A classification-based framework for predicting and analyzing gene regulatory response

Predicting gene expression in the human malaria parasite Plasmodium falciparum using histone modification, nucleosome positioning, and 3D localization features

Empirical evidence suggests that the malaria parasite Plasmodium falciparum employs a broad range of mechanisms to regulate gene transcription throughout the organism's complex life cycle. To better understand this regulatory machinery, we assembled a rich collection of genomic and epigenomic data sets, including information about transcription factor (TF) binding motifs, patterns of covalent histone modifications, nucleosome occupancy, GC content, and global 3D genome architecture. We used these data to train machine learning models to discriminate between high-expression and low-expression genes, focusing on three distinct stages of the red blood cell phase of the Plasmodium life cycle. Our results highlight the importance of histone modifications and 3D chromatin architecture in Plasmodium transcriptional regulation and suggest that AP2 transcription factors may play a limited regulatory role, perhaps operating in conjunction with epigenetic factors.

LPRP: A Gene-Gene Interaction Network Construction Algorithm and Its Application in Breast Cancer Data Analysis

The importance of the construction of gene-gene interaction (GGI) network to better understand breast cancer has previously been highlighted. In this study, we propose a novel GGI network construction method called linear and probabilistic relations prediction (LPRP) and used it for gaining system level insight into breast cancer mechanisms. We construct separate genome-wide GGI networks for tumor and normal breast samples, respectively, by applying LPRP on their gene expression datasets profiled by The Cancer Genome Atlas. According to our analysis, a large loss of gene interactions in the tumor GGI network was observed (7436; 88.7 % reduction), which also contained fewer functional genes (4757; 32 % reduction) than the normal network. Tumor GGI network was characterized by a bigger network diameter and a longer characteristic path length but a smaller clustering coefficient and much sparse network connections. In addition, many known cancer pathways, especially immune response pathways, are enriched by genes in the tumor GGI network. Furthermore, potential cancer genes are filtered in this study, which may act as drugs targeting genes. These findings will allow for a better understanding of breast cancer mechanisms.

An unsupervised approach to predict functional relations between genes based on expression data

This work presents a novel approach to predict functional relations between genes using gene expression data. Genes may have various types of relations between them, for example, regulatory relations, or they may be concerned with the same protein complex or metabolic/signaling pathways and obviously gene expression data should contain some clues to such relations. The present approach first digitizes the log-ratio type gene expression data of S. cerevisiae to a matrix consisting of 1, 0, and −1 indicating highly expressed, no major change, and highly suppressed conditions for genes, respectively. For each gene pair, a probability density mass function table is constructed indicating nine joint probabilities. Then gene pairs were selected based on linear and probabilistic relation between their profiles indicated by the sum of probability density masses in selected points. The selected gene pairs share many Gene Ontology terms. Furthermore a network is constructed by selecting a large number of gene pairs based on FDR analysis and the clustering of the network generates many modules rich with similar function genes. Also, the promoters of the gene sets in many modules are rich with binding sites of known transcription factors indicating the effectiveness of the proposed approach in predicting regulatory relations.

Biomedical informatics and translational medicine

Biomedical informatics involves a core set of methodologies that can provide a foundation for crossing the "translational barriers" associated with translational medicine. To this end, the fundamental aspects of biomedical informatics (e.g., bioinformatics, imaging informatics, clinical informatics, and public health informatics) may be essential in helping improve the ability to bring basic research findings to the bedside, evaluate the efficacy of interventions across communities, and enable the assessment of the eventual impact of translational medicine innovations on health policies. Here, a brief description is provided for a selection of key biomedical informatics topics (Decision Support, Natural Language Processing, Standards, Information Retrieval, and Electronic Health Records) and their relevance to translational medicine. Based on contributions and advancements in each of these topic areas, the article proposes that biomedical informatics practitioners ("biomedical informaticians") can be essential members of translational medicine teams.

