Scholars Central

Short communicationPublished 16 Sep 2020

Protein-Ligand Binding Affinity Prediction: quantifying the entropic contribution with artificial intelligence and quantum chemistry

Authors: Evangelidis T

Ask about this article

Abstract

Select any words in the title or abstract, or press this and choose a sentence.

Despite the advances in synthetic chemistry and ligand binding assay technologies, the time and cost of synthesizing and testing thousands of compounds is prohibitive. Herein, will be presented deepScaffOpt algorithm for highly accurate, 1-sec fast, 2D-ligand based binding affinity prediction with minimal human input. deepScaffOpt employs artificial intelligence to build “on the fly” a receptor-specific Meta-Predictor that combines the output of multiple deep neural networks, which are engineered from feature vectors (“warheads”) carrying information only about 2D chemical structure. The arsenal of deepScaffOpt comprises warheads suitable for a wide range of molecules, including macrocycles, covalent inhibitors, peptidomimetics, even small fragments. deepScaffOpt’s automated scoring protocol achieved top performance in D3R Grand Challenges 2017 & 2018, and could predict free energies significantly closer to the experimental ones than Free Energy Perturbations (FEP). Unlike structure-based methods, deepScaffOpt can work well in the absence of receptor structure, and can be easily adapted for virtual screening of large chemical libraries to discover new diverse hit compounds, as well as off-target prediction and drug repurposing. However, in the absence of training samples, one must resort to first principles. Therefore, we develop in parallel semiempirical quantum mechanical (SQM) free energy methods [2]. We have demonstrated the superiority of SQM scoring protocols in native pose recognition and hit identification over the most widely used docking scoring functions on a variety of systems where binding was dominated by Enthalpy. A new SQM-based ligand conformational Entropy descriptor was recently introduced, which can be coupled both with physics based and machine learning methods for superior performance. In the case studies that will be shown in this presentation, Enthalpy alone failed to explain inhibitory activity, but SQMscoring enhanced with the Entropy descriptor reversed the situation. Analogous effects were observed when the Entropy descriptor was incorporated into deepScaffOpt’s warheads.

Ask about this article

Answers come only from this article's title, abstract and keywords, each sentence pointing to where it comes from. Your question is sent to OpenAI to write the answer. Scholars Central does not store it.

Try:

Similar by topic

More from this journal

The newest in Journal of Pharmacogenomics & Pharmacoproteomics.

All its articles

Conferences in this field

Upcoming conferences in this field.

Follow

New articles from what you follow go into your email digest, once you agree to alert emails.

  • JournalJournal of Pharmacogenomics & Pharmacoproteomics
  • SubjectPharmaceutical Sciences
  • BylineArticles whose byline prints “Evangelidis T”

For authors and organisers

Publish, present and keep up with your field

Find the right journal for your paper and submit your manuscript.

Photo: Pexels