TIGRESS: Trustful Inference of Gene REgulation using Stability Selection.
Haury AC, Mordelet F, Vera-Licona P, Vert JP. · 2012
Read TIGRESS: Trustful Inference of Gene REgulation using Stability Selection. by Haury AC, Mordelet F, Vera-Licona P, Vert JP. (2012) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/europmc-pmc3598250.txt.
Introduction
Anne-Claire Haury and colleagues presented a network-finding method called TIGRESS in BMC Systems Biology in 2012. Gene regulatory networks map which genes switch which others on and off, guiding everything from basic cell biology to drug target hunts. Rebuilding those maps from gene activity data is notoriously error-prone, and many methods exist with modest accuracy. TIGRESS recasts the job as picking a few strong predictors for each gene from a crowd of candidates.
The method pairs least angle regression, a stepwise fitting technique, with stability selection, which reruns the fit on many data samples and keeps only links that recur. A new scoring rule sharpens that selection. In the DREAM5 challenge, a blind community contest, TIGRESS ranked among the best overall and first among regression-based methods. Tests on computer-made networks and on real bacteria and yeast data fill out the paper, and code is offered online.
Catalog record
| CREATOR | Haury AC, Mordelet F, Vera-Licona P, Vert JP. |
|---|---|
| YEAR | 2012 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 56 KB |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |
Browse the full library · About the Tower of Babel
Full text
The opening of the work, from the library's hosted text:
TIGRESS: Trustful Inference of Gene REgulation using Stability Selection By Anne-Claire Haury, Fantine Mordelet, Paola Vera-Licona, Jean-Philippe Vert Published in: BMC Systems Biology DOI: 10.1186/1752-0509-6-145 ABSTRACT Abstract Background Inferring the structure of gene regulatory networks (GRN) from a collection of gene expression data has many potential applications, from the elucidation of complex biological processes to the identification of potential drug targets. It is however a notoriously difficult problem, for which the many existing methods reach limited accuracy. Results In this paper, we formulate GRN inference as a sparse regression problem and investigate the performance of a popular feature selection method, least angle regression (LARS) combined with stability selection, for that purpose. We introduce a novel, robust and accurate scoring technique for stability selection, which improves the performance of feature selection with LARS. The resulting method, which we call TIGRESS (for Trustful Inference of Gene REgulation with Stability Selection), was ranked among the top GRN inference methods in the DREAM5 gene network inference challenge. In particular, TIGRESS was evaluated to be the best linear regression-based method in the challenge. We investigate in depth the influence of the various parameters of the method, and show that a fine parameter tuning can lead to significant improvements and state-of-the-art performance for GRN inference, in both directed and undirected settings. Conclusions TIGRESS reaches state-of-the-art performance on benchmark data, including both in silico and in vivo (E. coli and S. cerevisiae) networks. This study confirms the potential of feature selection techniques for GRN inference. Code and data are available on http://cbio.ensmp.fr/tigress. Moreover, TIGRESS can be run online through the GenePattern platform (GP-DREAM, http://dream.broadinstitute.org). Keywords: Gene Regulatory Network inference, Feature selection, Gene expression data, LARS, Stability selection BACKGROUND In order to meet their needs and adapt to changing environments, cells have developed various mechanisms to regulate the production of the thousands of proteins they can synthesize. Among them, the regulation of gene expression by transcription factors (TF) is preponderant: by binding to the promoter regions of their target genes (TG), TF can activate or inhibit their expression. Deciphering and understanding TF-TG interactions has many potential far-reaching applications in biology and medicine, ranging from the in silico modeling and simulation of the gene regulatory network (GRN) to the identification of new potential drug targets. However, while many TF-TG interactions have been experimentally characterized in model organisms, the systematic experimental characterization of the full GRN remains a daunting task due to the large number of potential regulations. The development of high-throughput methods, in particular DNA microarrays, to monitor gene expression on a genome-wide scale has promoted new strategies to elucidate GRN. By systematically assessing how gene expression varies in different experimental conditions, one can try to reverse engineer the TF-TG interactions responsible