Recently added Catalysts

ABSI Positive Sentiment

IgDesign: In vitro validated antibody design against multiple therapeutic antigens using inverse folding

Wednesday, December 18, 2024 BiopharmaWatch Research 8 min read

Key Takeaway: IgDesign is a novel deep learning method for antibody design that has been validated in vitro. It successfully designs heavy chain complementarity-determining regions (CDRs) for eight therapeutic antigens, demonstrating superior performance compared to traditional methods. The model's ability to create high-affinity antibody binders positions it as a significant advancement in drug development. Additionally, the open-sourcing of its code and datasets promotes further research and application.

Price reaction · baseline $3.325 (2024-12-18T15:31:00.000Z) · hit during market hours · clean, no other ABSI news in the window

day 0 close

-8.6%

day 1 · peak

-12.2%

day 3

-11.9%

Market Sentiment Analysis

POSITIVE FACTORS

IgDesign successfully designs antibody binders for multiple therapeutic antigens.
The method outperforms existing HCDR3-only baselines in binding affinity.
IgDesign is the first experimentally validated antibody inverse folding model.
The open-sourcing of code and datasets enhances collaboration and innovation.

BiopharmaWatch Analysis

From our catalyst data and publicly available data · not financial advice

Cash runway

~12 mo

Medium dilution risk

Lead asset

ABS-201 Single Dose

Phase 1 · Androgenetic Alopecia (AGA)

