Search

Post-translational modifications (PTMs) either enhance a protein's activity in various sub-cellular processes, or degrade their activity which leads toward failure of intracellular processes. Tyrosine nitration (NT) modification degrades protein's activity that initiates and propagates various diseases including neurodegenerative, cardiovascular, autoimmune diseases and carcinogenesis. Identification of NT modification supports development of novel therapies and drug discoveries for associated diseases. Identification of NT modification in biochemical labs is expensive, time consuming and error-prone. To supplement this process, several computational approaches have been proposed. However these approaches fail to precisely identify NT modification, due to the extraction of irrelevant, redundant and less discriminative features from protein sequences. This paper presents the NTpred framework that is competent in extracting comprehensive features from raw protein sequences using four different sequence encoders. To reap the benefits of different encoders, it generates four additional feature spaces by fusing different combinations of individual encodings. Furthermore, it eradicates irrelevant and redundant features from eight different feature spaces through a Recursive Feature Elimination process. Selected features of four individual encodings and four feature fusion vectors are used to train eight different Gradient Boosted Tree classifiers. The probability scores from the trained classifiers are utilized to generate a new probabilistic feature space, which is used to train a Logistic Regression classifier. On the BD1 benchmark dataset, the proposed framework outperforms the existing best-performing predictor in 5-fold cross validation and independent test evaluation with combined improvement of 13.7% in MCC and 20.1% in AUC. Similarly, on the BD2 benchmark dataset, the proposed framework outperforms the existing best-performing predictor with combined improvement of 5.3% in MCC and 1.0% in AUC. NTpred is publicly available for further experimentation and predictive use at: https://sds_genetic_analysis.opendfki.de/PredNTS/. [ABSTRACT FROM AUTHOR]

• This review paper underscores how recent advances in artificial intelligence, particularly deep learning models, have revolutionized antibody design by accurately predicting antibody structures from amino acid sequences, addressing historical challenges in antibody structure prediction. • This paper discusses how AI techniques have significantly improved the accuracy of predicting antibody-antigen interactions, enhancing our understanding of antibody recognition. It emphasizes the importance of combining computational tools with experimental methods for more precise predictions. • This review paper sheds light on how AI methods, especially deep learning, have streamlined the process of antibody affinity maturation by predicting mutation effects. It emphasizes the need for considering environmental factors and molecular water in mutation prediction models. Given their high affinity and specificity for a range of macromolecules, antibodies are widely used in the treatment of autoimmune diseases, cancers, inflammatory diseases, and Alzheimer's disease (AD). Traditional experimental methods are time-consuming, expensive, and labor-intensive. Recent advances in artificial intelligence (AI) technologies provide complementary methods that can reduce the time and costs required for antibody design by minimizing failures and increasing the success rate of experimental tests. In this review, we scrutinize the plethora of AI-driven methodologies that have been deployed over the past 4 years for modeling antibody structures, predicting antibody–antigen interactions, optimizing antibody affinity, and generating novel antibody candidates. We also briefly address the challenges faced in integrating AI-based models with traditional antibody discovery pipelines and highlight the potential future directions in this burgeoning field. [ABSTRACT FROM AUTHOR]

The tremendous growth the pharmaceutical field witnessed especially concerning drug-development, caused drug-related experiments such as those concerned with estimating their interactions with targets harder to conduct. This issue led researchers to transition from vivo and vitro to selico experimenting methods, which deploy artificial intelligence (AI) techniques such as recommender systems (RS) to solve problems at hand. However, most RSs depend on global features such as indices, which render them incapable of fully understanding the behaviors of individuals. In this paper, we introduce our Convolutional Recurrent Deep Learning model-based RS approach, or 'RSCRDL', which tackles the interaction prediction problem from a natural language processing approach's (NLP) point of view. RSCDRL processes the textual representations of both protein sequences and drugs in order to learn the implicit features of the tokens forming them, rendering it able to process unseen and non-reactive individuals indirectly. We also present a greedier variant of RSCRDL that can exploit additional drugs explicit features for better predictive abilities. Experiments performed on two real-world datasets show significant outperformance achieved by our models over two general-purpose state-of-the-art RSs, while other experiments conducted on orphan protein sequences helped deduce drug candidates that are assumed to be capable of inhibiting their activities. [ABSTRACT FROM AUTHOR]

