Sign in

Sewon Lee

@sewonlee.bsky.social
284 followers 48 following 0 posts

Studying RecSys, Bioinfo @ Seoul National Univ. 🇰🇷 • former Steinegger Lab • 🧠 → 🧬 → 💻

PostsRepliesMedia
Reposted by Sewon Lee
Martin Steinegger 🇺🇦 @martinsteinegger.bsky.social · 03/06/2025
Our structural core gene pipeline Unicode is now published at GBE 📄 doi.org/10.1093/gbe/... Please also check out @dongwookkim.bsky.social’s 🧵 bsky.app/profile/dong...
doi.org
Unicore Enables Scalable and Accurate Phylogenetic Reconstruction with Structural Core Genes
Abstract. The analysis of single-copy core genes, common to most members of a clade, is important for key tasks in biology including phylogenetic reconstru
24519
Reposted by Sewon Lee
Dongwook Kim @dongwookkim.bsky.social · 03/06/2025
Unicore is now published on GBE 🚀 Unicore rapidly identifies structural single-copy core genes from input species proteomes for phylogenetic analysis. Powered by Foldseek and ProstT5, Unicore enables linear-scale structure-based phylogeny of any given set of taxa. 🧵1/n 📃 doi.org/10.1093/gbe/evaf109
36831
Reposted by Sewon Lee
Eugene Yan @eugeneyan.com · 08/04/2025
Can't wait for when I can vibe code a production recommender system. Until then, here's some system designs: • Retrieval vs. Ranking: eugeneyan.com/writing/syst... • Real-time retrieval: eugeneyan.com/writing/real... • Personalization: eugeneyan.com/writing/patt...
Two-stage recommender systemZalando's recommender systemUnified embeddingsDoordash's search system
1484
Reposted by Sewon Lee
Eugene Yan @eugeneyan.com · 31/01/2025
What industrial recsys papers have you enjoyed or found useful in the past year or two? Sharing my list: # 1. Integrating LLMs into recsys 1.1. LLM-augmented recommenders • Better Generalization with Semantic IDs: A Case Study in Ranking for Recommendations - arxiv.org/abs/2306.08121
1467
Reposted by Sewon Lee
snuchem.bsky.social @snuchem.bsky.social · 08/01/2025
SNU Profs Woon Ju Song & Martin Steinegger (Biology) developed the AI-based SeekRank algorithm to discover enzymes for cancer immunotherapy. doi.org/10.1093/nar/...
doi.org
Discovery of highly active kynureninases for cancer immunotherapy through protein language model
Abstract. Tailor-made enzymes empower a wide range of versatile applications, although searching for the desirable enzymes often requires high throughput s
076
Reposted by Sewon Lee
Martin Steinegger 🇺🇦 @martinsteinegger.bsky.social · 23/12/2024
Unicore identifies single-copy protein structures across genomes using Foldseek, bypassing slow structure predictions by utilizing 3Di predictions from ProstT5, enabling rapid phylogenetic inference at the tree-of-life scale. 1/n 📄 www.biorxiv.org/content/10.1... 💾 github.com/steineggerla...
212256
Reposted by Sewon Lee
bioRxiv Bioinfo @biorxiv-bioinfo.bsky.social · 23/12/2024
Unicore enables scalable and accurate phylogenetic reconstruction with structural core genes www.biorxiv.org/content/10.1101/202…
053
Reposted by Sewon Lee
Eugene Yan @eugeneyan.com · 27/11/2024
And if you're looking for more learning over the long thanksgiving weekend, this could be a good place to start: eugeneyan.com/start-here/
Writeups on machine learning systems, techniques, ml & engineering, and weekend prototypes
1145
Reposted by Sewon Lee
Martin Steinegger 🇺🇦 @martinsteinegger.bsky.social · 23/11/2024
Our Big Fantastic Virus Database (BFVD) is now published NAR! It contains protein structure predictions of major viral clades, enhanced by petabase-scale homology search and it's explorable on the web. 🌐 bfvd.foldseek.com 💾 bfvd.steineggerlab.workers.dev 📄 academic.oup.com/nar/advance-...
6339126