Conference Day One
9:00 am Login & Networking
Synopsis
Join our morning virtual coffee chat room to meet with your fellows and get the conversation going!9:20 am Opening Remarks from the Chair
Advanced Computational Biology & Bioinformatics 2.0
9:30 am Computer-Aided Drug Discovery & Chaperone Proteins as Drug Targets
Synopsis
- How to use computer-aided drug discovery, fragment based screening, homology modelling and docking for inhibitors identification
- Using fragment in-silico screening for drug rational design
- Novel AI approaches: Machine learning and deep learning to identify novel candidates
10:00 am Immunogenicity & Antigenicity-Based T-Cell & Epitopes Identification for Design of Biologic Therapeutics
Synopsis
- In silico analysis as an integrative approach for the assessment of immunogenicity in the pre-clinical phase
- In vitro validation study to offer predictive insights on immunogenicity of biotherapeutics
- Remaining challenges to offer better predictive insights to mitigate clinical immunogenicity risk of biotherapeutics
10:40 am Large-Scale Computational Analysis Reveals MHC-II-Based Antibody Gene Personalization Features
Synopsis
- Exploring datasets to follow patterns, trends, and associations in antibody genetics across individuals
- Studying the molecular pathways of somatic hypermutation and antibody immunogenicity
11:10 am Morning Speed Networking
Synopsis
Connect with your industry peers through our virtual speed networking tool. You will be paired up with a fellow colleague for a 5-minute ice breaking conversation!
11:30 am Computational Strategies for Targeted Protein Degradation
Synopsis
- This session will explore how computational tools can support targeted protein degradation, opening up previously undruggable opportunities.
12:00 pm Physics-Based Simulations to Investigate Developability for Therapeutic Antibodies
Synopsis
- The development of in silico models for stability prediction proves challenging due to the limited availability of adequately sized experimental data necessary for model training
- The emergence of novel therapeutic modalities can further restrict the sizes of datasets, and thus the transferability and generalizability of predictive methods
- Physics-based approaches that are not limited on training data offer a unique advantage by providing profound mechanistic insight into the physical and chemical stability, examples of such class of computations will be presented
12:30 pm Comparison of Antibody Interfaces – Lessons for the Design of Bispecific Antibodies
Synopsis
- Comparison CH1-CL and CH3-CH3 interfaces
- Exploring stabilities of antibodies
- CDR loop interactions as key determinants for pairing preferences in bispecific antibodies
1:00 pm Networking Lunch
Synopsis
Grab a bite while joining our virtual lunch chat room, or use this opportunity to visit our Partners’ Virtual Booths
2:00 pm Featurization of Protein-Protein Interfaces for Machine Learning in Large Molecule Drug Discovery
Synopsis
- Atomic-level characterization of protein interfaces can be computed from all experimental, and improved modelled, structures to generate a large dataset (4×10^6) suitable for machine learning input
- We created PiEx, a fully automated platform for protein:protein interface analysis, that allows navigation and exploration via interactive visuals of the large data
- PiEx generates novel insights from native and crystal interfaces, as exemplified in B-cell and T-cell receptor studies
Novel Drug Development Approach Using Computer-Aided Approach
2:30 pm Developing Novel Computational Models to Predict Antibody Stability
Synopsis
- In silico modelling to predict physical stability of antibodies in the early-stage design
- Predicting viscosity and aggregation propensity at high concentration using machine learning
- Combining coarse-grained simulations with hydrodynamic calculations to predict antibody viscosity
3:00 pm Panel Discussion: Drug Discovery & Development Involving Machine Learning & Artificial Intelligence
Synopsis
- Exploring how pharma are utilising ML with limited data
- Discovering how to improve speed of validation of the drug target and optimization of the drug structure design
- Identifying data challenges: scale, growth, diversity, and uncertainty of data
- Predicting complex biological properties, such as the efficacy and adverse effects of compounds
3:45 pm Afternoon Speed Networking
Synopsis
Take this opportunity to meet with our expert partners for 1-2-1 meetings to find out about their latest innovations.
4:15 pm Update on the Latest ML-based Methods for Biologics Engineering
Synopsis
- Novel machine learning algorithms along with increasing accumulation of data empowers digital innovation for biologics engineering
- Large Molecule Research in collaboration with Digital & Data Science at Sanofi, benchmarked state-of-the-art methods and developed ddG prediction tools
- This preliminary result demonstrated promising ability of ML-based models in biologics engineering
4:45 pm Accelerating Antibody Informatics with Machine Learning
Synopsis
- CDR-H3 is a fingerprint region of each antibody, and its conformation is key for antigen recognition
- Examining various kinds of machine learning methods (Random Forest, Decision Tree, Light GBM, SVM, MLP) for the prediction of CDR-H3’s structure type
- Recurrent neural network and convolutional neural network in combination with reinforcement learning for the de novo design of developable antibody sequences
5:15 pm Generative AI for Peptide Drug Discovery
Synopsis
- Applications of generative AI for peptides and peptidomimetics
- Applications to SARS-CoV-2 3CL protease and neurotensin receptor