scispace - formally typeset
Search or ask a question
Book ChapterDOI

Soft Computing in Bioinformatics

01 Jan 2021-pp 431-446
TL;DR: In this paper, the authors explored the soft computing based techniques for bioinformatics and discussed the necessity of soft computing techniques and their compatibility for solving wide spectrum of bio-informatic related problems.
Abstract: In this chapter, we explored the soft computing based techniques for bioinformatics. Necessity of soft computing techniques and their compatibility for solving wide spectrum of bioinformatics related problems is reviewed. Basics of soft computing techniques are discussed and their relevancy in solving many bioinformatics based problems is also elaborated. Actual experimental results on two real world bioinformatics data demonstrated the efficacy of soft computing techniques over conventional one for biological data problems.
References
More filters
Journal ArticleDOI
01 Jul 2012
TL;DR: The experimental results showed that the proposed incremental learning method achieved a good tradeoff between incremental learning ability and the recognition accuracy and the experimental results from comparison with other classification methods demonstrated the effectiveness of the proposed method.
Abstract: Human activity recognition by using wearable sensors has gained tremendous interest in recent years among a range of health-related areas. To automatically recognize various human activities from wearable sensor data, many classification methods have been tried in prior studies, but most of them lack the incremental learning abilities. In this study, an incremental learning method is proposed for sensor-based human activity recognition. The proposed method is designed based on probabilistic neural networks and an adjustable fuzzy clustering algorithm. The proposed method may achieve the following features. 1) It can easily learn additional information from new training data to improve the recognition accuracy. 2) It can freely add new activities to be detected, as well as remove existing activities. 3) The updating process from new training data does not require previously used training data. An experiment was performed to collect realistic wearable sensor data from a range of activities of daily life. The experimental results showed that the proposed method achieved a good tradeoff between incremental learning ability and the recognition accuracy. The experimental results from comparison with other classification methods demonstrated the effectiveness of the proposed method further.

139 citations

Journal ArticleDOI
TL;DR: It is hoped that a careful discussion of the relationship between systems that exhibit each of these properties will serve to guide rational expectations and the development of models that exhibit or mimic “human behavior.”

114 citations

Book ChapterDOI
01 Jan 2008
TL;DR: The role of SI algorithms in certain bioinformatics tasks like microarray data clustering, multiple sequence alignment, protein structure prediction and molecular docking is explored.
Abstract: Research in bioinformatics necessitates the use of advanced computing tools for processing huge amounts of ambiguous and uncertain biological data. Swarm Intelligence (SI) has recently emerged as a family of nature inspired algorithms, especially known for their ability to produce low cost, fast and reasonably accurate solutions to complex search problems. In this chapter, we explore the role of SI algorithms in certain bioinformatics tasks like microarray data clustering, multiple sequence alignment, protein structure prediction and molecular docking. The chapter begins with an overview of the basic concepts of bioinformatics along with their biological basis. It also gives an introduction to swarm intelligence with special emphasis on two specific SI algorithms well-known as Particle Swarm Optimization (PSO) and Ant Colony Systems (ACS). It then provides a detailed survey of the state of the art research centered around the applications of SI algorithms in bioinformatics. The chapter concludes with a discussion on how SI algorithms can be used for solving a few open ended problems in bioinformatics.

103 citations

Proceedings ArticleDOI
20 Mar 1995
TL;DR: An evolutionary algorithm for determining the "best" distance for given data, where the criterion of goodness is defined in terms of the performance of the fuzzy c-means clustering method is described.
Abstract: In this paper, a new approach to fuzzy clustering is introduced. This approach, which is based on the application of an evolutionary strategy to the fuzzy c-means clustering algorithm, utilizes the relationship between the various definitions of distance and structures implied in each given data set. As soon as a particular definition of distance is chosen, a particular structure in the data set is implied. Therefore, the search for a structure in given data can be viewed as a search for an appropriate definition of distance. We describe an evolutionary algorithm for determining the "best" distance for given data, where the criterion of goodness is defined in terms of the performance of the fuzzy c-means clustering method. We discuss relevant theoretical aspects as well as experimental results that characterize the utility of the proposed algorithm. >

96 citations

Journal ArticleDOI
11 Sep 2019-PLOS ONE
TL;DR: To the knowledge, this is the first machine learning methodology that can detect the presence of viral sequences among raw metagenomic contigs from diverse human samples and can be used as a recommendation system to further investigate sequences labeled as “unknown” by conventional alignment methods.
Abstract: Despite its clinical importance, detection of highly divergent or yet unknown viruses is a major challenge. When human samples are sequenced, conventional alignments classify many assembled contigs as "unknown" since many of the sequences are not similar to known genomes. In this work, we developed ViraMiner, a deep learning-based method to identify viruses in various human biospecimens. ViraMiner contains two branches of Convolutional Neural Networks designed to detect both patterns and pattern-frequencies on raw metagenomics contigs. The training dataset included sequences obtained from 19 metagenomic experiments which were analyzed and labeled by BLAST. The model achieves significantly improved accuracy compared to other machine learning methods for viral genome classification. Using 300 bp contigs ViraMiner achieves 0.923 area under the ROC curve. To our knowledge, this is the first machine learning methodology that can detect the presence of viral sequences among raw metagenomic contigs from diverse human samples. We suggest that the proposed model captures different types of information of genome composition, and can be used as a recommendation system to further investigate sequences labeled as "unknown" by conventional alignment methods. Exploring these highly-divergent viruses, in turn, can enhance our knowledge of infectious causes of diseases.

75 citations