Prediction of compound-target interaction using several artificial intelligence algorithms and comparison with a consensus-based strategy.

For understanding a chemical compound's mechanism of action and its side effects, as well as for drug discovery, it is crucial to predict its possible protein targets. This study examines 15 developed target-centric models (TCM) employing different molecular descriptions and machine learning algorithms. They were contrasted with 17 third-party models implemented as web tools (WTCM). In both sets of models, consensus strategies were implemented as potential improvement over individual predictions. The findings indicate that TCM reach f1-score values greater than 0.8. Comparing both approaches, the best TCM achieves values of 0.75, 0.61, 0.25 and 0.38 for true positive/negative rates (TPR, TNR) and false negative/positive rates (FNR, FPR); outperforming the best WTCM. Moreover, the consensus strategy proves to have the most relevant results in the top 20 % of target profiles. TCM consensus reach TPR and FNR values of 0.98 and 0; while on WTCM reach values of 0.75 and 0.24. The implemented computational tool with the TCM and their consensus strategy at: https://bioquimio.udla.edu.ec/tidentification01/ . Scientific Contribution: We compare and discuss the performances of 17 public compound-target interaction prediction models and 15 new constructions. We also explore a compound-target interaction prioritization strategy using a consensus approach, and we analyzed the challenging involved in interactions modeling.

A chemical analysis of the Pelargonium species: P. odoratissimum, P. graveolens, and P. zonale identifies secondary metabolites with activity against gram-positive bacteria with multidrug-resistance.

The Pelargonium genus encompasses around 280 species, most of which are used for medicinal purposes. While P. graveolens, P. odoratissimum, and P. zonale are known to exhibit antimicrobial activity, there is an evident absence of studies evaluating all three species to understand their chemical differences and biological effects. Through the analysis of the hydroalcoholic extracts of P. graveolens, P. odoratissimum, and P. zonale, using HPLC-DAD-MS/MS, quercetin and kaempferol derivatives were identified in these three species. Conversely, gallotannins and anthocyanins were uniquely detected in P. zonale. P. graveolens stood out due to the various types of myricetin derivatives that were not detected in P. odoratissimum and P. zonale extracts. Evaluation of their biological activities revealed that P. zonale displayed superior antibacterial and antibiofilm activities in comparison to the other two species. The antibacterial efficacy of P. zonale was observed towards the clinically relevant strains of Staphylococcus aureus ATCC 25923, Methicillin-resistant Staphylococcus aureus (MRSA) 333, Enterococcus faecalis ATCC 29212, and the Vancomycin-resistant E. faecalis INSPI 032. Fractionation analysis of P. zonale suggested that the antibacterial activity attributed to this plant is due to the presence of quercetin derivatives and kaempferol and its derivatives, alongside their synergistic interaction with gallotannins and anthocyanins. Lastly, the three Pelargonium species exhibited notable antioxidant activity, which may be attributed to their high content of total phenolic compounds.

Unraveling druggable cancer-driving proteins and targeted drugs using artificial intelligence and multi-omics analyses.

The druggable proteome refers to proteins that can bind to small molecules with appropriate chemical affinity, inducing a favorable clinical response. Predicting druggable proteins through screening and in silico modeling is imperative for drug design. To contribute to this field, we developed an accurate predictive classifier for druggable cancer-driving proteins using amino acid composition descriptors of protein sequences and 13 machine learning linear and non-linear classifiers. The optimal classifier was achieved with the support vector machine method, utilizing 200 tri-amino acid composition descriptors. The high performance of the model is evident from an area under the receiver operating characteristics (AUROC) of 0.975 ± 0.003 and an accuracy of 0.929 ± 0.006 (threefold cross-validation). The machine learning prediction model was enhanced with multi-omics approaches, including the target-disease evidence score, the shortest pathways to cancer hallmarks, structure-based ligandability assessment, unfavorable prognostic protein analysis, and the oncogenic variome. Additionally, we performed a drug repurposing analysis to identify drugs with the highest affinity capable of targeting the best predicted proteins. As a result, we identified 79 key druggable cancer-driving proteins with the highest ligandability, and 23 of them demonstrated unfavorable prognostic significance across 16 TCGA PanCancer types: CDKN2A, BCL10, ACVR1, CASP8, JAG1, TSC1, NBN, PREX2, PPP2R1A, DNM2, VAV1, ASXL1, TPR, HRAS, BUB1B, ATG7, MARK3, SETD2, CCNE1, MUTYH, CDKN2C, RB1, and SMARCA4. Moreover, we prioritized 11 clinically relevant drugs targeting these proteins. This strategy effectively predicts and prioritizes biomarkers, therapeutic targets, and drugs for in-depth studies in clinical trials. Scripts are available at https://github.com/muntisa/machine-learning-for-druggable-proteins .