Supervised learning with decision tree-based methods in computational and systems biology

At the intersection between artificial intelligence and statistics, supervised learning allows algorithms to automatically build predictive models from just observations of a system. During the last twenty years, supervised learning has been a tool of choice to analyze the always increasing and complexifying data generated in the context of molecular biology, with successful applications in genome annotation, function prediction, or biomarker discovery. Among supervised learning methods, decision tree-based methods stand out as non parametric methods that have the unique feature of combining interpretability, efficiency, and, when used in ensembles of trees, excellent accuracy. The goal of this paper is to provide an accessible and comprehensive introduction to this class of methods. The first part of the review is devoted to an intuitive but complete description of decision tree-based methods and a discussion of their strengths and limitations with respect to other supervised learning methods. The second part of the review provides a survey of their applications in the context of computational and systems biology.

A predictive model of the oxygen and heme regulatory network in yeast

Deciphering gene regulatory mechanisms through the analysis of high-throughput expression data is a challenging computational problem. Previous computational studies have used large expression datasets in order to resolve fine patterns of coexpression, producing clusters or modules of potentially coregulated genes. These methods typically examine promoter sequence information, such as DNA motifs or transcription factor occupancy data, in a separate step after clustering. We needed an alternative and more integrative approach to study the oxygen regulatory network in Saccharomyces cerevisiae using a small dataset of perturbation experiments. Mechanisms of oxygen sensing and regulation underlie many physiological and pathological processes, and only a handful of oxygen regulators have been identified in previous studies. We used a new machine learning algorithm called MEDUSA to uncover detailed information about the oxygen regulatory network using genome-wide expression changes in response to perturbations in the levels of oxygen, heme, Hap1, and Co²⁺. MEDUSA integrates mRNA expression, promoter sequence, and ChIP-chip occupancy data to learn a model that accurately predicts the differential expression of target genes in held-out data. We used a novel margin-based score to extract significant condition-specific regulators and assemble a global map of the oxygen sensing and regulatory network. This network includes both known oxygen and heme regulators, such as Hap1, Mga2, Hap4, and Upc2, as well as many new candidate regulators. MEDUSA also identified many DNA motifs that are consistent with previous experimentally identified transcription factor binding sites. Because MEDUSA's regulatory program associates regulators to target genes through their promoter sequences, we directly tested the predicted regulators for OLE1, a gene specifically induced under hypoxia, by experimental analysis of the activity of its promoter. In each case, deletion of the candidate regulator resulted in the predicted effect on promoter activity, confirming that several novel regulators identified by MEDUSA are indeed involved in oxygen regulation. MEDUSA can reveal important information from a small dataset and generate testable hypotheses for further experimental analysis. Supplemental data are included.

The cell uses complex regulatory networks to modulate the expression of genes in response to changes in cellular and environmental conditions. The transcript level of a gene is directly affected by the binding of transcriptional regulators to DNA motifs in its promoter sequence. Therefore, both expression levels of transcription factors and other regulatory proteins as well as sequence information in the promoters contribute to transcriptional gene regulation. In this study, we describe a new computational strategy for learning gene regulatory programs from gene expression data based on the MEDUSA algorithm. We learn a model that predicts differential expression of target genes from the expression levels of regulators, the presence of DNA motifs in promoter sequences, and binding data for transcription factors. Unlike many previous approaches, we do not assume that genes are regulated in clusters, and we learn DNA motifs de novo from promoter sequences as an integrated part of our algorithm. We use MEDUSA to produce a global map of the yeast oxygen and heme regulatory network. To demonstrate that MEDUSA can reveal detailed information about regulatory mechanisms, we perform biochemical experiments to confirm the predicted regulators for an important hypoxia gene.

Learning regulatory programs that accurately predict differential expression with MEDUSA

