Efficient experimental design for uncertainty reduction in gene regulatory networks.

The need for efficient computational screening of molecular candidates that possess desired properties frequently arises in various scientific and engineering problems, including drug discovery and materials design. However, the large size of the search space containing the candidates and the substantial computational cost of high-fidelity property prediction models makes screening practically challenging. In this work, we propose a general framework for constructing and optimizing a virtual screening (HTVS) pipeline that consists of multi-fidelity models. The central idea is to optimally allocate the computational resources to models with varying costs and accuracy to optimize the return-on-computational-investment (ROCI). Based on both simulated as well as real data, we demonstrate that the proposed optimal HTVS framework can significantly accelerate screening virtually without any degradation in terms of accuracy. Furthermore, it enables an adaptive operational strategy for HTVS, where one can trade accuracy for efficiency.

Design has become a salient part of most of the scientific and engineering tasks, embracing a wide range of domains including real experimental settings (e.g., material discovery or drug design), simulation-based design, and hyperparameter tuning. Model-based experimental design refers to a broad class of techniques, applicable to domains that a partial knowledge about the underlying process exists. Unlike entropy- based techniques which aim to reduce the whole uncertainty in the process, the mean objective cost of uncertainty (MOCU) is a rigorous statistically-oriented experimental design framework which takes the main objective into account during the decision making. However, the lack of scalability of this framework has restricted its application to domains with very small design spaces. This paper proposes a framework using the combination of Bayesian optimization and MOCU policy, which enables experimental design to much larger design spaces and systems. The reliability, scalability and efficiency of the proposed framework are investigated through experimental design for optimal structural intervention in gene regulatory networks.

Optimal experimental design for materials discovery

Inferring transcriptional gene regulatory networks from transcriptomic datasets is a key challenge of systems biology, with potential impacts ranging from medicine to agronomy. There are several techniques used presently to experimentally assay transcription factors to target relationships, defining important information about real gene regulatory networks connections. These techniques include classical ChIP-seq, yeast one-hybrid, or more recently, DAP-seq or target technologies. These techniques are usually used to validate algorithm predictions. Here, we developed a reverse engineering approach based on mathematical and computer simulation to evaluate the impact that this prior knowledge on gene regulatory networks may have on training machine learning algorithms. First, we developed a gene regulatory networks-simulating engine called FRANK (Fast Randomizing Algorithm for Network Knowledge) that is able to simulate large gene regulatory networks (containing 104 genes) with characteristics of gene regulatory networks observed in vivo. FRANK also generates stable or oscillatory gene expression directly produced by the simulated gene regulatory networks. The development of FRANK leads to important general conclusions concerning the design of large and stable gene regulatory networks harboring scale free properties (built ex nihilo). In combination with supervised (accepting prior knowledge) support vector machine algorithm we (i) address biologically oriented questions concerning our capacity to accurately reconstruct gene regulatory networks and in particular we demonstrate that prior-knowledge structure is crucial for accurate learning, and (ii) draw conclusions to inform experimental design to performed learning able to solve gene regulatory networks in the future. By demonstrating that our predictions concerning the influence of the prior-knowledge structure on support vector machine learning capacity holds true on real data (Escherichia coli K14 network reconstruction using network and transcriptomic data), we show that the formalism used to build FRANK can to some extent be a reasonable model for gene regulatory networks in real cells.

Genotype networks are sets of genotypes connected by small mutational changes that share the same phenotype. They facilitate evolutionary innovation by enabling the exploration of different neighborhoods in genotype space. Genotype networks, first suggested by theoretical models, have been empirically confirmed for proteins and RNAs. Comparative studies also support their existence for gene regulatory networks (GRNs), but direct experimental evidence is lacking. Here, we report the construction of three interconnected genotype networks of synthetic GRNs producing three distinct phenotypes in Escherichia coli. Our synthetic GRNs contain three nodes regulating each other by CRISPR interference and governing the expression of fluorescent reporters. The genotype networks, composed of over twenty different synthetic GRNs, provide robustness in face of mutations while enabling transitions to innovative phenotypes. Through realistic mathematical modeling, we quantify robustness and evolvability for the complete genotype-phenotype map and link these features mechanistically to GRN motifs. Our work thereby exemplifies how GRN evolution along genotype networks might be driving evolutionary innovation.