Eco-alternative treatments for Vibrio parahaemolyticus and V. cholerae biofilms from shrimp industry through Eucalyptus (Eucalyptus globulus) and Guava (Psidium guajava) extracts: A road for an Ecuadorian sustainable economy.

Understanding how environmental variables influence biofilm formation becomes relevant for managing Vibrio biofilm-related infections in shrimp production. Therefore, we evaluated the impact of temperature, time, and initial inoculum in the biofilm development of these two Vibrio species using a multifactorial experimental design. Planktonic growth inhibition and inhibition/eradication of Vibrio biofilms, more exactly V. parahaemolyticus (VP87 and VP275) and V. cholerae (VC112) isolated from shrimp farms were evaluated by Eucalyptus and Guava aqueous leaf extracts and compared to tetracycline and ceftriaxone. Preliminary results showed that the best growth conditions of biofilm development for V. parahaemolyticus were 24 h and 24°C (p <0.001), while V. cholerae biofilms were 72 h and 30°C (p <0.001). Multivariate linear regression ANOVA was applied using colony-forming unit (CFU) counting assays as a reference, and R-squared values were applied as goodness-of-fit measurements for biofilm analysis. Then, both plant extracts were analyzed with HPLC using double online detection by diode array detector (DAD) and mass spectrometry (MS) for the evaluation of their chemical composition, where the main identified compounds for Eucalyptus extract were cypellogin A, cypellogin B, and cypellocarpin C, while guavinoside A, B, and C compounds were the main compounds for Guava extract. For planktonic growth inhibition, Eucalyptus extract showed its maximum effect at 200 µg/mL with an inhibition of 75% (p < 0.0001) against all Vibrio strains, while Guava extract exhibited its maximum inhibition at 1600 µg/mL with an inhibition of 70% (p < 0.0001). Both biofilm inhibition and eradication assays were performed by the two conditions (24 h at 24°C and 72 h at 30°C) on Vibrio strains according to desirability analysis. Regarding 24 h at 24°C, differences were observed in the CFU counting between antibiotics and plant extracts, where both plant extracts demonstrated a higher reduction of viable cells when compared with both antibiotics at 8x, 16x, and 32x MIC values (Eucalyptus extract: 1600, 3200, and 6400 µg/mL; while Guava extract: 12800, 25600, and 52000 µg/mL). Concerning 72 h at 30°C, results showed a less notorious biomass inhibition by Guava leaf extract and tetracycline. However, Eucalyptus extract significantly reduced the total number of viable cells within Vibrio biofilms from 2x to 32x MIC values (400-6400 µg/mL) when compared to the same MIC values of ceftriaxone (5-80 µg/mL), which was not able to reduce viable cells. Eucalyptus extract demonstrated similar results at both growth conditions, showing an average inhibition of approximately 80% at 400 µg/mL concentration for all Vibrio isolates (p < 0.0001). Moreover, eradication biofilm assays demonstrated significant eradication against all Vibrio strains at both growth conditions, but biofilm eradication values were substantially lower. Both extract plants demonstrated a higher reduction of viable cells when compared with both antibiotics at 8x, 16x, and 32x MIC values at both growth sets, where Eucalyptus extract at 800 µg/mL reduced 70% of biomass and 90% of viable cells for all Vibrio strains (p < 0.0001). Overall results suggested a viable alternative against vibriosis in the shrimp industry in Ecuador.