Grigory Khimulya

@grigonomics

Using deep learning to solve problems in biology.

Vrijeme pridruživanja: lipanj 2015.

Tweetovi

Blokirali ste korisnika/cu @grigonomics

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @grigonomics

  1. Prikvačeni tweet
    24. sij

    Excited to share our latest pre-print🎉 - a framework for low-N protein engineering with data-efficient deep learning! Had a blast working with brilliant and . Thread (1/7)

    Prikaži ovu nit
    Poništi
  2. 28. sij

    In DC for , so much cool work here in rapid countermeasure response for new pathogens! If you are working on this, I want to talk - dms open.

    Poništi
  3. 24. sij

    Stay tuned for code and more! (7/7)

    Prikaži ovu nit
    Poništi
  4. 24. sij

    Low-N protein engineering with eUniRep+in silico evolution enables engineers to screen 10s of millions of variants even if assaying the target function is very resource intensive, as is often the case in drug development, agriculture, and industrial production. (6/7)

    Prikaži ovu nit
    Poništi
  5. 24. sij

    Even without any experimental data, eUniRep encodes protein function from raw amino acid sequences alone as the representation’s first principal component. This is likely why eUniRep generalizes so well - maybe even less training data is needed! (5/7)

    Prikaži ovu nit
    Poništi
  6. 24. sij

    eUniRep also engineers enzymes and leverages epistasis! Despite training on just single mutants of beta lactamase, we generate many >WT epistatically non-trivial variants. (4/7)

    Prikaži ovu nit
    Poništi
  7. 24. sij

    With just hours of GPU computing and 24 assayed mutants of wild GFP💚as training data, we generate much brighter diverse fluorescent proteins, some practically as bright as sfGFP - a fruit of a multi-year effort in high-throughput protein engineering. (3/7)

    Prikaži ovu nit
    Poništi
  8. 24. sij

    With less than a 96well plate worth of assayed variants, our semi-supervised eUniRep method constructs accurate virtual fitness landscapes and screens ten million protein sequences with in silico directed evolution🎢. (2/7)

    Prikaži ovu nit
    Poništi
  9. 21. lis 2019.
    Poništi
  10. proslijedio/la je Tweet
    18. ruj 2019.

    Pai-chan and Son-kun are the mascots for the Python certification exam in Japan.

    Poništi
  11. proslijedio/la je Tweet
    19. ruj 2019.
    Poništi
  12. 16. ruj 2019.
    Prikaži ovu nit
    Poništi
  13. 16. ruj 2019.

    new heights of automation

    Prikaži ovu nit
    Poništi
  14. 15. ruj 2019.
    Poništi
  15. proslijedio/la je Tweet
    4. srp 2019.

    VEGAS: Platform for Facile Directed Evolution in Cells •One day/round , based on RNA alphavirus •Mutation rates up to 10^−3 from and

    Poništi
  16. proslijedio/la je Tweet
    2. tra 2019.

    New blogpost up on protein representation learning: . I use our recent UniRep preprint () in collab with as a springboard for reflecting on the future of the field.

    Poništi
  17. 27. ožu 2019.

    Delighted to have been a part of this! Also want to thank @YangKevinK for inspiration, help, and/or kickass data.

    Poništi

Čini se da učitavanje traje već neko vrijeme.

Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.

    Možda bi vam se svidjelo i ovo:

    ·