Discovery and development of biopeptides are time-consuming, laborious, and dependent on various factors. Data-driven computational methods, especially machine learning (ML) approach, can rapidly and efficiently predict the utility of therapeutic peptides. ML methods offer an array of tools that can accelerate and enhance decision making and discovery for well-defined queries with ample and sophisticated data quality. Various ML approaches, such as support vector machines, random forest, extremely randomized tree, and more recently deep learning methods, are useful in peptide-based drug discovery. These approaches leverage the peptide data sets, created via high-throughput sequencing and computational methods, and enable the prediction of functional peptides with increased levels of accuracy. The use of ML approaches in the development of peptide-based therapeutics is relatively recent; however, these techniques are already revolutionizing protein research by unraveling their novel therapeutic peptide functions. In this review, we discuss several ML-based state-of-the-art peptide-prediction tools and compare these methods in terms of their algorithms, feature encodings, prediction scores, evaluation methodologies, and software utilities. We also assessed the prediction performance of these methods using well-constructed independent data sets. In addition, we discuss the common pitfalls and challenges of using ML approaches for peptide therapeutics. Overall, we show that using ML models in peptide research can streamline the development of targeted peptide therapies.

Machine intelligence in peptide therapeutics: A next-generation tool for rapid disease screening

One of the ubiquitous chemical modifications in RNA, pseudouridine modification is crucial for various cellular biological and physiological processes. To gain more insight into the functional mechanisms involved, it is of fundamental importance to precisely identify pseudouridine sites in RNA. Several useful machine learning approaches have become available recently, with the increasing progress of next-generation sequencing technology; however, existing methods cannot predict sites with high accuracy. Thus, a more accurate predictor is required. In this study, a random forest-based predictor named RF-PseU is proposed for prediction of pseudouridylation sites. To optimize feature representation and obtain a better model, the light gradient boosting machine algorithm and incremental feature selection strategy were used to select the optimum feature space vector for training the random forest model RF-PseU. Compared with previous state-of-the-art predictors, the results on the same benchmark data sets of three species demonstrate that RF-PseU performs better overall. The integrated average leave-one-out cross-validation and independent testing accuracy scores were 71.4% and 74.7%, respectively, representing increments of 3.63% and 4.77% versus the best existing predictor. Moreover, the final RF-PseU model for prediction was built on leave-one-out cross-validation and provides a reliable and robust tool for identifying pseudouridine sites. A web server with a user-friendly interface is accessible at http://148.70.81.170:10228/rfpseu.

/pdf/rf-pseu-a-random-forest-predictor-for-rna-pseudouridine-1au05bcixl.pdf

RF-PseU: A Random Forest Predictor for RNA Pseudouridine Sites

Motivation Promoter is a short region of DNA which is responsible for initiating transcription of specific genes. Development of computational tools for automatic identification of promoters is in high demand. According to the difference of functions, promoters can be of different types. Promoters may have both intra- and interclass variation and similarity in terms of consensus sequences. Accurate classification of various types of sigma promoters still remains a challenge. Results We present iPromoter-BnCNN for identification and accurate classification of six types of promoters-σ24,σ28,σ32,σ38,σ54,σ70. It is a CNN-based classifier which combines local features related to monomer nucleotide sequence, trimer nucleotide sequence, dimer structural properties and trimer structural properties through the use of parallel branching. We conducted experiments on a benchmark dataset and compared with six state-of-the-art tools to show our supremacy on 5-fold cross-validation. Moreover, we tested our classifier on an independent test dataset. Availability and implementation Our proposed tool iPromoter-BnCNN web server is freely available at http://103.109.52.8/iPromoter-BnCNN. The runnable source code can be found https://colab.research.google.com/drive/1yWWh7BXhsm8U4PODgPqlQRy23QGjF2DZ. Supplementary information Supplementary data are available at Bioinformatics online.

iPromoter-BnCNN: a novel branched CNN-based predictor for identifying and classifying sigma promoters.

A proinflammatory peptide (PIP) is a type of signaling molecules that are secreted from immune cells, which contributes to the first line of defense against invading pathogens. Numerous experiments have shown that PIPs play an important role in human physiology such as vaccines and immunotherapeutic drugs. Considering high-throughput laboratory methods that are time consuming and costly, effective computational methods are great demand to timely and accurately identify PIPs. Thus, in this study, we proposed a computational model in conjunction with a multiple feature representation, called ProIn-Fuse, to improve the performance of PIPs identification. Specifically, a feature representation learning model was utilized to generate the probabilistic scores by using the random forest models employing eight sequence encoding schemes. Finally, the ProIn-Fuse was constructed by linearly combining the resultant eight probabilistic scores. Evaluated through independent test, the ProIn-Fuse yielded an accuracy of 0.746, which was 10% higher than those obtained by the state-of-the-art PIP predictors. The proposed ProIn-Fuse can facilitate faster and broader applications of PIPs in drug design and development. The web server, datasets and online instruction are freely accessible at 
http://kurata14.bio.kyutech.ac.jp/ProIn-Fuse

.