Which active learning methods can we expect to yield good performance in learning binary and multi-category logistic regression classifiers? Addressing this question is a natural first step in providing robust solutions for active learning across a wide variety of exponential models including maximum entropy, generalized linear, log-linear, and conditional random field models. For the logistic regression model we re-derive the variance reduction method known in experimental design circles as `A-optimality.' We then run comparisons against different variations of the most widely used heuristic schemes: query by committee and uncertainty sampling, to discover which methods work best for different classes of problems and why. We find that among the strategies tested, the experimental design methods are most likely to match or beat a random sample baseline. The heuristic alternatives produced mixed results, with an uncertainty sampling variant called margin sampling and a derivative method called QBB-MM providing the most promising performance at very low computational cost. Computational running times of the experimental design methods were a bottleneck to the evaluations. Meanwhile, evaluation of the heuristic methods lead to an accumulation of negative results. We explore alternative evaluation design parameters to test whether these negative results are merely an artifact of settings where experimental design methods can be applied. The results demonstrate a need for improved active learning methods that will provide reliable performance at a reasonable computational cost.

The transcriptional basis of homeostasis and disease is implied by the non-coding nature of genetic variation identified by GWAS. Functional genomic approaches to unveil the gene regulatory networks (GRNs) relevant to disease are therefore a high priority. Most models for transcriptional dysregulation presume that perturbation of a wild-type gene regulatory network causes disease risk. For example, the T-box transcription factor (TF) TBX5, is essential for atrial rhythm homeostasis and directly drives a physiologically relevant GRN composed of cardiac channel genes. Alternatively, the expression of many genes pertinent to cardiac pathology are upregulated after the removal of Tbx5, implicating a disease-specific GRN absent from the wild-type atrium. We applied TF-dependent noncoding RNA (ncRNA) profiling, using differential deep ncRNA sequencing from atria of wild-type and Tbx5 mutant mice, to identify TBX5-dependent enhancers and ncRNAs that were only activated following TBX5 removal. We hypothesized that these regulatory elements would reveal disease-response enhancers, essential for coping with atrial dysfunction. To identify the cell-specific regulatory elements, we generated cell-type specific Assay from Transposase-Accessible Chromatin (ATAC) datasets for left atrial tissue, cardiac fibroblasts, and cardiomyocytes. Overlap with the Tbx5 -repressed ncRNAs defined candidate cell-type specific regulatory elements. Candidate regulatory elements were identified upstream of Sox9, a known modulator of cardiac fibrosis, along with other cardiac stress-response pathways, including mediators of TGF-β signaling. Activation of the enhancer at Sox9 was confirmed in isolated cardiac fibroblasts treated with TGF-β. We hypothesized that the disease-acquired GRN in TBX5 mutant atria may be generalizable to other cardiac insults. We therefore examined the transcriptional and genomic changes in the left atria of the heart failure Transverse Aortic Constriction (TAC) mouse model. This analysis revealed remarkable correlation between differentially expressed genes and ncRNAs between TAC and TBX5 mutant disease models. The conservation of the coding and non-coding transcriptional response between arrhythmia and heart failure models supports a paradigm of a common disease-specific GRN that mediates the physiologic consequences of distinct cardiac diseases.

