arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.04491q-bio.QMcs.LG
收藏

使用自然语言处理技术的蛋白质序列分类

Protein sequence classification using natural language processing techniques

University of Sussex（萨塞克斯大学）

Huma Perveen, Julie Weeds

发表信息：
Discov Artif Intell 5, 66 (2025)
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本研究利用NLP技术进行蛋白质序列分类，比较多种机器学习与深度学习模型，发现投票分类器与ProtBERT性能最佳，并强调基于ECOD家族的划分对评估泛化能力至关重要。

摘要：

目的：本研究旨在利用自然语言处理（NLP）技术增强蛋白质序列分类，同时解决序列相似性对模型性能的影响。我们在两种不同的数据划分策略下比较了多种机器学习和深度学习模型：随机划分和基于ECOD家族的划分，后者确保进化相关的序列被分组在一起。方法：研究评估了K近邻（KNN）、多项式朴素贝叶斯、逻辑回归、多层感知器（MLP）、决策树、随机森林、XGBoost、投票和堆叠分类器、卷积神经网络（CNN）、长短期记忆网络（LSTM）以及Transformer模型（BertForSequenceClassification、DistilBERT和ProtBert）等模型。使用不同的氨基酸范围和序列长度测试了性能，重点关注在未见进化家族上的泛化能力。结果：在随机划分下，投票分类器取得了最高性能，准确率为74%，加权F1分数为74%，宏F1分数为65%；而在Transformer模型中，ProtBERT获得了77%的准确率、76%的加权F1分数和61%的宏F1分数。然而，当使用基于ECOD的划分进行测试时，所有模型的性能均下降，揭示了序列相似性对分类性能的影响。结论：先进的NLP技术，特别是集成方法如投票分类器和Transformer模型，在蛋白质分类中显示出显著潜力，但充足的训练数据和序列相似性管理对于最佳性能至关重要。然而，使用生物学上有意义的划分方法（如基于ECOD家族的划分）对于现实性能评估和对未见进化家族的泛化至关重要。

英文摘要：

Purpose: This study aimed to enhance protein sequence classification using natural language processing (NLP) techniques while addressing the impact of sequence similarity on model performance. We compared various machine learning and deep learning models under two different data-splitting strategies: random splitting and ECOD family-based splitting, which ensures evolutionary-related sequences are grouped together. 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 with a focus on generalization across unseen evolutionary families. Results: The Voting classifier achieved the highest performance with 74% accuracy, 74% weighted F1 score, and 65% macro F1 score under random splitting, while ProtBERT obtained 77% accuracy, 76% weighted F1 score, and 61% macro F1 score among transformer models. However, performance declined across all models when tested using ECOD-based splitting, revealing the impact of sequence similarity on classification performance. 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. However, the use of biologically meaningful splitting methods, such as ECOD family-based splitting, is crucial for realistic performance evaluation and generalization to unseen evolutionary families.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