Identification and classification of protein families are one of the most significant problem in bioinformatics and protein studies. It is essential to specify the family of a protein since proteins are highly used in smart drug therapies, protein functions, and, in some cases, phylogenetic trees. Some sequencing techniques provide researchers to identify the biological similarities of protein families and functions. Yet, determining these families with sequencing applications requires huge amount of time. Thus, a computer and artificial intelligence based classification system is needed to save time and avoid complexity in protein classification process. In order to designate the protein families with computeraided systems, protein sequences need to be converted to the numerical representations. In this paper, we provide a novel protein mapping method based on Fibonacci numbers and hashing table (FIBHASH). Each amino acid code is assigned to the Fibonacci numbers based on integer representations respectively. Later, these amino acid codes are inserted a hashing table with the size of 20 to be classified with recurrent neural networks. To determine the performance of the proposed mapping method, we used accuracy, f1-score, recall, precision, and AUC evaluation criteria. In addition, the results of evaluation metrics with other protein mapping techniques including EIIP, hydrophobicity, CPNR, Atchley factors, BLOSUM62, PAM250, binary one-hot encoding, and randomly encoded representations are compared. The proposed method showed a promising result with an accuracy of 92.77%, and 0.98 AUC score. [ABSTRACT FROM AUTHOR]

DNA-binding proteins play pivotal roles in alternative splicing, RNA editing, methylating and many other biological functions for both eukaryotic and prokaryotic proteomes. Predicting the functions of these proteins from primary amino acids sequences is becoming one of the major challenges in functional annotations of genomes. Traditional prediction methods often devote themselves to extracting physiochemical features from sequences but ignoring motif information and location information between motifs. Meanwhile, the small scale of data volumes and large noises in training data result in lower accuracy and reliability of predictions. In this paper, we propose a deep learning based method to identify DNA-binding proteins from primary sequences alone. It utilizes two stages of convolutional neutral network to detect the function domains of protein sequences, and the long short-term memory neural network to identify their long term dependencies, an binary cross entropy to evaluate the quality of the neural networks. When the proposed method is tested with a realistic DNA binding protein dataset, it achieves a prediction accuracy of 94.2% at the Matthew’s correlation coefficient of 0.961. Compared with the LibSVM on the arabidopsis and yeast datasets via independent tests, the accuracy raises by 9% and 4% respectively. Comparative experiments using different feature extraction methods show that our model performs similar accuracy with the best of others, but its values of sensitivity, specificity and AUC increase by 27.83%, 1.31% and 16.21% respectively. Those results suggest that our method is a promising tool for identifying DNA-binding proteins. [ABSTRACT FROM AUTHOR]

Since the importance of DNA-binding proteins in multiple biomolecular functions has been recognized, an increasing number of researchers are attempting to identify DNA-binding proteins. In recent years, the machine learning methods have become more and more compelling in the case of protein sequence data soaring, because of their favorable speed and accuracy. In this paper, we extract three features from the protein sequence, namely NMBAC (Normalized Moreau-Broto Autocorrelation), PSSM-DWT (Position-specific scoring matrix—Discrete Wavelet Transform), and PSSM-DCT (Position-specific scoring matrix—Discrete Cosine Transform). We also employ feature selection algorithm on these feature vectors. Then, these features are fed into the training SVM (support vector machine) model as classifier to predict DNA-binding proteins. Our method applys three datasets, namely PDB1075, PDB594 and PDB186, to evaluate the performance of our approach. The PDB1075 and PDB594 datasets are employed for Jackknife test and the PDB186 dataset is used for the independent test. Our method achieves the best accuracy in the Jacknife test, from 79.20% to 86.23% and 80.5% to 86.20% on PDB1075 and PDB594 datasets, respectively. In the independent test, the accuracy of our method comes to 76.3%. The performance of independent test also shows that our method has a certain ability to be effectively used for DNA-binding protein prediction. The data and source code are at . [ABSTRACT FROM AUTHOR]

