TY - JOUR
T1 - Structural Modeling of Nanobodies
T2 - A Benchmark of State-of-the-Art Artificial Intelligence Programs
AU - Valdés-Tresanco, Mario S.
AU - Valdés-Tresanco, Mario E.
AU - Jiménez-Gutiérrez, Daiver E.
AU - Moreno, Ernesto
N1 - Funding Information:
Work by M.S.V.-T., D.E.J.-G. and E.M. was supported by the University of Medellin and MINCIENCIAS, MINEDUCACIÓN, MINCIT, and ICETEX, through the Program NanoBioCáncer, Cod. FP44842-211-2018. M.E.V.-T. is an Eyes High Doctoral Recruitment Scholarship and Alberta Graduate Student Scholarship recipient at the University of Calgary.
Publisher Copyright:
© 2023 by the authors.
PY - 2023/5
Y1 - 2023/5
N2 - The number of applications for nanobodies is steadily expanding, positioning these molecules as fast-growing biologic products in the biotechnology market. Several of their applications require protein engineering, which in turn would greatly benefit from having a reliable structural model of the nanobody of interest. However, as with antibodies, the structural modeling of nanobodies is still a challenge. With the rise of artificial intelligence (AI), several methods have been developed in recent years that attempt to solve the problem of protein modeling. In this study, we have compared the performance in nanobody modeling of several state-of-the-art AI-based programs, either designed for general protein modeling, such as AlphaFold2, OmegaFold, ESMFold, and Yang-Server, or specifically designed for antibody modeling, such as IgFold, and Nanonet. While all these programs performed rather well in constructing the nanobody framework and CDRs 1 and 2, modeling CDR3 still represents a big challenge. Interestingly, tailoring an AI method for antibody modeling does not necessarily translate into better results for nanobodies.
AB - The number of applications for nanobodies is steadily expanding, positioning these molecules as fast-growing biologic products in the biotechnology market. Several of their applications require protein engineering, which in turn would greatly benefit from having a reliable structural model of the nanobody of interest. However, as with antibodies, the structural modeling of nanobodies is still a challenge. With the rise of artificial intelligence (AI), several methods have been developed in recent years that attempt to solve the problem of protein modeling. In this study, we have compared the performance in nanobody modeling of several state-of-the-art AI-based programs, either designed for general protein modeling, such as AlphaFold2, OmegaFold, ESMFold, and Yang-Server, or specifically designed for antibody modeling, such as IgFold, and Nanonet. While all these programs performed rather well in constructing the nanobody framework and CDRs 1 and 2, modeling CDR3 still represents a big challenge. Interestingly, tailoring an AI method for antibody modeling does not necessarily translate into better results for nanobodies.
KW - antibody
KW - artificial intelligence
KW - nanobody
KW - protein modeling
KW - protein structure
UR - http://www.scopus.com/inward/record.url?scp=85160376787&partnerID=8YFLogxK
U2 - 10.3390/molecules28103991
DO - 10.3390/molecules28103991
M3 - Artículo
C2 - 37241731
AN - SCOPUS:85160376787
SN - 1420-3049
VL - 28
JO - Molecules
JF - Molecules
IS - 10
M1 - 3991
ER -