Gerald Quon

@ItaiYanai One potential problem is that for deeper papers or those with lots of experiments (thinking about those with a big supplement), it might be hard to make an informed decision immediately. This sounds good for clear accepts or rejects, not sure about other less clear cut papers

Science is hard, but some of the frustration is unnecessary. My colleagues and I often feel that if we could just talk with the reviewers, we could easily overcome the constant misunderstandings that happen over months of back and forth rebuttals/revisions. Hear me out: (1/5)

Register (FREE) for #MLCB2021 mlcb.github.io Nov 22-23, 9am-5pm PST Keynotes: Regina Barzilay, @drklly, @seeliglab Industry panel: Kyle Farh @illumina, Berton Earnshaw @RecursionPharma, Amit Deshwar @deepgenomics, Ayla Ergun @FulcrumTx 16 talks, 21 spotlights, posters

Deep learning has obviously transformed protein structure prediction, but can it do the same for the rest of biology? In a perspective by @sorger_peter and myself out this week in @naturemethods, we begin to try to answer this question: rdcu.be/cyMvO

Machine Learning in Computational Biology deadline extended until Wednesday 10/6, submit your 2 page abstract or 8 page paper at cmt3.research.microsoft.com/MLCB2021/. #MLCB2021 Please RT!

Thrilled to be awarded an @NIHDirector New Innovator Award to work on frameworks for integrating multimodal datasets! #NIHHighRisk

@david_a_knowles PGP? pgp.med.harvard.edu

Genetics twitter: I'm teaching an ML for genetics/genomics class w/ a project. Some students want to do GWASy things that would need individual level data. Any fully open access options? Thinking non-human might be easier.

A friend (who does not work in science) asked me today whether it is true that "protein folding has been solved". My short answer: The AlphaFold method produced very impressive results on CASP14. Protein folding is not a solved problem.

@MoAlQuraishi Interesting, though there's no mention in the nature article on how novel the structures were this year -- how well represented are the structures predicted in existing datasets nowadays?

CASP14 #s just came out and they’re astounding—DeepMind looks to have solved protein structure prediction. Median GDT_TS went from 68.5 (CASP13) to 92.4!!!! Cf. their 2nd best CASP13 struct scored 92.8 (out of 100). Median RMSD is 2.1Å. I think it's over predictioncenter.org/casp14/zscores…

@DanStarrUCDavis I think there is already to some degree, I usually get a bunch of requests through applyweb.com from multiple schools for the same person?

I have over 50 letters of rec to send for grad schools and the first one crashed my computer. When are we going to figure out how to have a central service do this like the med schools do?

#MLCB 2020 is going live right now! Don't worry if you didn't register, you can watch the Youtube livestream youtube.com/watch?v=BYanbn…, schedule at sites.google.com/cs.washington.… Aviv Regev is first up!

@astrofrog @DrAnneCarpenter Upgraded a 2019 Intel based macbook pro, and it made my external monitor blink continuously immediately after install. Monitor still works fine with other machines so likely a big sur problem.

Researchers who use Macs, PLEASE don't upgrade to MacOS X Big Sur or buy a new M1 mac yet: a short thread. (1/n)

So many good conferences are happening virtually this month. Here is one more: MLCB2020 mlcb.org conference is next week, Nov 23-24. Check out the full schedule that is just up now. Make sure to register if you plan to join!

Application deadline 12/1/2020: Information and Tips for IGG Prospective Students | IGG Graduate Group igg.ucdavis.edu/information-an…

Assistant Professor of Teaching Position in Quantitative Biology at @ucdavis. The position will reside in the Dept. of Evolution & Ecology (eve.ucdavis.edu) and be affiliated with the planned interdisciplinary major in Quant. Bio. Please retweet! recruit.ucdavis.edu/JPF03860

@DanStarrUCDavis @gwgl1979 Congrats!

The Paul G. Allen Frontiers Group Announces New Allen Distinguished Investigators alleninstitute.org/what-we-do/fro… I am incredibly honored and grateful to be named an Allen Distinguished Investigator along with my co-PI @gwgl1979 1/n

@aaronquinlan We use Miro for brainstorming and planning, not as great for replacing traditional whiteboards like jamboard though

Anyone know of better alternatives to Google Jamboard for collaborative whiteboarding? jamboard.google.com

Happy to see this paper out. Interpreting what CNNs have learned on large compendium of ATAC-seq data was surprising: much of the learnt parameters point to validated biological mechanisms. Deep learning of immune cell differentiation pnas.org/content/early/…

Dear Colleagues, Good news! The deadline for Machine Learning in Computational Biology (MLCB) meeting has been extended to October 2nd (Fri), 2020. MLCB organizers mlcb.github.io @anshulkundaje @sara_mostafavi @james_y_zou @david_a_knowles @QuonBio

We have a fantastic lineup of keynotes for #MLCB2020 (Nov 23-24): Aviv Regev, @BarzilayRegina, @marinkazitnik & @segal_eran. Submissions due Sept 30th at cmt3.research.microsoft.com/mlcb2020. Register (for free!) at forms.gle/ZSwPFoLQ3iWBed…, more deets at mlcb.github.io Please RT!

@emukamel Octave? :)