge database.

Availability

The DisoMCS is available at http://cal.tongji.edu.cn/disorder/.     

DisPredict: A Predictor of Disordered Protein Using Optimized RBF Kernel

Intrinsically disordered proteins or, regions perform important biological functions through their dynamic conformations during binding. Thus accurate identification of these disordered regions have significant implications in proper annotation of function, induced fold prediction and drug design to combat critical diseases. We introduce DisPredict, a disorder predictor that employs a single support vector machine with RBF kernel and novel features for reliable characterization of protein structure. DisPredict yields effective performance. In addition to 10-fold cross validation, training and testing of DisPredict was conducted with independent test datasets. The results were consistent with both the training and test error minimal. The use of multiple data sources, makes the predictor generic. The datasets used in developing the model include disordered regions of various length which are categorized as short and long having different compositions, different types of disorder, ranging from fully to partially disordered regions as well as completely ordered regions. Through comparison with other state of the art approaches and case studies, DisPredict is found to be a useful tool with competitive performance. DisPredict is available at https://github.com/tamjidul/DisPredict_v1.0.     

NNvPDB: Neural Network based Protein Secondary Structure Prediction with PDB Validation

Availabilityhttp://bit.srmuniv.ac.in/cgi-bin/bit/cfpdb/nnsecstruct.pl     

CleavPredict: A Platform for Reasoning about Matrix Metalloproteinases Proteolytic Events

CleavPredict (http://cleavpredict.sanfordburnham.org) is a Web server for substrate cleavage prediction for matrix metalloproteinases (MMPs). It is intended as a computational platform aiding the scientific community in reasoning about proteolytic events. CleavPredict offers in silico prediction of cleavage sites specific for 11 human MMPs. The prediction method employs the MMP specific position weight matrices (PWMs) derived from statistical analysis of high-throughput phage display experimental results. To augment the substrate cleavage prediction process, CleavPredict provides information about the structural features of potential cleavage sites that influence proteolysis. These include: secondary structure, disordered regions, transmembrane domains, and solvent accessibility. The server also provides information about subcellular location, co-localization, and co-expression of proteinase and potential substrates, along with experimentally determined positions of single nucleotide polymorphism (SNP), and posttranslational modification (PTM) sites in substrates. All this information will provide the user with perspectives in reasoning about proteolytic events. CleavPredict is freely accessible, and there is no login required.     

EMu: probabilistic inference of mutational processes and their localization in the cancer genome

The spectrum of mutations discovered in cancer genomes can be explained by the activity of a few elementary mutational processes. We present a novel probabilistic method, EMu, to infer the mutational signatures of these processes from a collection of sequenced tumors. EMu naturally incorporates the tumor-specific opportunity for different mutation types according to sequence composition. Applying EMu to breast cancer data, we derive detailed maps of the activity of each process, both genome-wide and within specific local regions of the genome. Our work provides new opportunities to study the mutational processes underlying cancer development. EMu is available at http://www.sanger.ac.uk/resources/software/emu/.     

PDBsum extras: SARS‐CoV‐2 and AlphaFold models

The PDBsum web server provides structural analyses of the entries in the Protein Data Bank (PDB). Two recent additions are described here. The first is the detailed analysis of the SARS‐CoV‐2 virus protein structures in the PDB. These include the variants of concern, which are shown both on the sequences and 3D structures of the proteins. The second addition is the inclusion of the available AlphaFold models for human proteins. The pages allow a search of the protein against existing structures in the PDB via the Sequence Annotated by Structure (SAS) server, so one can easily compare the predicted model against experimentally determined structures. The server is freely accessible to all at http://www.ebi.ac.uk/pdbsum.     

sRNATarBase: A comprehensive database of bacterial sRNA targets verified by experiments

Bacterial sRNAs are an emerging class of small regulatory RNAs, 40–500 nt in length, which play a variety of important roles in many biological processes through binding to their mRNA or protein targets. A comprehensive database of experimentally confirmed sRNA targets would be helpful in understanding sRNA functions systematically and provide support for developing prediction models. Here we report on such a database—sRNATarBase. The database holds 138 sRNA–target interactions and 252 noninteraction entries, which were manually collected from peer-reviewed papers. The detailed information for each entry, such as supporting experimental protocols, BLAST-based phylogenetic analysis of sRNA–mRNA target interaction in closely related bacteria, predicted secondary structures for both sRNAs and their targets, and available binding regions, is provided as accurately as possible. This database also provides hyperlinks to other databases including GenBank, SWISS-PROT, and MPIDB. The database is available from the web page http://ccb.bmi.ac.cn/srnatarbase/.     

