SBSM-Pro: Support Bio-sequence Machine for Proteins

TL;DR

SBSM-Pro is a novel machine learning model that classifies proteins by integrating sequence alignment, physicochemical grouping, and multiple kernel learning, demonstrating strong performance across various datasets.

Contribution

The paper introduces SBSM-Pro, a new protein classification model that combines sequence alignment, physicochemical properties, and multiple kernel learning for improved accuracy.

Findings

Achieved high accuracy on ten protein datasets.

Effectively classifies protein functions and modifications.

Demonstrates state-of-the-art performance in protein classification.

Abstract

Proteins play a pivotal role in biological systems. The use of machine learning algorithms for protein classification can assist and even guide biological experiments, offering crucial insights for biotechnological applications. We introduce the Support Bio-Sequence Machine for Proteins (SBSM-Pro), a model purpose-built for the classification of biological sequences. This model starts with raw sequences and groups amino acids based on their physicochemical properties. It incorporates sequence alignment to measure the similarities between proteins and uses a novel multiple kernel learning (MKL) approach to integrate various types of information, utilizing support vector machines for classification prediction. The results indicate that our model demonstrates commendable performance across ten datasets in terms of the identification of protein function and posttranslational modification. This research not only exemplifies state-of-the-art work in protein classification but also paves avenues for new directions in this domain, representing a beneficial endeavor in the development of platforms tailored for the classification of biological sequences. SBSM-Pro is available for access at http://lab.malab.cn/soft/SBSM-Pro/.