NetMHCpan-3.0; improved prediction of binding to MHC class I molecules integrating information from multiple receptor and peptide length datasets
By Morten Nielsen, Massimo Andreatta. 2016
482 citations recorded by the source corpus.
Binding of peptides to MHC class I molecules (MHC-I) is essential for antigen presentation to cytotoxic T-cells. Here, we demonstrate how a simple alignment step allowing insertions and deletions in a pan-specific MHC-I binding machine-learning model enables combining information across both multiple MHC molecules and peptide lengths. This pan-allele/pan-length algorithm significantly outperforms state-of-the-art methods, and captures differences in the length profile of binders to different MHC molecules leading to increased accuracy for ligand identification. Using this model, we demonstrate that percentile ranks in contrast to affinity-based thresholds are optimal for ligand identification due to uniform sampling of the MHC space. We have developed a neural network-based machine-learning algorithm leveraging information across multiple receptor specificities and ligand length scales, and demonstrated how this approach significantly improves the accuracy for prediction of peptide binding and identification of MHC ligands. The method is available at www.cbs.dtu.dk/services/NetMHCpan-3.0.
Subfields: Immunology, Molecular Biology, Radiology, Nuclear Medicine and Imaging
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Immunology
- Bjoern Peters
- Sinu Paul
- Massimo Andreatta
- Morten Nielsen
- Xiaohui S. Xie
- Yeeleng Scott Vang
- Alessandro Sette
- Swapnil Mahajan
In Molecular Biology
- Bjoern Peters
- Massimo Andreatta
- Morten Nielsen
- Alessandro Sette
- Sinu Paul
- Xiaohui S. Xie
- Yeeleng Scott Vang
- Paolo Marcatili
In Radiology, Nuclear Medicine and Imaging
- Bjoern Peters
- Alessandro Sette
- Yeeleng Scott Vang
- Sinu Paul
- Xiaohui S. Xie
- Massimo Andreatta
- Morten Nielsen
- Paolo Marcatili
Citations in the corpus
- Evolution of neoantigen landscape during immune checkpoint blockade in non-small cell lung cancer (2016, methodology): “The HLA genotype served as input to netMHCpan to predict the MHC class I binding potential of each somatic and wild-type peptide (IC50 nM), with each peptide classified as a strong binder (SB), weak binder (WB) or non-binder (NB) (41-43).”
- Comprehensive Molecular Characterization of Muscle-Invasive Bladder Cancer. (2017, unknown): “0 algorithm (Nielsen and Andreatta, 2016).”
- The Immune Epitope Database and Analysis Resource in Epitope Discovery and Synthetic Vaccine Design (2017, methodology): “The available methods and their performance have been published starting from 2005 and have seen an improvement in performance over that time (14, 15).”
- HLA class I binding prediction via convolutional neural networks (2017, methodology): “In the - CNN architecture, we run a one hidden layer (66 units) neural network like NetMHCpan [Nielsen et al ., 2016] using the HLA-Vec distributed representation encoding and allow for fine-tuning during training step.”
- NetMHCpan-4.1 and NetMHCIIpan-4.0: improved predictions of MHC antigen presentation by concurrent motif deconvolution and integration of MS MHC eluted ligand data (2020, background): “The first category corresponds to predictors trained on binding affinity (BA) data (3–6).”
- NetMHCpan 4.0: Improved peptide-MHC class I interaction predictions integrating eluted ligand and peptide binding affinity data (2017, methodology): “Our earlier work suggests that different MHC molecules present peptides at different predicted BA thresholds (1, 24).”
- Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development (2021, unknown): “0 (Nielsen & Andreatta 2016).”