ProIn-Fuse: improved and robust prediction of proinflammatory peptides by fusing of multiple feature representations

5-Methylcytosine (m5C) is a well-known post-transcriptional modification that plays significant roles in biological processes, such as RNA metabolism, tRNA recognition, and stress responses. Traditional high-throughput techniques on identification of m5C sites are usually time consuming and expensive. In addition, the number of RNA sequences shows explosive growth in the post-genomic era. Thus, machine-learning-based methods are urgently requested to quickly predict RNA m5C modifications with high accuracy. Here, we propose a noval support-vector-machine (SVM)-based tool, called iRNA-m5C_SVM, by combining multiple sequence features to identify m5C sites in Arabidopsis thaliana. Eight kinds of popular feature-extraction methods were first investigated systematically. Then, four well-performing features were incorporated to construct a comprehensive model, including position-specific propensity (PSP) (PSNP, PSDP, and PSTP, associated with frequencies of nucleotides, dinucleotides, and trinucleotides, respectively), nucleotide composition (nucleic acid, di-nucleotide, and tri-nucleotide compositions; NAC, DNC, and TNC, respectively), electron-ion interaction pseudopotentials of trinucleotide (PseEIIPs), and general parallel correlation pseudo-dinucleotide composition (PC-PseDNC-general). Evaluated accuracies over 10-fold cross-validation and independent tests achieved 73.06% and 80.15%, respectively, which showed the best predictive performances in A. thaliana among existing models. It is believed that the proposed model in this work can be a promising alternative for further research on m5C modification sites in plant.

Prediction of m5C Modifications in RNA Sequences by Combining Multiple Sequence Features

MOTIVATION: Extracting useful feature set which contains significant discriminatory information is a critical step in effectively presenting sequence data to predict structural, functional, interaction and expression of proteins, DNAs, and RNAs. Also, being able to filter features with significant information and avoid sparsity in the extracted features require the employment of efficient feature selection techniques. Here we present PyFeat as a practical and easy to use toolkit implemented in Python for extracting various features from proteins, DNAs, and RNAs. To build PyFeat we mainly focused on extracting features that capture information about the interaction of neighboring residues to be able to provide more local information. We then employ AdaBoost technique to select features with maximum discriminatory information. In this way, we can significantly reduce the number of extracted features and enable PyFeat to represent the combination of effective features from large neighboring residues. As a result, PyFeat is able to extract features from 13 different techniques and represent context free combination of effective features. The source code for PyFeat standalone toolkit and employed benchmarks with a comprehensive user manual explaining its system and workflow in a step by step manner are publicly available. RESULTS: https://github.com/mrzResearchArena/PyFeat/blob/master/RESULTS.md. AVAILABILITY: Toolkit, source code, and manual to use PyFeat: https://github.com/mrzResearchArena/PyFeat/.

/pdf/pyfeat-a-python-based-effective-feature-generation-tool-for-1zronkk0gc.pdf

PyFeat: A Python-based Effective Feature Generation Tool for DNA, RNA, and Protein Sequences.

Although advancing the therapeutic alternatives for treating deadly cancers has gained much attention globally, still the primary methods such as chemotherapy have significant downsides and low specificity. Most recently, Anticancer peptides (ACPs) have emerged as a potential alternative to therapeutic alternatives with much fewer negative side-effects. However, the identification of ACPs through wet-lab experiments is expensive and time-consuming. Hence, computational methods have emerged as viable alternatives. During the past few years, several computational ACP identification techniques using hand-engineered features have been proposed to solve this problem. In this study, we propose a new multi headed deep convolutional neural network model called ACP-MHCNN, for extracting and combining discriminative features from different information sources in an interactive way. Our model extracts sequence, physicochemical, and evolutionary based features for ACP identification through simultaneous interaction with different numerical peptide representations while restraining parameter overhead. It is evident through rigorous experiments using cross-validation and independent-dataset that ACP-MHCNN outperforms other models for anticancer peptide identification by a substantial margin. ACP-MHCNN outperforms state-of-the-art model by 6.3%, 8.6%, 3.7%, 4.0%, and 0.20 in terms of accuracy, sensitivity, specificity, precision, and MCC respectively. ACP-MHCNN and its relevant codes and datasets are publicly available at: https://github.com/mrzResearchArena/Anticancer-Peptides-CNN.

https://biorxiv.org/content/10.1101/2020.09.25.313668v1.full.pdf

ACP-MHCNN: An Accurate Multi-Headed Deep-Convolutional Neural Network to Predict Anticancer peptides

The classification of motor imagery electroencephalogram (MI-EEG) is a pivotal part of the biosignal classification in the brain-computer interface (BCI) applications. Currently, this bio-engineering based technology is being employed by researchers in various fields to develop cutting edge applications. The classification of real-time MI-EEG signal is the core computing and challenging task in these applications. It is well-known that the existing classification methods are not so accurate due to the high dimensionality and dynamic behaviors of the real-time EEG data. To improve the classification performance of real-time BCI applications, this paper presents a clustering-based ensemble technique and a developed brain game that distinguishes different human thoughts. At first, we have gathered the brain signals, extracted and selected informative features from these signals to generate training and testing sets. After that, we have constructed several classifiers using Artificial Neural Network (ANN), Support Vector Machine (SVM), naive Bayes, Decision Tree (DT), Random Forest, Bagging, AdaBoost and compared the performance of these existing approaches with suggested clustering-based ensemble technique. On average, the proposed ensemble technique improved the classification accuracy of roughly 5 to 15% compared to the existing methods. Finally, we have developed the targeted brain game employing our suggested ensemble technique. In this game, real-time EEG signal classification and prediction tabulation through animated ball are controlled via threads. By playing this game, users can control the movements of the balls via the brain signals of motor imagery movements without using any traditional input devices. All relevant codes are available via open repository at: https://github.com/mrzResearchArena/MI-EEG.

/pdf/prediction-of-motor-imagery-tasks-from-multi-channel-eeg-1xie0oh8qd.pdf

Rafsanjani Muhammod

Papers

PyFeat: A Python-based Effective Feature Generation Tool for DNA, RNA, and Protein Sequences.

ACP-MHCNN: An Accurate Multi-Headed Deep-Convolutional Neural Network to Predict Anticancer peptides

Prediction of Motor Imagery Tasks from Multi-Channel EEG Data for Brain-Computer Interface Applications

CluSem: Accurate clustering-based ensemble method to predict motor imagery tasks from multi-channel EEG data