Predicting Blood-Brain Barrier Passage using AWV and Machine Learning

The blood-brain barrier (BBB) is a highly selective permeability barrier that separates circulating blood from brain extracellular fluid in the central nervous system (CNS). This barrier allows the passage of water, some gases, and lipid-soluble molecules by passive diffusion, as well as the selective transport of molecules such as glucose and amino acids that are crucial for neuronal function. In this research, we present an exploratory study, where several machine learning techniques are applied to predict blood-brain barrier passage by applying molecular descriptors based on atomic vectors, obtained by MD-LOVIs software. Several techniques such as KNN-AWV(ACC= 0.712), AVNNET-AWV(ACC=0.768), Random Forest-AWV(ACC=0.776) and GBM-AWV(ACC=0.784) obtained good prediction performance. The results show that machine learning techniques are powerful tools for the prediction of this activity.