pLM4Alg: Protein language model-based predictors for allergenic proteins and peptides

The webserver is the implementation of the paper (underreview)

Special needs: very large dataset processing or extremely long peptide or pLM4Alg-1280 and pLM4Alg-2560 model usage: please run them seperately, contact us for assistant or download our model locally for running Model files for server. or contact us at zhenjiao@ksu.edu or yonghui@ksu.edu for more assistant.

Alternative solution: You can turn to our user-friendly protocol based on GoogleColab free subscription,Download those files and open the .ipynb file with GoogleColab and follow the guideline.

Quick output version: 1. Choose a model → 2. Input a protein/peptide sequence



Large-scale output version: 1. Prepare your files (xls, xlsx, fasta, or txt) and click “Choose File” for uploading → 2. Choose one or multiple models → 3. Download the results.


Usage of the webserver:

Example for “Quick output version” :

1. Select “pLM4Alg-320” model for pLM4Algicity prediction.  →   →  →  2. Insert a peptide or protein sequence, “pLM4AlgS” →   →  →  3. Click “Run”→   →  → 4. The result will be returned in seconds below the “Run” button

Notice: it also support multiple sequence at the same time. Just input as "ALL,PREDICT" (sequences are separated by comma, no space, capitalize)

Example for “Large-scale output version:” :

1. Prepare your xls, xlsx, txt or fasta files → → → 2. Upload the file through “Choose File” botton → → → 3. Select a model models → → → 4. Click “Run” → → → 5. It will automatically download your results.

Notice: File preparation should follow the examples under this repository.

Explaination of the model names

pLM4Alg-320 represent the model based on the pretrained language model with 320 output dimension Whole architecture

The performance of the deployed models

The scripts for the five model generaton and local running are available at here and here

Project name Accuracy Sensitivity Specificity MCC AUC
pLM4Alg-320 94.4% 94.2% 94.6% 0.89 98.3%
pLM4Alg-480 94.5% 94.0% 95.0% 0.89 98.5%
pLM4Alg-640 95.1% 96.1% 94.2% 0.90 98.7%
pLM4Alg-1280 95.4% 94.7% 96.1% 0.91 98.8%
pLM4Alg-2560 95.8% 95.9% 95.6% 0.92 99.1%