Machine Learning for Protein Engineering – Part 2 banner

In silico prediction, engineering and design are changing the way drugs will be discovered, designed and optimized in the future. These tools are still in their early development and much needs to be learned on how to adapt them for use in antibody and vaccine discovery, training, prediction, developability, simulation and optimization.

Scientific Advisory Board:
     M. Frank Erasmus, PhD, Head, Bioinformatics, Specifica, Inc. 
     Victor Greiff, PhD, Associate Professor, Oslo University Hospital
     Maria Wendt, PhD, Global Head and Vice President, Digital and Biologics Strategy and Innovation, Sanofi
 

Recommended Short Course*
Monday, 13 November, 14:00 – 17:00
SC1: Machine Learning Tools for Protein Engineering
*Separate registration required. See short courses page for details. All short courses take place in-person only.

Thursday, 16 November

Registration Open and Morning Coffee07:30

PLM AND GENERATIVE MODELING FOR DE NOVO DESIGN

08:55

Chairperson's Remarks

Victor Greiff, PhD, Associate Professor, Immunology, University of Oslo

09:00

Enhancing Antibody Discovery with Generative AI

Melody Shahsavarian, PhD, Digital Biologics Platform, Large Molecules Research, Sanofi

With a growing majority of its pipeline composed of biologics, there is an increasing need at Sanofi to bring more molecules to development at a faster pace. Generative AI and in silico screening methods provide opportunities to improve probability of success and decrease discovery-to-lead timelines. Combining deep repertoire mining technologies and generative ML modeling, we are building a de novo protein design platform and a more targeted drug discovery approach.

09:30

The Singular Immune Response to Dengue and Machine Learning Identification of Antibodies in High-Throughput Sequences

Enkelejda Miho, PhD, Professor, University of Applied Sciences and Arts Northwestern Switzerland, and Managing Director, aiNET

Dengue virus is a threat to global health. However, no specific therapeutics are available so far. Broadly neutralizing antibodies recognizing the various serotypes could serve as potential treatment. High-throughput adaptive immune receptor repertoire high-throughput sequencing (AIRR-seq) and bioinformatic analyses enable in-depth understanding of the B cell immune response. We investigated the dengue antibody response with these technologies and machine learning to identify rare and underrepresented broadly neutralizing antibody sequences. Dengue immunization elicited following signatures on the antibody repertoire: (i) an increase of CDR3 and germline gene diversity; (ii) a change in the architecture by eliciting power-law network distributions and CDR3 enrichment in polar amino acids; and (iii) an increase in the expression of JNK/Fos transcription factors and ribosomal proteins. Our work shows the applicability of computational methods and machine learning to AIRR-seq datasets for identification of potential neutralizing antibody candidate sequences. Further investigation of antibody expression and functional binding assays validated the obtained results.

Coffee Break in the Exhibit Hall with Poster Viewing10:00

10:45

Protein Engineering with Large Language Models

Ali Madani, PhD, Founder and CEO, Profluent Bio

Generative models have shown promise in capturing the distribution of natural proteins. In this talk, we'll cover a research evolutionary trajectory of the application of large language models from natural language processing to functional protein design. We'll conclude with a look into future scaling and preliminary trends.

11:15

Computational Counterselection Identifies Nonspecific Therapeutic Biologic Candidates

Stefan Ewert, PhD, Associate Director, Biologics Center, Novartis Institutes for Biomedical Research

Biologics require high specificity for targets, but current affinity-selection-based discovery methods do not guarantee this property. We present a method, computational counterselection, that identifies nonspecific candidates using machine learning models of affinity trained on high-throughput data from single-target affinity selection experiments.

11:45

Applying Deep Learning Anomaly Detection to Antibody Structures

Hiroki Shirai, PhD, Coordinator, RIKEN Center for Computational Science

We developed a new end-to-end method to evaluate the humanness of antibodies from 2D pixel images of antibody structures using CNN-VAE, which is a technique used to detect outliers in factory-produced products. This is expected to ensure the humanness of antibody sequences automatically generated by AI.

12:15 Computational Nanobody Binding Epitope prediction and Re-epitoping

Anne Goupil-Lamy, PhD, Science Council Fellow at BIOVIA, BIOVIA, Dassault Systèmes

Discover how molecular modeling and deep learning are transforming nanobody epitope mapping and re-epitoping, advancing precision antibody engineering for diverse applications in biotechnology and medicine.

12:45Enjoy Lunch on Your Own

Dessert Break in the Exhibit Hall & Last Chance for Poster Viewing13:50

Session Break14:45

STRUCTURE, DOCKING, AND DYNAMICS FUNDAMENTALS

15:00

Chairperson's Remarks

Victor Greiff, PhD, Associate Professor, Immunology, University of Oslo

15:05

Unconstrained Generation of Synthetic Antibody-Antigen Structures to Guide Machine Learning Methodology for Antibody Specificity Prediction

Rahmad Akbar, PhD, Researcher, Computational Systems Immunology, University of Oslo

Antibody structures inform and improve machine learning predictions. We devise a method for the parameter-based unconstrained generation of synthetic lattice-based three-dimensional antibody–antigen-binding structures. Our method provides ground-truth access to conformational paratope, epitope, and affinity. We showcase the utility of synthetic datasets to benchmark the real-world relevance of machine learning models for antibody binding prediction.

