SaaS, Big Data and Artificial Intelligence for Drug Discovery
We have developed SmartDock using Artificial Intelligence to turn docking methods into reliable virtual screening and profiling tools. Our applications greatly outperform currently available methods.
Computational docking is widely used in drug discovery for the study of protein ligand interactions and as a tool for virtual screening and virtual profiling. However, despite recent improvements in docking and scoring methods, docking calculations are still challenged by the identification of enormous amounts of false positives. To address these limitations, at Mind the Byte we have developed a brand new docking protocol: SmartDock. Among other features, it uses Artificial Intelligence to minimize the conformational energies and extracts interaction patterns from the Protein Data Bank (PDB).
Our prototype system is able to discriminate binders and non-binders from docking results based on Artificial Intelligence with striking results.
The pharmacologic impact of drugs depends on their ability to engage and occupy physiologically relevant target receptor binding sites. However, this binding is not static but dynamic and the pharmacologic action is determined by the temporal stability of the drug-target complex. Very often, drug-target residence time is directly linked to the ability of the drug to establish specific molecular interactions with the target protein.
In order to discriminate binders (true positives) and non-binders (false positives) in docking experiments, SmartDock uses information from the tons of structural data deposited on the Protein Data Bank to develop an intelligent system able to learn the pattern of interactions leading to experimental ligand-protein binding and, thus, to the desired biological effect. With this data, models for 700 protein targets have been built based on active and decoy compounds, extracting an interaction model for active compounds. Three decoys have been used for each active compound.
We have validated SmartDock with excellent results on PARP1, a protein involved in DNA damage repair and with an important role in both cancer and aging. Our software outperforms traditional enrichment processes, promoting thus the use of ligand docking methods as reliable virtual screening/profiling tools.
Thanks to this intelligent system we build ROC curves with AUCs higher than 0.9, and in the case of PARP1, AUC=0.94 (in red). This contrasts the AUC=0.74 (in blue) obtained using other docking protocols.