Background: Identifying conserved regions in protein sequences is a fundamental operation, occurring in numerous sequence-driven analysis pipelines. It is used as a way to decode domain-rich regions within proteins, to compute protein clusters, to annotate sequence function, and to compute evolutionary relationships among protein sequences. A number of approaches exist for identifying and characterizing protein families based on their domains, and because domains represent conserved portions of a protein sequence, the primary computation involved in protein family characterization is identification of such conserved regions. However, identifying conserved regions from large collections (millions) of protein sequences presents significant challenges. Methods: In this paper we present a new, alignment-free method for detecting conserved regions in protein sequences called NADDA (No-Alignment Domain Detection Algorithm). Our method exploits the abundance of exact matching short subsequences (k-mers) to quickly detect conserved regions, and the power of machine learning is used to improve the prediction accuracy of detection. We present a parallel implementation of NADDA using the MapReduce framework and show that our method is highly scalable. Results: We have compared NADDA with Pfam and InterPro databases. For known domains annotated by Pfam, accuracy is 83%, sensitivity 96%, and specificity 44%. For sequences with new domains not present in the training set an average accuracy of 63% is achieved when compared to Pfam. A boost in results in comparison with InterPro demonstrates the ability of NADDA to capture conserved regions beyond those present in Pfam. We have also compared NADDA with ADDA and MKDOM2, assuming Pfam as ground-truth. On average NADDA shows comparable accuracy, more balanced sensitivity and specificity, and being alignment-free, is significantly faster. Excluding the one-time cost of training, runtimes on a single processor were 49s, 10,566s, and 456s for NADDA, ADDA, and MKDOM2, respectively, for a data set comprised of approximately 2500 sequences. [ABSTRACT FROM AUTHOR]

Abstract: This paper addresses computational prediction of protein structural classes. Although in recent years progress in this field was made, the main drawback of the published prediction methods is a limited scope of comparison procedures, which in same cases were also improperly performed. Two examples include using protein datasets of varying homology, which has significant impact on the prediction accuracy, and comparing methods in pairs using different datasets. Based on extensive experimental work, the main aim of this paper is to revisit and reevaluate state of the art in this field. To this end, this paper performs a first-of-its-kind comprehensive and multi-goal study, which includes investigation of eight prediction algorithms, three protein sequence representations, three datasets with different homologies and finally three test procedures. Quality of several previously unused prediction algorithms, newly proposed sequence representation, and a new-to-the-field testing procedure is evaluated. Several important conclusions and findings are made. First, the logistic regression classifier, which was not previously used, is shown to perform better than other prediction algorithms, and high quality of previously used support vector machines is confirmed. The results also show that the proposed new sequence representation improves accuracy of the high quality prediction algorithms, while it does not improve results of the lower quality classifiers. The study shows that commonly used jackknife test is computationally expensive, and therefore computationally less demanding 10-fold cross-validation procedure is proposed. The results show that there is no statistically significant difference between these two procedures. The experiments show that sequence homology has very significant impact on the prediction accuracy, i.e. using highly homologous datasets results in higher accuracies. Thus, results of several past studies that use homologous datasets should not be perceived as reliable. The best achieved prediction accuracy for low homology datasets is about 57% and confirms results reported by Wang and Yuan [How good is the prediction of protein structural class by the component-coupled method?. Proteins 2000;38:165–175]. For a highly homologous dataset instance based classification is shown to be better than the previously reported results. It achieved 97% prediction accuracy demonstrating that homology is a major factor that can result in the overestimated prediction accuracy. [Copyright &y& Elsevier]

COVID-19 disease causes serious respiratory illnesses. Therefore, accurate identification of the viral infection cycle plays a key role in designing appropriate vaccines. The risk of this disease depends on proteins that interact with human receptors. In this paper, we formulate a novel model for COVID-19 named "amino acid encoding based prediction" (AAPred). This model is accurate, classifies the various coronavirus types, and distinguishes SARS-CoV-2 from other coronaviruses. With the AAPred model, we reduce the number of features to enhance its performance by selecting the most important ones employing statistical criteria. The protein sequence of SARS-CoV-2 for understanding the viral infection cycle is analyzed. Six machine learning classifiers related to decision trees, k-nearest neighbors, random forest, support vector machine, bagging ensemble, and gradient boosting are used to evaluate the model in terms of accuracy, precision, sensitivity, and specificity. We implement the obtained results computationally and apply them to real data from the National Genomics Data Center. The experimental results report that the AAPred model reduces the features to seven of them. The average accuracy of the 10-fold cross-validation is 98.69%, precision is 98.72%, sensitivity is 96.81%, and specificity is 97.72%. The features are selected utilizing information gain and classified with random forest. The proposed model predicts the type of Coronavirus and reduces the number of extracted features. We identify that SARS-CoV-2 has similar physicochemical characteristics in some regions of SARS-CoV. Also, we report that SARS-CoV-2 has similar infection cycles and sequences in some regions of SARS CoV indicating the affectedness of vaccines on SARS-CoV-2. A comparison with deep learning shows similar results with our method. • We formulate a novel model for COVID-19 that classifies the coronavirus types and differentiates SARS-CoV-2 from other coronaviruses, reducing the number of features of the model to enhance its performance. • We use machine learning techniques for evaluating the model in terms of accuracy, precision, sensitivity, and specificity. • We analyze the protein sequence of SARS-CoV-2 for understanding the viral infection cycle and obtain results that are implemented computationally and compared to deep learning tools. • We implement the obtained results computationally and apply them to real-world data. [ABSTRACT FROM AUTHOR]

