I'm a PhD student in Computer Science at Stanford University. My research focuses on machine learning applied to biomedicine and drug discovery.
Stanford, CA
- Tweets 108
- Following 486
- Followers 884
- Likes 513
Really cool work on self-organizing agents from @aneeshpappu!
The recent breakthrough in Navier-Stokes has garnered a lot of attention to the new possibilities that emerge when agents work together.
We have been interested in this question for a while. How can a team of agents achieve more than agents working alone?
I'm excited to finally share our new work, "Self-Organizing Agent Teams Learn to Reason Together" 🧵
1
4
622
Kyle Swanson retweeted
1/ Today, @james_y_zou, @pmphlt, @jurafsky, and I are releasing string2string Studio: an open-source, in-browser platform that brings alignment, comparison, search, and evaluation into one interactive, visual environment for strings and sequences.
See: string2string.org/
1
12
54
21,566
Kyle Swanson retweeted
Really cool to see SynthMol-RL featured on the cover of @MolSystBiol!
Reinforcement learning makes small-molecule drug discovery more effective and easier to synthesize.
Paper: link.springer.com/article/10…
Code: github.com/swansonk14/Synthe…
Awesome collaboration w/ @ItsJonStokes lab led by @KyleWSwanson and Gary Liu
1
9
44
3,852
Kyle Swanson retweeted
A sparse autoencoder aims to learn a dictionary of interpretable features from a model's activations — but a lot can come out "dead," never firing once. On some models this is rare; on others, >70% die even with fixes like AuxK. We went down a rabbit hole to understand why...
6
36
163
41,613
Kyle Swanson retweeted
1/ AI chatbots are quietly becoming news intermediaries: about 1 in 10 U.S. adults already use them for news, and more among the young. So we asked whether they're ready. In mid-February, over 14 days, we tested six leading systems on same-day BBC reporting in six languages.
1
9
45
26,878
Kyle Swanson retweeted
Oral GLP-1s make 1 thing clear: patients want pills. But orals, small molecules especially, are still brutally hard to develop. A close look at why the oral small molecule problem persists, and how the AI wave may finally solve it.
With Isomorphic's $2.1B raise and multiple programs in Phase 3, the first AI-enabled oral drug could be approved within the next few years.
“The future has already arrived. It’s just not evenly distributed yet.”
nitter.net/SylvainGariel/status/2…
1
2
7
696
Kyle Swanson retweeted
Sutton's Bitter Lesson has a bitter footnote in drug discovery.
Two atoms turned xanomeline into Cobenfy ($14B Karuna acquisition). One residue separates sotorasib's modest PFS from daraxonrasib's near-doubling of OS in pancreatic cancer.
Pure scale won't get you there anytime soon. ↓
nitter.net/SylvainGariel/status/2…
2
6
25
2,785
Kyle Swanson retweeted
Excited to share @tutorintel's Data Factory 1, a 100 robot semi-humanoid research farm and the largest robot data factory in the United States.
Our first embodiment “Cassie” is deployed at industrial scale across the supply chain. We built DF1 to bootstrap fleet-scale learning for our "Sonny" industrial semi-humanoid embodiment, powered by our first end-to-end robot foundation model Ti0.
41
103
590
102,991
Following our publication of SyntheMol-RL last week, I'm excited to share the results and learnings from an extensive collaboration with @Merck applying SyntheMol-RL to two of their internal drug discovery pipelines. 1/5
swansonkyle.com/blog/synthem…
2
2
29
3,131
We share our results and learnings on two internal programs at Merck: a human therapeutic program and an antibacterial program. We were excited to see promising preliminary results on both projects. We also discuss challenges and share takeaways for future work. 4/5
1
3
169
Thank you @alanchengsf, Maria Chiriac, @james_y_zou, and all of our other colleagues at Merck for a great project and a really unique opportunity to apply SyntheMol-RL to real-world drug discovery programs! 5/5
5
138
Kyle Swanson retweeted
>700K people die every year due to S. aureus infection.
SyntheMol-RL created a new molecule that stops drug-resistant S. aureus MRSA—validated in mice studies.
AI accelerating drug discovery; published today!👇
Great collab w/ @ItsJonStokes' lab led by @KyleWSwanson Gary Liu
SyntheMol-RL has now been published! SyntheMol-RL is a reinforcement learning model for synthesizable small molecule drug design. We used it to design antibiotic candidates for the bacteria S. aureus with hits validated in vitro and in vivo in mice. 1/6 link.springer.com/article/10…
1
16
83
49,144
SyntheMol-RL has now been published! SyntheMol-RL is a reinforcement learning model for synthesizable small molecule drug design. We used it to design antibiotic candidates for the bacteria S. aureus with hits validated in vitro and in vivo in mice. 1/6 link.springer.com/article/10…
5
15
79
41,545
We tested one particularly potent molecule, which we call synthecin, in a mouse skin infection model of methicillin-resistant S. aureus (MRSA) and found that it was safe and highly effective at treating the infection. 5/6
1
2
6
611
SyntheMol-RL is fully open source for everyone to use. Thank you Gary Liu, Denise Catacutan, @ItsJonStokes, @james_y_zou, and our collaborators for a fun project! 6/6 github.com/swansonk14/Synthe…
2
9
527