Search

A previously developed model to predict antibacterial activity of ionic liquids against a resistant A. baumannii strain was used to assess activity of phosphonium ionic liquids. Their antioxidant potential was additionally evaluated with newly developed models, which were based on public data. The accuracy of the models was rigorously evaluated using cross-validation as well as test set prediction. Six alkyl triphenylphosphonium and alkyl tributylphosphonium bromides with the C8, C10, and C12 alkyl chain length were synthesized and tested in vitro. Experimental studies confirmed their activity against A. baumannii as well as showed pronounced antioxidant properties. These results suggest that phosphonium ionic liquids could be promising lead structures against A. baumannii.

Melanogenesis is the chemical process responsible for synthesizing melanin, which occurs in melanocytes, in subcellular lysosome-like organelles called melanosomes. Melanin plays a vital role in protecting the skin from damage caused by ultraviolet rays. However, excess melanin production or abnormal distribution can cause various pigmentation disorders, such as over-tanning, age spots, and melasma. Skin disorders like these, have prompted the development of skin-whitening compounds to reduce melanin content. Furthermore, inhibition of melanin synthesis is considered a valid therapeutic strategy for treating advanced melanotic melanomas Human tyrosinase (hsTYR) is the most important enzyme involved in the melanogenesis process, as it catalyzes, at least, its first two steps. Tyrosinase from the white button mushroom Agaricus bisporus (abTYR) has been widely available at low cost from commercial sources for several decades, whereas hsTYR is still expensive and difficult to produce. The importance of discovering more and better hsTYR inhibitors has been widely discussed, as when tested against hsTYR, several abTYR inhibitors provide disappointing results, including some of the most extensively used depigmenting compounds now used in dermocosmetics. An in silico methodology that can be used to predict compound bioactivities is QSAR (quantitative structure-activity relationship) modelling. A QSAR model tries to find correlations between a biological activity of interest and molecular descriptors calculated from the compound structure. In this work, a QSAR model was developed to predict hsTYR inhibition activity using the PYTHON computer language and its PyQSAR package. To develop a QSAR model, a library of 196 known hsTYR inhibitors was gathered, and compounds were divided into 6 groups according to their scaffold structure. A total of 33 QSAR models were prepared using different combinations of the defined groups and different pools of molecular descriptors. QSAR model 32 was selected for further use as it presented good statistical robustness and had the highest number of compounds, 41 in total. Of the 28,933 molecular descriptors calculated by the OCHEM platform for the 41 compounds used, PyQSAR selected 4 to be used in the model: C-026; DISSM2C; MaxdssC; WHALES90_Rem. The statistical data obtained after the validation of the QSAR model by cross-validation was excellent, namely the determination coefficient (R2CV=0.9147), the value of the square root of the mean error (RMSE CV=0.1878) and the mean value of the score of the multiple linear regression method (Q2CV=0.8922). This QSAR model originates a mathematical equation that allows the prediction of hsTYR inhibition activity by new compounds with similar structures. A library of natural compounds, with a structure similar to those used to develop QSAR model 32, was created using the COCONUT database of natural compounds. A total of 1,628 natural compounds were gathered, their molecular descriptors were calculated, and the QSAR model 32 equation was applied. The results are displayed on a website and can be viewed by accessing the URL http://esa.ipb.pt/qsar/. The ZINC15 database was used to determine which of the compounds in the developed natural compound library would be available for purchase after predicting the hsTYR inhibitory activity of each compound in the library. A total of 18 different