Increasingly, multiple parallel omics datasets are collected from biological samples. Integrating these datasets for classification is an open area of research. Additionally, whilst multiple datasets may be available for the training samples, future samples may only be measured by a single technology requiring methods which do not rely on the presence of all datasets for sample prediction. This enables us to directly compare the protein and the gene profiles. New samples with just one set of measurements (e.g., just protein) can then be mapped to this latent common space where classification is performed. Using this approach, we achieved an improvement of up to 12 percent in accuracy when classifying samples based on their protein measurements compared with baseline methods which were trained on the protein data alone. We illustrate that the additional inclusion of the gene expression or protein expression in the training process enabled the separation between the classes to become clearer.

Many studies now produce parallel data sets from different omics technologies; however, the task of interpreting the acquired data in an integrated fashion is not trivial. This review covers those methods that have been used over the past decade to statistically integrate and interpret metabolomics and transcriptomic data sets. It defines four categories of approaches, correlation-based integration, concatenation-based integration, multivariate-based integration and pathway-based integration, into which all existing statistical methods fit. It also explores the choices in study design for generating samples for analysis by these omics technologies and the impact that these technical decisions have on the subsequent data analysis options.

MOTIVATION: Comparing time courses of gene expression with time courses of phenotypic data may provide new insights in cellular mechanisms. In this study, we compared the performance of five pattern recognition methods with respect to their ability to relate genes and phenotypic data: one classical method (k-means) and four methods especially developed for time series [Short Time-series Expression Miner (STEM), Linear Mixed Model mixtures, Dynamic Time Warping for -Omics and linear modeling with R/Bioconductor limma package]. The methods were evaluated using data available from toxicological studies that had the aim to relate gene expression with phenotypic endpoints (i.e. to develop biomarkers for adverse outcomes). Additionally, technical aspects (influence of noise, number of time points and number of replicates) were evaluated on simulated data. RESULTS: None of the methods outperforms the others in terms of biology. Linear modeling with limma is mostly influenced by noise. STEM is mostly influenced by the number of biological replicates in the dataset, whereas k-means and linear modeling with limma are mostly influenced by the number of time points. In most cases, the results of the methods complement each other. We therefore provide recommendations to integrate the five methods. AVAILABILITY: The Matlab code for the simulations performed in this research is available in the Supplementary Data (Word file). The microarray data analysed in this paper are available at ArrayExpress (E-TOXM-22 and E-TOXM-23) and Gene Expression Omnibus (GSE39291). The phenotypic data are available in the Supplementary Data (Excel file). Links to the pattern recognition tools compared in this paper are provided in the main text. CONTACT: [email protected] SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: Pathway-level analysis is a powerful approach enabling interpretation of post-genomic data at a higher level than that of individual biomolecules. Yet, it is currently hard to integrate more than one type of omics data in such an approach. Here, we present a web tool 'IMPaLA' for the joint pathway analysis of transcriptomics or proteomics and metabolomics data. It performs over-representation or enrichment analysis with user-specified lists of metabolites and genes using over 3000 pre-annotated pathways from 11 databases. As a result, pathways can be identified that may be disregulated on the transcriptional level, the metabolic level or both. Evidence of pathway disregulation is combined, allowing for the identification of additional pathways with changed activity that would not be highlighted when analysis is applied to any of the functional levels alone. The tool has been implemented both as an interactive website and as a web service to allow a programming interface. AVAILABILITY: The web interface of IMPaLA is available at http://impala.molgen.mpg.de. A web services programming interface is provided at http://impala.molgen.mpg.de/wsdoc. CONTACT: [email protected]; [email protected]; [email protected] SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Using transcriptomic and metabolomic measurements from the NCI60 cell line panel, together with a novel approach to integration of molecular profile data, we show that the biochemical pathways associated with tumour cell chemosensitivity to platinum-based drugs are highly coincident, i.e. they describe a consensus phenotype. Direct integration of metabolome and transcriptome data at the point of pathway analysis improved the detection of consensus pathways by 76%, and revealed associations between platinum sensitivity and several metabolic pathways that were not visible from transcriptome analysis alone. These pathways included the TCA cycle and pyruvate metabolism, lipoprotein uptake and nucleotide synthesis by both salvage and de novo pathways. Extending the approach across a wide panel of chemotherapeutics, we confirmed the specificity of the metabolic pathway associations to platinum sensitivity. We conclude that metabolic phenotyping could play a role in predicting response to platinum chemotherapy and that consensus-phenotype integration of molecular profiling data is a powerful and versatile tool for both biomarker discovery and for exploring the complex relationships between biological pathways and drug response.

