Reconstructing biological gene regulatory networks: where optimization meets big data

Thomas, Spencer A.; Jin, Yaochu

doi:10.1007/s12065-013-0098-7

Cited by 46 publications

(21 citation statements)

References 139 publications

(184 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the clustering algorithm used and the regression model for estimating the needed number of clusters may need to be tailored. Future efforts should also address the other challenges imposed by the particular nature of the data, e.g., by combining advanced learning and evolutionary techniques for dealing with big data [56], [84].…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Data-Driven Surrogate-Assisted Multiobjective Evolutionary Optimization of a Trauma System

Wang

Jin

Jansen

2016

IEEE Trans. Evol. Computat.

Self Cite

214

102

View full text Add to dashboard Cite

Abstract-Most existing work on evolutionary optimization assumes that there are analytic functions for evaluating the objectives and constraints. In the real-world, however, the objective or constraint values of many optimization problems can be evaluated solely based on data and solving such optimization problems is often known as data-driven optimization. In this paper, we divide data-driven optimization problems into two categories, i.e., off-line and on-line data-driven optimization, and discuss the main challenges involved therein. An evolutionary algorithm is then presented to optimize the design of a trauma system, which is a typical off-line data-driven multi-objective optimization problem, where the objectives and constraints can be evaluated using incidents only. As each single function evaluation involves large amount of patient data, we develop a multi-fidelity surrogate management strategy to reduce the computation time of the evolutionary optimization. The main idea is to adaptively tune the approximation fidelity by clustering the original data into different numbers of clusters and a regression model is constructed to estimate the required minimum fidelity. Experimental results show that the proposed algorithm is able to save up to 90% of computation time without much sacrifice of the solution quality.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Either a too small size or a very large size of training data samples will create difficulties for training surrogates. Lack of training data will make it impossible to build accurate surrogates when the dimension of the decision space is high [5], while large amounts of training may result in increasing computational cost [55], [56].…”

Section: Challengesmentioning

confidence: 99%

Data-Driven Surrogate-Assisted Multiobjective Evolutionary Optimization of a Trauma System

Wang

Jin

Jansen

2016

IEEE Trans. Evol. Computat.

Self Cite

214

102

View full text Add to dashboard Cite

show abstract

“…Since the year 2000, some thirty review articles that we know of have been published on the inference of gene networks alone (in addition to those referenced or mentioned throughout, see ), and an increasing number have begun to specialize on the unique challenges faced by network reverse-engineers rather than merely listing different algorithms [29,97,[323][324][325][326][327][328]. One DREAM report [92] notes that the number of PubMed articles on reverse-engineering had doubled each year for over a decade through 2009, and "novel" algorithms (new twists on the same foundational principles we outline above) continue to emerge even as we write [329].…”

Section: Discussionmentioning

confidence: 99%

Reverse-engineering biological networks from large data sets

Natale

Hofmann

Hernández

et al. 2017

Preprint

View full text Add to dashboard Cite

Much of contemporary systems biology owes its success to the abstraction of a network, the idea that diverse kinds of molecular, cellular, and organismal species and interactions can be modeled as relational nodes and edges in a graph of dependencies. Since the advent of high-throughput data acquisition technologies in fields such as genomics, metabolomics, and neuroscience, the automated inference and reconstruction of such interaction networks directly from large sets of activation data, commonly known as reverse-engineering, has become a routine procedure. Whereas early attempts at network reverse-engineering focused predominantly on producing maps of system architectures with minimal predictive modeling, reconstructions now play instrumental roles in answering questions about the statistics and dynamics of the underlying systems they represent. Many of these predictions have clinical relevance, suggesting novel paradigms for drug discovery and disease treatment. While other reviews focus predominantly on the details and effectiveness of individual network inference algorithms, here we examine the emerging field as a whole. We first summarize several key application areas in which inferred networks have made successful predictions. We then outline the two major classes of reverse-engineering methodologies, emphasizing that the type of prediction that one aims to make dictates the algorithms one should employ. We conclude by discussing whether recent breakthroughs justify the computational costs of large-scale reverse-engineering sufficiently to admit it as a mainstay in the quantitative analysis of living systems.

show abstract

“…Reconstruction of gene regulatory networks can be seen as a complex optimization problem, where a large number of parameters and connectivity of the network need to be determined. While meta-heuristic optimization algorithms have been shown to be very promising, the gene expression data for reconstruction is substantially big data in nature [51]. Data available from gene expression is increasing at an exponential rate [59].…”

Section: Big Data In Optimizationmentioning

confidence: 99%

Big Data Opportunities and Challenges: Discussions from Data Analytics Perspectives [Discussion Forum]

Zhou

Chawla

Jin

et al. 2014

IEEE Comput. Intell. Mag.

Self Cite

244

100

View full text Add to dashboard Cite

Abstract-"Big Data" as a term has been among the biggest trends of the last three years, leading to an upsurge of research, as well as industry and government applications. Data is deemed a powerful raw material that can impact multidisciplinary research endeavors as well as government and business performance. The goal of this discussion paper is to share the data analytics opinions and perspectives of the authors relating to the new opportunities and challenges brought forth by the big data movement. The authors bring together diverse perspectives, coming from different geographical locations with different core research expertise and different affiliations and work experiences. The aim of this paper is to evoke discussion rather than to provide a comprehensive survey of big data research.

show abstract

Reconstructing biological gene regulatory networks: where optimization meets big data

Abstract: To be written. Items to address: 1) long URLs in bibliography (have been removed for the time being) 2) check run/time plot papers 3) add metaheuristic plot 4) spell check 5) check journal style eg punctuaution 6) write abstract (after paper has been finalised) 7) check refs

Cited by 46 publications

References 139 publications

Data-Driven Surrogate-Assisted Multiobjective Evolutionary Optimization of a Trauma System

Data-Driven Surrogate-Assisted Multiobjective Evolutionary Optimization of a Trauma System

Reverse-engineering biological networks from large data sets

Big Data Opportunities and Challenges: Discussions from Data Analytics Perspectives [Discussion Forum]

Contact Info

Product

Resources

About