Picture

akshay Balsubramani @_bakshay

💻ML/AI |🧬🧪| 📈 • Biotech industry • Ex @StanfordMed, PhD @UCSD, big tech &c • 🇸🇬🇺🇸🇮🇳 • Caveat: humor akshay.bio SF Bay Area Joined August 2016
  • Tweets
    673
  • Followers
    789
  • Following
    639
  • Likes
    10K
akshay Balsubramani retweeted
salonium Profile Picture

Saloni @salonium

3 months ago

Has nominative determinism gone too far (h/t @bschne)

akshay Balsubramani retweeted
bclavie Profile Picture

Ben Clavié @bclavie

7 months ago

What if a [MASK] was all you needed? ModernBERT is great, but we couldn't stop wondering if it could be greater than previous encoders in different ways. Maybe we don't need task-specific heads? Maybe it can do all sort of tasks with only its generative head? Spoilers: Yes

akshay Balsubramani retweeted
PhDemetri Profile Picture

Demetri (is over at the other place too) @PhDemetri

11 months ago

“Shotgun” is a way better name than bootstrap, it isn’t even close.

carlislerainey Profile Picture

Carlisle Rainey @carlislerainey

11 months ago

“Shotgun” is a way better name than bootstrap, it isn’t even close.

akshay Balsubramani retweeted
wpwalters Profile Picture

Patrick Walters @wpwalters

a year ago

Thrilled to announce a preprint describing collaborative work between our group and @fraser_lab, @BShoichet, and @adamrenslo. The paper shows a practical application of the Thompson Sampling method we published earlier this year. biorxiv.org/content/10.110…

akshay Balsubramani retweeted
schwabpa Profile Picture

Patrick Schwab @schwabpa

a year ago

A central challenge of AI-driven biotech is that in drug discovery a fully validated medicine is worth a million times more than a million early-stage ideas that only have little validation. This is unfortunately at odds with the AI domain where we almost always attempt to…

akshay Balsubramani retweeted
SashaGusevPosts Profile Picture

Sasha Gusev @SashaGusevPosts

a year ago

I wrote about some recent studies identifying widespread gene-environment interactions (GxE) acting on common traits, but through an unexpected mechanism. A few highlights 🧵:

akshay Balsubramani retweeted
btnaughton Profile Picture

Brian Naughton @btnaughton

a year ago

Short, interesting antibody design paper using available tools (EvoDiff, ColabFold, HADDOCK, OpenMM). No wet-lab validation, but interesting to see the pipelines people are putting together. Appears to be related to silico.bio biorxiv.org/content/10.110…

akshay Balsubramani retweeted
ccanonne_ Profile Picture

Clément Canonne (on Blue🦋Sky) @ccanonne_

a year ago

Complex numbers are weird and counter-intuitive. For instance, did you know that

akshay Balsubramani retweeted
rlmcelreath Profile Picture

Richard McElreath 🐈‍⬛ @rlmcelreath

a year ago

This last chapter "Horoscopes" is only 3 pages but I keep thinking it should be at the start of the book, because it is about scientific and social context of statistics. Anyway here it is:

economeager Profile Picture

Rafe Meager (they/them) @economeager

a year ago

This last chapter "Horoscopes" is only 3 pages but I keep thinking it should be at the start of the book, because it is about scientific and social context of statistics. Anyway here it is: https://t.co/dHHyE8QxIh

akshay Balsubramani retweeted
jrotwitguez Profile Picture

Juan A. Rodríguez @jrotwitguez

a year ago

Then we repeated the experiment, but we dehydrated the tissue first. The architecture was fine. We left it at room temperature for a year. Still fine. Ran over it with a car, had a former Astros starting pitcher throw a fastball at it, fired a shotgun at it. Still fine. (15/18)

akshay Balsubramani retweeted
sokrypton Profile Picture

Sergey Ovchinnikov @sokrypton

a year ago

📈 One standard graph in all bio deep learning papers should be: max similarity to anything in training set vs performance. (Reviewers shouldn't have to guess if there might be overfitting issues).

akshay Balsubramani retweeted
sarahookr Profile Picture

Sara Hooker @sarahookr

a year ago

Does more compute equate with greater risk? What is our track record at predicting what risks emerge with scale? I don't have much time anymore to write, but this felt important enough to write down some thoughts on. arxiv.org/pdf/2407.05694…

_bakshay Profile Picture

akshay Balsubramani @_bakshay

a year ago

👇👇 for biotech

kchonyc Profile Picture

Kyunghyun Cho @kchonyc

a year ago

👇👇 for biotech

akshay Balsubramani retweeted
thomasahle Profile Picture

Thomas Ahle @thomasahle

a year ago

@Thom_Wolf I'm surprised the MuMath-Code paper wasn't more discussed on Twitter. It is awesome! Super dense in information. Only reference I found was: x.com/gm8xx8/status/… who incidentally tweets about a lot of really interesting papers that don't get much attention.

gm8xx8 Profile Picture

𝚐𝔪𝟾𝚡𝚡𝟾 @gm8xx8

a year ago

@Thom_Wolf I'm surprised the MuMath-Code paper wasn't more discussed on Twitter. It is awesome! Super dense in information. Only reference I found was: x.com/gm8xx8/status/… who incidentally tweets about a lot of really interesting papers that don't get much attention.

