Big data analytics in bioinformatics: architectures, techniques, tools and issues

Kashyap, Hirak J.; Ahmed, Hasin Afzal; Hoque, Nazrul; Roy, Swarup; Bhattacharyya, Dhruba K.

doi:10.1007/s13721-016-0135-4

Cited by 38 publications

(31 citation statements)

References 147 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many contributions addressed the issues and challenges posed by several big data problems in bioinformatics and given an overview of the state of the art and the future research opportunities [29].…”

Section: Bio-informatics and Big Datamentioning

confidence: 99%

A Review on Big Data: Views, Categories and Aspects

Shukla¹,

Alim²

2018

IJCA

View full text Add to dashboard Cite

Now-a-days every organization is moving towards on web based application and cope up lots of data sets. Data may be structured, unstructured or semi-structure. These data need processing, analysis and storage in proper format using innovative techniques and methodologies. Big data parameterized into three basic categories Volume, Variety and Velocity. The social media like Facebook, Whatsapp, Twitter, hike. are generating lots of data in a day in the form of textmessages, audio-recording, images, videos etc. The problem which appears is how to manage this huge data in a systematic way because users want quick response on web search or on smart phone access using web apps. In this paper we have studied how big data invoke in different areas like social media, atmosphere, hospitals, research centers etc. We have suggested contributions in big data categories, applications in different area's like in Machine learning, Social Network, Bio-Informatics, Data Mining, and Clouds along with challenges, future scope and storage prospects.

show abstract

Section: Bio-informatics and Big Datamentioning

confidence: 99%

A Review on Big Data: Views, Categories and Aspects

Shukla¹,

Alim²

2018

IJCA

View full text Add to dashboard Cite

show abstract

“…Thus, it needs more complicated tools rather than the traditional ones to be analyzed and managed. Managing this data brings more challenges and requires more efficient methods [1,2].…”

Section: Big Datamentioning

confidence: 99%

“…Managing Big Data is one of the main challenges that faces large corporations, and has attracted the interest of researchers in the past years [1,2]. Big Data has several characteristics known by nV's characteristics, and it has several type of architectures for Big Data analysis.…”

Section: Big Datamentioning

confidence: 99%

“…There are three main types of architectures for Big Data analysis, MapReduce architectures, fault-tolerant graph architectures and streaming graph architectures. Some of the characteristics of these styles as shown in Table 1 in terms of the used memory type: if the used memory is local memory or shared global memory, in addition to the fault tolerance [2].…”

Section: B Architectures Of Big Data Analyticsmentioning

confidence: 99%

See 1 more Smart Citation

A New Technique to Manage Big Bioinformatics Data Using Genetic Algorithms

Dikhil¹,

Shkoukani²,

Owais³

2016

ijarai

View full text Add to dashboard Cite

Abstract-The continuous growth of data, mainly the medical data at laboratories becomes very complex to use and to manage by using traditional ways. So, the researchers started studying genetic information field in bioinformatics domain (the computer science field, genetic biology field, and DNA) which has increased in past thirty years. This growth of data is known as big bioinformatics data. Thus, efficient algorithms such as Genetic Algorithms are needed to deal with this big and vast amount of bioinformatics data in genetic laboratories. So the researchers proposed two models to manage the big bioinformatics data in addition to the traditional model. The first model by applying Genetic Algorithms before MapReduce, the second model by applying Genetic Algorithms after the MapReduce, and the original or the traditional model by applying only MapReduce without using Genetic Algorithms. The three models were implemented and evaluated using big bioinformatics data collected from the Duchenne Muscular Dystrophy (DMD) disorder. The researchers conclude that the second model is the best one among the three models in reducing the size of the data, in execution time, and in addition to the ability to manage and summarize big bioinformatics data. Finally by comparing the percentage errors of the second model with the first model and the traditional model, the researchers obtained the following results 1.136%, 10.227%, and 11.363%, respectively. So the second model is the most accurate model with less percentage error.

show abstract

“…Feature selection methods are used to reduce dimensionality of data for big data analytics [8,16], gene expression data analysis and network traffic traffic analysis [7,13,19]. For a given dataset, different feature selection algorithms may select different subset of features and hence the result obtained may have different accuracy.…”

Section: Introductionmentioning

confidence: 99%

EFS-MI: an ensemble feature selection method for classification

Hoque

Singh

Bhattacharyya

2017

Complex Intell. Syst.

Self Cite

View full text Add to dashboard Cite

Feature selection methods have been used in various applications of machine learning, bioinformatics, pattern recognition and network traffic analysis. In high dimensional datasets, due to redundant features and curse of dimensionality, a learning method takes significant amount of time and performance of the model decreases. To overcome these problems, we use feature selection technique to select a subset of relevant and non-redundant features. But, most feature selection methods are unstable in nature, i.e., for different training datasets, a feature selection method selects different subsets of features that yields different classification accuracy. In this paper, we provide an ensemble feature selection method using feature-class and feature-feature mutual information to select an optimal subset of features by combining multiple subsets of features. The method is validated using four classifiers viz., decision trees, random forests, KNN and SVM on fourteen UCI, five gene expression and two network datasets.

show abstract

Big data analytics in bioinformatics: architectures, techniques, tools and issues

Cited by 38 publications

References 147 publications

A Review on Big Data: Views, Categories and Aspects

A Review on Big Data: Views, Categories and Aspects

A New Technique to Manage Big Bioinformatics Data Using Genetic Algorithms

EFS-MI: an ensemble feature selection method for classification

Contact Info

Product

Resources

About