Developing an Antiviral Peptides Predictor with Generative Adversarial Network Data Augmentation
Lin, T.-T.; Sun, Y.-Y.; Cheng, W.-C.; Lu, I.-H.; Chen, S.-H.; Lin, C.-Y.
Show abstract
MotivationNew antiviral drugs are urgently needed because of emerging viral pathogens increasing severity and drug resistance. Antiviral peptides (AVPs) have multiple antiviral properties and are appealing candidates for antiviral drug development. We developed a sequence-based binary classifier to identify whether an unknown short peptide has AVP activity. We collected AVP sequence data from six existing databases. We used a generative adversarial network to augment the number of AVPs in the positive training dataset and allow our deep convolutional neural network model to train on more data. ResultsOur classifier achieved outstanding performance on the testing dataset compared with other state-of-the-art classifiers. We deployed our trained classifier on a user-friendly web server. Availability and implementationAI4AVP is freely accessible at http://axp.iis.sinica.edu.tw/AI4AVP/ Contactcylin@iis.sinica.edu.tw Supplementary informationSupplementary data is also available.
Matching journals
The top 9 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- CaLMPhosKAN: Prediction of General Phosphorylation Sites in Proteins via Fusion of Codon Aware Embeddings with Amino Acid Aware Embeddings and Wavelet-based Kolmogorov Arnold Network 94%
- BERTrand - peptide:TCR binding prediction using Bidirectional Encoder Representations from Transformers augmented with random TCR pairing 94%
- BERTMHC: Improves MHC-peptide class II interaction prediction with transformer and multiple instance learning 93%
Similar papers in this journal
- Accelerating protein engineering with fitness landscape modeling and reinforcement learning 93%
- Personalized deep learning of individual immunopeptidomes to identify neoantigens for cancer vaccines 93%
- PepFlow: direct conformational sampling from peptide energy landscapes through hypernetwork-conditioned diffusion 93%
Similar papers in this journal
- THLANet: A Deep Learning Framework for Predicting TCR-pHLA Binding in Immunotherapy Applications 95%
- Positional SHAP (PoSHAP) for Interpretation of Machine Learning Models Trained from Biological Sequences 94%
- A novel transformer-based platform for the prediction and design of biosynthetic gene clusters for (un)natural products 93%
Similar papers in this journal
Similar papers in this journal
- NetTCR 2.2 - Improved TCR specificity predictions by combining pan- and peptide-specific training strategies, loss-scaling and integration of sequence similarity 95%
- PARROT: a flexible recurrent neural network framework for analysis of large protein datasets 93%
- AIVE: accurate predictions of SARS-CoV-2 infectivity from comprehensive analysis 93%
"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.