Full Press Release Details

• Find this author on Google Scholar

• Find this author on PubMed

• Search for this author on this site

• For correspondence: ashanehsazzadeh{at}absci.com

• Find this author on Google Scholar

• Find this author on PubMed

• Search for this author on this site

• Find this author on Google Scholar

• Find this author on PubMed

• Search for this author on this site

• Find this author on Google Scholar

• Find this author on PubMed

• Search for this author on this site

• Find this author on Google Scholar

• Find this author on PubMed

• Search for this author on this site

• Find this author on Google Scholar

• Find this author on PubMed

• Search for this author on this site

• Find this author on Google Scholar

• Find this author on PubMed

• Search for this author on this site

• Find this author on Google Scholar

• Find this author on PubMed

• Search for this author on this site

• Find this author on Google Scholar

• Find this author on PubMed

• Search for this author on this site

• Find this author on Google Scholar

• Find this author on PubMed

• Search for this author on this site

• Find this author on Google Scholar

• Find this author on PubMed

• Search for this author on this site

• Find this author on Google Scholar

• Find this author on PubMed

• Search for this author on this site

• Find this author on Google Scholar

• Find this author on PubMed

• Search for this author on this site

• Find this author on Google Scholar

• Find this author on PubMed

• Search for this author on this site

• Find this author on Google Scholar

• Find this author on PubMed

• Search for this author on this site

• Find this author on Google Scholar

• Find this author on PubMed

• Search for this author on this site

• Find this author on Google Scholar

• Find this author on PubMed

• Search for this author on this site

• Find this author on Google Scholar

• Find this author on PubMed

• Search for this author on this site

• Find this author on Google Scholar

• Find this author on PubMed

• Search for this author on this site

• Find this author on Google Scholar

• Find this author on PubMed

• Search for this author on this site

• Find this author on Google Scholar

• Find this author on PubMed

• Search for this author on this site

• Find this author on Google Scholar

• Find this author on PubMed

• Search for this author on this site

• Find this author on Google Scholar

• Find this author on PubMed

• Search for this author on this site

• Find this author on Google Scholar

• Find this author on PubMed

• Search for this author on this site

• Find this author on Google Scholar

• Find this author on PubMed

• Search for this author on this site

• Find this author on Google Scholar

• Find this author on PubMed

• Search for this author on this site

• Find this author on Google Scholar

• Find this author on PubMed

• Search for this author on this site

• Find this author on Google Scholar

• Find this author on PubMed

• Search for this author on this site

• Find this author on Google Scholar

• Find this author on PubMed

• Search for this author on this site

• Find this author on Google Scholar

• Find this author on PubMed

• Search for this author on this site

• Find this author on Google Scholar

• Find this author on PubMed

• Search for this author on this site

• Find this author on Google Scholar

• Find this author on PubMed

• Search for this author on this site

• Find this author on Google Scholar

• Find this author on PubMed

• Search for this author on this site

• Find this author on Google Scholar

• Find this author on PubMed

• Search for this author on this site

• Find this author on Google Scholar

• Find this author on PubMed

• Search for this author on this site

• Find this author on Google Scholar

• Find this author on PubMed

• Search for this author on this site

• Find this author on Google Scholar

• Find this author on PubMed

• Search for this author on this site

• Find this author on Google Scholar

• Find this author on PubMed

• Search for this author on this site

• Find this author on Google Scholar

• Find this author on PubMed

• Search for this author on this site

• Find this author on Google Scholar

• Find this author on PubMed

• Search for this author on this site

• Find this author on Google Scholar

• Find this author on PubMed

• Search for this author on this site

• Find this author on Google Scholar

• Find this author on PubMed

• Search for this author on this site

• Abstract

• Full Text

• Info/History

• Metrics

• Data/Code

• Preview PDF

Abstract

Deep learning approaches have demonstrated the ability to design protein sequences given backbone structures [ 1 , 2 , 3 , 4 , 5 ]. While these approaches have been applied in silico to designing antibody complementarity-determining regions (CDRs), they have yet to be validated in vitro for designing antibody binders, which is the true measure of success for antibody design. Here we describe IgDesign , a deep learning method for antibody CDR design, and demonstrate its robustness with successful binder design for 8 therapeutic antigens. The model is tasked with designing heavy chain CDR3 (HCDR3) or all three heavy chain CDRs (HCDR123) using native backbone structures of antibody-antigen complexes, along with the antigen and antibody framework (FWR) sequences as context. For each of the 8 antigens, we design 100 HCDR3s and 100 HCDR123s, scaffold them into the native antibody’s variable region, and screen them for binding against the antigen using surface plasmon resonance (SPR). As a baseline, we screen 100 HCDR3s taken from the model’s training set and paired with the native HCDR1 and HCDR2. We observe that both HCDR3 design and HCDR123 design outperform this HCDR3-only baseline. IgDesign is the first experimentally validated antibody inverse folding model. It can design antibody binders to multiple therapeutic antigens with high success rates and, in some cases, improved affinities over clinically validated reference antibodies. Antibody inverse folding has applications to both de novo antibody design and lead optimization, making IgDesign a valuable tool for accelerating drug development and enabling therapeutic design. The data generated in this study serve as a useful benchmark of diverse antibody-antigen interactions. We use this data to benchmark self-consistency RMSD (scRMSD), using ABodyBuilder2 [ 6 ], ABodyBuilder3 [ 7 ], and ESMFold [ 8 ], as a metric for assessing binding. We open source the code for IgDesign and the SPR datasets.

Code and datasets can be found at https://github.com/AbSciBio/igdesign .

Competing Interest Statement

The authors are current or former employees, contractors, interns, or executives of Absci Corporation and may hold shares in Absci Corporation.

Footnotes

• Open sourcing data and code. Analysis of self-consistency RMSD (scRMSD) as a metric for predicting binding.

• https://github.com/AbSciBio/igdesign/tree/main

• ↵ 8 https://github.com/BytedProtein/ByProt/issues/3

• ↵ 9 https://github.com/dauparas/ProteinMPNN

• ↵ 10 https://github.com/dauparas/ProteinMPNN/blob/main/examples/submit_example_3.sh

Open sourcing data and code. Analysis of self-consistency RMSD (scRMSD) as a metric for predicting binding.

https://github.com/AbSciBio/igdesign/tree/main

↵ 8 https://github.com/BytedProtein/ByProt/issues/3

↵ 9 https://github.com/dauparas/ProteinMPNN

↵ 10 https://github.com/dauparas/ProteinMPNN/blob/main/examples/submit_example_3.sh

Citation Manager Formats

• BibTeX

• Bookends

• EasyBib

• EndNote (tagged)

• EndNote 8 (xml)

• Medlars

• Mendeley

• Papers

• RefWorks Tagged

• Ref Manager

• RIS

• Zotero

• Tweet Widget

• Facebook Like

• Google Plus One

Subject Area

• Synthetic Biology

• Animal Behavior and Cognition (7770)

• Biochemistry (18119)

• Bioengineering (14294)

• Bioinformatics (42892)

• Biophysics (21870)

• Cancer Biology (18775)

• Cell Biology (25753)

• Clinical Trials (138)

• Developmental Biology (13472)

• Ecology (20303)

• Epidemiology (2067)

• Evolutionary Biology (24772)

• Genetics (15804)

• Genomics (22891)

• Immunology (18110)

• Microbiology (41164)

• Molecular Biology (17307)

• Neuroscience (90411)

• Paleontology (679)

• Pathology (2895)

• Pharmacology and Toxicology (4928)

• Physiology (7841)

• Plant Biology (15271)

• Scientific Communication and Education (2061)

• Synthetic Biology (4347)

• Systems Biology (9883)

• Zoology (2307)

Frequently Asked Questions

What is IgDesign?

IgDesign is a deep learning method for designing antibody complementarity-determining regions.

How does IgDesign validate its antibody designs?

IgDesign's designs are validated in vitro by screening for binding against therapeutic antigens.

What are the advantages of using IgDesign?

IgDesign outperforms traditional methods in binding affinity and is the first validated inverse folding model.

Is the IgDesign code available for public use?

Yes, IgDesign's code and datasets are open-sourced for public access.