Inferring gene regulatory networks from high-throughput genomic data is one of the central problems in computational biology. In this paper, we describe a predictive modeling approach for studying regulatory networks, based on a machine learning algorithm called MEDUSA. MEDUSA integrates promoter sequence, mRNA expression, and transcription factor occupancy data to learn gene regulatory programs that predict the differential expression of target genes. Instead of using clustering or correlation of expression profiles to infer regulatory relationships, MEDUSA determines condition-specific regulators and discovers regulatory motifs that mediate the regulation of target genes. In this way, MEDUSA meaningfully models biological mechanisms of transcriptional regulation. MEDUSA solves the problem of predicting the differential (up/down) expression of target genes by using boosting, a technique from statistical learning, which helps to avoid overfitting as the algorithm searches through the high-dimensional space of potential regulators and sequence motifs. Experimental results demonstrate that MEDUSA achieves high prediction accuracy on held-out experiments (test data), that is, data not seen in training. We also present context-specific analysis of MEDUSA regulatory programs for DNA damage and hypoxia, demonstrating that MEDUSA identifies key regulators and motifs in these processes. A central challenge in the field is the difficulty of validating reverse-engineered networks in the absence of a gold standard. Our approach of learning regulatory programs provides at least a partial solution for the problem: MEDUSA's prediction accuracy on held-out data gives a concrete and statistically sound way to validate how well the algorithm performs. With MEDUSA, statistical validation becomes a prerequisite for hypothesis generation and network building rather than a secondary consideration.

Predictive modeling of genome-wide mRNA expression: from modules to molecules

Various algorithms are available for predicting mRNA expression and modeling gene regulatory processes. They differ in whether they rely on the existence of modules of coregulated genes or build a model that applies to all genes, whether they represent regulatory activities as hidden variables or as mRNA levels, and whether they implicitly or explicitly model the complex cis-regulatory logic of multiple interacting transcription factors binding the same DNA. The fact that functional genomics data of different types reflect the same molecular processes provides a natural strategy for integrative computational analysis. One promising avenue toward an accurate and comprehensive model of gene regulation combines biophysical modeling of the interactions among proteins, DNA, and RNA with the use of large-scale functional genomics data to estimate regulatory network connectivity and activity parameters. As the ability of these models to represent complex cis-regulatory logic increases, the need for approaches based on cross-species conservation may diminish.

A classification-based framework for predicting and analyzing gene regulatory response

BACKGROUND

We have recently introduced a predictive framework for studying gene transcriptional regulation in simpler organisms using a novel supervised learning algorithm called GeneClass. GeneClass is motivated by the hypothesis that in model organisms such as Saccharomyces cerevisiae, we can learn a decision rule for predicting whether a gene is up- or down-regulated in a particular microarray experiment based on the presence of binding site subsequences ("motifs") in the gene's regulatory region and the expression levels of regulators such as transcription factors in the experiment ("parents"). GeneClass formulates the learning task as a classification problem--predicting +1 and -1 labels corresponding to up- and down-regulation beyond the levels of biological and measurement noise in microarray measurements. Using the Adaboost algorithm, GeneClass learns a prediction function in the form of an alternating decision tree, a margin-based generalization of a decision tree.

METHODS

In the current work, we introduce a new, robust version of the GeneClass algorithm that increases stability and computational efficiency, yielding a more scalable and reliable predictive model. The improved stability of the prediction tree enables us to introduce a detailed post-processing framework for biological interpretation, including individual and group target gene analysis to reveal condition-specific regulation programs and to suggest signaling pathways. Robust GeneClass uses a novel stabilized variant of boosting that allows a set of correlated features, rather than single features, to be included at nodes of the tree; in this way, biologically important features that are correlated with the single best feature are retained rather than decorrelated and lost in the next round of boosting. Other computational developments include fast matrix computation of the loss function for all features, allowing scalability to large datasets, and the use of abstaining weak rules, which results in a more shallow and interpretable tree. We also show how to incorporate genome-wide protein-DNA binding data from ChIP chip experiments into the GeneClass algorithm, and we use an improved noise model for gene expression data.

RESULTS

Using the improved scalability of Robust GeneClass, we present larger scale experiments on a yeast environmental stress dataset, training and testing on all genes and using a comprehensive set of potential regulators. We demonstrate the improved stability of the features in the learned prediction tree, and we show the utility of the post-processing framework by analyzing two groups of genes in yeast--the protein chaperones and a set of putative targets of the Nrg1 and Nrg2 transcription factors--and suggesting novel hypotheses about their transcriptional and post-transcriptional regulation. Detailed results and Robust GeneClass source code is available for download from http://www.cs.columbia.edu/compbio/robust-geneclass.