Reconstructing Causal Biological Networks through Active Learning

Causal network inference from gene transcriptional time-series response to glucocorticoids

Gene regulatory network inference is essential to uncover complex relationships among gene pathways and inform downstream experiments, ultimately enabling regulatory network re-engineering. Network inference from transcriptional time-series data requires accurate, interpretable, and efficient determination of causal relationships among thousands of genes. Here, we develop Bootstrap Elastic net regression from Time Series (BETS), a statistical framework based on Granger causality for the recovery of a directed gene network from transcriptional time-series data. BETS uses elastic net regression and stability selection from bootstrapped samples to infer causal relationships among genes. BETS is highly parallelized, enabling efficient analysis of large transcriptional data sets. We show competitive accuracy on a community benchmark, the DREAM4 100-gene network inference challenge, where BETS is one of the fastest among methods of similar performance and additionally infers whether causal effects are activating or inhibitory. We apply BETS to transcriptional time-series data of differentially-expressed genes from A549 cells exposed to glucocorticoids over a period of 12 hours. We identify a network of 2768 genes and 31,945 directed edges (FDR ≤ 0.2). We validate inferred causal network edges using two external data sources: Overexpression experiments on the same glucocorticoid system, and genetic variants associated with inferred edges in primary lung tissue in the Genotype-Tissue Expression (GTEx) v6 project. BETS is available as an open source software package at https://github.com/lujonathanh/BETS.

Emergence of informative higher scales in biological systems: a computational toolkit for optimal prediction and control

The biological sciences span many spatial and temporal scales in attempts to understand the function and evolution of complex systems-level processes, such as embryogenesis. It is generally assumed that the most effective description of these processes is in terms of molecular interactions. However, recent developments in information theory and causal analysis now allow for the quantitative resolution of this question. In some cases, macro-scale models can minimize noise and increase the amount of information an experimenter or modeler has about "what does what." This result has numerous implications for evolution, pattern regulation, and biomedical strategies. Here, we provide an introduction to these quantitative techniques, and use them to show how informative macro-scales are common across biology. Our goal is to give biologists the tools to identify the maximally-informative scale at which to model, experiment on, predict, control, and understand complex biological systems.

A Bayesian Active Learning Experimental Design for Inferring Signaling Networks

Machine learning methods for learning network structure are applied to quantitative proteomics experiments and reverse-engineer intracellular signal transduction networks. They provide insight into the rewiring of signaling within the context of a disease or a phenotype. To learn the causal patterns of influence between proteins in the network, the methods require experiments that include targeted interventions that fix the activity of specific proteins. However, the interventions are costly and add experimental complexity. We describe an active learning strategy for selecting optimal interventions. Our approach takes as inputs pathway databases and historic data sets, expresses them in form of prior probability distributions on network structures, and selects interventions that maximize their expected contribution to structure learning. Evaluations on simulated and real data show that the strategy reduces the detection error of validated edges as compared with an unguided choice of interventions and avoids redundant interventions, thereby increasing the effectiveness of the experiment.

Active learning of cortical connectivity from two-photon imaging data

Understanding how groups of neurons interact within a network is a fundamental question in system neuroscience. Instead of passively observing the ongoing activity of a network, we can typically perturb its activity, either by external sensory stimulation or directly via techniques such as two-photon optogenetics. A natural question is how to use such perturbations to identify the connectivity of the network efficiently. Here we introduce a method to infer sparse connectivity graphs from in-vivo, two-photon imaging of population activity in response to external stimuli. A novel aspect of the work is the introduction of a recommended distribution, incrementally learned from the data, to optimally refine the inferred network. Unlike existing system identification techniques, this “active learning” method automatically focuses its attention on key undiscovered areas of the network, instead of targeting global uncertainty indicators like parameter variance. We show how active learning leads to faster inference while, at the same time, provides confidence intervals for the network parameters. We present simulations on artificial small-world networks to validate the methods and apply the method to real data. Analysis of frequency of motifs recovered show that cortical networks are consistent with a small-world topology model.

