A multi-objective gene clustering algorithm guided by apriori biological knowledge with intensification and diversification strategies

Abstract

BackgroundBiologists aim to understand the genetic background of diseases, metabolic disorders or any other genetic condition. Microarrays are one of the main high-throughput technologies for collecting information about the behaviour of genetic information on different conditions. In order to analyse this data, clustering arises as one of the main techniques used, and it aims at finding groups of genes that have some criterion in common, like similar expression profile. However, the problem of finding groups is normally multi dimensional, making necessary to approach the clustering as a multi-objective problem where various cluster validity indexes are simultaneously optimised. They are usually based on criteria like compactness and separation, which may not be sufficient since they can not guarantee the generation of clusters that have both similar expression patterns and biological coherence.MethodWe propose a Multi-Objective Clustering algorithm Guided by a-Priori Biological Knowledge (MOC-GaPBK) to find clusters of genes with high levels of co-expression, biological coherence, and also good compactness and separation. Cluster quality indexes are used to optimise simultaneously gene relationships at expression level and biological functionality. Our proposal also includes intensification and diversification strategies to improve the search process.ResultsThe effectiveness of the proposed algorithm is demonstrated on four publicly available datasets. Comparative studies of the use of different objective functions and other widely used microarray clustering techniques are reported. Statistical, visual and biological significance tests are carried out to show the superiority of the proposed algorithm.ConclusionsIntegrating a-priori biological knowledge into a multi-objective approach and using intensification and diversification strategies allow the proposed algorithm to find solutions with higher quality than other microarray clustering techniques available in the literature in terms of co-expression, biological coherence, compactness and separation.

RoCoLe: A robusta coffee leaf images dataset for evaluation of machine learning based methods in plant diseases recognition

“…In machine learning area, object segmentation aims separating parts of an image into pieces which are conceptually meaning. Methods as artificial neural networks, genetic algorithms and clustering have been used to perform segmentation tasks [2], [3], [4]. Meanwhile, classification aims finding a class to which an item belongs as from patterns in a labeled data set.…”

A hybrid multi-objective whale optimization algorithm for analyzing microarray data based on Apache Spark

“…2018). This converted the clustering problem from a single objective problem to a multi-objective one (Parraga-Alava, Dorn & Inostroza-Ponta, 2018). An example of applying multiple objective functions to analyze microarray data was proposed by Maulik, Mukhopadhyay & Bandyopadhyay (2009).…”

Peer Review #1 of "A hybrid multi-objective whale optimization algorithm for analyzing microarray data based on Apache Spark (v0.1)"

“…Since (Schaffer (1984)) proposed combining SI methods with PO to solve MOPs, many SI methods have been developed for analyzing microarray data using this strategy (Maulik et al (2011), Mukhopadhyay et al (2015), Paul et al (2016), Mandal and Mukhopadhyay (2017) , Zareizadeh et al (2018)). An example of these methods was a Multi-Objective Clustering algorithm Guided by a-Priori Biological Knowledge (MOC-GaPBK) for microarray data analysis, proposed by (Parraga-Alava et al (2018)). The method focused on developing efficient intensification and diversification techniques to cover the solution space efficiently, and used PO to ensure an optimization of the whole objectives.…”

“…MOC-GaPBK developed a gene ontology method to enhance the identification of similarity among genes. The method was tested over small and medium-sized datasets and presented its ability to obtain clustering solutions with good quality (Parraga-Alava et al (2018)). The method was not extended to be applied over large datasets.…”

“…Clustering methods used a single objective function to evaluate the quality of generated clusters (McDowell et al (2018), Chandra and Tripathi (2019)). To improve the quality of the obtained clusters, clustering methods used multiple objective functions to evaluate the generated clusters (Mukhopadhyay et al (2015), Acharya and Saha (2018) Parraga-Alava et al (2018)). This converted the clustering problem into a Multi-Objective Problem (MOP).…”