National Institutes of Health/National Institute Of Allergy and Infectious Diseases (NIH/NIAID)
AI167910
United States
National Institutes of Health/National Institute of Arthritis and Musculoskeletal and Skin Diseases (NIH/NIAMS)
AT011966
United States
Michelson Medical Research Foundation
Prize for Human Immunology and Vaccine Research
United States
Searle Scholars Program
United States
Citation
Journal: Immunity / Year: 2024 Title: An explainable language model for antibody specificity prediction using curated influenza hemagglutinin antibodies. Authors: Yiquan Wang / Huibin Lv / Qi Wen Teo / Ruipeng Lei / Akshita B Gopal / Wenhao O Ouyang / Yuen-Hei Yeung / Timothy J C Tan / Danbi Choi / Ivana R Shen / Xin Chen / Claire S Graham / Nicholas C Wu / Abstract: Despite decades of antibody research, it remains challenging to predict the specificity of an antibody solely based on its sequence. Two major obstacles are the lack of appropriate models and the ...Despite decades of antibody research, it remains challenging to predict the specificity of an antibody solely based on its sequence. Two major obstacles are the lack of appropriate models and the inaccessibility of datasets for model training. In this study, we curated >5,000 influenza hemagglutinin (HA) antibodies by mining research publications and patents, which revealed many distinct sequence features between antibodies to HA head and stem domains. We then leveraged this dataset to develop a lightweight memory B cell language model (mBLM) for sequence-based antibody specificity prediction. Model explainability analysis showed that mBLM could identify key sequence features of HA stem antibodies. Additionally, by applying mBLM to HA antibodies with unknown epitopes, we discovered and experimentally validated many HA stem antibodies. Overall, this study not only advances our molecular understanding of the antibody response to the influenza virus but also provides a valuable resource for applying deep learning to antibody research.
In the structure databanks used in Yorodumi, some data are registered as the other names, "COVID-19 virus" and "2019-nCoV". Here are the details of the virus and the list of structure data.
Jan 31, 2019. EMDB accession codes are about to change! (news from PDBe EMDB page)
EMDB accession codes are about to change! (news from PDBe EMDB page)
The allocation of 4 digits for EMDB accession codes will soon come to an end. Whilst these codes will remain in use, new EMDB accession codes will include an additional digit and will expand incrementally as the available range of codes is exhausted. The current 4-digit format prefixed with “EMD-” (i.e. EMD-XXXX) will advance to a 5-digit format (i.e. EMD-XXXXX), and so on. It is currently estimated that the 4-digit codes will be depleted around Spring 2019, at which point the 5-digit format will come into force.
The EM Navigator/Yorodumi systems omit the EMD- prefix.
Related info.:Q: What is EMD? / ID/Accession-code notation in Yorodumi/EM Navigator
Yorodumi is a browser for structure data from EMDB, PDB, SASBDB, etc.
This page is also the successor to EM Navigator detail page, and also detail information page/front-end page for Omokage search.
The word "yorodu" (or yorozu) is an old Japanese word meaning "ten thousand". "mi" (miru) is to see.
Related info.:EMDB / PDB / SASBDB / Comparison of 3 databanks / Yorodumi Search / Aug 31, 2016. New EM Navigator & Yorodumi / Yorodumi Papers / Jmol/JSmol / Function and homology information / Changes in new EM Navigator and Yorodumi