Peptide Computational Methods and Applications
Location: University College Dublin CECAM-IRL
Organisers
Timing: 0900h Mon 1st Sept - to 1400h Tues 2nd Sept 2025.
Location: University College Dublin main campus, Ireland.
We have some spaces left and are still considering registration applications, this is subject to capacity.
Costs: there is no registration fee to attend this workshop.
The workshop will bring together experts working in AI and peptide research. The workshop will highlight current state of the art machine learning techniques.
DAY 1
Monday 1st September 2025
0845-0915 Registration Conway Foyer.
0915-0920 Welcome Conway Lecture Theatre
0920-0950 Denis Shields, University College Dublin: “Predicting bioactive peptides.”
0950-1020 Martin Zacharias, Technical University of Munich: “Modelling Cyclic Peptides”
1020-1050 Ioana M. Ilie University of Amsterdam: “Computational engineering of Bax-inhibiting cyclic peptides”
1050-1120 Niklas Halbwedl, Technical University of Munich: “Designing Cyclic Peptides to Modulate Protein–Protein Interactions“
1120-1130 Discussion
1130-1200 Tea & coffee break, Conway Foyer
1200-1230 Anushka Pahuja, Zuse Institute Berlin: “Analysis of folding pathway of VGVAPG hexapeptide using MoKiTo”
1230-1300 Raul Fernandez-Diaz: “Partitioning, representation and automation in canonical and non-canonical peptide modelling”
1300-1400 Lunch , Conway Foyer
1400-1430 Raquel Rodriguez Perez, Novartis, Switzerland: “Uncertainty Estimation“
1430-1500 Patrick Timmons, Nuritas Ltd, Dublin: “Peptide Design for Protein Binding”
1500-1515 Discussion
1515-1545 Tea & coffee break.
1545-1615 Nuno Costa, Technical University of Munich: “'Enabling Aggregation-Prone and Morphology-Guided Peptide Discovery via Masked Conditional Generative Modeling”
1615-1715 Wolfgang Banzhaf, Michigan State University, & Aidan Murphy, University College Dublin: “Evolutionary Computation based Novel Peptide Design“ (talk sponsored by UCD AI Healthcare Hub).
1715-1745 General discussion.
1830 Dinner, University Club
Tuesday 2nd September
0830 meet in the UCD Agriculture and Food Science Building Active Learning Environment (ALE) room 1.47 on first floor (follow signs).
0830-1000 hands on workshop on choices peptide ML prediction (leader: Raul Fernandez-Diaz)
1000-1030 tea and coffee
1030-1200 workshop generative approaches (Leader Patrick Timmons).
1200-1230 Discussions of what is most needed in the field.
1240-1320 Talk (move back to Conway lecture theatre) Pierre Tuffery University Paris Diderot “Building scoring functions for peptide de-orphaning using Alphafold”
1320-1340 General discussion
1320-1500 Sitting space booked in nearby Pi cafeteria for those who wish to join for lunch which they pay for themselves.
BACKGROUND
The peptide global market is rapidly expanding with its value estimated at $14.4 billion, accounting for 1.5% of the total worldwide pharmaceutical market. These peptides are usually between 5 and 40 amino acids and have a diverse range of applications and many advantages, including their ability to be produced at a large scale. Significant advancements in synthetic and recombination technologies have been a driving force in bringing bio-active peptides back to center stage as therapeutic and diagnostic tools. However, similar advances in artificial intelligence (AI) and data analytics methods for peptides are needed.
Recent advances in structural protein prediction have enabled rapid design of proteins with desired structural properties. However, understanding how to design proteins with specific functional or multi-functional properties is still challenging. This is critically important for smaller proteins – peptides – where there is often less secondary or tertiary structure to predict, and the functionality has a great dependence on extrinsically bound factors.
It is clear that new computational technology is needed to meet the requirements of the community that leverages the AI advances seen in protein modelling. However, peptide datasets are generally much smaller than protein training datasets, making it harder to build relevant AI representations, especially for non-canonical amino acids. To successfully scale AI in peptide studies, collaboration is necessary that integrates activities of data collection, software development, transfer learning and implementation.
Much of the critical data during drug development of peptide leads comprises datasets of relatively few compounds in a particular class with relevant key assays. AI approaches can support iterative experimentation and computation approaches that accelerate the design of peptides of interest.
We welcome attendees interested in these topics, and who may be interested to present a talk or poster on related topics, including but not limited to:
-
Discovering peptides with target structures or functions.
-
Discovering linear, cyclic or other rigid structure peptides.
-
Creating peptides with unusual amino acids.
-
Discovering regulatable peptides or multi-functional peptides.
-
Using large language models (LLMs), protein language models. (PLMs) or chemical language models (CLMs) to improve peptide machine learning.
-
Generative AI.
-
Explainable AI applied to peptide analysis and prediction.
-
Open-source software.
-
Best practices & legal issues for peptide AI drug development.
-
AI with uncertainty in assay measurement
-
Active learning for selection of important peptide training cases in low data experiments.
-
Human in the loop AI for fitness evaluation.
-
Dataset augmentation using generative AI.
-
Approximate/partial peptide discovery.
-
Data curation.
-
Collaboration methods.
-
Visualization methods.
-
GUI based tools.
-
Human computer interaction design principles needed for peptide design.
-
Tools to visualize/inform trade-offs in peptide functions.
-
Peptide search space visualization methods.
-
AI methods to ensure peptide safety (e.g. lowering toxicity, ensuring stability).
-
Collaboration to overcome the hurdle of small dataset sizes, including federated learning across distributed proprietary datasets.
References
Indrani Bera (UCD) - Organiser
Raul Fernandez-Diaz (University College Dublin | IBM Research) - Organiser
Aidan Murphy (University College Dublin) - Organiser
Denis Shields (University College Dublin) - Organiser