compounds were bought from different companies. To evaluate these compounds experimental ability to inhibit hsTYR and thus validate QSAR model 32, the compounds will be tested against this enzyme. If those compounds activity is confirmed, they may be used in cosmeceutical applications. A melanogénese é o processo químico responsável pela síntese da melanina, que ocorre nos melanócitos, em organelos subcelulares semelhantes aos lisossomas chamados melanossomas. A melanina desempenha um papel vital na proteção da pele dos danos causados pelos raios ultravioleta. No entanto, a produção excessiva de melanina ou distribuição anormal pode causar vários distúrbios de pigmentação, como bronzeamento excessivo, manchas senis e melasma. Distúrbios de pele como estes levaram ao desenvolvimento de compostos de clareamento da pele para reduzir o conteúdo de melanina. Além disso, a inibição da síntese de melanina é considerada uma estratégia terapêutica válida para o tratamento de melanomas melanóticos avançados A tirosinase humana (hsTYR) é a enzima mais importante envolvida no processo de melanogénese, pois catalisa, pelo menos, as suas duas primeiras etapas. A tirosinase do cogumelo branco Agaricus bisporus (abTYR) está amplamente disponível a baixo custo em fontes comerciais há várias décadas, enquanto a hsTYR ainda é cara e difícil de produzir. A importância de descobrir mais e melhores inibidores de hsTYR tem sido amplamente discutida, pois quando testados contra hsTYR, vários inibidores de abTYR fornecem resultados dececionantes, incluindo alguns dos compostos despigmentantes mais usados atualmente em dermocosméticos. Uma metodologia in silico que pode ser usada para prever bioatividades compostas é a modelação QSAR (quantitative structure-activity relationship). Um modelo QSAR tenta encontrar correlações entre uma atividade biológica de interesse e descritores moleculares calculados a partir da estrutura do composto. Neste trabalho, um modelo QSAR foi desenvolvido para prever a atividade de inibição de hsTYR usando a linguagem de computador PYTHON e seu pacote PyQSAR. Para desenvolver um modelo QSAR, uma biblioteca de 196 inibidores hsTYR conhecidos foi reunida e os compostos foram divididos em 6 grupos de acordo com sua estrutura de base. Um total de 33 modelos QSAR foram preparados usando diferentes combinações dos grupos definidos e diferentes pools de descritores moleculares. O modelo QSAR 32 foi selecionado para uso posterior por apresentar boa robustez estatística e possuir o maior número de compostos, 41 no total. Dos 28 933 descritores moleculares calculados pela plataforma OCHEM para os 41 compostos utilizados, o PyQSAR selecionou 4 para serem utilizados no modelo: C-026; DISSM2C; MaxdssC; WHALES90_Rem. Os dados estatísticos obtidos após a validação do modelo QSAR por validação cruzada foram excelentes, nomeadamente o coeficiente de correlação (R2CV=0,9147), o valor da raiz quadrada do erro médio (RMSE CV=0,1878) e o valor médio da pontuação do método de regressão linear múltipla (Q2CV=0,8922). Este modelo QSAR origina uma equação matemática que permite prever a atividade de inibição de hsTYR por novos compostos com estruturas semelhantes. Uma biblioteca de compostos naturais, com uma estrutura similar àquelas usadas para desenvolver o modelo QSAR 32, foi criada usando o banco de dados de compostos naturais COCONUT. Um total de 1 628 compostos naturais foram recolhidos, os seus descritores moleculares calculados e a equação do modelo QSAR 32 foi aplicada. Os resultados são apresentados num website criado por nós e podem ser visualizados acedendo ao URL http://esa.ipb.pt/qsar/. O banco de dados ZINC15 foi usado para determinar quais compostos na biblioteca de compostos naturais desenvolvidos estariam disponíveis para compra após prever a atividade inibitória de hsTYR de cada composto na biblioteca. Um total de 18 compostos diferentes foram comprados de diferentes empresas. Para avaliar a capacidade experimental destes compostos em inibir a hsTYR e assim validar o modelo QSAR 32, os compostos serão testados contra esta enzima. Caso a atividade desses compostos seja confirmada, eles poderão ser utilizados em aplicações cosmecêuticas.

