The diffusion of next-generation sequencing technologies has revolutionized research and diagnosis in the field of rare Mendelian disorders, notably via whole-exome sequencing (WES). However, one of the main issues hampering achievement of a diagnosis via WES analyses is the extended list of variants of unknown significance (VUS), mostly composed of missense variants. Hence, improved solutions are needed to address the challenges of identifying potentially deleterious variants and ranking them in a prioritized short list. We present MISTIC (MISsense deleTeriousness predICtor), a new prediction tool based on an original combination of two complementary machine learning algorithms using a soft voting system that integrates 113 missense features, ranging from multi-ethnic minor allele frequencies and evolutionary conservation, to physiochemical and biochemical properties of amino acids. Our approach also uses training sets with a wide spectrum of variant profiles, including both high-confidence positive (deleterious) and negative (benign) variants. Compared to recent state-of-the-art prediction tools in various benchmark tests and independent evaluation scenarios, MISTIC exhibits the best and most consistent performance, notably with the highest AUC value (> 0.95). Importantly, MISTIC maintains its high performance in the specific case of discriminating deleterious variants from benign variants that are rare or population-specific. In a clinical context, MISTIC drastically reduces the list of VUS (<30%) and significantly improves the ranking of "causative" deleterious variants. Pre-computed MISTIC scores for all possible human missense variants are available at http://lbgi.fr/mistic.

Background Ab initio prediction of splice sites is an essential step in eukaryotic genome annotation. Recent predictors have exploited Deep Learning algorithms and reliable gene structures from model organisms. However, Deep Learning methods for non-model organisms are lacking. Results We developed Spliceator to predict splice sites in a wide range of species, including model and non-model organisms. Spliceator uses a convolutional neural network and is trained on carefully validated data from over 100 organisms. We show that Spliceator achieves consistently high accuracy (89–92%) compared to existing methods on independent benchmarks from human, fish, fly, worm, plant and protist organisms. Conclusions Spliceator is a new Deep Learning method trained on high-quality data, which can be used to predict splice sites in diverse organisms, ranging from human to protists, with consistently high accuracy.

Protein kinases regulate a variety of biological signaling pathways affecting cell proliferation, differentiation, migration and apoptosis. In tumor cells the activity of many protein kinases are frequently found to be upregulated linking deregulation of protein kinases causally to the development and progression of many human cancers and other diseases. Therefore, protein kinases have become a prime molecular target for therapeutic intervention, and up to now fourteen small molecule inhibitors have been approved for treatment of various types of cancer. These inhibitors block the activity of the target protein kinases by either blocking the ATP binding site in a direct competitive manner (type1-inhibitors) or by indirectly interfering with ATP/kinase interaction by binding to an inactive state, referred to as DFG-out (type2-inhibitors). Due to the fact that these inhibitor types bind to a region which is highly conserved among the protein kinase superfamily, achieving target selectivity represent a major challenge in the development of protein kinase inhibitors. Allosteric inhibitors, also sometimes referred to as type3-inhibitors, bind to structural sites different to the ATP-binding pocket region, and have, therefore, a significant higher potential to inhibit kinases much more selective than ATP-competitive compounds. The majority of the currently clinically approved small molecule protein kinase inhibitors are commonly classified as ATP-competitive inhibitors, and are able to inhibit different protein kinases with high potency. Interestingly, analysing the effect of the ATP-concentration on the IC50 of Sorafinib against different target kinases, we observed that the inhibitory potency against various target kinases is differently affected by the ATP concentration indicating differences in the exact mode of action of the inhibitor. To answer the question whether this is a specific property of Sorafenib, or also relevant for other inhibitors, we perfomed similar studies with seven additional clinically approved kinase inhibitors (Axitinib, Crizotinib, Erlotinib, Gefitinib, Lapatinib, Pazopanib and Sunitinib) using a panel of up to 16 different target protein kinases. We extended these studies and will in addition also present data investigating the influences of (a) the tags to which the respective recombinant kinase was fused, (b) the activation status of the kinase, and (c) of activating point mutations on the mode of action of the different inhibitors. Citation Format: Daniel Müller, Christian Beisenherz-Huss, Frank Totzke, Carolin Heidemann-Dinger, Constance Ketterer, Thomas Weber, Michael H.G. Kubbutat. Effects of point mutations, recombinant tags, activation status, and identity of target kinases on the mode of action of approved kinase inhibitors. [abstract]. In: Proceedings of the 104th Annual Meeting of the American Association for Cancer Research; 2013 Apr 6-10; Washington, DC. Philadelphia (PA): AACR; Cancer Res 2013;73(8 Suppl):Abstract nr 5168. doi:10.1158/1538-7445.AM2013-5168

Anaplastic lymphoma kinase (ALK) is a human receptor tyrosine kinase which has important functions in the development and maintenance of the peripheral and central nervous system. It has also been shown to be one causative agent in the development of several human malignancies including neuroblastoma, anaplastic lymphoma and non small cell lung cancer (NSCLC). One mechanism of pathological activation of ALK occurs by chromosomal translocation of the ALK gene to EML4 giving rise to an abnormal fusion protein. In order to develop small molecule inhibitors targeting ALK, in-vitro kinase assays have been developed which use recombinant ALK fragments fused to affinity tags to facilitate purification. Here we present data which demonstrate that biochemical parameters of recombinant ALK fusion proteins, like substrate specificity, ATP Km, Vmax and effects of chemical compounds, are significantly influenced by the type of affinity tag used. That influence partially persists even after cleavage of the affinity tag during the purification process. Since affinity-tagged recombinant proteins are widely used in drug discovery, a careful evaluation of potential tag-related effects should be considered. Citation Format: {Authors}. {Abstract title} [abstract]. In: Proceedings of the AACR-NCI-EORTC International Conference: Molecular Targets and Cancer Therapeutics; 2011 Nov 12-16; San Francisco, CA. Philadelphia (PA): AACR; Mol Cancer Ther 2011;10(11 Suppl):Abstract nr B121.