The interest in the application of machine learning techniques (MLT) as drug design tools is growing in the last decades. The reason for this is related to the fact that the drug design is very complex and requires the use of hybrid techniques. A brief review of some MLT such as self-organizing maps, multilayer perceptron, bayesian neural networks, counter-propagation neural network and support vector machines is described in this paper. A comparison between the performance of the described methods and some classical statistical methods (such as partial least squares and multiple linear regression) shows that MLT have significant advantages. Nowadays, the number of studies in medicinal chemistry that employ these techniques has considerably increased, in particular the use of support vector machines. The state of the art and the future trends of MLT applications encompass the use of these techniques to construct more reliable QSAR models. The models obtained from MLT can be used in virtual screening studies as well as filters to develop/discovery new chemicals. An important challenge in the drug design field is the prediction of pharmacokinetic and toxicity properties, which can avoid failures in the clinical phases. Therefore, this review provides a critical point of view on the main MLT and shows their potential ability as a valuable tool in drug design.

No abstract

No abstract

The purpose of our work was to select phages displaying peptides capable of binding to vascular markers present in human atheroma, and validate their capacity to target the vascular markers in vitro and in low-density lipoprotein receptor knockout (LDLr−/−) mouse model of atherosclerosis. By peptide fingerprinting on human atherosclerotic tissues, we selected and isolated four different peptides sequences, which bind to atherosclerotic lesions and share significant similarity to known human proteins with prominent roles in atherosclerosis. The CTHRSSVVC-phage peptide displayed the strongest reactivity with human carotid atherosclerotic lesions (p < 0.05), when compared to tissues from normal carotid arteries. This peptide sequence shares similarity to a sequence present in the fifth scavenger receptor cysteine-rich (SRCR) domain of CD163, which appeared to bind to CD163, and subsequently, was internalized by macrophages. Moreover, the CTHRSSVVC-phage targets atherosclerotic lesions of a low-density lipoprotein receptor knockout (LDLr−/−) mouse model of atherosclerosis in vivo to High-Fat diet group versus Control group. Tetraazacyclododecane-1,4,7,10-tetraacetic acid-CTHRSSVVC peptide (DOTA-CTHRSSVVC) was synthesized and labeled with 111InCl3 in >95% yield as determined by high performance liquid chromatography (HPLC), to validate the binding of the peptide in atherosclerotic plaque specimens. The results supported our hypothesis that CTHRSSVVC peptide has a remarkable sequence for the development of theranostics approaches in the treatment of atherosclerosis and other diseases.

In a series of tritrophic-level interaction experiments, the effect of selected host plants of the spider mites, Tetranychus evansi and Tetranychus urticae, on Neozygites floridana was studied by evaluating the attachment of capilliconidia, presence of hyphal bodies in the infected mites, mortality from fungal infection, mummification and sporulation from fungus-killed mite cadavers. Host plants tested for T. evansi were tomato, cherry tomato, eggplant, nightshade, and pepper while host plants tested for T. urticae were strawberry, jack bean, cotton and Gerbera. Oviposition rate of the mites on each plant was determined to infer host plant suitability while host-switching determined antibiosis effect on fungal activity. T. evansi had a high oviposition on eggplant, tomato and nightshade but not on cherry tomato and pepper. T. urticae on jack bean resulted in a higher oviposition than on strawberry, cotton and Gerbera. Attachment of capilliconidia to the T. evansi body, presence of hyphal bodies in infected T. evansi and mortality from fungal infection were significantly higher on pepper, nightshade and tomato. The highest level of T. evansi mummification was observed on tomato. T. evansi cadavers from tomato and eggplant produced more primary conidia than those from cherry tomato, nightshade and pepper. Switching N. floridana infected T. evansi from one of five Solanaceous host plants to tomato had no prominent effect on N. floridana performance. For T. urticae, strawberry and jack bean provided the best N. floridana performance when considering all measured parameters. Strawberry also had the highest primary conidia production. This study shows that performance of N. floridana can vary with host plants and may be an important factor for the development of N. floridana epizootics.

No abstract

No abstract

No abstract