Back

Serverless Prediction of Peptide Properties with Recurrent Neural Networks

Ansari, M.; White, A. D.

2022-05-19 bioinformatics
10.1101/2022.05.18.492545 bioRxiv
Show abstract

We present three deep learning sequence prediction models for hemolysis, solubility, and resistance to non-specific interactions of peptides that achieve comparable results to the state-of-the-art models. Our sequence-based solubility predictor, MahLooL, outperforms the current state-of-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 typically that require upkeep and maintenance. That trend leads to a relatively longer lifetime of web-based models. These predictive models do not require servers, require no installation of dependencies, and work on across a range of devices. The models are bidirectional recurrent neural networks. This serverless prediction model is a demonstration of edge machine learning that removes the dependence on cloud providers. The code and models are accessible at https://github.com/ur-whitelab/peptide-dashboard.

Matching journals

The top 8 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.