|
Surge Biswas
@
SurgeBiswas
|
|
Interested in what machine learning can do for protein engineering & sports. @geochurch lab @wyssinstitute. PhD candidate @harvard. Dog dad.
|
|
|
306
Tweetovi
|
340
Pratim
|
605
Osobe koje vas prate
|
| Tweetovi |
|
Surge Biswas
@SurgeBiswas
|
30. sij |
|
🤯Using this to calculate tips from now on twitter.com/peterpur/statu…
|
||
|
|
||
| Surge Biswas proslijedio/la je tweet | ||
|
Jasper
@latentjasper
|
29. sij |
|
Cool new result in protein design. Multitask from large data to small - transfer learning from a general protein representation to one tailored to a particular function of interest. twitter.com/grigonomics/st…
|
||
|
|
||
| Surge Biswas proslijedio/la je tweet | ||
|
PlesaLab
@PlesaLab
|
28. sij |
|
We're hiring a bioinformatician to help us tackle a number of projects involving large scale sequence design, optimization, and analysis: plesalab.org/joinus/#0128ra…
|
||
|
|
||
| Surge Biswas proslijedio/la je tweet | ||
|
Grigory Khimulya
@grigonomics
|
28. sij |
|
In DC for #ASMBiothreats, so much cool work here in rapid countermeasure response for new pathogens! If you are working on this, I want to talk #proteinengineering - dms open.
|
||
|
|
||
| Surge Biswas proslijedio/la je tweet | ||
|
Kevin Yang 楊凱筌
@KevinKaichuang
|
27. sij |
|
Great work on using ML for protein engineering.
Key insights:
- fine-tuning global LM using local landscape helps
- pretrained model can predict epistatic effects from single mutants
@SurgeBiswas @grigonomics @EthanAlley @kesvelt @geochurch
biorxiv.org/content/10.110… pic.twitter.com/cjOvH6jiwf
|
||
|
|
||
|
Surge Biswas
@SurgeBiswas
|
25. sij |
|
Thanks for reading Andrew! Surprising for us too! Definitely curious to hear more thoughts on that finding if you have them
|
||
|
|
||
| Surge Biswas proslijedio/la je tweet | ||
|
andrew giessel
@giessel
|
25. sij |
|
This was fantastic! The PC1 correlation is actually just amazing.
|
||
|
|
||
|
Surge Biswas
@SurgeBiswas
|
25. sij |
|
haha. or less asparagine?
|
||
|
|
||
| Surge Biswas proslijedio/la je tweet | ||
|
Gleb Kuznetsov
@glebkuz
|
24. sij |
|
Interesting potential for ML-guided protein engineering: might be able to systematically optimize proteins after just a few choice measurements. Check out this new preprint from @SurgeBiswas @geochurch and team. twitter.com/SurgeBiswas/st…
|
||
|
|
||
| Surge Biswas proslijedio/la je tweet | ||
|
Jase Gehring
@JaseGehring
|
24. sij |
|
won't stop me from working on ways to get big-N, but sometimes small-N is hard enough twitter.com/SurgeBiswas/st…
|
||
|
|
||
| Surge Biswas proslijedio/la je tweet | ||
|
Anush Chiappino-Pepe
@AnushChP
|
25. sij |
|
Super cool work from @SurgeBiswas, @grigonomics, @EthanAlley, @kesvelt, and @geochurch! Efficiently identifying mutant proteins with higher activity using ML, i.e., eUniRep. Congrats!!! twitter.com/SurgeBiswas/st…
|
||
|
|
||
| Surge Biswas proslijedio/la je tweet | ||
|
Mohammed AlQuraishi
@MoAlQuraishi
|
24. sij |
|
Had an early look at this work and it’s really impressive stuff! Demonstrates the remarkable power of semi-supervised learning in very low N contexts. twitter.com/grigonomics/st…
|
||
|
|
||
| Surge Biswas proslijedio/la je tweet | ||
|
Ethan C. Alley
@EthanAlley
|
24. sij |
|
Our new paper! My favorite bits were:
- Discovering WAY more functional proteins out there (1000+!!) then previously explored by evolution OR decades of engineering
- Connecting engineering and tech-translation failures with Goodhart's law
- @grigonomics 's first thread :P twitter.com/grigonomics/st…
|
||
|
|
||
|
Surge Biswas
@SurgeBiswas
|
24. sij |
|
Hope you enjoy the read! We haven't submitted this anywhere yet so feedback and venue/journal suggestions welcome! DMs open
|
||
|
|
||
|
Surge Biswas
@SurgeBiswas
|
24. sij |
|
As always, inspiring to work with and learn from @grigonomics and @EthanAlley, and have the mentorship of @kesvelt and @geochurch :)
|
||
|
|
||
|
Surge Biswas
@SurgeBiswas
|
24. sij |
|
For the ML folks reading this, we're excited by the extreme data-efficiency we saw here, and for forward design of a complicated natural object no less. Another feather in the cap of unsupervised/semi-supervised learning, no doubt!
|
||
|
|
||
|
Surge Biswas
@SurgeBiswas
|
24. sij |
|
This has been a really fun one! challenging the wisdom that one needs a lot of data to do ML guided biodesign. In fact, if you have to choose, think about getting HQ small-N data aligned w your endpoint, vs HT proxy data. low-N ML now helps you succeed w the former! twitter.com/grigonomics/st…
|
||
|
|
||
|
Surge Biswas
@SurgeBiswas
|
19. sij |
|
*Turns off FACS machine* twitter.com/ZoherGueroui/s…
|
||
|
|
||
|
Surge Biswas
@SurgeBiswas
|
17. sij |
|
11/10 opportunity to work for a great company, @PathAI, with an insanely fun and smart person! twitter.com/amarotaylorw/s…
|
||
|
|
||
|
Surge Biswas
@SurgeBiswas
|
16. sij |
|
Is there a faster form of info transfer you prefer?
|
||
|
|
||