Anvita Gupta
@avgupta.bsky.social
Founder/CEO @ AINovo Biotech. Prev: AI + Genomics @ Stanford Computer Science, computational drug discovery @ ETH, Harvard. AI Optimist for Human Health.
Reposted by Anvita Gupta
Exciting discovery by Svensson lab and collaborators @stanfordmedicine.bsky.social, computational discovery of 2500 new bioactive peptides, including 12-mer named BRP that reduces food intake leading to weight loss w/o nausea in mice!
www.nature.com/articles/s41...
www.nature.com/articles/s41...
Prohormone cleavage prediction uncovers a non-incretin anti-obesity peptide - Nature
Computational drug discovery is used to identify a 12-mer peptide derived from BRINP2 with potent anti-obesity effects that are independent of leptin, glucagon-like peptide 1 receptor and melanocortin...
www.nature.com
March 11, 2025 at 11:22 PM
Exciting discovery by Svensson lab and collaborators @stanfordmedicine.bsky.social, computational discovery of 2500 new bioactive peptides, including 12-mer named BRP that reduces food intake leading to weight loss w/o nausea in mice!
www.nature.com/articles/s41...
www.nature.com/articles/s41...
Reposted by Anvita Gupta
There it is again: using PLMs to predict antigen-epitope interactions from sequence alone yields a prediction accuracy of 0.65, in line with a proposed upper limit from a previous study QTed below (from doi.org/10.1101/2025.02.12.637989; I deleted an older version of this post due to typos/errors)
March 3, 2025 at 5:45 AM
There it is again: using PLMs to predict antigen-epitope interactions from sequence alone yields a prediction accuracy of 0.65, in line with a proposed upper limit from a previous study QTed below (from doi.org/10.1101/2025.02.12.637989; I deleted an older version of this post due to typos/errors)
Reposted by Anvita Gupta
🔥 Benchmark Alert! MotifBench sets a new standard for evaluating protein design methods in motif scaffolding.
Why does this matter? Reproducibility & fair comparison have been lacking—until now.
Paper: arxiv.org/abs/2502.12479 | Repo: github.com/blt2114/Moti...
A thread ⬇️
Why does this matter? Reproducibility & fair comparison have been lacking—until now.
Paper: arxiv.org/abs/2502.12479 | Repo: github.com/blt2114/Moti...
A thread ⬇️
February 19, 2025 at 8:50 PM
🔥 Benchmark Alert! MotifBench sets a new standard for evaluating protein design methods in motif scaffolding.
Why does this matter? Reproducibility & fair comparison have been lacking—until now.
Paper: arxiv.org/abs/2502.12479 | Repo: github.com/blt2114/Moti...
A thread ⬇️
Why does this matter? Reproducibility & fair comparison have been lacking—until now.
Paper: arxiv.org/abs/2502.12479 | Repo: github.com/blt2114/Moti...
A thread ⬇️
For April Fool's day they should rename "LinkedIn" to "LockedIn"
February 7, 2025 at 4:13 AM
For April Fool's day they should rename "LinkedIn" to "LockedIn"
Reposted by Anvita Gupta
How a heart medication—digoxin—might help prevent cancer spread by dissolving clusters of circulating tumor cells
www.nature.com/articles/s41...
www.nature.com/articles/s41...
January 24, 2025 at 2:50 PM
How a heart medication—digoxin—might help prevent cancer spread by dissolving clusters of circulating tumor cells
www.nature.com/articles/s41...
www.nature.com/articles/s41...
The bluesky algorithm is so much more peaceful than X. I'm learning again rather than being bombarded with extreme views! I even saw a picture of an Owl!
January 25, 2025 at 12:14 AM
The bluesky algorithm is so much more peaceful than X. I'm learning again rather than being bombarded with extreme views! I even saw a picture of an Owl!