Stated Choice Design Comparison in a Developing Country: Attribute Nonattendance and Choice Task Dominance

Systems biology aims for building quantitative models to address unresolved issues in molecular biology. In order to describe the behavior of biological cells adequately, gene regulatory networks (GRNs) are intensively investigated. As the validity of models built for GRNs depends crucially on the kinetic rates, various methods have been developed to estimate these parameters from experimental data. For this purpose, it is favorable to choose the experimental conditions yielding maximal information. However, existing experimental design principles often rely on unfulfilled mathematical assumptions or become computationally demanding with growing model complexity. To solve this problem, we combined advanced methods for parameter and uncertainty estimation with experimental design considerations. As a showcase, we optimized three simulated GRNs in one of the challenges from the Dialogue for Reverse Engineering Assessment and Methods (DREAM). This article presents our approach, which was awarded the best performing procedure at the DREAM6 Estimation of Model Parameters challenge. For fast and reliable parameter estimation, local deterministic optimization of the likelihood was applied. We analyzed identifiability and precision of the estimates by calculating the profile likelihood. Furthermore, the profiles provided a way to uncover a selection of most informative experiments, from which the optimal one was chosen using additional criteria at every step of the design process. In conclusion, we provide a strategy for optimal experimental design and show its successful application on three highly nonlinear dynamic models. Although presented in the context of the GRNs to be inferred for the DREAM6 challenge, the approach is generic and applicable to most types of quantitative models in systems biology and other disciplines.

Inferring gene regulatory networks (GRNs) from microarray expression data are an important but challenging issue in systems biology. In this study, the authors propose a Bayesian information criterion (BIC)-guided sparse regression approach for GRN reconstruction. This approach can adaptively model GRNs by optimising the l1-norm regularisation of sparse regression based on a modified version of BIC. The use of the regularisation strategy ensures the inferred GRNs to be as sparse as natural, while the modified BIC allows incorporating prior knowledge on expression regulation and thus avoids the overestimation of expression regulators as usual. Especially, the proposed method provides a clear interpretation of combinatorial regulations of gene expression by optimally extracting regulation coordination for a given target gene. Experimental results on both simulation data and real-world microarray data demonstrate the competent performance of discovering regulatory relationships in GRN reconstruction.

Experimental design methods are tools for conducting informative, time‐ and cost‐effective experiments. Used during product development, these methods can contribute to building quality into products as well as shortening the development cycle time. These techniques make it possible to study the effect of many factors (parameters) simultaneously, to select the factor combination that results in both improved quality and reduced cost, and hence allow for the development of reliable and robust products of high quality. In addition, these methods provide a systematic approach for problem solving during the product development process. This article provides a non‐technical discussion of the role of experimentation and the advantage of using experimental design during product development. Different experimental design methods and examples of their application during product development will also be presented.

BackgroundInferring a gene regulatory network (GRN) from high throughput biological data is often an under-determined problem and is a challenging task due to the following reasons: (1) thousands of genes are involved in one living cell; (2) complex dynamic and nonlinear relationships exist among genes; (3) a substantial amount of noise is involved in the data, and (4) the typical small sample size is very small compared to the number of genes. We hypothesize we can enhance our understanding of gene interactions in important biological processes (differentiation, cell cycle, and development, etc) and improve the inference accuracy of a GRN by (1) incorporating prior biological knowledge into the inference scheme, (2) integrating multiple biological data sources, and (3) decomposing the inference problem into smaller network modules.ResultsThis study presents a novel GRN inference method by integrating gene expression data and gene functional category information. The inference is based on module network model that consists of two parts: the module selection part and the network inference part. The former determines the optimal modules through fuzzy c-mean (FCM) clustering and by incorporating gene functional category information, while the latter uses a hybrid of particle swarm optimization and recurrent neural network (PSO-RNN) methods to infer the underlying network between modules. Our method is tested on real data from two studies: the development of rat central nervous system (CNS) and the yeast cell cycle process. The results are evaluated by comparing them to previously published results and gene ontology annotation information.ConclusionThe reverse engineering of GRNs in time course gene expression data is a major obstacle in system biology due to the limited number of time points. Our experiments demonstrate that the proposed method can address this challenge by: (1) preprocessing gene expression data (e.g. normalization and missing value imputation) to reduce the data noise; (2) clustering genes based on gene expression data and gene functional category information to identify biologically meaningful modules, thereby reducing the dimensionality of the data; (3) modeling GRNs with the PSO-RNN method between the modules to capture their nonlinear and dynamic relationships. The method is shown to lead to biologically meaningful modules and networks among the modules.