A possibility to accurately predict the absorption maximum wavelength of BODIPYs was investigated. We found that previously reported models had a low accuracy (40–57 nm) to predict BODIPYs due to the limited dataset sizes and/or number of BODIPYs (few hundreds). New models developed in this study were based on data of 6000-plus fluorescent dyes (including 4000-plus BODIPYs) and the deep neural network architecture. The high prediction accuracy (five-fold cross-validation room mean squared error (RMSE) of 18.4 nm) was obtained using a consensus model, which was more accurate than individual models. This model provided the excellent accuracy (RMSE of 8 nm) for molecules previously synthesized in our laboratory as well as for prospective validation of three new BODIPYs. We found that solvent properties did not significantly influence the model accuracy since only few BODIPYs exhibited solvatochromism. The analysis of large prediction errors suggested that compounds able to have intermolecular interactions with solvent or salts were likely to be incorrectly predicted. The consensus model is freely available at https://ochem.eu/article/134921 and can help the other researchers to accelerate design of new dyes with desired properties.

AlphaScreen is one of the most widely used assay technologies in drug discovery due to its versatility, dynamic range and sensitivity. However, a presence of false positives and frequent hitters contributes to difficulties with an interpretation of measured HTS data. Although filters do exist to identify frequent hitters for AlphaScreen, they are frequently based on privileged scaffolds. The development of such filters is time consuming and requires deep domain knowledge. Recently, machine learning and artificial intelligence methods are emerging as important tools to advance drug discovery and chemoinformatics, including their application to identification of frequent hitters in screening assays. However, the relative performance and complementarity of the Machine Learning and scaffold-based techniques has not yet been comprehensively compared. In this study, we analysed filters based on the privileged scaffolds with filters built using machine learning. Our results demonstrate that machine-learning methods provide more accurate filters for identification of frequent hitters in AlphaScreen assays than scaffold-based methods and can be easily redeveloped once new data are measured. We present highly accurate models to identify frequent hitters in AlphaScreen assays.

Online Chemical Modeling Environment (OCHEM) was used for QSAR analysis of a set of ionic liquids (ILs) tested against multi-drug resistant (MDR) clinical isolate Acinetobacter baumannii and Staphylococcus aureus strains. The predictive accuracy of regression models has coefficient of determination q2 = 0.66 − 0.79 with cross-validation and independent test sets. The models were used to screen a virtual chemical library of ILs, which was designed with targeted activity against MDR Acinetobacter baumannii and Staphylococcus aureus strains. Seven most promising ILs were selected, synthesized, and tested. Three ILs showed high activity against both these MDR clinical isolates.

The problem of designing new antitubercular drugs against multiple drug‐resistant tuberculosis (MDR‐TB) was addressed using advanced machine learning methods. As there are only few published measurements against MDR‐TB, we collected a large literature data set and developed models against the non‐resistant H37Rv strain. The predictive accuracy of these models had a coefficient of determination q2=.7–.8 (regression models) and balanced accuracies of about 80% (classification models) with cross‐validation and independent test sets. The models were applied to screen a virtual chemical library, which was designed to have MDR‐TB activity. The seven most promising compounds were identified, synthesized and tested. All of them showed activity against the H37Rv strain, and three molecules demonstrated activity against the MDR‐TB strain. The docking analysis indicated that the discovered molecules could bind enoyl reductase, InhA, which is required in mycobacterial cell wall development. The models are freely available online (http://ochem.eu/article/103868) and can be used to predict potential anti‐TB activity of new chemicals.

QSAR analysis of a set of previously synthesized phosphonium ionic liquids (PILs) tested against Gram-negative multidrug-resistant clinical isolate Acinetobacter baumannii was done using the Online Chemical Modeling Environment (OCHEM). To overcome the problem of overfitting due to descriptor selection, fivefold cross-validation with variable selection in each step of the model development was applied. The predictive ability of the classification models was tested by cross-validation, giving balanced accuracies (BA) of 76%-82%. The validation of the models using an external test set proved that the models can be used to predict the activity of newly designed compounds with a reasonable accuracy within the applicability domain (BA = 83%-89%). The models were applied to screen a virtual chemical library with expected activity of compounds against MDR Acinetobacter baumannii. The eighteen most promising compounds were identified, synthesized, and tested. Biological testing of compounds was performed using the disk diffusion method in Mueller-Hinton agar. All tested molecules demonstrated high anti-A. baumannii activity and different toxicity levels. The developed classification SAR models are freely available online at http://ochem.eu/article/113921 and could be used by scientists for design of new more effective antibiotics.

