|
Greg Koytiger
@
GregKoytiger
Boston, MA
|
|
VP, Head of AI Products @ Cascade.bio
|
|
|
75
Tweetovi
|
144
Pratim
|
73
Osobe koje vas prate
|
| Tweetovi |
| Greg Koytiger proslijedio/la je tweet | ||
|
Mohammed AlQuraishi
@MoAlQuraishi
|
23. sij |
|
Here is the promised blogpost: protocolsmethods.springernature.com/users/346093-m… 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.
|
||
|
|
||
| Greg Koytiger proslijedio/la je tweet | ||
|
Mohammed AlQuraishi
@MoAlQuraishi
|
15. sij |
|
Glad to see @DeepMindAI’s AlphaFold paper finally out. I had the pleasure of being one of the reviewers and getting to write the accompanying @NatureNV article. The future of protein structure prediction is looking very bright! twitter.com/mvicaracal/sta…
|
||
|
|
||
|
Greg Koytiger
@GregKoytiger
|
14. sij |
|
I gonna fit a Transformer to that and get SOTA
|
||
|
|
||
| Greg Koytiger proslijedio/la je tweet | ||
|
emedgene
@emedgene
|
10. sij |
|
Researchers developed a bespoke machine-learning approach, hierarchical statistical mechanical modelling, for the accurate prediction of protein–peptide interactions across multiple protein families. @MoAlQuraishi @GregKoytiger @naturemethods nature.com/articles/s4159…
|
||
|
|
||
|
Greg Koytiger
@GregKoytiger
|
8. sij |
|
For me, the most important take away is Figure 5 - that current machine learning approaches are of higher fidelity than high throughput experiments! For another example, see Figure 2b from the Nature Methods paper yesterday nature.com/articles/s4159…
|
||
|
|
||
|
Greg Koytiger
@GregKoytiger
|
8. sij |
|
Dream Kinase prediction challenge paper is now on Biorxiv! (Unofficial) top performing model by yours truly @DR_E_A_M biorxiv.org/content/10.110…
|
||
|
|
||
| Greg Koytiger proslijedio/la je tweet | ||
|
François Chollet
@fchollet
|
7. sij |
|
Our field isn't quite "artificial intelligence" -- it's "cognitive automation": the encoding and operationalization of human-generated abstractions / behaviors / skills. The "intelligence" label is a category error
|
||
|
|
||
| Greg Koytiger proslijedio/la je tweet | ||
|
Mohammed AlQuraishi
@MoAlQuraishi
|
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 @naturemethods with Joe Cunningham, @GregKoytiger, and @sorger_peter! A blogpost is forthcoming but for now a tweetstorm (1/8) nature.com/articles/s4159…
|
||
|
|
||
| Greg Koytiger proslijedio/la je tweet | ||
|
Kevin Yang 楊凱筌
@KevinKaichuang
|
7. sij |
|
Joseph Cunningham @GregKoytiger Peter Sorger and @MoAlQuraishi use energy-based ML to predict protein-peptide interactions. Their model is interpretable, naturally incorporates physical "priors", and outperforms high-throughput experiments!
nature.com/articles/s4159… pic.twitter.com/BhXCDQSYCJ
|
||
|
|
||
| Greg Koytiger proslijedio/la je tweet | ||
|
Tim Urban
@waitbutwhy
|
6. sij |
|
The path of a maturing thinker. In order to get to Grown-Up Mountain and start real learning, you have to brave the cold winds of Insecure Canyon. If you're not willing to say "I don't know" for a while, you might spend your whole life on Child’s Hill. pic.twitter.com/8YT6emJcB3
|
||
|
|
||
| Greg Koytiger proslijedio/la je tweet | ||
|
Mohammed AlQuraishi
@MoAlQuraishi
|
31. pro |
|
A piece of holiday-time reflection: one thing I’m grateful about in science is the existence of a real field-wide community, made more visible by Twitter. I suspect this is less true in other professions and is a genuinely positive feature.
|
||
|
|
||
| Greg Koytiger proslijedio/la je tweet | ||
|
Lara Yuan
@LaraMYuan
|
25. pro |
|
Happy holidays from the Cascade team (minus a few)! It's been an amazing year with these incredible people, here's to an even better 2020! pic.twitter.com/S5Owwwq1N5
|
||
|
|
||
| Greg Koytiger proslijedio/la je tweet | ||
|
Arvind Narayanan
@random_walker
|
24. pro |
|
Reminder: student evaluations of teaching tend to show stark racial and gender biases, and don't actually measure teaching effectiveness. A statement endorsed by 22 scholarly associations calls for limiting the role of student ratings in faculty review: asanet.org/sites/default/…
|
||
|
|
||
| Greg Koytiger proslijedio/la je tweet | ||
|
XKCD Comic
@xkcdComic
|
27. stu |
|
|
||
|
|
||
| Greg Koytiger proslijedio/la je tweet | ||
|
Kevin Yang 楊凱筌
@KevinKaichuang
|
25. stu |
|
Cool paper on combining meta- and active learning to efficiently learn protein function from protein sequence, from Rainier Barrett and @andrewwhite01
arxiv.org/abs/1911.09103 pic.twitter.com/olB7VS9AO6
|
||
|
|
||
| Greg Koytiger proslijedio/la je tweet | ||
|
Mohammed AlQuraishi
@MoAlQuraishi
|
19. stu |
|
Great work using inter-residue orientations to exceed AlphaFold’s performance on protein structure prediction by Jianyi Yang, Ivan Anishchenko, and others from the Baker lab: biorxiv.org/content/10.110…. First heard about this at RosettaCon and I’m very glad to finally see it out!
|
||
|
|
||
| Greg Koytiger proslijedio/la je tweet | ||
|
Vala Afshar
@ValaAfshar
|
13. stu |
|
This is how octopuses use camouflage in the wild pic.twitter.com/csAIOcSBix
|
||
|
|
||
| Greg Koytiger proslijedio/la je tweet | ||
|
cj battey
@cj_battey
|
4. stu |
|
And the oscar for best figure goes to ... twitter.com/biorxiv_evobio… pic.twitter.com/YGoyJqLCi2
|
||
|
|
||
| Greg Koytiger proslijedio/la je tweet | ||
|
Daniel MacArthur
@dgmacarthur
|
31. lis |
|
Your annual reminder of arguably the greatest thread of science Twitter poetry of all time.
To all scientists this Halloween eve: may the sparrow of doubt hover close enough to guide you to rigor, but not so close that you are paralyzed into inaction. 🎃 twitter.com/dallandrummond…
|
||
|
|
||
| Greg Koytiger proslijedio/la je tweet | ||
|
Tami Lieberman
@conTaminatedsci
|
29. lis |
|
Engineering orthogonal signalling pathways reveals the sparse occupancy of sequence space. nature.com/articles/s4158… Congrats on the great paper @michael_laub8 @conor_mcclune
|
||
|
|
||