Romero lab
@romerolab1
Followers
846
Following
275
Media
27
Statuses
131
Romero Lab @DukeUBME. Run by his grad students. We love proteins and engineering them.
Joined February 2021
🎉Congrats to Nate for his preprint, jointly with @vatsanraman, where training on multifunctional data enabled precise control over designing phages with complex infectivity & specificity. Big shifts in host targeting come from just a few mutations!
1
6
51
RT @romerolab1: 🎉Congrats to Nate for his preprint, jointly with @vatsanraman, where training on multifunctional data enabled precise contr….
0
6
0
We love having Nate in both the Raman and Romero labs!.
Designing proteins for multiple, often competing objectives is a major challenge. In our new preprint, we use deep learning + protein language models to design phages with higher activity, defined specificity, and generalizable infectivity—meeting 26 design goals across several
0
0
1
RT @vatsanraman: Designing proteins for multiple, often competing objectives is a major challenge. In our new preprint, we use deep learnin….
0
13
0
RT @BiologyAIDaily: Multiobjective learning and design of bacteriophage specificity. １．This study presents a landmark demonstration of mult….
0
11
0
RT @romerolab1: Excited to share @NathanielBlalo2 and @srivsesh preprint teaching protein language models to generate beyond what evolution….
0
8
0
RT @KevinKaichuang: Reinforcement learning with experimental feedback (RLXF) shifts protein language models so that they generate sequences….
0
24
0
RT @BiologyAIDaily: Functional alignment of protein language models via reinforcement learning. １．This work introduces RLXF, a general fram….
0
9
0
RT @BiologyAIDaily: Functional alignment of protein language models via reinforcement learning. １．This work introduces RLXF, a general fram….
0
6
0
RT @NathanielBlalo2: We are excited at the @romerolab1 to share our new preprint introducing RLXF for the functional alignment of protein l….
0
27
0
RT @srivsesh: RLXF is on @biorxivpreprint! We introduce a PPO-based workflow to align the logits of any protein language model away from e….
0
24
0
RT @BiologyAIDaily: Functional Alignment of Protein Language Models via Reinforcement Learning with Experimental Feedback. 1. This study in….
0
7
0
RT @biorxiv_bioeng: Functional alignment of protein language models via reinforcement learning #biorxiv_bioeng.
0
1
0
RT @bioRxiv_bioE: Functional alignment of protein language models via reinforcement learning . #biorxiv_bioE.
0
1
0
RT @srivsesh: . it works in silico across a wide number of targets, and in vivo! We designed 5 & 10 mutants of CreiLOV - aligned models d….
0
1
0
This work also builds on recent work they presented @workshopmlsb @NeurIPSConf back in December! Short form paper can be found here⬇️.
Excited that @srivsesh and I will be attending our 1st NeurIPS conference and presenting our preliminary work in the Functional Alignment of Protein Language Models via Reinforcement Learning with Experimental Feedback! We'd love to talk ab/ our work with those attending!
0
0
5
Importantly, wet lab validation of aligned models generate CreiLOV variants with improved fluorescence. A big step toward function-driven protein design!
1
0
4