Alan Amin
@AlanNawzadAmin
Followers
270
Following
157
Statuses
67
Faculty fellow at NYU working with @andrewgwils. Statistics & machine learning for proteins, RNA, DNA. Prev: @jura_bio, PhD with @deboramarks
New York City
Joined September 2022
How do you go from a hit in your antibody screen to a suitable drug? Now introducing CloneBO: we optimize antibodies in the lab by teaching a generative model how we optimize them in our bodies! w/ @gruver_nate @KuangYilun @yucenlily @andrewgwils and the team at @BigHatBio! 1/7
1
10
63
Paper in question now on arXiv!
How do you go from a hit in your antibody screen to a suitable drug? Now introducing CloneBO: we optimize antibodies in the lab by teaching a generative model how we optimize them in our bodies! w/ @gruver_nate @KuangYilun @yucenlily @andrewgwils and the team at @BigHatBio! 1/7
0
0
3
RT @AlanNawzadAmin: How do you go from a hit in your antibody screen to a suitable drug? Now introducing CloneBO: we optimize antibodies in…
0
10
0
RT @andrewgwils: Really excited about this new work on Bayesian optimization for antibody design! It works by teaching a generative model h…
0
5
0
RT @gruver_nate: This project has something for everyone to love! Multi-sequence language models, twisted SMC, wet lab experiments. Go chec…
0
1
0
Details and more results in the paper, trained models on github! Great working with @BigHatBio team: Hunter Elliot, Ani Raghu, @CalvinMccarter @peytongreenside! (Also got outstanding poster at AIDrugX at Neurips!) 7/7 arXiv: Code:
0
1
5
RT @shae_mcl: Many of these detect Alu elements —stretches of DNA about 300bp that are abundant through copy-paste events during evolution.…
0
1
0
New model trained on new dataset of nearly a million evolving antibody families at AIDrugX workshop Sunday at 4:20 pm (#76) #Neurips! Collab between @andrewgwils and @BigHatBio. Stay tuned for full thread on how we used the model to optimize antibodies in the lab in coming days!
0
10
39
RT @EliWeinstein6: I'm thrilled to present a new paper with @blei_lab and @lizbwood about estimating the causal effects of T cell receptors…
0
32
0
Would you rather screen a huge library of random sequences or a small library of designed sequences? By building hardware-informed statistical models, @jura_bio is now building huge libraries of designed sequences!
I’m thrilled to announce: at @jura_bio we’ve constructed a new kind of generative protein model, which allows us to manufacture its generated designs in the real world at petascale. Paper: Blog:
0
5
28
RT @EliWeinstein6: I’m thrilled to announce: at @jura_bio we’ve constructed a new kind of generative protein model, which allows us to manu…
0
78
0
@sokrypton Yea! In their case they had very good recovery — they could do de novo design while recovering nature’s designs. But I totally appreciate your thoughtful points about how people frame what their benchmarks teach them
1
0
1
@sokrypton That noise is conceptually important and must be accounted for during evaluation is something I totally agree with!
0
0
3
@sokrypton In your example, I would say perhaps that if you condition on what you want the structure to do (include the ligand in the struct) then you bring the training more in line with the outcome. How realistic a design task is conditioning on structure without informing function? (2/2)
1
0
1