We present three deep learning sequence-based prediction models for peptide properties including hemolysis, solubility, and resistance to nonspecific interactions that achieve comparable results to the state-of-the-art models. Our sequence-based solubility predictor, MahLooL, outperforms the current state-of-the-art methods for short peptides. These models are implemented as a static website without the use of a dedicated server or cloud computing. Web-based models like this allow for accessible and effective reproducibility. Most existing approaches rely on third-party servers that typically require upkeep and maintenance. Our predictive models do not require servers, require no installation of dependencies, and work across a range of devices. The specific architecture is bidirectional recurrent neural networks. This serverless approach is a demonstration of edge machine learning that removes the dependence on cloud providers.
Web-app: peptide.bio
Check out this notebook for the CLI implementation of our trained models.
See paper and the citation:
@article{Ansari2023,
doi = {10.1021/acs.jcim.2c01317},
url = {https://doi.org/10.1021/acs.jcim.2c01317},
year = {2023},
month = apr,
publisher = {American Chemical Society ({ACS})},
volume = {63},
number = {8},
pages = {2546--2553},
author = {Mehrad Ansari and Andrew D. White},
title = {Serverless Prediction of Peptide Properties with Recurrent Neural Networks},
journal = {Journal of Chemical Information and Modeling}
}