Protein sequence classification using natural language processing techniques

Abstract Purpose This study aimed to improve protein sequence classification through natural language processing (NLP) techniques, addressing the need for precise, automated methods. The research focused on comparing various machine learning and deep learning models to determine the most effective approach for classifying protein sequences into 75 target classes. Methods The study evaluated models such as K-Nearest Neighbors (KNN), Multinomial Naïve Bayes, Logistic Regression, Multi-Layer Perceptron (MLP), Decision Tree, Random Forest, XGBoost, Voting and Stacking classifiers, Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and transformer models (BertForSequenceClassification, DistilBERT, and ProtBert). Performance was tested using different amino acid ranges and sequence lengths. Results The Voting classifier outperformed other models with 74% accuracy and 65% F1 score, while ProtBERT achieved 76% accuracy and 61% F1 score among transformers. Conclusion Advanced NLP techniques, particularly ensemble methods like Voting classifiers, and transformer models show significant potential in protein classification, with sufficient training data and sequence similarity management being crucial for optimal performance.