MOTIVATION: Metabolic profiles derived from high resolution (1)H-NMR data are complex, therefore statistical and machine learning approaches are vital for extracting useful information and biological insights. Focused modelling on targeted subsets of metabolites and samples can improve the predictive ability of models, and techniques such as genetic algorithms (GAs) have a proven utility in feature selection problems. The Consortium for Metabonomic Toxicology (COMET) obtained temporal NMR spectra of urine from rats treated with model toxins and stressors. Here, we develop a GA approach which simultaneously selects sets of samples and spectral regions from the COMET database to build robust, predictive classifiers of liver and kidney toxicity. RESULTS: The results indicate that using simultaneous sample and variable selection improved performance by over 9% compared with either method alone. Simultaneous selection also halved computation time. Successful classifiers repeatedly selected particular variables indicating that this approach can aid defining biomarkers of toxicity. Novel visualizations of the results from multiple computations were developed to aid the interpretability of which samples and variables were frequently selected. This method provides an efficient way to determine the most discriminatory variables and samples for any post-genomic dataset. AVAILABILITY: GA code available from http://www1.imperial.ac.uk/medicine/people/r.cavill/

The dynamics of variable length representations in evolutionary computation have been shown to be complex and different from those seen in standard fixed length genetic algorithms. This paper explores a simple variable length genetic algorithm with multiple chromosomes and its underlying dynamics when used for the onemax problem. The changes in length of the chromosomes are especially observed and explanations for these fluctuations are sought.

Embedded Cartesian Genetic Programming (ECGP) is an extension of Cartesian Genetic Programming (CGP) that can automatically acquire, evolve and re-use partial solutions in the form of modules. In this paper, we introduce for the first time a new multi-chromosome approach to CGP and ECGP that allows difficult problems with multiple outputs to be broken down into many smaller, simpler problems with single outputs, whilst still encoding the entire solution in a single genotype. We also propose a multi-chromosome evolutionary strategy which selects the best chromosomes from the entire population to form the new fittest individual, which may not have been present in the population. The multi-chromosome approach to CGP and ECGP is tested on a number of multiple output digital circuits. Computational Effort figures are calculated for each problem and compared against those for CGP and ECGP. The results indicate that the use of multiple chromosomes in both CGP and ECGP provide a significant performance increase on all problems tested.

This paper presents important new findings for a new method for evolving individual programs with multiple chromosomes. Previous results have shown that evolving individuals with multiple chromosomes produced improved results over evolving individuals with a single chromosome. The multiple chromosomes are organised along two axes; there are a number of different chromosomes and a number of copies of each chromosome. This paper investigates the effects which these two axes have on the performance of the algorithm; whether the improvement in performance comes from just one of these features or whether it is a combination of them both.

This paper introduces an evolutionary algorithm which uses multiple chromosomes to evolve solutions to a symbolic regression problem. Inspiration for this algorithm is provided by the existence of multiple chromosomes in natural evolution, particularly in plants. A multi-chromosomal system usually requires a dominance system and subsequently dominance in nature and in previous artificial evolutionary systems has also been considered. An implementation of a multi-chromosomal system is presented with initial results which support the use of multi-chromosomal techniques in evolutionary algorithms.