Artificial Intelligence-Accelerated Drug Discovery on the SpiNNaker2 Platform

Mentored by Jens Meiler, Christian Mayr
at Leipzig University

The development of a new therapeutic takes 10-20 years and costs billions of dollars, hampering the development of drugs for third-world diseases, neglected/rare diseases, or diseases caused by personal mutations, for example in cancer. Artificial Intelligence (AI) is poised to reduce both, cost and timeline, for key therapeutics with the potential to help millions of patients. This proposal develops key AI algorithms to tackle this challenge:

The advent of modern AI-based protein prediction tools combined with massive libraries of readily-available, ‘make-on-demand’ small molecules open up the path to a transformative in silico-first paradigm in drug discovery. While the readily accessible chemical space rapidly expands to billions out of 1060 estimated drug-like molecules, methods to prioritize high-affinity drug candidates are facing computational limits. Quantum Mechanical (QM) methods, which offer the most accurate biophysical description of drug properties, are too computationally intensive for ultra-large library screening, i.e. testing the billions of ‘make-on-demand’ small molecules. We propose an innovative approach to overcome this limitation by developing AI-accelerated drug discovery methods leveraging the neuromorphic, massively-parallel SpiNNaker2 platform.

Starting with basic QSAR models based on feed-forward neural networks, we will investigate how best to scale up models and take advantage of the SpiNNaker2 hardware in order to design screening algorithms custom-tailored to the architecture. Combined with a protocol to model protein variants, we will establish a pipeline for rapid personalized drug discovery.

The PhD candidate will work on these research objectives:

1. Develop Ultra-large library screening on SpiNNaker2
2. Development of Quantum Chemical 3D Descriptors for QSAR Modeling
3. Implement DFT acceleration on SpiNNaker2

This interdisciplinary project leverages Prof. Montufar's expertise in developing MPNN architectures with inductive biases specifically designed to capture the mathematical foundations of frustration calculations. His knowledge in geometric deep learning will enable neural networks that respect the physical constraints governing protein frustration. Prof. Meiler's expertise will guide the application of these models to protein engineering and antiviral development.

Building upon foundations established in Prof. Meiler's lab on FrustraMPNN, this project will bring frustration prediction into a design methodology for viral proteins. The approach has potential to advance both viral mechanism understanding and protein design by addressing the stability-function tradeoff in current methods.

Work Environment

You will be working with both PIs to implement drug discovery algorithms on Spinnaker2. Your algorithms will be used for drug discovery. Molecules will be synthesized and tested for biological activity on a number of application projects. Current application projects include drug development for neurological diseases including Schizophrenia, Alzheimer's, and Parkinson’s, probing the fundamentals of G-protein-coupled receptor signaling, understanding cardiac arrhythmia as caused by the complex interplay of potassium channel regulation and drug interactions, multidrug resistance in cancer and bacterial cells related to multidrug transporter proteins, and the structural basis of viral infections and antibody activity, among others.

SECAI offers a first-class environment for advancing your career. You can work with internationally renowned researchers and benefit from the school’s strong networks in industry and research. The graduation of highly qualified researchers is a central project goal in SECAI and doctoral students receive strong support for their professional and personal development.

Prerequisites

• Master's Degree (or equivalent) in bioinformatics, computational biology, mathematics, or related field
• Background in structural biology or protein biophysics
• Programming skills and interest in software/hardware integration
• Excellent communication skills and ability to work in interdisciplinary teams