Descripció del projecte
This project aims to develop machine learning methods applied to structural biology, drug discovery and computational chemistry. The aim is to go substantially beyond the state-of-the-art in the use of machine learning and GPU computing, exploring supervised, unsupervised and reinforcement learning approaches.
We expect the candidate to participate in the development of new learning approaches and applications derived from deep learning applied to medicinal chemistry for drug discovery. By working in this project, the researcher will have access to state of the art computational resources. This project is expected to lead to discoveries that will be publishable in the highest impact scientific journals.
Some examples of applications can be seen in PlayMolecule.org, a drug discovery platform used by thousands of scientists worldwide and pharmas and biotech companies. The platform is based on two main pillars, physical-based molecular simulations on GPUs and machine learning/AI, thus contributing to the company mission of accelerating the transition towards computerized drug discovery process. The platform was born in 2017 and serves as a repository of web applications for molecular modelling tools such as ProteinPrepare [Martínez-Rosell2017; doi:10.1021/acs.jcim.7b00190] and pioneering deep learning applications such as Kdeep [Jiménez2018; doi:10.1021/acs.jcim.7b00650].
You will closely work with Acellera scientists and medicinal chemistry to help developing new tools for drug discovery.
