Publications

MOTIVATION:
Rapidly expanding repositories of highly informative genomic data have generated increasing interest in methods for protein function prediction and inference of biological networks. The successful application of supervised machine learning to these tasks requires a gold standard for protein function: a trusted set of correct examples, which can be used to assess performance through cross-validation or other statistical approaches. Since gene annotation is incomplete for even the best studied model organisms, the biological reliability of such evaluations may be called into question.

RESULTS:
We address this concern by constructing and analyzing an experimentally based gold standard through comprehensive validation of protein function predictions for mitochondrion biogenesis in Saccharomyces cerevisiae. Specifically, we determine that (i) current machine learning approaches are able to generalize and predict novel biology from an incomplete gold standard and (ii) incomplete functional annotations adversely affect the evaluation of machine learning performance. While computational approaches performed better than predicted in the face of incomplete data, relative comparison of competing approaches-even those employing the same training data-is problematic with a sparse gold standard. Incomplete knowledge causes individual methods' performances to be differentially underestimated, resulting in misleading performance evaluations. We provide a benchmark gold standard for yeast mitochondria to complement current databases and an analysis of our experimental results in the hopes of mitigating these effects in future comparative evaluations.

AVAILABILITY:
The mitochondrial benchmark gold standard, as well as experimental results and additional data, is available at http://function.princeton.edu/mitochondria.

Tissue-specific gene expression plays a fundamental role in metazoan biology and is an important aspect of many complex diseases. Nevertheless, an organism-wide map of tissue-specific expression remains elusive due to difficulty in obtaining these data experimentally. Here, we leveraged existing whole-animal Caenorhabditis elegans microarray data representing diverse conditions and developmental stages to generate accurate predictions of tissue-specific gene expression and experimentally validated these predictions. These patterns of tissue-specific expression are more accurate than existing high-throughput experimental studies for nearly all tissues; they also complement existing experiments by addressing tissue-specific expression present at particular developmental stages and in small tissues. We used these predictions to address several experimentally challenging questions, including the identification of tissue-specific transcriptional motifs and the discovery of potential miRNA regulation specific to particular tissues. We also investigate the role of tissue context in gene function through tissue-specific functional interaction networks. To our knowledge, this is the first study producing high-accuracy predictions of tissue-specific expression and interactions for a metazoan organism based on whole-animal data.

Human genomic data of many types are readily available, but the complexity and scale of human molecular biology make it difficult to integrate this body of data, understand it from a systems level, and apply it to the study of specific pathways or genetic disorders. An investigator could best explore a particular protein, pathway, or disease if given a functional map summarizing the data and interactions most relevant to his or her area of interest. Using a regularized Bayesian integration system, we provide maps of functional activity and interaction networks in over 200 areas of human cellular biology, each including information from approximately 30,000 genome-scale experiments pertaining to approximately 25,000 human genes. Key to these analyses is the ability to efficiently summarize this large data collection from a variety of biologically informative perspectives: prediction of protein function and functional modules, cross-talk among biological processes, and association of novel genes and pathways with known genetic disorders. In addition to providing maps of each of these areas, we also identify biological processes active in each data set. Experimental investigation of five specific genes, AP3B1, ATP6AP1, BLOC1S1, LAMP2, and RAB11A, has confirmed novel roles for these proteins in the proper initiation of macroautophagy in amino acid-starved human fibroblasts. Our functional maps can be explored using HEFalMp (Human Experimental/Functional Mapper), a web interface allowing interactive visualization and investigation of this large body of information.

MOTIVATION:
The heterogeneity of cancer cannot always be recognized by tumor morphology, but may be reflected by the underlying genetic aberrations. Array comparative genome hybridization (array-CGH) methods provide high-throughput data on genetic copy numbers, but determining the clinically relevant copy number changes remains a challenge. Conventional classification methods for linking recurrent alterations to clinical outcome ignore sequential correlations in selecting relevant features. Conversely, existing sequence classification methods can only model overall copy number instability, without regard to any particular position in the genome.

RESULTS:
Here, we present the heterogeneous hidden conditional random field, a new integrated array-CGH analysis method for jointly classifying tumors, inferring copy numbers and identifying clinically relevant positions in recurrent alteration regions. By capturing the sequentiality as well as the locality of changes, our integrated model provides better noise reduction, and achieves more relevant gene retrieval and more accurate classification than existing methods. We provide an efficient L1-regularized discriminative training algorithm, which notably selects a small set of candidate genes most likely to be clinically relevant and driving the recurrent amplicons of importance. Our method thus provides unbiased starting points in deciding which genomic regions and which genes in particular to pursue for further examination. Our experiments on synthetic data and real genomic cancer prediction data show that our method is superior, both in prediction accuracy and relevant feature discovery, to existing methods. We also demonstrate that it can be used to generate novel biological hypotheses for breast cancer.

Mitochondria are central to many cellular processes including respiration, ion homeostasis, and apoptosis. Using computational predictions combined with traditional quantitative experiments, we have identified 100 proteins whose deficiency alters mitochondrial biogenesis and inheritance in Saccharomyces cerevisiae. In addition, we used computational predictions to perform targeted double-mutant analysis detecting another nine genes with synthetic defects in mitochondrial biogenesis. This represents an increase of about 25% over previously known participants. Nearly half of these newly characterized proteins are conserved in mammals, including several orthologs known to be involved in human disease. Mutations in many of these genes demonstrate statistically significant mitochondrial transmission phenotypes more subtle than could be detected by traditional genetic screens or high-throughput techniques, and 47 have not been previously localized to mitochondria. We further characterized a subset of these genes using growth profiling and dual immunofluorescence, which identified genes specifically required for aerobic respiration and an uncharacterized cytoplasmic protein required for normal mitochondrial motility. Our results demonstrate that by leveraging computational analysis to direct quantitative experimental assays, we have characterized mutants with subtle mitochondrial defects whose phenotypes were undetected by high-throughput methods.

