search

greenelab / deep-review

A collaboratively written review paper on deep learning, genomics, and precision medicine
https://greenelab.github.io/deep-review/
Other
1.25k stars 271 forks source link

HLA class I binding prediction via convolutional neural networks #196

Open agitter opened 7 years ago

agitter commented 7 years ago

https://doi.org/10.1101/099358 (http://biorxiv.org/content/early/2017/01/10/099358)

Many biological processes are governed by protein-ligand interactions. Of such is the recognition of self and nonself cells by the immune system. This immune response process is regulated by the major histocompatibility complex (MHC) protein which is encoded by the human leukocyte antigen (HLA) complex. Understanding the binding potential between MHC and peptides is crucial to our understanding of the functioning of the immune system, which in turns will broaden our understanding of autoimmune diseases and vaccine design. We introduce a new distributed representation of amino acids, named HLA-Vec, that can be used for a variety of downstream proteomic machine learning tasks. We then propose a deep convolutional neural network architecture, named HLA-CNN, for the task of HLA class I-peptide binding prediction. Experimental results show combining the new distributed representation with our HLA-CNN architecture achieves state-of-the-art results in the vast majority of the latest two Immune Epitope Database (IEDB) weekly automated benchmark datasets.

Code available at https://github.com/uci-cbcl/HLA-bind

hammer commented 7 years ago

FWIW we've been doing this for a few years at https://github.com/hammerlab/mhcflurry and have been performing well on the same benchmark http://tools.iedb.org/auto_bench/mhci/weekly. The preprint is at http://biorxiv.org/content/early/2016/06/07/054775 but doesn't say much about the neural network as it's a pretty simple one and neural networks have been used for this problem for decades.

agitter commented 7 years ago

@hammer Thanks for commenting, I hadn't actually read this new preprint beyond the abstract. Did you see whether it gives a fair treatment to prior work from your group and others?

I created #197 for your paper.

hammer commented 7 years ago

No worries TBH I don't read "deep learning" papers closely as I assume they're just throwing a minimally modified CNN/RNN/VAE at some well-studied data so did not notice if they referenced our work.

(Sorry that sounded angrier than I intended--I really appreciate y'all's comprehensive collection of papers on the repo and have found reading abstracts and your discussions to be sufficient!)