akshay Balsubramani retweeted
ronboger Profile Picture

ron boger @ronboger

a year ago

I’m really excited to share our new pre-print “Functional protein mining with conformal guarantees”, with @SeyoneC @ml_angelopoulos @PeterHYoon Michael Jordan @Doudna_lab biorxiv.org/content/10.110… 🧵

akshay Balsubramani retweeted
halilakin Profile Picture

halilakin @halilakin

a year ago

🧵Today is an exciting day! We have just announced ESM3, the design of a new green fluorescent protein, and the launch of our company. Here's a short thread about the scaling and infrastructure work involved in making ESM3 happen! 🧵

alexrives Profile Picture

Alex Rives @alexrives

a year ago

🧵Today is an exciting day! We have just announced ESM3, the design of a new green fluorescent protein, and the launch of our company. Here's a short thread about the scaling and infrastructure work involved in making ESM3 happen! 🧵

akshay Balsubramani retweeted
kchonyc Profile Picture

Kyunghyun Cho @kchonyc

a year ago

read the license before using ESM-3; github.com/evolutionarysc…. you're welcome, pharmas and biotechs.

akshay Balsubramani retweeted
samsinai Profile Picture

Sam Sinai @samsinai

a year ago

I think it's a relevant metric, it's just not very hard. If someone could take a GFP and make it 10000x brighter than any known ones with 192 shots I'd be far more impressed, even if it was at 3 mutations. ESM3 excites me most because it is a relatively high success rate model…

samuel_stanton_ Profile Picture

Samuel Stanton @samuel_stanton_

a year ago

I think it's a relevant metric, it's just not very hard. If someone could take a GFP and make it 10000x brighter than any known ones with 192 shots I'd be far more impressed, even if it was at 3 mutations. ESM3 excites me most because it is a relatively high success rate model…

akshay Balsubramani retweeted
pdhsu Profile Picture

Patrick Hsu @pdhsu

a year ago

What if we could universally recombine, insert, delete, or invert any two pieces of DNA? In back-to-back @Nature papers, we report the discovery of bridge RNAs and 3 atomic structures of the first natural RNA-guided recombinase - a new mechanism for programmable genome design

Trends for United States

Karen
83,5 B posts
Rachel
76,7 B posts
Chiefs
201 B posts
Herbert
57,6 B posts
AJ Lee
252 B posts
Mahomes
68,5 B posts
#SmackDown
198 B posts
Big Brother
24,3 B posts
Ken Dryden
4.143 posts
Kelce
41,8 B posts
Worthy
55,6 B posts
Rich Eisen
5.773 posts
#KCvsLAC
8.199 posts
#OverstockIsBack
Bader
14,3 B posts
Chris Jones
5.394 posts
Jarritos
Keenan Allen
5.588 posts
Tart
6.440 posts
Marvel Tokon
3.070 posts

You might like

My lab at Stanford studies human population genetics and complex traits.
Jonathan Pritchard
@jkpritch
15K Followers
Lab of Michael Elowitz at Caltech. Synthetic biology and systems biology
ElowitzLab
@ElowitzLab
12K Followers
Scientist at DKFZ and EMBL in Heidelberg, loving stats, genomics and genetics. @OliverStegle@genomic.social. For group news see @StatGenomics.
Oliver Stegle
@OliverStegle
8K Followers
Ray and Stephanie Lane Professor of Computational Biology at CMU School of Computer Science @CMUCompBio @SCSatCMU @CarnegieMellon
Jian Ma
@jmuiuc
8K Followers
Head of the Perception and Intelligence Lab (PINlab) and professor @ Computer Science Dept Sapienza University Research on computer vision and machine learning
Fabio Galasso
@GalassoFab10
848 Followers
Asst Prof @UMassGCB, Board of Directors @NumFOCUS. Prev Guest Scientist @impvienna @StanfordMed @uwcse. Studying genomics, machine learning, and fruit.
Jacob Schreiber
@jmschreiber91
5K Followers
Kipoi: Model zoo for genomics
Kipoi
@KipoiZoo
631 Followers
Co-founder and Head of Machine Learning @Dyno_Tx. Previously CompBio @Harvard + CS/AI @MIT. Tweets are my own views/interests.
Sam Sinai
@samsinai
3K Followers
Research scientist at @GoogleDeepMind. Previously PhD student @gagneurlab working on deep learning methods for genomics.
Žiga Avsec
@Avsecz
2K Followers
Computational methods for epigenetic, CRISPR genome editing and single-cell genomics. Associate Professor at MGH / Harvard Medical School. https://t.co/GouTKpGNR2
Luca Pinello
@lucapinello
4K Followers
Sr Lecturer at MIT Math/ESG, data science & topology. ML @CellarityBio; Institute Scientist, @hailgenetics & MIA @BroadInstitute; math at MIT, Columbia, Harvard
Jon Bloom
@MorseCell
2K Followers
Using computers to understand the molecular logic of life.
David Kelley
@drklly
2K Followers
Research Scientist @GoogleDeepMind | PhD from @ucberkeley in Computational Biology | Views are my own
Adam Gayoso
@adamgayoso
1K Followers
Machine learning and genetics @Genentech. Previously CS PhD @Stanford.
Surag Nair
@suragnair
961 Followers
Assistant Professor @Yale @YaleMed @YaleCSDept | ML/AI comp bio
David van Dijk
@david_van_dijk
5K Followers