Mohammed AlQuraishi

@MoAlQuraishi

Systems Biology and Pharmacology Fellow at Harvard Medical School. Building machine-learned molecular models for a structural systems biology.

Cambridge, MA
Vrijeme pridruživanja: studeni 2012.

Tweetovi

Blokirali ste korisnika/cu @MoAlQuraishi

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

  1. Prikvačeni tweet
    7. sij

    I’m late to my own party but excited to share our new work on predicting SLiM-mediated protein-protein interactions, out today in with Joe Cunningham, , and ! A blogpost is forthcoming but for now a tweetstorm (1/8)

    Prikaži ovu nit
    Poništi
  2. proslijedio/la je Tweet
    3. velj

    Excited to see this out ! Wonderful design by and great collaboration with our colleagues! Looking forward for the next iterations!

    Poništi
  3. proslijedio/la je Tweet
    23. sij

    I’m thrilled to announce the publication of the quantitive proteomic profiling of the Cancer Cell Line Encyclopedia. The in collaboration with colleagues at Novartis and the Broad we measured the proteomes of 375 cell lines from various tumor lineages (1/13)

    Prikaži ovu nit
    Poništi
  4. 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.

    Poništi
  5. 23. sij

    Here is the promised blogpost: on the motivation behind our modeling / ML approach for protein-peptide interactions. We'll likely have another post soon focused more on the (structural) biology.

    Prikaži ovu nit
    Poništi
  6. proslijedio/la je Tweet
    22. sij

    One of the hardest things to figure out as a PI, especially a young PI, is "when to hold em and when to fold em" with respect to appealing/revising a paper with tough reviews. A few thoughts

    Prikaži ovu nit
    Poništi
  7. proslijedio/la je Tweet
    20. sij

    Happy to share the results of a fun project with : poles are reinforcing asymmetry through selective sequestration of signaling proteins. Wonderful collaboration between and Lucy Shapiro lab.

    Poništi
  8. proslijedio/la je Tweet
    15. sij

    Interested in doing a PhD with me on for improving our understanding of ? Open PhD call . Get in touch if you would like to apply (and meet the eligibility requirements). Deadline Feb 13.

    Poništi
  9. 15. sij

    Glad to see ’s AlphaFold paper finally out. I had the pleasure of being one of the reviewers and getting to write the accompanying article. The future of protein structure prediction is looking very bright!

    Poništi
  10. proslijedio/la je Tweet
    13. sij

    Glycans finally join proteins, DNA, and RNA in getting the language model treatment. Great work by and Jim Collins. Even better, their model is named SweetTalk.

    Poništi
  11. proslijedio/la je Tweet
    13. sij
    Odgovor korisnicima

    If I understood his point, it is not about the difficulty of the questions. It is not about being hard to know how the brain works for example, but the difficulty in the concepts/theory. Are there theories that explain biology that are hard to understand?

    Poništi
  12. proslijedio/la je Tweet
    12. sij

    Does biology have truly difficult ideas? Studying math, comp sci, physics, etc., one quickly encounters material that is hard to truly grasp (and many of us get to a point where we mentally just can't go further, while some others can). Does this exist in biology? If not, why?

    Poništi
  13. proslijedio/la je Tweet
    9. sij

    Is there a list of junior & mid-career PIs that do machine learning for computational biology somewhere on twitter? Would be very useful to consult for speaker invitations, PCs, reviewers ... ?

    Poništi
  14. proslijedio/la je Tweet
    8. sij

    Dream Kinase prediction challenge paper is now on Biorxiv! (Unofficial) top performing model by yours truly

    Prikaži ovu nit
    Poništi
  15. proslijedio/la je Tweet
    7. sij

    Protein sequence design with a learned potential

    Poništi
  16. proslijedio/la je Tweet
    7. sij

    At this rate, Cryo-EM will have overtaken X-ray as the most common technique for new PDB structures in ~4 years.

    Poništi
  17. 7. sij

    Finally what makes this particularly special for me is that it’s Joe’s first paper! Joe came to work with me and Peter Sorger as an MIT undergraduate and it has been a singular joy to work with him throughout this time. His only vice is that he refuses to get on Twitter ;-) (8/8)

    Prikaži ovu nit
    Poništi
  18. 7. sij

    The code is on GitHub (), and there’s a website for interactive predictions and visualizations as well as bulk downloads () (7/8)

    Prikaži ovu nit
    Poništi
  19. 7. sij

    For now we used it to do a reasonably standard network-level analysis of the human proteome, which has revealed interesting aspects of the topological organization of peptide-binding domains. Stay tuned on this front however as we’ll have a lot more to say very soon (6/8)

    Prikaži ovu nit
    Poništi
  20. 7. sij

    It’s also mechanistic in the sense of providing residue-level energetic and structural insights consistent with our understanding of the domain families we have modeled (SH2s, SH3s, PDZs, WWs, PTBs, WH1s, and tyrosine kinases and phosphatases) (5/8)

    Prikaži ovu nit
    Poništi
  21. 7. sij

    The model is mechanistic and interpretable in the sense that we can decompose a multidentate protein-protein interaction, comprised of multiple peptide-binding domains and SLiMs, in terms of the underlying interactions between them (4/8)

    Prikaži ovu nit
    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:

    ·