NanoNet: Rapid and accurate end-to-end nanobody modeling by deep learning
Antibodies are a rapidly growing class of therapeutics. Recently, single domain camelid VHH antibodies, and their recognition nanobody domain (Nb) appeared as a cost-effective highly stable alternative to full-length antibodies. There is a growing need for high-throughput epitope mapping based on ac...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-08-01
|
| Series: | Frontiers in Immunology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fimmu.2022.958584/full |
| _version_ | 1798042999500832768 |
|---|---|
| author | Tomer Cohen Matan Halfon Dina Schneidman-Duhovny |
| author_facet | Tomer Cohen Matan Halfon Dina Schneidman-Duhovny |
| author_sort | Tomer Cohen |
| collection | DOAJ |
| description | Antibodies are a rapidly growing class of therapeutics. Recently, single domain camelid VHH antibodies, and their recognition nanobody domain (Nb) appeared as a cost-effective highly stable alternative to full-length antibodies. There is a growing need for high-throughput epitope mapping based on accurate structural modeling of the variable domains that share a common fold and differ in the Complementarity Determining Regions (CDRs). We develop a deep learning end-to-end model, NanoNet, that given a sequence directly produces the 3D coordinates of the backbone and Cβ atoms of the entire VH domain. For the Nb test set, NanoNet achieves 3.16Å average RMSD for the most variable CDR3 loops and 2.65Å, 1.73Å for the CDR1, CDR2 loops, respectively. The accuracy for antibody VH domains is even higher: 2.38Å RMSD for CDR3 and 0.89Å, 0.96Å for the CDR1, CDR2 loops, respectively. NanoNet run times allow generation of ∼1M nanobody structures in less than 4 hours on a standard CPU computer enabling high-throughput structure modeling. NanoNet is available at GitHub: https://github.com/dina-lab3D/NanoNet |
| first_indexed | 2024-04-11T22:43:27Z |
| format | Article |
| id | doaj.art-64f9013b2d3945a98764f43400f75b08 |
| institution | Directory Open Access Journal |
| issn | 1664-3224 |
| language | English |
| last_indexed | 2024-04-11T22:43:27Z |
| publishDate | 2022-08-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Immunology |
| spelling | doaj.art-64f9013b2d3945a98764f43400f75b082022-12-22T03:58:53ZengFrontiers Media S.A.Frontiers in Immunology1664-32242022-08-011310.3389/fimmu.2022.958584958584NanoNet: Rapid and accurate end-to-end nanobody modeling by deep learningTomer CohenMatan HalfonDina Schneidman-DuhovnyAntibodies are a rapidly growing class of therapeutics. Recently, single domain camelid VHH antibodies, and their recognition nanobody domain (Nb) appeared as a cost-effective highly stable alternative to full-length antibodies. There is a growing need for high-throughput epitope mapping based on accurate structural modeling of the variable domains that share a common fold and differ in the Complementarity Determining Regions (CDRs). We develop a deep learning end-to-end model, NanoNet, that given a sequence directly produces the 3D coordinates of the backbone and Cβ atoms of the entire VH domain. For the Nb test set, NanoNet achieves 3.16Å average RMSD for the most variable CDR3 loops and 2.65Å, 1.73Å for the CDR1, CDR2 loops, respectively. The accuracy for antibody VH domains is even higher: 2.38Å RMSD for CDR3 and 0.89Å, 0.96Å for the CDR1, CDR2 loops, respectively. NanoNet run times allow generation of ∼1M nanobody structures in less than 4 hours on a standard CPU computer enabling high-throughput structure modeling. NanoNet is available at GitHub: https://github.com/dina-lab3D/NanoNethttps://www.frontiersin.org/articles/10.3389/fimmu.2022.958584/fullnanobody (Nb)machine-learning (ML)protein modelingantibodydeep learning- artificial neural network |
| spellingShingle | Tomer Cohen Matan Halfon Dina Schneidman-Duhovny NanoNet: Rapid and accurate end-to-end nanobody modeling by deep learning Frontiers in Immunology nanobody (Nb) machine-learning (ML) protein modeling antibody deep learning- artificial neural network |
| title | NanoNet: Rapid and accurate end-to-end nanobody modeling by deep learning |
| title_full | NanoNet: Rapid and accurate end-to-end nanobody modeling by deep learning |
| title_fullStr | NanoNet: Rapid and accurate end-to-end nanobody modeling by deep learning |
| title_full_unstemmed | NanoNet: Rapid and accurate end-to-end nanobody modeling by deep learning |
| title_short | NanoNet: Rapid and accurate end-to-end nanobody modeling by deep learning |
| title_sort | nanonet rapid and accurate end to end nanobody modeling by deep learning |
| topic | nanobody (Nb) machine-learning (ML) protein modeling antibody deep learning- artificial neural network |
| url | https://www.frontiersin.org/articles/10.3389/fimmu.2022.958584/full |
| work_keys_str_mv | AT tomercohen nanonetrapidandaccurateendtoendnanobodymodelingbydeeplearning AT matanhalfon nanonetrapidandaccurateendtoendnanobodymodelingbydeeplearning AT dinaschneidmanduhovny nanonetrapidandaccurateendtoendnanobodymodelingbydeeplearning |