9th Machine Learning and AI in (Bio)Chemical Engineering Conference
06-07 July 2026​
In person-only event | Cambridge WEST Department of Computer Science and Technology
This is an annual scientific conference with scientific leadership by academic groups from University of Cambridge, Southampton University, University of Leeds, University College London, and Manchester University. The conference is hosted by the Innovation Centre in Digital Molecular Technologies (iDMT). In 2026 the conference is chaired by Professor Pietro Lio and will take place in the Department of Computer Science and Technology on Cambridge West site. This is a specialist conference, targeting developers and advanced users of AI/ML within the context of chemistry and biochemical engineering.
​​
​
Conference Agenda
TBD
Speakers
Keynote Speakers
Dr Teodoro Laino
IBM
From Transformers to Multimodal Chemistry
Invited Speakers
Dr Emma King-Smith
(The University of Edinburgh)
Fine-tuning Strategies for Deep Learning on Experimental Chemistry
Dr Carl Poelking
(Astex Pharmaceuticals)
Best or robust? AI in fragment-based drug discovery
Dr Zsuzsanna Koczor-Benda
(University of Warwick)
Property-driven computational molecular design for chemical nanoplasmonics
Accepted Speakers
​​​Kabeshov Mikhail (AstraZeneca) – Accelerating Chemical Synthesis with AI: From Chemoinformatics to Reaction and Condition Prediction
​
Lorenzo Di Fruscia (TU Delft) – Adapting and Grounding LLMs for Reaction Engineering Workflows
​
Daniel Armstrong – Agentic Rule Generation for Scalable, Deterministic Reaction Classification
​
Wenyao Lyu (UCL) – Automated Kinetic Model Discovery from Transient Electronic Absorption
Spectroscopy Data Using Sparse Identification of Nonlinear Dynamics
​
Hannes Stagge (University of Ulm) – Bayesian Design of Experiments using Parametric Models – Searching Kinetic Information
​
Abdulqader Bin Sahl (Maastricht University) – BORAG: A Bayesian Optimization with Retrieval Augmented Generation Framework for Smarter Plastic Formulations
​
Laura Hellecks (Imperial College London) – Efficient Bioprocess Development Across Scales Using Multi-Fidelity Batch Bayesian Optimisation
​
Shuyuan Zhang (University of Cambridge) – Enhancing molecular property prediction of transformer models with dual graph representation
​
Sebastian Soritz (University of Cambridge) – From Data Mining to Closed-loop Optimization in Fragment-based Drug Discovery (FBDD)
​
Alena Sheveleva (Dassault Systèmes / 3DS) – Language Models for Materials Innovation: Generative Formulation Design and Scientific Data Extraction
​
Roberto Aliaga Medina (Imperial College London) – LLM-Guided Symbolic Regression for Interpretable Kinetic Model Discovery
​
Elia Savino (University of Amsterdam) – Robochem-Flex: A Flexible and Affordable Self-Driving Laboratory for Automated Reaction Optimization
​
Jan Pavsek (RWTH Aachen University) – Thermodynamics-informed multi-task learning for single-species vapor liquid equilibria
​
Laura Ellington (Imperial College London) – Towards Bridging the Innovation-Implementation Gap in Sustainable Chemical Manufacturing​​​​​
Workshop
Generating structured data using LLM pipelines
Large language models have become remarkably capable, and hold significant promise across research workflows, ranging from literature extraction and reaction condition parsing, to reporting from high-throughput experimentation and robotic platforms. However, deploying these capabilities in production systems often demands outputs that are deterministic and machine-readable, rather than free-form text.
This workshop examines structured output generation: the principles of schema design, the distinction between constrained decoding and prompt-based approaches, and how structured outputs serve as the foundation for robust agentic workflows. Attendees will also gain hands-on implementation experience via LangChain and LangGraph.
Abstract Submission
The 9th MABC Cambridge: International Conference on Machine Learning (ML) and AI in (bio)Chemical Engineering will take place on 06-07 July 2026. We are requesting abstracts for posters and talks related to this theme. Potential topics/submissions include but are not limited to:
​
-
Software implementations of key methods
-
Experimental case studies using ML
-
Method development, particularly those that simplify user experience
-
Benchmarking of ML and AI methods
-
AI for polymer development and property predictions
-
Machine learning in life cycle analysis and process intensification
-
Coupling AI with high-throughput experimentation or robotic platforms
-
Synergies between ML and quantum computing for chemical property predictions
Abstracts may be up to 400 words and optionally include explanatory figures. We emphasise that abstracts should include sufficient introduction for newcomers.
There are still slots for oral presentation, with a deadline of 1st June​
​
There are still slots for poster presentation, with a deadline of 28th June.
Send Abstract to mab@ceb.cam.ac.uk
Sponsors
Registration
06-07 July 2026
Hosted by the University of Cambridge
Fees include access to the event, refreshments for both days and conference networking dinner in the evening of Day 1.
​
Early bird rate (£95) will finish on Friday May 16th and increase to the full rate (£150) thereafter. For any inquiries, please contact mab@ceb.cam.ac.uk.
​​​
​