Online Chemical Modeling Environment (OCHEM) was used for QSAR analysis of a set of ionic liquids (ILs) tested against multi-drug resistant (MDR) clinical isolate Acinetobacter baumannii and Staphylococcus aureus strains. The predictive accuracy of regression models has coefficient of determination q2 = 0.66 &minus, 0.79 with cross-validation and independent test sets. The models were used to screen a virtual chemical library of ILs, which was designed with targeted activity against MDR Acinetobacter baumannii and Staphylococcus aureus strains. Seven most promising ILs were selected, synthesized, and tested. Three ILs showed high activity against both these MDR clinical isolates.

Inorganic nanomaterials have become one of the new areas of modern knowledge and technology and have already found an increasing number of applications. However, some nanoparticles show toxicity to living organisms, and can potentially have a negative influence on environmental ecosystems. While toxicity can be determined experimentally, such studies are time consuming and costly. Computational toxicology can provide an alternative approach and there is a need to develop methods to reliably assess Quantitative Structure Property Relationships for nanomaterials (nano-QSPRs). Importantly, development of such models requires careful collection and curation of data. This article overviews freely available nano-QSPR models, which were developed using the Online Chemical Modeling Environment (OCHEM). Multiple data on toxicity of nanoparticles to different living organisms were collected from the literature and uploaded in the OCHEM database. The main characteristics of nanoparticles such as chemical composition of nanoparticles, average particle size, shape, surface charge and information about the biological test species were used as descriptors for developing QSPR models. QSPR methodologies used Random Forests (WEKA-RF), k-Nearest Neighbors and Associative Neural Networks. The predictive ability of the models was tested through cross-validation, giving cross-validated coefficients q(2) = 0.58-0.80 for regression models and balanced accuracies of 65-88% for classification models. These results matched the predictions for the test sets used to develop the models. The proposed nano-QSPR models and uploaded data are freely available online at http://ochem.eu/article/103451 and can be used for estimation of toxicity of new and emerging nanoparticles at the early stages of nanomaterial development.

A matched molecular pair (MMP) analysis was used to examine the change in melting point (MP) between pairs of similar molecules in a set of ∼275k compounds. We found many cases in which the change in MP (ΔMP) of compounds correlates with changes in functional groups. In line with the results of a previous study, correlations between ΔMP and simple molecular descriptors, such as the number of hydrogen bond donors, were identified. In using a larger dataset, covering a wider chemical space and range of melting points, we observed that this method remains stable and scales well with larger datasets. This MMP-based method could find use as a simple privacy-preserving technique to analyze large proprietary databases and share findings between participating research groups.

BACKGROUND: QSAR is an established and powerful method for cheap in silico assessment of physicochemical properties and biological activities of chemical compounds. However, QSAR models are rather complex mathematical constructs that cannot easily be interpreted. Medicinal chemists would benefit from practical guidance regarding which molecules to synthesize. Another possible approach is analysis of pairs of very similar molecules, so-called matched molecular pairs (MMPs). Such an approach allows identification of molecular transformations that affect particular activities (e.g. toxicity). In contrast to QSAR, chemical interpretation of these transformations is straightforward. Furthermore, such transformations can give medicinal chemists useful hints for the hit-to-lead optimization process. RESULTS: The current study suggests a combination of QSAR and MMP approaches by finding MMP transformations based on QSAR predictions for large chemical datasets. The study shows that such an approach, referred to as prediction-driven MMP analysis, is a useful tool for medicinal chemists, allowing identification of large numbers of "interesting" transformations that can be used to drive the molecular optimization process. All the methodological developments have been implemented as software products available online as part of OCHEM (http://ochem.eu/). CONCLUSIONS: The prediction-driven MMPs methodology was exemplified by two use cases: modelling of aquatic toxicity and CYP3A4 inhibition. This approach helped us to interpret QSAR models and allowed identification of a number of "significant" molecular transformations that affect the desired properties. This can facilitate drug design as a part of molecular optimization process. Graphical AbstractMolecular matched pairs and transformation graphs facilitate interpretable molecular optimisation process.