Machine Learning Search of Novel Selective NaV1.2 and NaV1.6 Inhibitors as Potential Treatment Against Dravet Syndrome

FALLICO, M.; ALBERCA, L.N.; PRADA GORI, D.; GAVERNET, L.; TALEVI, A.

Workshop; III Latin American Workshop in Computational Neuroscience (LAWCN 2021); 2021

Federal University of Maranhão

Abstract. Dravet syndrome is a type of drug-resistant and devastating childhoodepilepsy, which begins in the first year of life. Etiologically, it is most frequentlyassociated with loss-of-function de novo mutations in the gene SCN1A,which encodes for the NaV1.1 channel, a voltage-operated sodium channelhighly expressed in inhibitoryGABAergic interneurons.Dysfunction of this channelcauses global hyperexcitability. Whereas exacerbation of seizures in Dravetpatients has been observed after the administration of voltage-operated sodiumchannel blockers with low or no selectivity towards specific channel subtypes,recent preclinical evidence suggests that highly selective blockade of sodiumchannels other than NaV1.1 or the selective activation of NaV1.1 could correctAQ2 the Dravet phenotype.Here, we report the development and validation of ligand-based computationalmodels for the identification of selective NaV1.2 or NaV1.6 with no inhibitoryeffect on NaV1.1. The models have been jointly applied to screen the chemicallibrary of the DrugBank 5.1.8 database, in order to select starting points forthe development of specific drugs against Dravet syndrome. The ligand-basedmodels were built using free software for molecular descriptor calculation (Mordred)in combination with in-house Python scripts. Training data was retrievedfrom ChemBL and specialized literature, and representatively sampled using anin- house clustering procedure (RaPCA). Linear classifiers were generated usinga combination of the random subspace method (feature bagging) and forwardstepwise. Later, ensemble learning was used to obtain meta-classifiers, whichwere validated in retrospective screening experiments before their use in the final,AQ34 prospective screen.