• Submission system is now closed. We are looking forward to meeting you at the workshop.

Enzyme design with machine learning represents a transformative approach in biotechnology, leveraging computational power to tackle the intricate challenge of creating or optimizing enzymes for specific functions. However, despite significant progress, many challenges remain unresolved, and the success rate of such endeavors remains relatively low. Issues such as the accurate modeling of enzyme dynamics, the scarcity of high-quality training data, and the complexity of protein function prediction hinder the reliability and scalability of machine learning approaches. Additionally, bridging the gap between in silico predictions and experimental validation often reveals limitations in current computational tools. For these reasons, the full potential of machine learning in enzyme design and engineering is yet to be realized. This highlights the need for continued innovation and interdisciplinary efforts to overcome these hurdles and unlock transformative applications in biotechnology.

We welcome submissions of posters. Technical topics of interest include (but are not limited to):

• De novo enzyme design
• Machine learning-assisted directed evolution
• Protein representation with ML
• Enzyme discovery and function prediction
• Molecular dynamics and docking
• Enzyme property prediction
• Biocatalytic retrosynthesis
• Laboratory automation
• High-throughput experimentation

Poster requirements: A1 format.