Building a Better Fragment Library for De Novo Protein Structure Prediction

Fragment-based approaches are the current standard for de novo protein structure prediction. These approaches rely on accurate and reliable fragment libraries to generate good structural models. In this work, we describe a novel method for structure fragment library generation and its application in fragment-based de novo protein structure prediction. The importance of correct testing procedures in assessing the quality of fragment libraries is demonstrated. In particular, the exclusion of homologs to the target from the libraries to correctly simulate a de novo protein structure prediction scenario, something which surprisingly is not always done. We demonstrate that fragments presenting different predominant predicted secondary structures should be treated differently during the fragment library generation step and that exhaustive and random search strategies should both be used. This information was used to develop a novel method, Flib. On a validation set of 41 structurally diverse proteins, Flib libraries presents both a higher precision and coverage than two of the state-of-the-art methods, NNMake and HHFrag. Flib also achieves better precision and coverage on the set of 275 protein domains used in the two previous experiments of the the Critical Assessment of Structure Prediction (CASP9 and CASP10). We compared Flib libraries against NNMake libraries in a structure prediction context. Of the 13 cases in which a correct answer was generated, Flib models were more accurate than NNMake models for 10. “Flib is available for download at: http://www.stats.ox.ac.uk/research/proteins/resources”.     

Mammalian Mitochondrial ncRNA Database

Mammalian Mitochondrial ncRNA is a web-based database, which provides specific information on non-coding RNA in mammals. This database includes easy searching, comparing with BLAST and retrieving information on predicted structure and its function about mammalian ncRNAs.

Availability

The database is available for free at http://www.iitm.ac.in/bioinfo/mmndb/     

HNHDb: A database on pattern based classification of HNH domains reveals functional relevance of sequence patterns and domain associations.

The HNH Database is a collection and sequence-based classification of HNH domain proteins. The database contains about 1913 HNH domain containing proteins, and is classified into 10 subsets based on the sequence pattern. Each of these subsets has unique signature sequences. We have shown a correlation between the subset combination and their domain association and function. Functional divergence of this domain may be due to the combination of these conserved patterns and the large variations in the non-conserved regions. HNHDb is freely available at http://bicmku.in:8081/hnh.     

SECISearch3 and Seblastian: new tools for prediction of SECIS elements and selenoproteins

Selenoproteins are proteins containing an uncommon amino acid selenocysteine (Sec). Sec is inserted by a specific translational machinery that recognizes a stem-loop structure, the SECIS element, at the 3′ UTR of selenoprotein genes and recodes a UGA codon within the coding sequence. As UGA is normally a translational stop signal, selenoproteins are generally misannotated and designated tools have to be developed for this class of proteins. Here, we present two new computational methods for selenoprotein identification and analysis, which we provide publicly through the web servers at http://gladyshevlab.org/SelenoproteinPredictionServer or http://seblastian.crg.es. SECISearch3 replaces its predecessor SECISearch as a tool for prediction of eukaryotic SECIS elements. Seblastian is a new method for selenoprotein gene detection that uses SECISearch3 and then predicts selenoprotein sequences encoded upstream of SECIS elements. Seblastian is able to both identify known selenoproteins and predict new selenoproteins. By applying these tools to diverse eukaryotic genomes, we provide a ranked list of newly predicted selenoproteins together with their annotated cysteine-containing homologues. An analysis of a representative candidate belonging to the AhpC family shows how the use of Sec in this protein evolved in bacterial and eukaryotic lineages.     

Seed Pro-Nutra Care: A tool for characterization of seed storage proteins and database of bioactive peptides having potential health benefits

Seed storage proteins, the major food proteins, possess unique physicochemical characteristics which determine their nutritional importance and influence their utilization by humans. Here, we describe a database driven tool named Seed Pro-Nutra Care which comprises a systematic compendium of seed storage proteins and their bioactive peptides influencing several vital organ systems for maintenance of health. Seed Pro-Nutra Careis an integrated resource on seed storage protein. This resource help in the (I) Characterization of proteins whether they belong to seed storage protein group or not. (II) Identification the bioactive peptides with their sequences using peptide name (III) Determination of physico chemical properties of seed storage proteins. (IV) Epitope identification and mapping (V) Allergenicity prediction and characterization. Seed Pro-Nutra Care is a compilation of data on bioactive peptides present in seed storage proteins from our own collections and other published and unpublished sources. The database provides an information resource of a variety of seed related biological information and its use for nutritional and biomedical application.

Availability

http://www.gbpuat-cbsh.ac.in/departments/bi/database/seed_pro_nutra_care/