Harnessing protein folding neural networks for peptide–protein docking

2022/01/10 by Tomer Tsaban, Julia K. Varga, Orly Avraham +3 · 1 voice · 31 citations
Biochemistry, Genetics and Molecular Biology · #Machine Learning in Bioinformatics #Protein Degradation and Inhibitors #Ubiquitin and proteasome pathways

paper · pdf · doi:10.1038/s41467-021-27838-9

openalex publication_date 2022/01/10 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/31

Abstract

Highly accurate protein structure predictions by deep neural networks such as AlphaFold2 and RoseTTAFold have tremendous impact on structural biology and beyond. Here, we show that, although these deep learning approaches have originally been developed for the in silico folding of protein monomers, AlphaFold2 also enables quick and accurate modeling of peptide-protein interactions. Our simple implementation of AlphaFold2 generates peptide-protein complex models without requiring multiple sequence alignment information for the peptide partner, and can handle binding-induced conformational changes of the receptor. We explore what AlphaFold2 has memorized and learned, and describe specific examples that highlight differences compared to state-of-the-art peptide docking protocol PIPER-FlexPepDock. These results show that AlphaFold2 holds great promise for providing structural insight into a wide range of peptide-protein complexes, serving as a starting point for the detailed characterization and manipulation of these interactions.

Citations

• Matplotlib: A 2D Graphics Environment
• The Structural Basis of Peptide-Protein Binding Strategies
• Highly accurate protein structure prediction with AlphaFold
• Highly accurate protein structure prediction for the human proteome
• Accurate prediction of protein structures and interactions using a three-track neural network
• Critical assessment of methods of protein structure prediction (CASP)—Round XIV
• Доочистка биологически очищенных фенольных сточных вод методом коагуляции с использованием FeCl3·6H2O
• ColabFold: making protein folding accessible to all

Cited by

• Benchmarking AlphaFold2 on peptide structure prediction
• Propofol anesthesia destabilizes neural dynamics across cortex
• Targeting protein disorder: the next hurdle in drug discovery
• AFM-RL: Large Protein Complex Docking Using AlphaFold-Multimer and Reinforcement Learning
• Generation of multi-lineage kidney assembloids with integration between nephrons and a single exiting collecting duct
• Therapeutic CD8+T cell tissue retention and immunomodulation during ART interruption fails to prevent SIV rebound
• Conservation of Hot Spots and Ligand Binding Sites in Protein Models by AlphaFold2
• Ranking Peptide Binders by Affinity with AlphaFold**
• Behavioral State-Dependent Modulation of Prefrontal Cortex Activity by Respiration
• De novo designed cyclic MC4R peptide agonist reduces food intake in mice
• Cortical thickness changes precede high levels of amyloid by at least seven years
• Brain-wide topographic coordination of traveling spiral waves
• WASp activity in macrophages prevents mechano-induced inflammation by protecting the nuclear envelope
• Artificial intelligence in drug development
• Base edited “universal” donor CAR T cell strategies for acute myeloid leukaemia
• Automated 3D multi-color single-molecule localization microscopy
• Global abundance patterns, diversity, and ecology of Patescibacteria in wastewater treatment plants
• HLA-G engineering reprograms CAR-T cells with an immune privilege
• The transcriptional mechanism behind Mimosa pudica leaf folding in response to mechanical disturbance
• Single-cell transcriptional mapping reveals genetic and non-genetic determinants of aberrant differentiation in AML
• Complex interactions in the life cycle of a simple parasite shape the evolution of virulence
• A Perspective on the Prospective Use of AI in Protein Structure Prediction
• Depolymerizing F-actin accelerates the exit from pluripotency to enhance stem cell-derived islet differentiation
• Distinct Orbitofrontal Feedback Signals Shape Sensory Behavioral Strategies during Flexible Learning
• Systematic discovery of protein interaction interfaces using AlphaFold and experimental validation
• DeepFold-PLM: accelerating protein structure prediction via efficient homology search using protein language models
• Data-driven strategies for model-informed decision-making during the COVID-19 pandemic: a systematic review
• MAVISp: A Modular Structure-Based Framework for Protein Variant Effects
• Cryogenic Electron Tomography by the Numbers: Charting Underexplored Lineages in Structural Cell Biology
• Mechanisms of host exploitation by a microsporidian parasite
• Computational methods for modeling protein–protein interactions in the AI era: Current status and future directions

Discussions

• There are quite a few examples. Here’s one that comes to mind: Harnessing protein folding neural networks for peptide–protein docking doi.org/10.1038/s414... We might have more examples in our revie [bsky, 7 points, 1 comments]

Related

• Assessment of Alphafold Protein Models for Small-Molecule Ligand Docking versus Co-Folding
• Highly accurate protein structure prediction with AlphaFold
• AlphaFold3 for Structure-guided Ligand Discovery
• State-specific protein-ligand complex structure prediction with a multi-scale deep generative model
• Assessing the potential of deep learning for protein-ligand docking