Possu Huang Lab
@PossuHuangLab
Followers
2K
Following
103
Media
22
Statuses
80
Our lab uses experimental and computational methods to design de novo proteins | @Stanford
Stanford, CA
Joined October 2022
1/ In two back-to-back papers, we present our de novo TRACeR platform for targeting MHC-I and MHC-II antigens. TRACeR for MHC-I: TRACeR for MHC-II: @HaotianDu4 @ljjchem @SgourakisLab @StanfordBiosci @UPennAllergyImm @CHOP_Research
5
73
282
RT @CryoKhan: Full-atom MPNN (FAMPNN) - a sequence design method that explicitly models both sequence identity and sidechain conformation.….
0
35
0
RT @BiologyAIDaily: Sidechain conditioning and modeling for full-atom protein sequence design with FAMPNN. 1. This paper introduces FAMPNN….
0
12
0
RT @KevinKaichuang: All-atom fixed backbone protein sequence design with FAMPNN. @richardwshuai @talaldotpdb @PossuHuangLab @BrianHie https….
0
30
0
RT @BrianHie: In new work led by @talaldotpdb and @richardwshuai, we make exciting progress toward functional molecular design by augmentin….
0
8
0
RT @talaldotpdb: Excited to share our joint work with @richardwshuai, Full-Atom MPNN (FAMPNN), a protein sequence design method that explic….
0
52
0
RT @KevinKaichuang: A framework for evaluating how well generative models of protein structure match the distribution of natural structures….
0
31
0
RT @MoAlQuraishi: I'm organizing a Keystone symposium, along with @kellogg_liz and @PossuHuangLab, on machine learning and macromolecules.….
0
21
0
Our supplement has many additional figures of the rasterized protein structure space, stratified by designable and not designable and spatially organized by ESM3 and ProtDomainSegmentor embeddings. Also includes Foldseek token distributions and more designability analysis.
1
0
2
One consequence of unbiased sampling of protein structure space is a higher likelihood of finding TERtiary Motifs (TERMs) which involve complex loops, with implications for functional protein design (see Figure 5 legend for group labels).
1
0
2
Inspired by the FPD metric in EvoDiff for protein sequence distributions, we compute Fréchet distance using protein structure embeddings, subsetted to designable and non-designable samples (FPD-D and FPD-ND).
1
0
3
New preprint from our group! We propose SHAPES, a set of metrics to quantify the distributional coverage of generative models of protein structures with embeddings at different structural hierarchies and quantify undersampling / extrapolation behaviors.
4
41
154
RT @biorxiv_bioeng: Assessing Generative Model Coverage of Protein Structures with SHAPES #biorxiv_bioeng.
0
2
0
RT @BiologyAIDaily: Assessing Generative Model Coverage of Protein Structures with SHAPES. 1. This paper introduces SHAPES, a comprehensive….
0
8
0
RT @StanfordCancer: TRACeR platforms more accurately recognize a wide variety of surface proteins expressed by cancer cells, which makes th….
0
3
0
RT @NatureBiotech: A method for designing high-affinity, specific binders to peptide–MHC complexes may improve the next generation of antig….
0
40
0
RT @Steph_Gaglione: Our piece celebrating the @PossuHuangLab's clever approach to designing high-affinity, specific binders to peptide–MHC….
0
7
0
RT @StanfordOTL: New immunotherapy platform could increase potential to target cancer cells.@PossuHuangLab.🔬Read ab….
0
1
0