Evaluation of non-commercial models for genotoxicity and carcinogenicity in the assessment of EFSA's databases

Multitask Deep Neural Networks for Ames Mutagenicity Prediction

The Ames mutagenicity test constitutes the most frequently used assay to estimate the mutagenic potential of drug candidates. While this test employs experimental results using various strains of Salmonella typhimurium, the vast majority of the published in silico models for predicting mutagenicity do not take into account the test results of the individual experiments conducted for each strain. Instead, such QSAR models are generally trained employing overall labels (i.e., mutagenic and nonmutagenic). Recently, neural-based models combined with multitask learning strategies have yielded interesting results in different domains, given their capabilities to model multitarget functions. In this scenario, we propose a novel neural-based QSAR model to predict mutagenicity that leverages experimental results from different strains involved in the Ames test by means of a multitask learning approach. To the best of our knowledge, the modeling strategy hereby proposed has not been applied to model Ames mutagenicity previously. The results yielded by our model surpass those obtained by single-task modeling strategies, such as models that predict the overall Ames label or ensemble models built from individual strains. For reproducibility and accessibility purposes, all source code and datasets used in our experiments are publicly available.

Artificial Intelligence, Machine Learning, and Deep Learning in Real-Life Drug Design Cases

The discovery and development of drugs is a long and expensive process with a high attrition rate. Computational drug discovery contributes to ligand discovery and optimization, by using models that describe the properties of ligands and their interactions with biological targets. In recent years, artificial intelligence (AI) has made remarkable modeling progress, driven by new algorithms and by the increase in computing power and storage capacities, which allow the processing of large amounts of data in a short time. This review provides the current state of the art of AI methods applied to drug discovery, with a focus on structure- and ligand-based virtual screening, library design and high-throughput analysis, drug repurposing and drug sensitivity, de novo design, chemical reactions and synthetic accessibility, ADMET, and quantum mechanics.

Biodiversity and dairy traits of lactic acid bacteria from foliage of aromatic plants before and after dehydration process monitored by a smart sensors system

The main hypothesis of this work was to evaluate the presence of lactic acid bacteria (LAB) intrinsically resistant to plant essential oils in sage (Salvia officinalis L.) and laurel (Laurus nobilis), for future applications in functional cheese production by addition of aromatic herbs. The effect of the drying process on the viability of LAB was evaluated with three biomass densities (3, 4 and 5 kg/m2). The drying densities did not affect weight loss, but influenced the levels of LAB of sage and laurel. A total of 10 different strains of Enterococcus faecium, Enterococcus mundtii, Enterococcus raffinosus and Leuconostoc mesenteroides were identified from laurel, while sage did not host any LAB species. In particular, L. mesenteroides was the only species sensitive to the heat treatment. Only five strains, all enterococci, were resistant to at least one antibiotic, even though no strain showed gelatinase or haemolytic activity. The investigation on the technological traits useful in cheese making demonstrated that all LAB can be considered non starter LAB, because they were characterized by a slow acidification capacity (the pH was still above 6.00 after 3 d) and a very limited autolysis (the maximum decrease of the optical density at 599 nm was barely 0.2).