Background: This paper deals with the preprocessing of protein sequences for supervised classification. Motif extraction is one way to address that task. It has been largely used to encode biological sequences into feature vectors to enable using well-known machine-learning classifiers which require this format. However, designing a suitable feature space, for a set of proteins, is not a trivial task. For this purpose, we propose a novel encoding method that uses amino-acid substitution matrices to define similarity between motifs during the extraction step. Results: In order to demonstrate the efficiency of such approach, we compare several encoding methods using some machine learning classifiers. The experimental results showed that our encoding method outperforms other ones in terms of classification accuracy and number of generated attributes. We also compared the classifiers in term of accuracy. Results indicated that SVM generally outperforms the other classifiers with any encoding method. We showed that SVM, coupled with our encoding method, can be an efficient protein classification system. In addition, we studied the effect of the substitution matrices variation on the quality of our method and hence on the classification quality. We noticed that our method enables good classification accuracies with all the substitution matrices and that the variances of the obtained accuracies using various substitution matrices are slight. However, the number of generated features varies from a substitution matrix to another. Furthermore, the use of already published datasets allowed us to carry out a comparison with several related works. Conclusions: The outcomes of our comparative experiments confirm the efficiency of our encoding method to represent protein sequences in classification tasks. [ABSTRACT FROM AUTHOR]

Researchers devoted considerable effort to detect the periodicity in DNA sequences, namely, the DNA segments that wrap the Histone protein. It is anticipated that periodic dinucleotide signals are indicators of certain important spots (like binding regions) within a DNA sequence; they are equally spaced along nucleosomal DNA with ~ 10 base-pair period. Positioned nucleosomes are believed to play an important role in transcriptional regulation and for the organization of chromatin in cell nuclei. In this paper, we describe and apply a dynamic periodicity detection algorithm to discover the periodicity of certain dinucleotides in DNA and Protein sequences. Our algorithm is based on suffix tree as the underlying data structure. The proposed approach is suitable to analyze different kinds of data and can serve different targets. It considers the periodicity of alternative substrings like the three dinucleotides AA/TA/TT, in addition to considering dynamic window to detect the periodicity of certain instances of substrings. We tested the applicability, effectiveness and resilience of the proposed approach to noise as compared to the other existing algorithms described in the literature. [ABSTRACT FROM AUTHOR]

Abstract: This paper proposes an efficient conserved region detection method for multiple protein sequences. Instead of detecting conserved regions directly from the set of all participatory protein sequences, the proposed method separates the detection process as two stages. In the fist stage, a serial of principal component analysis (PCA) techniques are applied to infer the common ancestor protein from the participatory proteins based on a hypothetical evolutionary history. Then, wavelet transform is employed to derive conserved regions from the common ancestor protein in the second stage. The detected conserved regions are considered as the common conserved regions of the original protein sequences. A set of experiments indicate that the two stage strategy makes the proposed method not only prevents the residue divergence problem but also increases the detection accuracy and efficiency. [Copyright &y& Elsevier]

The architectural landscape of high-performance computing stretches from superscalar uniprocessor to explicitly parallel systems to dedicated hardware implementations of algorithms. Single-purpose hardware can achieve the highest performance and uniprocessors can be the most programmable. Between these extremes, programmable and reconfigurable architectures provide a wide range of choice in flexibility, programmability, computational density, and performance. The UCSC Kestrel parallel processor strives to attain single-purpose performance while maintaining user programmability. Kestrel is a single-instruction stream, multiple- data stream (SIMD) parallel processor with a 512-element linear array of 8-bit processing elements. The system design focuses on efficient high-throughput DNA and protein sequence analysis, but its programmability enables high performance on computational chemistry, image processing, machine learning, and other applications. The Kestrel system has had unexpected longevity in its utility due to a careful design and analysis process. Experience with the system leads to the conclusion that programmable SIMD architectures can excel in both programmability and performance. This paper presents the architecture, implementation, applications, and observations of the Kestrel project at the University of California at Santa Cruz. [ABSTRACT FROM AUTHOR]