Tuning hyperparameters of machine learning algorithms and deep neural networks using metaheuristics: A bioinformatics study on biomedical and biological cases.

The performance of a model in machine learning problems highly depends on the dataset and training algorithms. Choosing the right training algorithm can change the tale of a model. While some algorithms have a great performance in some datasets, they may fall into trouble in other datasets. Moreover, by adjusting hyperparameters of an algorithm, which controls the training processes, the performance can be improved. This study contributes a method to tune hyperparameters of machine learning algorithms using Grey Wolf Optimization (GWO) and Genetic algorithm (GA) metaheuristics. Also, 11 different algorithms including Averaged Perceptron, FastTree, FastForest, Light Gradient Boost Machine (LGBM), Limited memory Broyden Fletcher Goldfarb Shanno algorithm Maximum Entropy (LbfgsMxEnt), Linear Support Vector Machine (LinearSVM), and a Deep Neural Network (DNN) including four architectures are employed on 11 datasets in different biological, biomedical, and nature categories such as molecular interactions, cancer, clinical diagnosis, behavior related predictions, RGB images of human skin, and X-rays images of Covid19 and cardiomegaly patients. Our results show that in all trials, the performance of the training phases is improved. Also, GWO demonstrates a better performance with a p-value of 2.6E-5. Moreover, in most experiment cases of this study, the metaheuristic methods demonstrate better performance and faster convergence than Exhaustive Grid Search (EGS). The proposed method just receives a dataset as an input and suggests the best-explored algorithm with related arguments. So, it is appropriate for datasets with unknown distribution, machine learning algorithms with complex behavior, or users who are not experts in analytical statistics and data science algorithms.

High-throughput analysis of the interactions between viral proteins and host cell RNAs.

RNA-protein interactions of a virus play a major role in the replication of RNA viruses. The replication and transcription of these viruses take place in the cytoplasm of the host cell; hence, there is a probability for the host RNA-viral protein and viral RNA-host protein interactions. The current study applies a high-throughput computational approach, including feature extraction and machine learning methods, to predict the affinity of protein sequences of ten viruses to three categories of RNA sequences. These categories include RNAs involved in the protein-RNA complexes stored in the RCSB database, the human miRNAs deposited at the mirBase database, and the lncRNA deposited in the LNCipedia database. The results show that evolution not only tries to conserve key viral proteins involved in the replication and transcription but also prunes their interaction capability. These proteins with specific interactions do not perturb the host cell through undesired interactions. On the other hand, the hypermutation rate of NSP3 is related to its affinity to host cell RNAs. The Gene Ontology (GO) analysis of the miRNA with affiliation to NSP3 suggests that these miRNAs show strongly significantly enriched GO terms related to the known symptoms of COVID-19. Docking and MD simulation study of the obtained miRNA through high-throughput analysis suggest a non-coding RNA (an RNA antitoxin, ToxI) as a natural aptamer drug candidate for NSP5 inhibition. Finally, a significant interplay of the host RNA-viral protein in the host cell can disrupt the host cell's system by influencing the RNA-dependent processes of the host cells, such as a differential expression in RNA. Furthermore, our results are useful to identify the side effects of mRNA-based vaccines, many of which are caused by the off-label interactions with the human lncRNAs.

RPINBASE: An online toolbox to extract features for predicting RNA-protein interactions.

Feature extraction is one of the most important preprocessing steps in predicting the interactions between RNAs and proteins by applying machine learning approaches. Despite many efforts in this area, still, no suitable structural feature extraction tool has been designed. Therefore, an online toolbox, named RPINBASE which can be applied to different scopes of biological applications, is introduced in this paper. This toolbox employs efficient nested queries that enhance the speed of the requests and produces desired features in the form of positive and negative samples. To show the capabilities of the proposed toolbox, the developed toolbox was investigated in the aptamer design problem, and the obtained results are discussed. RPINBASE is an online toolbox and is accessible at http://rpinbase.com.