Applications of Bayesian network models in predicting types of hematological malignancies

Network analysis is the preferred approach for the detection of subtle but coordinated changes in expression of an interacting and related set of genes. We introduce a novel method based on the analyses of coexpression networks and Bayesian networks, and we use this new method to classify two types of hematological malignancies; namely, acute myeloid leukemia (AML) and myelodysplastic syndrome (MDS). Our classifier has an accuracy of 93%, a precision of 98%, and a recall of 90% on the training dataset (n = 366); which outperforms the results reported by other scholars on the same dataset. Although our training dataset consists of microarray data, our model has a remarkable performance on the RNA-Seq test dataset (n = 74, accuracy = 89%, precision = 88%, recall = 98%), which confirms that eigengenes are robust with respect to expression profiling technology. These signatures are useful in classification and correctly predicting the diagnosis. They might also provide valuable information about the underlying biology of diseases. Our network analysis approach is generalizable and can be useful for classifying other diseases based on gene expression profiles. Our previously published Pigengene package is publicly available through Bioconductor, which can be used to conveniently fit a Bayesian network to gene expression data.

Machine learning for epigenetics and future medical applications

Understanding epigenetic processes holds immense promise for medical applications. Advances in Machine Learning (ML) are critical to realize this promise. Previous studies used epigenetic data sets associated with the germline transmission of epigenetic transgenerational inheritance of disease and novel ML approaches to predict genome-wide locations of critical epimutations. A combination of Active Learning (ACL) and Imbalanced Class Learning (ICL) was used to address past problems with ML to develop a more efficient feature selection process and address the imbalance problem in all genomic data sets. The power of this novel ML approach and our ability to predict epigenetic phenomena and associated disease is suggested. The current approach requires extensive computation of features over the genome. A promising new approach is to introduce Deep Learning (DL) for the generation and simultaneous computation of novel genomic features tuned to the classification task. This approach can be used with any genomic or biological data set applied to medicine. The application of molecular epigenetic data in advanced machine learning analysis to medicine is the focus of this review.

miRsig: a consensus-based network inference methodology to identify pan-cancer miRNA-miRNA interaction signatures

Decoding the patterns of miRNA regulation in diseases are important to properly realize its potential in diagnostic, prog- nostic, and therapeutic applications. Only a handful of studies computationally predict possible miRNA-miRNA interactions; hence, such interactions require a thorough investigation to understand their role in disease progression. In this paper, we design a novel computational pipeline to predict the common signature/core sets of miRNA-miRNA interactions for different diseases using network inference algorithms on the miRNA-disease expression profiles; the individual predictions of these algorithms were then merged using a consensus-based approach to predict miRNA-miRNA associations. We next selected the miRNA-miRNA associations across particular diseases to generate the corresponding disease-specific miRNA-interaction networks. Next, graph intersection analysis was performed on these networks for multiple diseases to identify the common signature/core sets of miRNA interactions. We applied this pipeline to identify the common signature of miRNA-miRNA inter- actions for cancers. The identified signatures when validated using a manual literature search from PubMed Central and the PhenomiR database, show strong relevance with the respective cancers, providing an indirect proof of the high accuracy of our methodology. We developed miRsig, an online tool for analysis and visualization of the disease-specific signature/core miRNA-miRNA interactions, available at: http://bnet.egr.vcu.edu/miRsig.

New Algorithm and Software (BNOmics) for Inferring and Visualizing Bayesian Networks from Heterogeneous Big Biological and Genetic Data

Bayesian network (BN) reconstruction is a prototypical systems biology data analysis approach that has been successfully used to reverse engineer and model networks reflecting different layers of biological organization (ranging from genetic to epigenetic to cellular pathway to metabolomic). It is especially relevant in the context of modern (ongoing and prospective) studies that generate heterogeneous high-throughput omics datasets. However, there are both theoretical and practical obstacles to the seamless application of BN modeling to such big data, including computational inefficiency of optimal BN structure search algorithms, ambiguity in data discretization, mixing data types, imputation and validation, and, in general, limited scalability in both reconstruction and visualization of BNs. To overcome these and other obstacles, we present BNOmics, an improved algorithm and software toolkit for inferring and analyzing BNs from omics datasets. BNOmics aims at comprehensive systems biology—type data exploration, including both generating new biological hypothesis and testing and validating the existing ones. Novel aspects of the algorithm center around increasing scalability and applicability to varying data types (with different explicit and implicit distributional assumptions) within the same analysis framework. An output and visualization interface to widely available graph-rendering software is also included. Three diverse applications are detailed. BNOmics was originally developed in the context of genetic epidemiology data and is being continuously optimized to keep pace with the ever-increasing inflow of available large-scale omics datasets. As such, the software scalability and usability on the less than exotic computer hardware are a priority, as well as the applicability of the algorithm and software to the heterogeneous datasets containing many data types—single-nucleotide polymorphisms and other genetic/epigenetic/transcriptome variables, metabolite levels, epidemiological variables, endpoints, and phenotypes, etc.