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 ma-chine 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 em-ployed 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 high-lights hot topics for further development.

The emergence of nanoinformatics as a key component of nanotechnology and nanosafety assessment for the prediction of engineered nanomaterials (NMs) properties, interactions, and hazards, and for grouping and read-across to reduce reliance on animal testing, has put the spotlight firmly on the need for access to high-quality, curated datasets. To date, the focus has been around what constitutes data quality and completeness, on the development of minimum reporting standards, and on the FAIR (findable, accessible, interoperable, and reusable) data principles. However, moving from the theoretical realm to practical implementation requires human intervention, which will be facilitated by the definition of clear roles and responsibilities across the complete data lifecycle and a deeper appreciation of what metadata is, and how to capture and index it. Here, we demonstrate, using specific worked case studies, how to organise the nano-community efforts to define metadata schemas, by organising the data management cycle as a joint effort of all players (data creators, analysts, curators, managers, and customers) supervised by the newly defined role of data shepherd. We propose that once researchers understand their tasks and responsibilities, they will naturally apply the available tools. Two case studies are presented (modelling of particle agglomeration for dose metrics, and consensus for NM dissolution), along with a survey of the currently implemented metadata schema in existing nanosafety databases. We conclude by offering recommendations on the steps forward and the needed workflows for metadata capture to ensure FAIR nanosafety data.

Chemoinformatics has developed efficient ways of representing chemical structures for small molecules as simple text strings, simplified molecular-input line-entry system (SMILES) and the IUPAC International Chemical Identifier (InChI), which are machine-readable. In particular, InChIs have been extended to encode formalized representations of mixtures and reactions, and work is ongoing to represent polymers and other macromolecules in this way. The next frontier is encoding the multi-component structures of nanomaterials (NMs) in a machine-readable format to enable linking of datasets for nanoinformatics and regulatory applications. A workshop organized by the H2020 research infrastructure NanoCommons and the nanoinformatics project NanoSolveIT analyzed issues involved in developing an InChI for NMs (NInChI). The layers needed to capture NM structures include but are not limited to: core composition (possibly multi-layered); surface topography; surface coatings or functionalization; doping with other chemicals; and representation of impurities. NM distributions (size, shape, composition, surface properties, etc.), types of chemical linkages connecting surface functionalization and coating molecules to the core, and various crystallographic forms exhibited by NMs also need to be considered. Six case studies were conducted to elucidate requirements for unambiguous description of NMs. The suggested NInChI layers are intended to stimulate further analysis that will lead to the first version of a “nano” extension to the InChI standard.

A literature curated dataset containing 24 distinct metal oxide (Me_xO_y) nanoparticles (NPs), including 15 physicochemical, structural and assay-related descriptors, was enriched with 62 atomistic computational descriptors and exploited to produce a robust and validated in silico model for prediction of NP cytotoxicity. The model can be used to predict the cytotoxicity (cell viability) of Me_xO_y NPs based on the colorimetric lactate dehydrogenase (LDH) assay and the luminometric adenosine triphosphate (ATP) assay, both of which quantify irreversible cell membrane damage. Out of the 77 total descriptors used, 7 were identified as being significant for induction of cytotoxicity by Me_xO_y NPs. These were NP core size, hydrodynamic size, assay type, exposure dose, the energy of the Me_xO_y conduction band (E_C), the coordination number of the metal atoms on the NP surface (Avg. C.N. Me atoms surface) and the average force vector surface normal component of all metal atoms (v⊥ Me atoms surface). The significance and effect of these descriptors is discussed to demonstrate their direct correlation with cytotoxicity. The produced model has been made publicly available by the Horizon 2020 (H2020) NanoSolveIT project and will be added to the project’s Integrated Approach to Testing and Assessment (IATA).

The varied transcriptomic response to nanoparticles has hampered the understanding of the mechanism of action. Here, by performing a meta-analysis of a large collection of transcriptomics data from various engineered nanoparticle exposure studies, we identify common patterns of gene regulation that impact the transcriptomic response. Analysis identifies deregulation of immune functions as a prominent response across different exposure studies. Looking at the promoter regions of these genes, a set of binding sites for zinc finger transcription factors C₂H₂, involved in cell stress responses, protein misfolding and chromatin remodelling and immunomodulation, is identified. The model can be used to explain the outcomes of mechanism of action and is observed across a range of species indicating this is a conserved part of the innate immune system.

The discovery and development of new drugs are extremely long and costly processes. Recent progress in artificial intelligence has made a positive impact on the drug development pipeline. Numerous challenges have been addressed with the growing exploitation of drug-related data and the advancement of deep learning technology. Several model frameworks have been proposed to enhance the performance of deep learning algorithms in molecular design. However, only a few have had an immediate impact on drug development since computational results may not be confirmed experimentally. This systematic review aims to summarize the different deep learning architectures used in the drug discovery process and are validated with further in vivo experiments. For each presented study, the proposed molecule or peptide that has been generated or identified by the deep learning model has been biologically evaluated in animal models. These state-of-the-art studies highlight that even if artificial intelligence in drug discovery is still in its infancy, it has great potential to accelerate the drug discovery cycle, reduce the required costs, and contribute to the integration of the 3R (Replacement, Reduction, Refinement) principles. Out of all the reviewed scientific articles, seven algorithms were identified: recurrent neural networks, specifically, long short-term memory (LSTM-RNNs), Autoencoders (AEs) and their Wasserstein Autoencoders (WAEs) and Variational Autoencoders (VAEs) variants; Convolutional Neural Networks (CNNs); Direct Message Passing Neural Networks (D-MPNNs); and Multitask Deep Neural Networks (MTDNNs). LSTM-RNNs were the most used architectures with molecules or peptide sequences as inputs.