Serverless Prediction of Peptide Properties with Recurrent Neural Networks

Abstract

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 sequencebased 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. The code and models are accessible at https://github.com/urwhitelab/peptide-dashboard.

PeptideBERT: A Language Model Based on Transformers for Peptide Property Prediction

“…Following the encoding procedure, we split each data set into three nonoverlapping subsets: a training set (to train the model) consisting of 81% of the data set, a validation set (for hyperparameter tuning) consisting of 9% of the data set, and a test set (to benchmark the model’s performance on unseen data) consisting of 10% of the data set. This specific train–validation–test split of 81%–9%–10% has been selected to ensure a proper comparison between our approach and the previous methodologies . Data augmentations, if any (such as in the solubility task), are then applied to the training set, while the validation and test sets remain unchanged.…”

“…The training data for the nonfouling task primarily consist of shorter sequences in the range of 2–20 residues. The data set employed for this task consists of instances of negative examples that are predominantly associated with insoluble peptides, which could lead to an increase in accuracy if only soluble peptides are compared . Our predictive model achieves an accuracy of 70.018% with augmentations for the solubility task.…”

“…Our predictive model achieves an accuracy of 70.018% with augmentations for the solubility task. This accuracy can be primarily attributed to the challenges involved in predicting solubility in cheminformatics …”

“…For instance, a sequence such as "RVKRVWPLVIRTVIAGYNLYRAIKKK" has been found to exhibit both hemolytic and nonhemolytic behavior in two different laboratory experiments, resulting in two distinct training examples. 33 The solubility data set consists of 18,453 sequences, with 47.6% being labeled as positives and 52.4% being labeled as negatives. These labels are based on information sourced from PROSO II.…”

“…This pattern was also observed within chaperone proteins, an area where mitigating nonspecific interactions is crucial. 46 The provided data sets 33 have been preprocessed by applying a custom encoding method. In this encoding, the integer representation of each of the 20 amino acids is given by its index in the following array (indexing starts from 1): [A, R, N, D, C, Q, E, G, H, I, L, K, M, F, P, S, T, W, Y, V].…”