IPF-LASSO: Integrative L1-Penalized Regression with Penalty Factors for Prediction Based on Multi-Omics Data.

As modern biotechnologies advance, it has become increasingly frequent that different modalities of high-dimensional molecular data (termed "omics" data in this paper), such as gene expression, methylation, and copy number, are collected from the same patient cohort to predict the clinical outcome. While prediction based on omics data has been widely studied in the last fifteen years, little has been done in the statistical literature on the integration of multiple omics modalities to select a subset of variables for prediction, which is a critical task in personalized medicine. In this paper, we propose a simple penalized regression method to address this problem by assigning different penalty factors to different data modalities for feature selection and prediction. The penalty factors can be chosen in a fully data-driven fashion by cross-validation or by taking practical considerations into account. In simulation studies, we compare the prediction performance of our approach, called IPF-LASSO (Integrative LASSO with Penalty Factors) and implemented in the R package ipflasso, with the standard LASSO and sparse group LASSO. The use of IPF-LASSO is also illustrated through applications to two real-life cancer datasets. All data and codes are available on the companion website to ensure reproducibility.

Connecting high-dimensional mRNA and miRNA expression data for binary medical classification problems.

In modern molecular biology, high-throughput experiments allow the simultaneous study of expression levels of thousands of biopolymers such as mRNAs, miRNAs or proteins. A typical goal of such experiments is to find molecular signatures that can distinguish between different types of tissue or that can predict a therapy outcome. While research typically focuses on just one type of molecular features of a gene, e.g. mRNA expression levels, there is increasing interest in the study of several types of features in parallel, i.e. within the same biological samples. In this manuscript, we aim at elucidating the peculiarities of the combination of mRNA and miRNA expression levels in binary medical classification problems by proposing and comparing different methodologies. The ensuing combined classifiers are evaluated within a simulation study. They are based on linear discriminant analysis, linear support vector machines, as well as on a non-linear classifier. In addition, we compare the performance of the different approaches on real expression data sets. In the simulations as well as in the real data sets, in most though not all cases the combinations yield equal or higher accuracy than the individual classifiers based on only one type of features.

Integration of gene expression data with prior knowledge for network analysis and validation.

BACKGROUND: Reconstruction of protein-protein interaction or metabolic networks based on expression data often involves in silico predictions, while on the other hand, there are unspecific networks of in vivo interactions derived from knowledge bases.We analyze networks designed to come as close as possible to data measured in vivo, both with respect to the set of nodes which were taken to be expressed in experiment as well as with respect to the interactions between them which were taken from manually curated databases RESULTS: A signaling network derived from the TRANSPATH database and a metabolic network derived from KEGG LIGAND are each filtered onto expression data from breast cancer (SAGE) considering different levels of restrictiveness in edge and vertex selection.We perform several validation steps, in particular we define pathway over-representation tests based on refined null models to recover functional modules. The prominent role of the spindle checkpoint-related pathways in breast cancer is exhibited. High-ranking key nodes cluster in functional groups retrieved from literature. Results are consistent between several functional and topological analyses and between signaling and metabolic aspects. CONCLUSIONS: This construction involved as a crucial step the passage to a mammalian protein identifier format as well as to a reaction-based semantics of metabolism. This yielded good connectivity but also led to the need to perform benchmark tests to exclude loss of essential information. Such validation, albeit tedious due to limitations of existing methods, turned out to be informative, and in particular provided biological insights as well as information on the degrees of coherence of the networks despite fragmentation of experimental data.Key node analysis exploited the networks for potentially interesting proteins in view of drug target prediction.

Planar cell movements and oriented cell division during early primitive streak formation in the mammalian embryo.

Formation of the mammalian primitive streak appears to rely on cell proliferation to a minor extent only, but compensating cell movements have not yet been directly observed. This study analyses individual cell migration and proliferation simultaneously, using multiphoton and differential interference contrast time-lapse microscopy of late pregastrulation rabbit blastocysts. Epiblast cells in the posterior gastrula extension area accumulated medially and displayed complex planar movements including U-turns and a novel type of processional cell movement. In the same area metaphase plates tended to be aligned parallel to the anterior-posterior axis, and statistical analysis showed that rotations of metaphase plates causing preferred orientation were near-complete 8 min before anaphase onset; in some cases, rotations were strikingly rapid, achieving up to 45° per min. The mammalian primitive streak appears to be formed initially with its typically minimal anteroposterior elongation by a combination of oriented cell divisions with dedicated planar cell movements.