Machine Learning (ML) approaches are increasingly being used in biomedical applications. Important challenges of ML include choosing the right algorithm and tuning the parameters for optimal performance. Automated ML (AutoML) methods, such as Tree-based Pipeline Optimization Tool (TPOT), have been developed to take some of the guesswork out of ML thus making this technology available to users from more diverse backgrounds. The goals of this study were to assess applicability of TPOT to genomics and to identify combinations of single nucleotide polymorphisms (SNPs) associated with coronary artery disease (CAD), with a focus on genes with high likelihood of being good CAD drug targets. We leveraged public functional genomic resources to group SNPs into biologically meaningful sets to be selected by TPOT. We applied this strategy to data from the U.K. Biobank, detecting a strikingly recurrent signal stemming from a group of 28 SNPs. Importance analysis of these SNPs uncovered functional relevance of the top SNPs to genes whose association with CAD is supported in the literature and other resources. Furthermore, we employed game-theory based metrics to study SNP contributions to individual-level TPOT predictions and discover distinct clusters of well-predicted CAD cases. The latter indicates a promising approach towards precision medicine.

Susceptibility to common human diseases such as cancer is influenced by many genetic and environmental factors that work together in a complex manner. The state of the art is to perform a genome-wide association study (GWAS) that measures millions of single-nucleotide polymorphisms (SNPs) throughout the genome followed by a one-SNP-at-a-time statistical analysis to detect univariate associations. This approach has identified thousands of genetic risk factors for hundreds of diseases. However, the genetic risk factors detected have very small effect sizes and collectively explain very little of the overall heritability of the disease. Nonetheless, it is assumed that the genetic component of risk is due to many independent risk factors that contribute additively. The fact that many genetic risk factors with small effects can be detected is taken as evidence to support this notion. It is our working hypothesis that the genetic architecture of common diseases is partly driven by non-additive interactions. To test this hypothesis, we developed a heuristic simulation-based method for conducting experiments about the complexity of genetic architecture. We show that a genetic architecture driven by complex interactions is highly consistent with the magnitude and distribution of univariate effects seen in real data. We compare our results with measures of univariate and interaction effects from two large-scale GWASs of sporadic breast cancer and find evidence to support our hypothesis that is consistent with the results of our computational experiment.

BACKGROUND: A typical task in bioinformatics consists of identifying which features are associated with a target outcome of interest and building a predictive model. Automated machine learning (AutoML) systems such as the Tree-based Pipeline Optimization Tool (TPOT) constitute an appealing approach to this end. However, in biomedical data, there are often baseline characteristics of the subjects in a study or batch effects that need to be adjusted for in order to better isolate the effects of the features of interest on the target. Thus, the ability to perform covariate adjustments becomes particularly important for applications of AutoML to biomedical big data analysis. RESULTS: We developed an approach to adjust for covariates affecting features and/or target in TPOT. Our approach is based on regressing out the covariates in a manner that avoids 'leakage' during the cross-validation training procedure. We describe applications of this approach to toxicogenomics and schizophrenia gene expression data sets. The TPOT extensions discussed in this work are available at https://github.com/EpistasisLab/tpot/tree/v0.11.1-resAdj . CONCLUSIONS: In this work, we address an important need in the context of AutoML, which is particularly crucial for applications to bioinformatics and medical informatics, namely covariate adjustments. To this end we present a substantial extension of TPOT, a genetic programming based AutoML approach. We show the utility of this extension by applications to large toxicogenomics and differential gene expression data. The method is generally applicable in many other scenarios from the biomedical field.

MOTIVATION: Microarray data analysis has expanded from testing individual genes for differential expression to testing gene sets for differential expression. The tests at the gene set level may focus on multivariate expression changes or on the differential expression of at least one gene in the gene set. These tests may be powerful at detecting subtle changes in expression, but findings at the gene set level need to be examined further to understand whether they are informative and if so how. RESULTS: We propose to first test for differential expression at the gene set level but then proceed to test for differential expression of individual genes within discovered gene sets. We introduce the overall false discovery rate (OFDR) as an appropriate error rate to control when testing multiple gene sets and genes. We illustrate the advantage of this procedure over procedures that only test gene sets or individual genes.