15:35

Third-Generation Approaches of Antibody Discovery and Optimisation

Pietro Sormanni, PhD, Group Leader, Royal Society University Research Fellow, Chemistry of Health, Yusuf Hamied Department of Chemistry, University of Cambridge

Current technologies for antibody discovery and optimization have been widely successful, but are still subject to limitations. Established screening procedures are laborious, and targeting predetermined epitopes and optimizing multiple biophysical traits simultaneously remains a challenge. In this presentation, I will discuss emerging computational antibody design methods, which enable the targeted design of antibodies for predetermined epitopes and the prediction and modulation of their developability potential through the co-optimization of multiple biophysical properties. Overall, it is increasingly possible to complement well-established in vivo (first-generation) and in vitro (second-generation) methods of antibody discovery with in silico (third-generation) approaches, with time- and cost-saving benefits. These approaches are becoming sufficiently mature to be highly competitive for some applications, thus offering novel opportunities to streamline antibody development.

NOVEL/ALTERNATIVE ML-ENABLED SCREENING TECHNOLOGIES FOR HIGHER POS

16:04

Chairperson's Remarks

M. Frank Erasmus, PhD, Head, Bioinformatics, Specifica, Inc.

16:05

scifAI: An Explainable Machine Learning Framework Applied to Functional Characterization of Therapeutic Antibodies

Fabian Schmich, PhD, Principal Scientist and AI/ML Lead, Roche Pharma Research and Early Development

scifAI is a comprehensive, open-source explainable machine learning framework for the analysis of imaging flow cytometry data. In this presentation, I will focus on alterations to the immunological synapse, analyzing class frequency- and morphological changes of the cell, as well as showcasing the prediction of T cell cytokine production under stimulation with different antibodies, linking morphological features with function and thus demonstrating the potential to significantly impact antibody design.

16:35 Accelerating Antibody Development: Advancing Discovery through Integrated Bioinformatics and Machine Learning

Jannick Bendtsen, CEO, PipeBio

Early-stage antibody discovery requires efficient and comprehensive approaches to identify promising candidates with optimal developability characteristics. This presentation explores how next-generation sequencing (NGS) analysis and machine learning can be applied to optimize antibody developability. We explore a practical implementation of analysis pipelines using PipeBio Bioinformatics Platform and illustrate the benefits of applying such analysis tools through case studies, showing their efficacy in expediting early-stage antibody discovery.

16:50

Low-Data Interpretable Deep Learning Prediction of Antibody Viscosity Using a Biophysically Meaningful Representation

Brajesh K. Rai, PhD, Senior Director, Machine Learning Computational Sciences, Pfizer Inc.

Deep learning has led to substantial advances across many disciplines. However, many scientific problems of practical interest lack sufficiently large datasets amenable to deep learning. Prediction of antibody viscosity is one such problem where these methods have not yet been explored due to the relative scarcity of relevant training data. We will describe how we have overcome this limitation using a biophysically meaningful representation to develop generalizable deep learning models.

17:20

Integrating Single-Cell Immune Repertoire Sequencing, Machine Learning, and Biophysical Properties of Antibodies

Alexander Yermanos, PhD, Lecturer, Systems & Synthetic Immunology, ETH Zurich

Immune repertoires represent a diverse collection of B and T cell receptors which interact with a seemingly infinite number of molecular structures. Recent advancements in deep sequencing and microfluidics allow high-throughput recovery of paired heavy and light chain sequences, thereby linking computational features of immune repertoires to biophysical properties of antibodies at an unprecedented resolution. I will explore the intersection of repertoires, ML, and biophysical features like antigen-specificity, affinity, and epitope.


17:50 PANEL DISCUSSION:

Current State of AI in Antibody Therapeutics: The Promise, the Reality and the Hype

PANEL MODERATORS:

M. Frank Erasmus, PhD, Head, Bioinformatics, Specifica, Inc.

Victor Greiff, PhD, Associate Professor, Immunology, University of Oslo

  • Of the methods currently presented in ML tracks… 

                >Which ones are ready to be implemented? 

                >What types of challenges are foreseen?                

                >What are the limitations?               

                >What are the quick wins companies/institutions are seeing through these implementations?

  •  Which AI approaches currently exhibit the greatest savings in time/cost savings relative to existing capabilities? 
  •  Which AI methodologies are likely to be most disruptive to existing capabilities and how soon will this occur?   
  •  Do you think there AI-based approaches may enhance our regulatory approval systems and reduce the time/cost of the time to clinic?​
PANELISTS:

Andrew R.M. Bradbury, PhD, CSO, Specifica, Inc.

Rebecca Croasdale-Wood, PhD, Director, Augmented Biologics Discovery & Design, Biologics Engineering, Oncology, AstraZeneca

Enkelejda Miho, PhD, Professor, University of Applied Sciences and Arts Northwestern Switzerland, and Managing Director, aiNET

Close of PEGS Europe Summit18:30