The binding energy predictions were highly correlated with r2 = 0.88, F = 692.4, SEE = 0.775, and P-value < 0.0001 for selected blood-brain barrier choline transporter (BBB-ChT)-active/inactive compounds (n = 93). Both programs were able to cluster active (Gibbs free energy of binding < -6.0 kcal/mol and inactive (Gibbs free energy of binding > -6.0 kcal/mol) molecules and dock them significantly better than at random with an area under the curve value of 0.86 and 0.84, respectively. In ranking smaller molecules with few torsional bonds and the small number of heavy atoms (< 20), a size-related bias in scoring producing false-negative outcomes was detected.
- Badges
- Science topic
- Similar topics
- Mathematics
More Sergey Shityakov's questions See All
Similar questions and discussions