Applying pattern recognition methods plus quantum and physico‐chemical molecular descriptors to analyze the anabolic activity of structurally diverse steroids

Abstract

The great cost associated with the development of new anabolic-androgenic steroid (AASs) makes necessary the development of computational methods that shorten the drug discovery pipeline. Toward this end, quantum, and physicochemical molecular descriptors, plus linear discriminant analysis (LDA) were used to analyze the anabolic/androgenic activity of structurally diverse steroids and to discover novel AASs, as well as also to give a structural interpretation of their anabolic-androgenic ratio (AAR). The obtained models are able to correctly classify 91.67% (86.27%) of the AASs in the training (test) sets, respectively. The results of predictions on the 10% full-out cross-validation test also evidence the robustness of the obtained model. Moreover, these classification functions are applied to an "in house" library of chemicals, to find novel AASs. Two new AASs are synthesized and tested for in vivo activity. Although both AASs are less active than some commercially AASs, this result leaves a door open to a virtual variational study of the structure of the two compounds, to improve their biological activity. The LDA-assisted QSAR models presented here, could significantly reduce the number of synthesized and tested AASs, as well as could increase the chance of finding new chemical entities with higher AAR.

Computational chemistry study of 3D‐structure‐function relationships for enzymes based on Markov models for protein electrostatic, HINT, and van der Waals potentials

“…The present model showed a 74.18% average predictability. This level of accuracy is usually considered as very good by researchers using LDA-QSAR models 22 ; we have to take into consideration that the model is linear and it uses only two variables while the previously reported D&D models 3 are nonlinear SVMs and they used 30-50 parameters to obtain a similar accuracy.…”

Using entropy of drug and protein graphs to predict FDA drug-target network: Theoretic-experimental study of MAO inhibitors and hemoglobin peptides from Fasciola hepatica

“…These collections are atoms with a common characteristic as for instance are: halogens (X), heteroatom (Het), hydrogen atom bonded to one heteroatom (H-Het) or protein region (protein region). In Table 1 [65,66].…”

Anabolic and androgenic activities of 19-nor-testosterone steroids: QSAR study using quantum and physicochemical molecular descriptors

“…In pharmacological activity determination were used thirty male Wistar rats (21 ± 23 days old, body weight: 50-90 g) maintained seven days with food and water available ad libitum. In the determination of the anabolic and androgenic activities, researchers isolated three organs from each rat: the seminal vesicle (SV), the ventral prostate (VP), and the levator ani muscle (LA) [22].…”

“…Recently, we reported multi-linear regression (MLR) QSAR models for congeneric series of AAS: 17␤-hydroxy-5␣-androstane [19], 4,5␣-dihydrotestosterone [20] and testosterone [21] steroid families. We reported too a robust biosilico model of linear discriminant analysis (LDA) [22]. This model was used to analyze the anabolic-androgenic activities of structurally diverse steroids and to discover novel AAS, as well as to give a structural interpretation of their AAR.…”