for the observed variations. Not surprisingly, many different approaches have been proposed in the last decade to solve this GRN reverse engineering problem from collections of gene expression data. When expression data are collected over time, for example, several methods have been proposed to construct dynamic models where TF-TG interactions dictate how the expression level of a TG at a given time allows to predict the expression levels of its TG in subsequent times [1-11]. When expression data are not limited to time series, many methods attempt to capture statistical association between the expression levels of TG and candidate TF using correlation or information-theoretic measures such as mutual information [12-14] or take explicit advantage of perturbations in the experiments such as gene knock-downs [15]. The difficulty to separate direct from indirect regulations has been addressed with the formalism of Bayesian networks [16-19], or by formulating the GRN inference problem as a feature selection problem [20]. Mutual information-based ARACNE [13] was also designed to eliminate redundant edges. We refer to [21,22] for detailed reviews and comparisons of existing methods. Recent benchmarks and challenges have highlighted the good performance of methods which formalize the GRN inference problem as a regression and feature selection problem, namely, identifying a small set of TF whose expression levels are sufficient to predict the expression level of each TG of interest. The general idea that edges in a directed graph can be discovered node by node was addressed in, e.g.,[23]. Regarding the GRN inference application, this idea underlies the Bayesian network formalism [16], but is more directly addressed by GENIE3 [20], a method which uses random forests to identify TF whose expression levels are predictive for the expression level of each TG, and which is now recognized as state-of-the-art on several benchmarks [20,22]. Feature selection with random forests remains however poorly understood theoretically, and one may wonder how other well-established statistical and machine learning techniques for feature selection would behave to solve the GRN inference problem. In this paper, we investigate the performance of a popular feature selection method, least angle regression (LARS) [24] combined with stability selection [25,26], for GRN inference. LARS is a computationally efficient procedure for multivariate feature selection, closely related to Lasso regression [27]. Stability selection consists in running LARS or Lasso many times, resampling the samples and the variables at each run, and in computing the frequency with which each variable was selected across the runs. We introduce a novel, robust and accurate scoring technique for stability selection, which improves the performance of feature selection with LARS. The resulting method, which we call TIGRESS (for Trustful Inference of Gene REgulation with Stability Selection), was ranked among the top GRN inference methods in the DREAM5 gene reconstruction challenge and was evaluated to be the best linear regression- based method [28]. We furthermore investigate in depth the influence of the various parameters of the method, and show that a fine parameter tuning can lead to significant improvements and state-of-the-art performance for GRN inference. Finally, we show that TIGRESS performs well when TFs are not known in advance, i.e. it can predict edge directionality.Overall this study confirms the potential of state-of-the-art feature selection techniques for GRN inference. METHODS Problem formulation We consider a set of p genes G=[1,p], including a subset T⊂[1,p] of transcription factors, among which we wish to discover direct interactions of the form (t,g) for t∈T and g∈G. We do not try to infer self-regulation, meaning that for each target gene g∈G we define the set of possible regulators as Tg=T∖{g} if g∈T is itself a transcription factor, and Tg=T otherwise. The set of all candidate regulations is therefore E=(t,g),g∈G,t∈Tg, and the GRN inference problem is to identify a subset of true regulations among E. For that purpose, we assume we have gene expression measurements for all genes G in n experimental conditions. Although the nature of the experiments may vary and typically include knock-down or knock-out experiments and even replicates, for simplicity we do not exploit this information and only consider the n×p data matrix of expression levels X as input for the GRN inference problem. Each row of X corresponds to an experiment and each column to a gene. We assume that the expression data have been pre-processed for quality control and missing values imputation. In order to infer the regulatory network from the expression data X, we compute a score s:E→R to assess the evidence that each candidate regulation is true, and then predict as true