Alan Kai Hassen


Nationality: German

Project descriptionThe modern organic synthesis is subject to yield, reliability, safety, hazard analysis, control performance, environmental quality, etc., apart from the major goal of achieving economic efficiency. Those outcomes are often measured in different scales and are non-commensurate, therefore they cannot be combined into a single, meaningful scalar objective function suited for conventional optimization techniques. ESR will work on developing multi- objective optimization approaches for simultaneously design new compounds and their synthetic route planning. The major outcomes are expected to be  development of the methodology of multi-objective synthesis planning; development of publicly available software for building and using models for retrosynthesis; benchmarking of the method with the state-of-the-art algorithms for retrosynthesis planning in collaboration with other ESRs.

Personal Introduction: I am a PhD researcher in the Advanced Machine Learning for Innovative Drug Discovery (AIDD) consortium, focusing on (multi-objective) computer-aided synthesis planning.

I hold an MSc and BSc in Information Systems from the University of Münster, Germany, where I focused on artificial intelligence, data science, and process management. In my master thesis, I examined how to recover the molecular structure from different chemical fingerprints using machine learning. I was co-supervised by Professor Glorius (chemistry department) and Professor Kuchen (computer science department). My MA-level research encouraged me to pursue a PhD at the intersection of life sciences and computer science, an application-oriented field that allows me to discover solutions to complex, real-world problems.

My research focuses on computer-aided synthesis planning, which aims to discover building plans for molecules to be used by chemists. Given that there are multiple possible solutions to synthesize desired molecules, it is essential to offer alternative synthesis plans to chemists that represent a trade-off between different selected synthesis route properties. In my research, I focus on measuring these route properties, improving contemporary route finding methods, and transferring this knowledge to a real-world lab setting. The ultimate goal of my research is to improve a critical part of the current drug discovery pipeline.

In my research, I combine state-of-the-art methods from computer science and cheminformatics with feedback from lab chemists. In particular, I use (graph) neural networks to better capture chemical information and reinforcement learning to improve the synthesis finding capabilities of current approaches.

Contact: GitHub LinkedIn Twitter


Universiteit Leiden, June 1st, 2021 - November 30th, 2023

Bayer Research, December 1st , 2022 - May 30th, 2024

    ULEI           Bayer

Secondments:  AstraZeneca AB, Sweden, August  - October 2022