Near-infrared spectroscopy (NIRS) is a valuable tool in the pharmaceutical industry, presenting opportunities for online analyses to achieve real-time assessment of intermediates and finished dosage forms. The purpose of this work was to investigate the effect of experimental designs on prediction performance of quantitative models based on NIRS using a five-component formulation as a model system. The following experimental designs were evaluated: five-level, full factorial (5-L FF); three-level, full factorial (3-L FF); central composite; I-optimal; and D-optimal. The factors for all designs were acetaminophen content and the ratio of microcrystalline cellulose to lactose monohydrate. Other constituents included croscarmellose sodium and magnesium stearate (content remained constant). Partial least squares-based models were generated using data from individual experimental designs that related acetaminophen content to spectral data. The effect of each experimental design was evaluated by determining the statistical significance of the difference in bias and standard error of the prediction for that model's prediction performance. The calibration model derived from the I-optimal design had similar prediction performance as did the model derived from the 5-L FF design, despite containing 16 fewer design points. It also outperformed all other models estimated from designs with similar or fewer numbers of samples. This suggested that experimental-design selection for calibration-model development is critical, and optimum performance can be achieved with efficient experimental designs (i.e., optimal designs).

BackgroundA salient purpose for studying gene regulatory networks is to derive intervention strategies, the goals being to identify potential drug targets and design gene-based therapeutic intervention. Optimal stochastic control based on the transition probability matrix of the underlying Markov chain has been studied extensively for probabilistic Boolean networks. Optimization is based on minimization of a cost function and a key goal of control is to reduce the steady-state probability mass of undesirable network states. Owing to computational complexity, it is difficult to apply optimal control for large networks.ResultsIn this paper, we propose three new greedy stationary control policies by directly investigating the effects on the network long-run behavior. Similar to the recently proposed mean-first-passage-time (MFPT) control policy, these policies do not depend on minimization of a cost function and avoid the computational burden of dynamic programming. They can be used to design stationary control policies that avoid the need for a user-defined cost function because they are based directly on long-run network behavior; they can be used as an alternative to dynamic programming algorithms when the latter are computationally prohibitive; and they can be used to predict the best control gene with reduced computational complexity, even when one is employing dynamic programming to derive the final control policy. We compare the performance of these three greedy control policies and the MFPT policy using randomly generated probabilistic Boolean networks and give a preliminary example for intervening in a mammalian cell cycle network.ConclusionThe newly proposed control policies have better performance in general than the MFPT policy and, as indicated by the results on the mammalian cell cycle network, they can potentially serve as future gene therapeutic intervention strategies.

Large-scale microarray gene expression data provide the possibility of constructing genetic networks or biological pathways. Gaussian graphical models have been suggested to provide an effective method for constructing such genetic networks. However, most of the available methods for constructing Gaussian graphs do not account for the sparsity of the networks and are computationally more demanding or infeasible, especially in the settings of high dimension and low sample size. We introduce a threshold gradient descent (TGD) regularization procedure for estimating the sparse precision matrix in the setting of Gaussian graphical models and demonstrate its application to identifying genetic networks. Such a procedure is computationally feasible and can easily incorporate prior biological knowledge about the network structure. Simulation results indicate that the proposed method yields a better estimate of the precision matrix than the procedures that fail to account for the sparsity of the graphs. We also present the results on inference of a gene network for isoprenoid biosynthesis in Arabidopsis thaliana. These results demonstrate that the proposed procedure can indeed identify biologically meaningful genetic networks based on microarray gene expression data.