Back

NanoLAS 2.0: A Comprehensive Update on a Nanobody-Focused Platform with Advanced Visualization and Docking Simulation Features

Zheng, Z.; Qin, W.; Yu, K.; Hong, Y.; Tang, Y.; Wang, T.; Liang, L.; Huang, B.; Wang, X.

2024-07-17 bioinformatics
10.1101/2024.07.15.603553 bioRxiv
Show abstract

SummaryNanobodies, a unique subclass of antibodies initially discovered in camelids, characterized by the absence of light chains and consisting solely of a heavy chain variable region. This distinctive structure endows nanobodies with inherent advantages in the realms of disease treatment and biopharmaceutical applications. Presently, research and applications concerning nanobodies are experiencing rapid growth. However, existing databases suffer from non-uniform data sources and a lack of data standardization. To address these issues, we developed the NanoLAS database in 2023. Despite the progress in data integration made by NanoLAS, there was room for improvement in search functionality, three-dimensional structural display, and other areas. Building upon this foundation, we introduce the comprehensively updated NanoLAS 2.0. This version offers updates to data sources, precise 3D structural presentation, and molecular docking simulation capabilities, refines the multi-condition search mechanism, and incorporates a brand-new sequence viewer as well as epitope prediction functionality. Additionally, to cater to the needs of researchers, we have designed a user-friendly and intuitive interface. In summary, we anticipate that NanoLAS 2.0 will serve as a powerful and easy-to-use research tool, facilitating researchers in their exploration of nanobodies and propelling advancements in the field of nanobody research and application. AvailabilityNanoLAS 2.0 is available at https://www.nanolas2.online Contactbingdinghuang@sztu.edu.cn and wangxin@sztu.edu.cn

Matching journals

The top 8 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.