2023
DOI: 10.1101/2023.03.16.531341
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

AlphaFold2 enables accurate deorphanization of ligands to single-pass receptors

Abstract: Secreted proteins are extracellular ligands that play key roles in paracrine and endocrine signaling, classically by binding cell surface receptors. Experimental assays to identify new extracellular ligand-receptor interactions are challenging, which has hampered the rate of novel ligand discovery. Here, using AlphaFold-multimer, we developed and applied an approach for extracellular ligand-binding prediction to a structural library of 1,108 single-pass transmembrane receptors. We demonstrate high discriminato… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
3
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
5
2

Relationship

0
7

Authors

Journals

citations
Cited by 12 publications
(3 citation statements)
references
References 60 publications
0
3
0
Order By: Relevance
“…In the latest version of the alphafold2_multimer_v3 model (AF2_v3) training set, only peptides with fewer than four amino acid residues were excluded, including most cyclic peptide complexes registered in the Protein Data Bank (PDB). However, there were no training sets for the alphafold2_ptm model (AF2_ptm) and alphafold2_multimer_v2 model (AF2_v2), because the training excluded peptides with fewer than 16 amino acid residues [53,55]. The AF2_ptm was developed to predict single proteins [40].…”
Section: Structure Prediction Of the Protein And Cyclic Peptide Complexmentioning
confidence: 99%
“…In the latest version of the alphafold2_multimer_v3 model (AF2_v3) training set, only peptides with fewer than four amino acid residues were excluded, including most cyclic peptide complexes registered in the Protein Data Bank (PDB). However, there were no training sets for the alphafold2_ptm model (AF2_ptm) and alphafold2_multimer_v2 model (AF2_v2), because the training excluded peptides with fewer than 16 amino acid residues [53,55]. The AF2_ptm was developed to predict single proteins [40].…”
Section: Structure Prediction Of the Protein And Cyclic Peptide Complexmentioning
confidence: 99%
“…AF-M was trained using five distinct regimens, yielding five models, each of which makes a structure prediction. Many groups are now using AF-M to uncover novel PPIs on the scale of pathways and organisms [12][13][14][15][16][17][18][19] . While many studies have examined AF-M's ability to correctly model individual protein complexes and predict structures for complexes in curated PPI databases [20][21][22] , there has been considerably less focus on finding systematic ways to separate true from false interactions in large-scale unbiased screens.…”
Section: Introductionmentioning
confidence: 99%
“…The recent emergence of computational structure prediction methods has led to a dramatic increase in the availability of predicted structures (Danneskiold-Samsøe et al, 2023;Rossi Sebastiano et al, 2022;Varadi et al, 2022), offering unparalleled insights into biological mechanisms at a molecular level (Bordin et al, 2023;Mosalaganti et al, 2022). New-generation AI-powered tools like AlphaFold (Jumper et al, 2021), ESMFold (Lin et al, 2023), RoseTTAFold (Baek et al, 2021), and others employ advanced algorithms to provide a bounty of predicted protein structures (or computed structure models) that have significantly broadened the scope of accessible molecular data.…”
Section: Introductionmentioning
confidence: 99%