Hologram QSAR model for the prediction of human oral bioavailability.

摘要: Abstract A drug intended for use in humans should have an ideal balance of pharmacokinetics and safety, as well potency selectivity. Unfavorable can negatively affect the clinical development many otherwise promising candidates. variety silico ADME (absorption, distribution, metabolism, excretion) models are receiving increased attention due to a better appreciation that pharmacokinetic properties be considered early phases discovery process. Human oral bioavailability is important property, which directly related amount available systemic circulation exert pharmacological therapeutic effects. In present work, hologram quantitative structure–activity relationships (HQSAR) were performed on training set 250 structurally diverse molecules with known human bioavailability. The most significant HQSAR model (q2 = 0.70, r2 = 0.93) was obtained using atoms, bond, connection, chirality fragment distinction. predictive ability evaluated by external test containing 52 not included set, predicted values good agreement experimental values. useful design new candidates having process chemical library design, virtual screening, high-throughput screening.