Close
Go To Macao Polytechnic University

Research Seminar: Machine Learning-based Binding Affinity Prediction for Protein- ligand Complexes

To facilitate academic discussion and collaboration, Dr. Debby Wang, followed by her affiliated research team from the School of Science and Technology of the Hong Kong Metropolitan University, was invited to visit the Centre for Artificial Intelligence Driven Drug Discovery (AIDD) on the afternoon of August 22nd. They participated in a research seminar held by AIDD Centre, and the theme was "Machine Learning-based Binding Affinity Prediction for Protein-ligand Complexes." The seminar was hosted by Dr. Tang, the director of AIDD Centre, and attended by faculty and students from AIDD Centre.

The seminar proceeded in two main parts:

At first, during the meeting, Dr. Wang shared several effective feature representation methods based on her research topic, "Target-specific BAP and drug efficacy exploration in studies of non-small-cell lung (NSCL) cancer," which focuses on protein-ligand interaction fingerprint patterns. These methods have achieved good results in affinity prediction. In the long term, these predictive models will have a positive impact on virtual screening, lead optimization, and drug repositioning.

Following that, Dr. Tang briefly introduced the establishment process, development direction, and prospects of AIDD Centre. And Dr. Guo from AIDD Centre shared her personal experience and recent research outcomes about the allosteric mechanisms of drug-target proteins.

After the presentations, there was in-depth discussion and interaction among the attending faculty members, expressing their willingness and direction for further collaboration. It is believed that this academic seminar will deepen mutual understanding and foster stronger connections between the two academic teams. Additionally, it also enhances students' knowledge and awareness of machine learning algorithms, further providing us with new perspectives and directions for future learning and research.

 

Top Top