Computational approaches have promised to organize collections of functional genomics data into testable predictions of gene and protein involvement in biological processes and pathways. However, few such predictions have been experimentally validated on a large scale, leaving many bioinformatic methods unproven and underutilized in the biology community. Further, it remains unclear what biological concerns should be taken into account when using computational methods to drive real-world experimental efforts. To investigate these concerns and to establish the utility of computational predictions of gene function, we experimentally tested hundreds of predictions generated from an ensemble of three complementary methods for the process of mitochondrial organization and biogenesis in Saccharomyces cerevisiae. The biological data with respect to the mitochondria are presented in a companion manuscript published in PLoS Genetics (doi:10.1371/journal.pgen.1000407). Here we analyze and explore the results of this study that are broadly applicable for computationalists applying gene function prediction techniques, including a new experimental comparison with 48 genes representing the genomic background. Our study leads to several conclusions that are important to consider when driving laboratory investigations using computational prediction approaches. While most genes in yeast are already known to participate in at least one biological process, we confirm that genes with known functions can still be strong candidates for annotation of additional gene functions. We find that different analysis techniques and different underlying data can both greatly affect the types of functional predictions produced by computational methods. This diversity allows an ensemble of techniques to substantially broaden the biological scope and breadth of predictions. We also find that performing prediction and validation steps iteratively allows us to more completely characterize a biological area of interest. While this study focused on a specific functional area in yeast, many of these observations may be useful in the contexts of other processes and organisms.

In 2005, Dr. Elias Zerhouni, Director of the National Institutes of Health (NIH), wrote:

"It is the responsibility of those of us involved in today's biomedical research enterprise to translate the remarkable scientific innovations we are witnessing into health gains for the nation... At no other time has the need for a robust, bidirectional information flow between basic and translational scientists been so necessary."

In that publication, Dr. Zerhouni introduced his ideas to re-engineer the way clinical research was performed in the United States. With the doubling of the NIH budget in the past decade, and coincident completion of the Human Genome Project, there is a perceived need to translate products of the genome era into products for clinical care.

Metabolite concentrations can regulate gene expression, which can in turn regulate metabolic activity. The extent to which functionally related transcripts and metabolites show similar patterns of concentration changes, however, remains unestablished. We measure and analyze the metabolomic and transcriptional responses of Saccharomyces cerevisiae to carbon and nitrogen starvation. Our analysis demonstrates that transcripts and metabolites show coordinated response dynamics. Furthermore, metabolites and gene products whose concentration profiles are alike tend to participate in related biological processes. To identify specific, functionally related genes and metabolites, we develop an approach based on Bayesian integration of the joint metabolomic and transcriptomic data. This algorithm finds interactions by evaluating transcript–metabolite correlations in light of the experimental context in which they occur and the class of metabolite involved. It effectively predicts known enzymatic and regulatory relationships, including a gene–metabolite interaction central to the glycolytic–gluconeogenetic switch. This work provides quantitative evidence that functionally related metabolites and transcripts show coherent patterns of behavior on the genome scale and lays the groundwork for building gene–metabolite interaction networks directly from systems-level data.

Maintaining balanced growth in a changing environment is a fundamental systems-level challenge for cellular physiology, particularly in microorganisms. While the complete set of regulatory and functional pathways supporting growth and cellular proliferation are not yet known, portions of them are well understood. In particular, cellular proliferation is governed by mechanisms that are highly conserved from unicellular to multicellular organisms, and the disruption of these processes in metazoans is a major factor in the development of cancer. In this paper, we develop statistical methodology to identify quantitative aspects of the regulatory mechanisms underlying cellular proliferation in Saccharomyces cerevisiae. We find that the expression levels of a small set of genes can be exploited to predict the instantaneous growth rate of any cellular culture with high accuracy. The predictions obtained in this fashion are robust to changing biological conditions, experimental methods, and technological platforms. The proposed model is also effective in predicting growth rates for the related yeast Saccharomyces bayanus and the highly diverged yeast Schizosaccharomyces pombe, suggesting that the underlying regulatory signature is conserved across a wide range of unicellular evolution. We investigate the biological significance of the gene expression signature that the predictions are based upon from multiple perspectives: by perturbing the regulatory network through the Ras/PKA pathway, observing strong upregulation of growth rate even in the absence of appropriate nutrients, and discovering putative transcription factor binding sites, observing enrichment in growth-correlated genes. More broadly, the proposed methodology enables biological insights about growth at an instantaneous time scale, inaccessible by direct experimental methods. Data and tools enabling others to apply our methods are available at http://function.princeton.edu/growthrate.

Modern experimental techniques have produced a wealth of high-throughput data that has enabled the ongoing genomic revolution. As the field continues to integrate experimental and computational analyzes of this data, it is essential that performance evaluations of high-throughput results be carried out in a consistent and biologically informative manner. Here, we present an overview of evaluation techniques for high-throughput experimental data and computational methods, and we discuss a number of potential pitfalls in this process. These primarily involve the biological diversity of genomic data, which can be masked or misrepresented in overly simplified global evaluations. We describe systems for preserving information about biological context during dataset evaluation, which can help to ensure that multiple different evaluations are more directly comparable. This biological variety in high-throughput data can also be taken advantage of computationally through data integration and process specificity to produce richer systems-level predictions of cellular function. An awareness of these considerations can greatly improve the evaluation and analysis of any high-throughput experimental dataset.