darya filippova

@lynxoid

Scientist & engineer. Computational biology, sequencing, and algorithms. UMD/CMU alum. Tweets are my own.

Menlo Park, CA
Vrijeme pridruživanja: travanj 2010.

Tweetovi

Blokirali ste korisnika/cu @lynxoid

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

  1. 24. sij

    Cryptography: Alice, Bob, and Eve. Why not Evan? 😆

    Poništi
  2. 29. pro 2019.

    I resolve not to have any 2020 resolutions (+-). If you want to do something, start today, not in the future.🦉😎

    Poništi
  3. proslijedio/la je Tweet
    15. stu 2019.

    Check out our new method Solo for filtering doublets in scRNA-seq: Using autoencoder embeddings of single cell gene expression profiles and a neural network classifier, we improved doublet identification accuracy.

    Prikaži ovu nit
    Poništi
  4. proslijedio/la je Tweet
    14. stu 2019.

    Machine learning is a bit like cocaine in the 1880s: - been used in a weaker form for centuries - some surprisingly successful early applications led to it now being over-prescribed - beginning to understand that performance degrades after repeated use, negative feedback loops

    Prikaži ovu nit
    Poništi
  5. proslijedio/la je Tweet

    software is essential to science—that’s why we’re supporting 42 open source tools that accelerate biomedical research and serve the larger community. Learn about the grantees

    Prikaži ovu nit
    Poništi
  6. proslijedio/la je Tweet
    8. stu 2019.

    "Go has also found adoption well beyond its original cloud target, with uses ranging from controlling tiny embedded systems with GoBot and TinyGo to detecting cancer with massive big data analysis and machine learning at GRAIL, and everything in between."

    Prikaži ovu nit
    Poništi
  7. proslijedio/la je Tweet

    "Few diagnoses strike more fear than cancer." Read more in on why GRAIL's Josh Ofman believes detecting cancer at earlier stages when treatment may be more effective could translate into improved outcomes.

    Poništi
  8. proslijedio/la je Tweet
    11. stu 2019.

    Collaborator: I know you are super busy finishing the analysis for our current project, but when you are done I need help with this new cool dataset ... Applied statistician:

    Poništi
  9. proslijedio/la je Tweet
    13. stu 2019.

    Release of DeepVariant v0.9: Recommendations for multi-sample calling New visualizations for VCF output Improved Indel accuracy for WGS and WES Improvements for WES at low coverage and buffer regions Updates for new PacBio chemistry and CCS algorithms

    Poništi
  10. 4. lis 2019.

    Aftershocks paper (with questionable machine learning) saga continues

    Poništi
  11. proslijedio/la je Tweet

    Meet the latest addition to our random forest!

    Poništi
  12. proslijedio/la je Tweet
    3. lis 2019.

    I think it would be helpful if people stopped trying to work out whether the (28-year-old) arXiv is 'sustainable' and instead learned from it as a success of non-market approaches to scholarly communication projects.

    Poništi
  13. proslijedio/la je Tweet
    4. lis 2019.

    "We reformulate the 2017 results using two-parameter logistic regression (that is, one neuron) and obtain the same performance as that of the 13,451-parameter deep neural network "

    Poništi
  14. proslijedio/la je Tweet
    3. lis 2019.

    FOUR Productivity FEYNMAN- strategies: • Stop trying to know-it-all. • Don't worry about what others are thinking. • Don't think about what you want to be, but what you want to do. • Have a sense of humor and talk honestly.

    Poništi
  15. 2. lis 2019.

    With bigslice, I can process (i.e. derive features) from ~10K "bams" in ~4h hours. Limiting factor: availability of the instances 😀.

    Prikaži ovu nit
    Poništi
  16. proslijedio/la je Tweet
    2. lis 2019.

    This is a really exciting project. is basically writing a completely new stack of cloud-native cluster computing in the Go ecosystem. Just an amazing set of capabilities. Bigslice is essentially a Spark replacement, built for serverless, with an awesome local exec story.

    Prikaži ovu nit
    Poništi
  17. 2. lis 2019.

    Bigslice - developed and used . Makes it super easy to scale your computations. And it's in Go -- so you also get all the benefits of a compilable language!

    Prikaži ovu nit
    Poništi
  18. proslijedio/la je Tweet
    29. ruj 2019.
    Poništi
  19. 24. ruj 2019.

    This is an awesome way to demystify your predictive models:

    Poništi
  20. proslijedio/la je Tweet
    26. kol 2019.

    Academic statistician tries to apply his recently published method to real-world 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:

    ·