←
Keating Lab17 posts
Keating Lab avatar

Keating Lab

@keating_lab

We use computational and experimental methods to study protein structure, function, and interactions at @MITBiology @MITBE

◷ Joined April 2021▧ 2 Photos and videos
Keating Lab avatar
Keating Lab@keating_lab·Jan 25

To solve this, Birnbaum and Keating present PottsMPNN, a sequence design model that learns a sequence-energy landscape from MSAs. PottsMPNN outperforms other sequence design models and is a drop-in alternative to ProteinMPNN. Code: github.com/KeatingLab/PottsM… (2/2)

Keating Lab avatar
Keating Lab@keating_lab·27 Nov 2024

RLA has been tested on several benchmark sets, including several design libraries of miniprotein designs for a variety of protein targets. For all but two targets, filtering with RLA results in a higher success rate after subsequent AF2-based filtering. 2/3

Post attachment
Keating Lab avatar
Keating Lab@keating_lab·27 Nov 2024

New work from the lab! Check out RLA (journals.aps.org/prxlife/abs…), a contrastive-learning approach that assesses sequence-structure compatibility by aligning sequence and structure machine learning representations! RLA can successfully filter protein binder designs. 1/3 🧶

Alex J Li avatar
⟳ Keating Lab retweeted
Alex J Li@alex_j_li·22 Aug 2022

First twitter thread🧵and also my first BioRxiv preprint! I’m excited to finally release my undergrad work into the world: combining GNNs, Potts models, and Tertiary Motifs (TERMs) for protein design! See the preprint here: biorxiv.org/content/10.1101/… 1/

PEC Conference avatar
⟳ Keating Lab retweeted
PEC Conference@PEC_conference·21 Jun 2022

Our first keynote speaker: Dr. Amy Keating (@keating_lab). Interested in protein interaction specificity, Dr. Keating highlights the power of data-driven computational exploration of protein interactions. Dr. Keating was our student choice of #PEC2022 and we are ecstatc to host!

Post attachmentPost attachment
Sebastian avatar
⟳ Keating Lab retweeted
Sebastian@SassSeabass·26 May 2022

Fast, reliable, computational methods for designing protein-binding peptides would be immensely useful. As a first step, we show that tertiary structural motifs from the PDB can be used to reconstruct known peptide structures and generate new ones. doi.org/10.1002/pro.4322 (1/9)