View source for 8xyr


==De novo designed protein GPX4-2==
<StructureSection load='8xyr' size='340' side='right'caption='[[8xyr]], [[Resolution|resolution]] 1.87&Aring;' scene=''>
== Structural highlights ==
<table><tr><td colspan='2'>[[8xyr]] is a 1 chain structure with sequence from [https://en.wikipedia.org/wiki/Synthetic_construct Synthetic construct]. Full crystallographic information is available from [http://oca.weizmann.ac.il/oca-bin/ocashort?id=8XYR OCA]. For a <b>guided tour on the structure components</b> use [https://proteopedia.org/fgij/fg.htm?mol=8XYR FirstGlance]. <br>
</td></tr><tr id='method'><td class="sblockLbl"><b>[[Empirical_models|Method:]]</b></td><td class="sblockDat" id="methodDat">X-ray diffraction, [[Resolution|Resolution]] 1.87&#8491;</td></tr>
<tr id='resources'><td class="sblockLbl"><b>Resources:</b></td><td class="sblockDat"><span class='plainlinks'>[https://proteopedia.org/fgij/fg.htm?mol=8xyr FirstGlance], [http://oca.weizmann.ac.il/oca-bin/ocaids?id=8xyr OCA], [https://pdbe.org/8xyr PDBe], [https://www.rcsb.org/pdb/explore.do?structureId=8xyr RCSB], [https://www.ebi.ac.uk/pdbsum/8xyr PDBsum], [https://prosat.h-its.org/prosat/prosatexe?pdbcode=8xyr ProSAT]</span></td></tr>
</table>
<div style="background-color:#fffaf0;">
== Publication Abstract from PubMed ==
Designing sequences for specific protein backbones is a key step in creating new functional proteins. Here, we introduce GeoSeqBuilder, a deep learning framework that integrates protein sequence generation with side chain conformation prediction to produce the complete all-atom structures for designed sequences. GeoSeqBuilder uses spatial geometric features from protein backbones and explicitly includes three-body interactions of neighboring residues. GeoSeqBuilder achieves native residue type recovery rate of 51.6%, comparable to ProteinMPNN and other leading methods, while accurately predicting side chain conformations. We first used GeoSeqBuilder to design sequences for thioredoxin and a hallucinated three-helical bundle protein. All the 15 tested sequences expressed as soluble monomeric proteins with high thermal stability, and the 2 high-resolution crystal structures solved closely match the designed models. The generated protein sequences exhibit low similarity (minimum 23%) to the original sequences, with significantly altered hydrophobic cores. We further redesigned the hydrophobic core of glutathione peroxidase 4, and 3 of the 5 designs showed improved enzyme activity. Although further testing is needed, the high experimental success rate in our testing demonstrates that GeoSeqBuilder is a powerful tool for designing novel sequences for predefined protein structures with atomic details. GeoSeqBuilder is available at https://github.com/PKUliujl/GeoSeqBuilder.

All-Atom Protein Sequence Design Based on Geometric Deep Learning.,Liu J, Guo Z, You H, Zhang C, Lai L Angew Chem Int Ed Engl. 2024 Sep 19:e202411461. doi: 10.1002/anie.202411461. PMID:39295564<ref>PMID:39295564</ref>

From MEDLINE&reg;/PubMed&reg;, a database of the U.S. National Library of Medicine.<br>
</div>
<div class="pdbe-citations 8xyr" style="background-color:#fffaf0;"></div>
== References ==
<references/>
__TOC__
</StructureSection>
[[Category: Large Structures]]
[[Category: Synthetic construct]]
[[Category: Guo Z]]
[[Category: Lai LH]]
[[Category: Liu LJ]]