MOTIVATION: We address the problem of identifying differentially expressed genes between two conditions in the scenario where the data arise from an observational study, in which confounding factors are likely to be present. RESULTS: We suggest to use matching methods to balance two groups of observed cases on measured covariates, and to identify differentially expressed genes using a test suited to matched data. We illustrate this approach on two microarray studies: the first study consists of data from patients with two cancer subtypes, and the second study consists of data from AMKL patients with and without Down syndrome. AVAILABILITY: R code (www.r-project.org) for implementing our approach is included as Supplementary Material. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Gene expression array technology has become increasingly widespread among researchers who recognize its numerous promises. At the same time, bench biologists and bioinformaticians have come to appreciate increasingly the importance of establishing a collaborative dialog from the onset of a study and of collecting and exchanging detailed information on the many experimental and computational procedures using a structured mechanism. This is crucial for adequate analyses of this kind of data. RESULTS: The RNA Abundance Database (RAD; http://www.cbil.upenn.edu/RAD) provides a comprehensive MIAME-supportive infrastructure for gene expression data management and makes extensive use of ontologies. Specific details on protocols, biomaterials, study designs, etc. are collected through a user-friendly suite of web annotation forms. Software has been developed to generate MAGE-ML documents to enable easy export of studies stored in RAD to any other database accepting data in this format (e.g. ArrayExpress). RAD is part of a more general Genomics Unified Schema (http://www.gusdb.org), which includes a richly annotated gene index (http://www.allgenes.org), thus providing a platform that integrates genomic and transcriptomic data from multiple organisms. This infrastructure enables a large variety of queries that incorporate visualization and analysis tools and have been tailored to serve the specific needs of projects focusing on particular organisms or biological systems.

Abstract Motivation and Results: A relational schema is described for capturing highly parallel gene expression experiments using different technologies. This schema grew out of efforts to build a database for collaborators working on different biological systems and using different types of platforms in their gene expression experiments as well as different types of image quantification software. The tables are conceptually organized into three categories of information: Platform, Experiment (which includes image scanning and quantification), and Data. The strengths of the schema are: (i) integrating information on array elements using a gene index; (ii) describing samples using ontologies; (iii) reducing an experiment to a single RNA source for precise descriptions yet not losing the relationships between experiments done at the same time or for the same project; and (iv) maintaining both raw and processed (e.g. cleansed and normalized) data and recording how the data is processed. The result is a novel schema, which can hold both array and non-array data, is extensible for detailed experimental descriptions that are precise and consistent, and allows for meaningful comparisons of genes between experiments. Availability: The schema is available at http://www.cbil.upenn.edu/cgi-bin/RAD2/schemaBrowserRAD.pl. Contact: [email protected] * To whom correspondence should be addressed. 2 Present address: Department of Molecular Cell Biology, Weizmann Institute of Science, Israel.

MOTIVATION: A protocol is described to attach expression patterns to genes represented in a collection of hybridization array experiments. Discrete values are used to provide an easily interpretable description of differential expression. Binning cutoffs for each sample type are chosen automatically, depending on the desired false-positive rate for the predictions of differential expression. Confidence levels are derived for the statement that changes in observed levels represent true changes in expression. We have a novel method for calculating this confidence, which gives better results than the standard methods. Our method reflects the broader change of focus in the field from studying a few genes with many replicates to studying many (possibly thousands) of genes simultaneously, but with relatively few replicates. Our approach differs from standard methods in that it exploits the fact that there are many genes on the arrays. These are used to estimate for each sample type an appropriate distribution that is employed to control the false-positive rate of the predictions made. Satisfactory results can be obtained using this method with as few as two replicates. RESULTS: The method is illustrated through applications to macroarray and microarray datasets. The first is an erythroid development dataset that we have generated using nylon filter arrays. Clones for genes whose expression is known in these cells were assigned expression patterns which are in accordance with what was expected and which are not picked up by the standards methods. Moreover, genes differentially expressed between normal and leukemic cells were identified. These included genes whose expression was altered upon induction of the leukemic cells to differentiate. The second application is to the microarray data by Alizadeh et al. (2000). Our results are in accordance with their major findings and offer confidence measures for the predictions made. They also provide new insights for further analysis.

Article Significance testing for genomic mismatch scanning Share on Authors: G. R. Grant Center for Bioinformatics, University of Pennsylvania Center for Bioinformatics, University of PennsylvaniaView Profile , R. S. Spielman Department of Genetics, University of Pennsylvania Department of Genetics, University of PennsylvaniaView Profile , E. Manduchi Center for Bioinformatics, University of Pennsylvania Center for Bioinformatics, University of PennsylvaniaView Profile , V. G. Cheung Department of Pediatrics, The Children's Hospital of Philadelphia Department of Pediatrics, The Children's Hospital of PhiladelphiaView Profile , W. J. Ewens Department of Biology, University of Pennsylvania Department of Biology, University of PennsylvaniaView Profile Authors Info & Claims RECOMB '99: Proceedings of the third annual international conference on Computational molecular biologyApril 1999 Pages 182–187https://doi.org/10.1145/299432.299482Published:01 April 1999 0citation182DownloadsMetricsTotal Citations0Total Downloads182Last 12 Months0Last 6 weeks0 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteGet Access