In the field of computational chemistry, computer models are quickly and cheaply constructed to predict toxicology hazards and results, with no need for test material or animals as these computational predictions are often based on physicochemical properties of chemical structures. Multiple methodologies are employed to support in silico assessments based on machine learning (ML) and deep learning (DL). This review introduces the development of computational toxicology, focusing on ML and DL and emphasizing their importance in the field of toxicology. A fine balance between target potency, selectivity, absorption, distribution, metabolism, excretion, toxicity (ADMET) and clinical safety properties should be achieved to discover a potential new drug. It is advantageous to perform virtual predictions as early as possible in drug development processes, even before a molecule is synthesized. Currently, there are numerous commercially available and free web-based programs for toxicity prediction, which can be used to construct various predictive models. The key features of the QSAR method are also outlined, and the selection of appropriate physicochemical descriptors is a prerequisite for robust predictions. In addition, examples of open-source tools applied to toxicity prediction are included, as well as examples of the application of different computational methods for the prediction of toxicity in drug design and environmental toxicology.

In this study, molecular topology was used to develop several discriminant equations capable of classifying compounds according to their antibacterial activity. Topological indices were used as structural descriptors and their relation to antibacterial activity was determined by applying linear discriminant analysis (LDA) on a group of quinolones and quinolone-like compounds. Four equations were constructed, named DF1, DF2, DF3, and DF4, all with good statistical parameters such as Fisher–Snedecor’s F (over 25 in all cases), Wilk’s lambda (below 0.36 in all cases) and percentage of correct classification (over 80% in all cases), which allows a reliable extrapolation prediction of antibacterial activity in any organic compound. From the four discriminant functions, it can be extracted that the presence of sp³ carbons, ramifications, and secondary amine groups in a molecule enhance antibacterial activity, whereas the presence of 5-member rings, sp² carbons, and sp² oxygens hinder it. The results obtained clearly reveal the high efficiency of combining molecular topology with LDA for the prediction of antibacterial activity.

Currently, the development of resistance of Enterobacteriaceae bacteria is one of the most important health problems worldwide. Consequently, there is a growing urge for finding new compounds with antibacterial activity. Furthermore, it is very important to find antibacterial compounds with a good pharmacokinetic profile too, which will lead to more efficient and safer drugs. In this work, we have mathematically described a series of antibacterial quinolones by means of molecular topology. We have used molecular descriptors and related them to various pharmacological properties by using multilinear regression (MLR) analysis. The regression functions selected by presenting the best combination of a number of quality and validation metrics allowed for the reliable prediction of clearance (CL), and minimum inhibitory concentration 50 against Enterobacter aerogenes (MIC50Ea) and Proteus mirabilis (MIC50Pm). The obtained results clearly reveal that the combination of molecular topology methods and MLR provides an excellent tool for the prediction of pharmacokinetic properties and microbiological activities in both new and existing compounds with different pharmacological activities.

The variability of methicillin-resistant Staphylococcus aureus (MRSA), its rapid adaptive response against environmental changes, and its continued acquisition of antibiotic resistance determinants have made it commonplace in hospitals, where it causes the problem of multidrug resistance. In this study, we used molecular topology to develop several discriminant equations capable of classifying compounds according to their anti-MRSA activity. Topological indices were used as structural descriptors and their relationship with anti-MRSA activity was determined by applying linear discriminant analysis (LDA) on a group of quinolones and quinolone-like compounds. Four extra equations were constructed, named DF_MRSA1, DF_MRSA2, DF_MRSA3 and DF_MRSA4 (DF_MRSA was built in a previous study), all with good statistical parameters, such as Fisher–Snedecor F (>68 in all cases), Wilk’s lambda (94% in all cases), which allows a reliable extrapolation prediction of antibacterial activity in any organic compound. The results obtained clearly reveal the high efficiency of combining molecular topology with LDA for the prediction of anti-MRSA activity.

Background: QSAR (Quantitative Structure–Activity Relationships) methods have been the basis for the design of new molecules with a certain activity. The great advantage of QSAR methods is that they can predict the pharmacological activity of compounds without the need to obtain or synthesize them previously. Currently, the development of antibiotic resistance by microorganisms is the most important issue in the treatment of infectious diseases. This elevated resistance is associated with expanded morbidity and mortality, as well as an increase in healthcare costs. The development of new molecules with antibacterial activity is therefore urgently needed. Methods: By means of molecular topology, we developed discriminant functions (DF1 and DF2) capable of predicting antibacterial activity. When applied to a database with 6373 chemicals, they selected 266 molecules as candidates, from which 41% have this activity, according to the bibliography. Regression equations determining pharmacokinetic properties such as mean residence time (MRT), volume of distribution (V_D), and clearance (CL) were applied to the selected molecules. Results: We have observed that most antibacterial compounds have pharmacokinetic theoretical values in the intervals 20 > MRT > 0, 3 > V_D > 0, and 500 > CL > 0. We have applied these intervals to our antibacterial model with the objective of finding new antibacterials with a good pharmacokinetic profile. We show that they are an effective tool for discriminating antibacterial compounds, increasing the bibliographic success rate to 50.8, 59, and 61.5%, respectively. When drug-like filters are applied to these new models, the vast majority (89.9–100%) of the selected molecules present antibacterial activity. Conclusions: Considering these results, these new models could avoid the application of drug-likeness filters when searching for new potential antibacterials. All of this proves the usefulness of these mathematical–topological models.

In this paper, a multilinear regression (MLR) analysis has been carried out in order to accurately predict physicochemical properties and biological activities on a group of antibacterial quinolones by means of a set of structural descriptors called topological indices. The aim of this work is to develop prediction equations for these properties after collecting the maximum number of data from the literature on antibacterial quinolones. The five regression functions selected by presenting the best combination of various statistical parameters, subsequently validated by means of internal validation (intercorrelation, Y-randomization and leave-one-out cross-validation tests), allowed the reliable prediction of minimum inhibitory concentration 50 versus Staphylococcus aureus (MIC50Sa), Streptococcus pyogenes (MIC50Spy) and Bacteroides fragilis (MIC50Bf), mean residence time (MRT) after oral administration and volume of distribution (V_D). We conclude that the combination of molecular topology methods and MLR provides an excellent tool for the prediction of pharmacological properties.