Unified drug-target interaction thermodynamic Markov model using stochastic entropies to predict multiple drugs side effects

Most of present molecular descriptors consider just the molecular structure. In the present article we pretend extending the use of Markov chain (MC) models to define novel molecular descriptors, which consider in addition other parameters like target site or toxic effect. Specifically, this molecular descriptor takes into consideration not only the molecular structure but the specific system the drug affects too. Herein, it is developed a general Markov model that describes 21 different drugs side effects grouped in 10 affected biological systems for 193 drugs, being 311 cases finally. The data were processed by linear discriminant analysis (LDA) classifying drugs according to their specific side effects, forward stepwise was fixed as strategy for variables selection. The average percentage of good classification and number of compounds used in the training/predicting sets were 92.6/91.7% for cardiovascular manifestation (25 out of 27)/(18 out of 20); 89.3/83.9% for dermal manifestations (25 out of 18)/(18 out of 21); 88.9/88.9% for endocrine manifestations (16 out of 18)/(12 out of 14); 88.9/88.2% for psychiatric manifestations (32 out of 36)/(24 out of 27); 88.5/85.6% for systemic phenomena (23 out of 26)/(17 out of 20); 85.7/91.7% for gastrointestinal manifestations (36 out of 42)/(29 out of 32); 83.3/79.2% for metabolic manifestations (15 out of 18)/(11 out of 14); 81.8/78.0% for neurological manifestations (27 out of 33)/(20 out of 25); 75.0/74.0% for hematological manifestations (36 out of 48)/(27 out of 36) and 74.3/72.8% for breathing manifestations (26 out of 35)/(19 out of 26). Finally, application of back-projection analysis (BPA) provides physic interpretation in structural terms through molecular graphics of the toxic effects predicted with these QSTR models. This article develops a mathematical model that encompasses a large number of drugs side effects grouped in specifics systems using stochastic entropies of interaction (Θk (j)) by the first time.