| About this Abstract |
| Meeting |
2024 TMS Annual Meeting & Exhibition
|
| Symposium
|
Computational Discovery and Design of Materials
|
| Presentation Title |
Enhancing Drug-target Affinity Predictions with the Binding Site-augmented DTA Framework: A Deep Learning Approach for Expedited Material Design |
| Author(s) |
Mehdi Yazdani Jahromi, Ali Khodabandeh Yalabadi, Aida Tayebi, Niloofar Yousefi, Elayaraja Kolanthai, Craig J. Neal, Sudipta Seal, Ozlem Ozmen Garibay |
| On-Site Speaker (Planned) |
Mehdi Yazdani Jahromi |
| Abstract Scope |
Artificial intelligence has been applied in different stages of drug design and development, leading to quicker and more cost-effective outcomes, compared to traditional in-silico virtual screening approaches. Besides, deep learning algorithms have shown significant improvements in the prediction of drug target interaction tasks. We proposed a deep learning-based framework, the BindingSite-AugmentedDTA.
This framework is highly generalizable, as it can be integrated with any deep learning-based regression model. It also enhances Drug-Target Affinity (DTA) predictions by identifying the most likely protein binding sites.
Computational findings indicate that this can enhance the efficiency of seven state-of-the-art DTA models by up to 20%. Additionally laboratory experiments of 13 compounds were tested in inhibiting the binding of the SARS-CoV-2 spike protein and the ACE2 receptor protein. The results were highly consistent with the model's predictions, reinforcing the potential of this framework as a valuable tool in expediting drug discovery and biomaterial design processes. |
| Proceedings Inclusion? |
Planned: |
| Keywords |
Computational Materials Science & Engineering, Machine Learning, Biomaterials |