Orion Pharma, Orionintie 1 A, 02101, Espoo, Finland.
Mol Inform. 2021 Sep;40(9):e2100089. doi: 10.1002/minf.202100089. Epub 2021 Jun 1.
The software macHine leArning booSTEd dockiNg (HASTEN) was developed to accelerate structure-based virtual screening using machine learning models. It has been validated using datasets both from literature (12 datasets, each containing three million molecules docked with FRED) and in-house sources (one dataset of four million compounds docked with Glide). HASTEN showed reasonable performance by having the mean recall value of 0.78 of the top one percent scoring molecules after docking 10 % of the dataset for the literature data, whereas excellent recall value of 0.95 was achieved for the in-house data. The program can be used with any docking- and machine learning methodology, and is freely available from https://github.com/TuomoKalliokoski/HASTEN.
基于机器学习的对接加速（HASTEN）软件是为了加速基于结构的虚拟筛选而开发的，它使用机器学习模型进行验证。该软件已经通过文献（包含 12 个数据集，每个数据集包含 300 万个用 FRED 对接的分子）和内部来源（一个包含 400 万个用 Glide 对接的化合物的数据集）的数据进行了验证。在对接文献数据的 10%的数据集后，HASTEN 的平均召回值为 0.78，在前 1%得分分子中排名合理，而对于内部数据则达到了优秀的 0.95 召回值。该程序可以与任何对接和机器学习方法一起使用，并可从 https://github.com/TuomoKalliokoski/HASTEN 免费获得。
