To kick off our Community Meetings this year, we invite you all to join us on 2025-01-29T14:00:00Z. We will hear from @Aubin, presenting about Advancing Nanobody Discovery and Engineering with Machine Learning.
Nanobodies, or single-domain antibodies, are small antibody fragments naturally expressed in camelids, characterised by their high expressibility, solubility and stability alongside an affinity comparable to full-length antibodies. They have gained significant momentum since the approval of the first nanobody drug in 2019, yet the development of these biologics as therapeutics remains a challenge. Despite the availability of established in vitro directed-evolution technologies that are relatively fast and cheap to deploy, the gold standard for generating therapeutic antibodies with favourable properties in vivo remains discovery from animal immunisation or patients. This raises the question of whether a computational design strategy will ever meet the challenge of generating fully functional and developable antibodies in silico.
Looking forward to seeing you all 2025-01-29T14:00:00Z to hear from @Aubin talking about Advancing Nanobody Discovery and Engineering with Machine Learning.
See the joining links in the first post above!
===
For fun, just two quick polls before you go:
What do you currently know about nanobodies?
1 - Nothing at all
2 - I have some theoretical knowledge
3 - I have practical experience of working with antibodies, but not nanobodies
4 - I have practical experience with antibodies and/or nanobodies
5 - Antibodies, nanobodies - it’s my bread and butter!
0voters
What do you currently know about using machine learning for engineering biology (and/or specifically for antibodies)?
1 - Nothing at all
2 - I have some theoretical knowledge
3 - I have practical experience of using machine learning, but not for engineering biology
4 - I have practical experience of using machine learning for engineering biology
5 - I have practical experience of using machine learning for engineering biology, particularly with antibodies
6 - I use machine learning every day… doesn’t everyone?
0voters
Feel free to comment below and tell us your interest and/or experiences with nanobody discovery, antibodies, machine learning. We’d love to hear and learn more!
Thanks for getting in touch again @Ahmed_Atef
Sorry we’ve been a bit slow with processing and uploading videos but this one will be uploaded by the end of the week, and we’ll be working backwards to upload the previous meetings too.
I’ll post the link to Aubin’s talk as soon as it’s up!
On 29 Jan 2025, we hosted an insightful Community Call with @Aubin, where he shared to the community about his PhD research in “Advancing Nanobody Discovery and Engineering with Machine Learning”
Aubin gave us a great overview from antibodies to nanobodies, and computational nanobody engineering, before diving into his research where he built AbNatiV to assess antibody nativeness and NanoMelt for predicting nanobody thermostability.
His open-source AbNatiV dataset has over 21M sequences that he collated from different immue repertoires, but he also recommended OAS: Observed Antibody Space from Prof Charlotte Deane’s group at the University of Oxford, which he used as a starting point.