摘要: This perspective concerns the methods employed within current drug discovery community to develop predictive quantitative structure–activity relationships (QSAR). Specifically, a number of cautions are provided which may circumvent misuse and misunderstanding technique. Ignorance such caveats has led discouraging tendency result in poorly models. Among these pitfalls fondness with we associate correlation causation, mesmerizing influence large numbers molecular descriptors, incessant leave-one-out paradigm, finally, QSAR enigma wherein model predictivity is not necessary component model’s usefulness.