AI/ML-Enabled Drug Discovery of MYC-MAX Inhibitors

High Level Description 

MYC, a key member of the Myc-proto-oncogene family, plays a crucial role in regulating many cell functions. However, it is also the main driver in more than 50% of human cancers, making the MYC oncogene one of the most important and sought-after drug targets in cancer research. Despite years of research, there are no clinically viable MYC inhibitor today and MYC has traditionally been described as “undruggable” due to its intrinsically disordered protein structure, which lacks both binding pocket and enzymatic activity. However, MYC’s function is dependent on heterodimerization with its obligate partner, MAX to activate transcription. As a result, inhibiting the interaction between MYC and MAX has become a key strategy, making the identification of small molecule inhibitors that disrupt this interaction critical in the development of MYC-targeted cancer therapies.

Therefore, this thesis shall focus on leveraging AI and Machine Learning algorithms to speed-up drug discovery and development by identifying small molecules capable of inhibiting the interaction between the MYC and MAX.

Project Description 

In this project, a data-driven approach will be used to research and implement the most suitable AI/ML techniques for identifying potential MYC-MAX inhibitors.

The thesis will begin with the collection or exploration of existing relevant datasets (if they are not available at the start of the project), focusing on small molecules known to interact with MYC-MAX or similar protein-protein interactions. If necessary, the collected data will need to be cleaned and pre-processed to prepare the data for training the machine learning models. Following this, feature engineering will be applied to transform the raw chemical structure data into formats that can be understood by machine learning algorithms. The selection of molecular representations—such as Molecular Descriptors, Molecular Fingerprints, or graph-based representations like Graph Neural Networks (GNNs)—should be carefully evaluated based on the nature of the dataset and the specific problem at hand.

Once these molecular representations are established, one or more machine learning models such as classification, regression or deep learning models will be developed using appropriate tools and frameworks. The performance of the model will then be evaluated using appropriate metrics and hyperparameter optimization techniques will be employed to fine-tune the models for optimal performance.

Who are we looking for?

We are looking for a master's student with knowledge in Artificial Intelligence, Machine Learning and bioinformatics. You should have a passion and a strong interest in applying AI to drug discovery. This thesis is suitable for students pursuing M.Sc. in Medical Biotechnology, Molecular Biotechnology, Bioinformatics, Computational Biology or an equivalent field.

Purpose

The purpose of the thesis is to apply AI and Machine Learning algorithms to identify small molecule inhibitors that disrupt the MYC-MAX interaction. The thesis aims to demonstrate how AI/ML can be leveraged to speed-up drug discovery and contribute to the fight against cancers driven by MYC.

The thesis project can be published and used in your personal portfolio as well as in company marketing. Include Resumé/CV and cover letter in your application.