. De novo drug design is a computational approach that generates novel molecular structures from atomic building blocks with no a priori relationships. Conventional methods include structure-based and ligand-based design, which depend on the properties of the active site of a biological target or its known active binders, respectively. Artificial intelligence, including machine learning, is an emerging field that has positively impacted the drug discovery process. Deep reinforcement learning is a subdivision of machine learning that combines artificial neural networks with reinforcement-learning architectures. This method has successfully been employed to develop novel de novo drug design approaches using a variety of artificial networks including recurrent neural networks, convolutional neural networks, generative adversarial networks, and autoencoders. This review article summarizes advances in de novo drug design, from conventional growth algorithms to advanced machine-learning methodologies and highlights hot topics for further development.

No abstract

The neurotoxicity of hard metal‐based nanoparticles (NPs) remains poorly understood. Here, we deployed the human neuroblastoma cell line SH‐SY5Y differentiated or not into dopaminergic‐ and cholinergic‐like neurons to study the impact of tungsten carbide (WC) NPs, WC NPs sintered with cobalt (Co), or Co NPs versus soluble CoCl2. Co NPs and Co salt triggered a dose‐dependent cytotoxicity with an increase in cytosolic calcium, lipid peroxidation, and depletion of glutathione (GSH). Co NPs and Co salt also suppressed glutathione peroxidase 4 (GPX4) mRNA and protein expression. Co‐exposed cells were rescued by N‐acetylcysteine (NAC), a precursor of GSH, and partially by liproxstatin‐1, an inhibitor of lipid peroxidation. Furthermore, in silico analyses predicted a significant correlation, based on similarities in gene expression profiles, between Co‐containing NPs and Parkinson's disease, and changes in the expression of selected genes were validated by RT‐PCR. Finally, experiments using primary human dopaminergic neurons demonstrated cytotoxicity and GSH depletion in response to Co NPs and CoCl2 with loss of axonal integrity. Overall, these data point to a marked neurotoxic potential of Co‐based but not WC NPs and show that neuronal cell death may occur through a ferroptosis‐like mechanism.

BackgroundMultiple high-throughput molecular profiling by omics technologies can be collected for the same individuals. Combining these data, rather than exploiting them separately, can significantly increase the power of clinically relevant patients subclassifications.ResultsWe propose a multi-view approach in which the information from different data layers (views) is integrated at the levels of the results of each single view clustering iterations. It works by factorizing the membership matrices in a late integration manner. We evaluated the effectiveness and the performance of our method on six multi-view cancer datasets. In all the cases, we found patient sub-classes with statistical significance, identifying novel sub-groups previously not emphasized in literature. Our method performed better as compared to other multi-view clustering algorithms and, unlike other existing methods, it is able to quantify the contribution of single views on the final results.ConclusionOur observations suggest that integration of prior information with genomic features in the subtyping analysis is an effective strategy in identifying disease subgroups. The methodology is implemented in R and the source code is available online at http://neuronelab.unisa.it/a-multi-view-genomic-data-integration-methodology/.Electronic supplementary materialThe online version of this article (doi:10.1186/s12859-015-0680-3) contains supplementary material, which is available to authorized users.