How to Use IgDesign Online
Try IgDesign
Commercially Available Online Web Server
IgDesign: A Breakthrough in Antibody Design
IgDesign, a deep learning-based method for designing antibody complementarity-determining regions (CDRs) that has been successfully validated in vitro. While previous deep learning approaches have been applied to antibody design in silico, IgDesign is the first experimentally validated inverse folding model for designing antibody binders. This makes it a valuable tool for accelerating drug development and enabling therapeutic design.
How IgDesign Works
IgDesign is a generative antibody inverse folding model based on the LM-Design approach, which combines a structure encoder and a sequence decoder. The model is capable of designing both the heavy chain CDR3 (HCDR3) and all three heavy chain CDRs (HCDR123) for a given antigen.
Inputs: IgDesign takes native backbone structures of antibody-antigen complexes, along with the antigen and antibody framework (FWR) sequences, as context for its design process.
Performance: The model has demonstrated its robustness by successfully designing binders for eight therapeutic antigens with high success rates. In some cases, the designed antibodies even showed improved affinities over clinically validated reference antibodies.
Inverse Folding: IgDesign's approach to inverse folding is a key component. It uses a specially trained model called IgMPNN, which is similar to ProteinMPNN, but with key differences. IgMPNN is provided with antigen and FWR sequences as context and decodes the CDRs sequentially (HCDR1, HCDR2, HCDR3, etc.) during training. This allows the model to produce high-quality CDR sequences for a given structure.
What is Tamarind Bio?
Tamarind Bio is a pioneering no-code bioinformatics platform built to democratize access to powerful computational tools for life scientists and researchers. Recognizing that many cutting-edge machine learning models are often difficult to deploy and use, Tamarind provides an intuitive, web-based environment that completely abstracts away the complexities of high-performance computing, software dependencies, and command-line interfaces.
The platform is designed provide easy access to biologists, chemists, and other researchers who may not have a background in programming or cloud infrastructure but want to run experimental models with their data. Key features include a user-friendly graphical interface for setting up and launching experiments, a robust API for integration into existing research pipelines, and an automated system for managing and scaling computational resources. By handling the technical heavy lifting, Tamarind empowers researchers to concentrate on their scientific questions and accelerate the pace of discovery.
Accelerating Discovery with IgDesign on Tamarind Bio
Using IgDesign on a platform like Tamarind could accelerate antibody discovery and lead optimization by providing a streamlined, high-throughput workflow.
De Novo Antibody Design: Researchers can use IgDesign on the platform to create novel antibody sequences for a given antigen backbone, helping them to explore new functional space in antibody design.
Lead Optimization: The model's ability to design CDRs and, in some cases, improve on the affinity of existing antibodies, makes it ideal for optimizing existing therapeutic leads.
Experimental Validation: The paper describes screening designed antibodies using Surface Plasmon Resonance (SPR) to measure their binding affinity. This suggests that a platform like Tamarind could integrate with experimental pipelines, allowing researchers to seamlessly transition from computational design to in vitro testing.
How to Use IgDesign on Tamarind Bio
To leverage IgDesign's power, a researcher could follow this streamlined workflow:
Access the Platform: Begin by logging in to the tamarind.bio website.
Select IgDesign: From the list of available computational models, choose the IgDesign tool.
Provide a 3D Structure: Upload the 3D backbone structure of an antibody-antigen complex (PDB file) as the starting point for the design.
Input Sequence Context: Provide the amino acid sequences for the antigen and the antibody's framework regions (FWR) as additional context for the model.
Specify Design Regions: Select which CDRs you want the model to design (e.g., HCDR3 only or all three heavy chain CDRs).
Generate and Evaluate: The platform runs IgDesign to produce novel CDR sequences. The best designs can then be selected based on their predicted affinity and can be sent for experimental validation to confirm binding to the target antigen.