Do you want to screen several billions of commercially available molecules in just a few days at low cost?
Are you looking for a virtual screening method that can handle even the largest and most diverse chemical libraries?
Iktos is pleased to introduce DockAI, a new technology that combines docking with a state-of-the-art active learning methodology to significantly improve the efficiency and effectiveness of this process.
With the advent of make-on-demand commercial libraries, the number of purchasable compounds available for virtual screening has grown exponentially in recent years, with several libraries containing over one billion compounds. These ultralarge libraries offer a wealth of potential hit compounds, but traditional docking approaches that score every compound individually can be cost-prohibitive and time-consuming. That’s where DockAI comes in.
Active Learning Methodology
Our unique active learning methodology enables us to select the most informative compounds from the virtual library by only docking less than 1% of the full database. Iktos active learning approach allows to recover 75% of the known active molecules in this benchmark study when docking less than 1% of the database. This approach of combining docking and AI allows us to reduce the computing costs by 100 fold, without compromising on the hit rate.
Robust Docking Pipeline
In addition to our active learning methodology, DockAI also utilizes a robust docking pipeline that has been carefully designed and tested to handle even the largest and most diverse chemical libraries. We also propose structure preparation and structure-based model development services to optimize the quality of the docking, as well as post-processing of the docking output using state-of-the-art selection and free energy prediction methods to provide you with an optimal list of compounds for synthesis and testing purposes. With DockAI, you can confidently and efficiently search ultralarge libraries or virtual compounds for hit discovery in less than a day.