Extreme Gradient Boosting as a Method for Quantitative Structure-Activity Relationships

In the pharmaceutical industry it is common to generate many QSAR models from training sets containing a large number of molecules and a large-number of descriptors. The best QSAR methods are those that can generate the most accurate predictions but that are not overly expensive computationally. In this paper we compare eXtreme Gradient Boosting (XGBoost) to random forest and single-task deep neural nets on 30 in-house data sets. While XGBoost has many adjustable parameters, we can define a set of standard parameters at which XGBoost makes predictions, on the average, better than those of random forest and almost as good as those of deep neural nets. The biggest strength of XGBoost is its speed. Whereas efficient use of random forest requires generating each tree in parallel on a duster, and deep neural nets are usually run on GPUs, XGBoost can be tun on a single CPU in less than a third of the wall-clock time of either of the other methods.