Training self-supervised peptide sequence models on artificially chopped proteins
November 09, 2022 ยท Declared Dead ยท ๐ arXiv.org
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Gil Sadeh, Zichen Wang, Jasleen Grewal, Huzefa Rangwala, Layne Price
arXiv ID
2211.06428
Category
q-bio.QM
Cross-listed
cs.LG,
q-bio.BM
Citations
2
Venue
arXiv.org
Last Checked
2 months ago
Abstract
Representation learning for proteins has primarily focused on the global understanding of protein sequences regardless of their length. However, shorter proteins (known as peptides) take on distinct structures and functions compared to their longer counterparts. Unfortunately, there are not as many naturally occurring peptides available to be sequenced and therefore less peptide-specific data to train with. In this paper, we propose a new peptide data augmentation scheme, where we train peptide language models on artificially constructed peptides that are small contiguous subsets of longer, wild-type proteins; we refer to the training peptides as "chopped proteins". We evaluate the representation potential of models trained with chopped proteins versus natural peptides and find that training language models with chopped proteins results in more generalized embeddings for short protein sequences. These peptide-specific models also retain information about the original protein they were derived from better than language models trained on full-length proteins. We compare masked language model training objectives to three novel peptide-specific training objectives: next-peptide prediction, contrastive peptide selection and evolution-weighted MLM. We demonstrate improved zero-shot learning performance for a deep mutational scan peptides benchmark.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
๐ Similar Papers
In the same crypt โ q-bio.QM
R.I.P.
๐ป
Ghosted
R.I.P.
๐ป
Ghosted
GuacaMol: Benchmarking Models for De Novo Molecular Design
R.I.P.
๐ป
Ghosted
DeepConv-DTI: Prediction of drug-target interactions via deep learning with convolution on protein sequences
R.I.P.
๐ป
Ghosted
ProtVec: A Continuous Distributed Representation of Biological Sequences
R.I.P.
๐ป
Ghosted
A Perspective on Deep Imaging
R.I.P.
๐
404 Not Found
Deep learning in bioinformatics: introduction, application, and perspective in big data era
Died the same way โ ๐ป Ghosted
R.I.P.
๐ป
Ghosted
Language Models are Few-Shot Learners
R.I.P.
๐ป
Ghosted
PyTorch: An Imperative Style, High-Performance Deep Learning Library
R.I.P.
๐ป
Ghosted
XGBoost: A Scalable Tree Boosting System
R.I.P.
๐ป
Ghosted