Research Article A Scalable Genetic Programming Approach to Integrate miRNA-Target Predictions: Comparing Different Parallel Implementations of M3GP Stefano Beretta , 1,2 Mauro Castelli , 3 Luis Muñoz, 4 Leonardo Trujillo, 4 Yuliana Martínez, 4 Aleš Popovič, 3,5 Luciano Milanesi, 2 and Ivan Merelli 2 1 DISCo, Università degli Studi di Milano-Bicocca, Milan, Italy 2 Istituto di Tecnologie Biomediche, Consiglio Nazionale delle Ricerche, Segrate, Italy 3 NOVA Information Management School (NOVA IMS), Universidade Nova de Lisboa, Campus de Campolide, 1070-312 Lisboa, Portugal 4 Tree-Lab, Posgrado en Ciencias de la Ingeniería, Instituto Tecnológico de Tijuana, Tijuana, BC, Mexico 5 Faculty of Economics, University of Ljubljana, Kardeljeva Ploščad 17, SI-1000 Ljubljana, Slovenia Correspondence should be addressed to Mauro Castelli; mcastelli@novaims.unl.pt Received 28 February 2018; Accepted 29 May 2018; Published 4 July 2018 Academic Editor: Dimitrios Vlachakis Copyright © 2018 Stefano Beretta et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. There are many molecular biology approaches to the analysis of microRNA (miRNA) and target interactions, but the experiments are complex and expensive. For this reason, in silico computational approaches able to model these molecular interactions are highly desirable. Although several computational methods have been developed for predicting the interactions between miRNA and target genes, there are substantial differences in the results achieved since most algorithms provide a large number of false positives. Accordingly, machine learning approaches are widely used to integrate predictions obtained from different tools. In this work, we adopt a method called multidimensional multiclass GP with multidimensional populations (M3GP), which relies on a genetic programming approach, to integrate and classify results from different miRNA-target prediction tools. The results are compared with those obtained with other classifiers, showing competitive accuracy. Since we aim to provide genome-wide predictions with M3GP and, considering the high number of miRNA-target interactions to test (also in different species), a parallel implementation of this algorithm is recommended. In this paper, we discuss the theoretical aspects of this algorithm and propose three different parallel implementations. We show that M3GP is highly parallelizable, it can be used to achieve genome-wide predictions, and its adoption provides great advantages when handling big datasets. 1. Introduction MicroRNAs (miRNAs) are approximately 22-nucleotide- long, single-stranded RNA molecules encoded in the genomes of plants, animals, and viruses and are capable of interfering with intracellular messenger RNAs (mRNA) [1]. miRNAs are key regulators of gene expression at the posttranscriptional level, but the precise mechanisms underlying their interactions with the respective gene targets are still poorly understood. The effect of the hybridization between a miRNA and its target mRNA is that the expression of the protein coded by the gene is silenced, either by stopping the translation process or by marking the mRNA for degradation. Since miRNAs are involved in the onset of many different diseases, the study of their interactions with the genome is very important. For instance, several recent reports suggest that miRNA aberrations may be an important factor in the development of cancer [2, 3]. Another study demonstrated that more than 50% of miRNA targeted genes are located in Hindawi Complexity Volume 2018, Article ID 4963139, 13 pages https://doi.org/10.1155/2018/4963139