Applied Machine Learning & AI for Synthetic Biology

Learning Outcomes

This module delivers comprehensive, hands-on training in machine learning approaches, from the fundamental concepts underlying ML technologies to advanced themes such as large language models (LLMs), specifically tailored for application in synthetic biological systems. The primary focus is on equipping students with robust ML competencies, exploring core concepts such as explorative data analysis, dimensionality reduction, decision trees and regression models, leading up to more complex techniques such as neural networks, deep learning, generative AI, and LLMs. Students will learn how to leverage these data-driven strategies to solve complex synthetic biology challenges, with a strong emphasis on biological sequence optimization, pathway engineering, and whole-system design. The module also addresses the crucial, emerging regulatory and standardization frameworks governing AI in biotechnology, including aspects such as Open and Sustainable AI. Through interactive coding sessions and a practical “Bring Your Own Data” workshop, participants will actively train their computational skills, leaving with the practical experience needed to drive AI-assisted innovation in synthetic biology.

Upon completion the students will be able to:

• to interrogate, clean, and compress high-dimensional biological datasets to prepare them for advanced computational modeling.
• to build, train, and tune predictive machine learning models tailored to synthetic biology applications.
• to leverage advanced AI to optimize biological sequences and engineer novel metabolic pathways.
• navigate data scarcity and privacy concerns using cutting-edge decentralized and synthetic frameworks.
• critically audit AI models for bias and ensure compliance with emerging bio-economy regulations and open science principles.
• to independently design and execute a complete, AI-assisted synthetic biology research project from end to end.

Module Syllabus

• Foundations of ML in Biology & Exploratory Data Analysis (EDA)
• Dimensionality Reduction and Unsupervised Learning
• Fundamental Predictive Modeling: Regression and Decision Trees
• Introduction to Neural Networks and Deep Learning
• Deep Learning for Biological Sequence Optimization
• Generative AI for Pathway Engineering
• Synthetic Data Generation and Digital Twins
• Assessment of AI: Benchmarking and Indicators in Biology
• AI Regulations, Ethics, and Open Science
• Use Cases of ML in Synthetic Biology
• “Bring Your Own Data” (BYOD) – Workshop

Suggested Bibliography

• Relevant literature per lecture, including scientific publications and reviews from international journals, which is available in the course e-class.
• “Deep Learning for the Life Sciences: Applying Deep Learning to Genomics, Microscopy, Drug Discovery, and More”, by Bharath Ramsundar and Peter Eastman, O’Reilly, 2019.
• “Machine Learning in Bioinformatics”, Edited by Yanqing Zhang and Jagath C. Rajapakse, Springer, 2020.
• “Introduction to Machine Learning for Biologists”, Tarca AL, Bioinformatics, 2019.