Gapped sequence alignment using artificial neural networks: application to the MHC class I system

By Massimo Andreatta, Morten Nielsen. 2016

1,025 citations recorded by the source corpus.

Subfields: Immunology, Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Immunology

1. Bjoern Peters
2. Massimo Andreatta
3. Morten Nielsen
4. Sinu Paul
5. Xiaohui S. Xie
6. Yeeleng Scott Vang
7. Paolo Marcatili
8. Vanessa Isabell Jurtz

In Molecular Biology

1. Bjoern Peters
2. Massimo Andreatta
3. Morten Nielsen
4. Sinu Paul
5. Xiaohui S. Xie
6. Yeeleng Scott Vang
7. Paolo Marcatili
8. Wanding Zhou

Citations in the corpus

• NetMHCpan 4.0: Improved peptide-MHC class I interaction predictions integrating eluted ligand and peptide binding affinity data (2017, methodology): “This novel training approach allows the incorporation of a larger set of training data and, maybe more importantly, enables the method to directly learn the length preference of presented peptides for each MHC molecule from the experimental binding data (4).”
• Comprehensive Analysis of Alternative Splicing Across Tumors from 8,705 Patients (2018, background): “, 2016) andMHC-I binding affinity prediction (Andreatta and Nielsen, 2016) incorporating information on the human leukocyte antigen (HLA) type of each donor (Figure 5A).”
• Allele-Specific HLA Loss and Immune Escape in Lung Cancer Evolution (2017, neutral): “0 Andreatta and Nielsen, 2016; Hoof et al., 2009; Nielsen et al., 2003 http://www.cbs.dtu.dk/services/ NetMHC/ LOHHLA This paper https://bitbucket.org/mcgranahanlab/ lohhla”
• HLA class I binding prediction via convolutional neural networks (2017, methodology): “Binary indicators were used directly while values given in ic50 measurements were denoted as binding if ic50 < 500 nM.”
• Mass Spectrometry Profiling of HLA-Associated Peptidomes in Mono-allelic Cells Enables More Accurate Epitope Prediction (2017, methodology): “Finally, we developed a neural network, MSIntrinsicEC, that integrates these different variables and improves prediction performance of endogenous peptides relative to neural networks trained on non-MS datasets (Andreatta and Nielsen, 2016; Hoof et al., 2009; Lundegaard et al., 2008).”
• NetMHCpan-3.0; improved prediction of binding to MHC class I molecules integrating information from multiple receptor and peptide length datasets (2016, methodology): “Moreover, we extended this pan-specific approach by allowing insertions and deletions in the multiple sequence alignment as described by Andreatta and Nielsen [15].”