Application of Traditional Machine Learning Techniques for the Classification of Human DNA Sequences - A Comparative Study of Random Forest and XGBoost

Aug 5, 2026

Upload by Violet

This study evaluates hybrid machine learning models, focusing on Random Forest and XGBoost, for classifying human DNA sequences into seven functional classes. Using feature vectorization to tackle high-dimensional genomic data, the models are trained and tested on annotated sequences to assess generalizability to unseen data. Random Forest achieves 87.98% accuracy, slightly higher than XGBoost at 87.06%. Results support traditional machine learning with effective preprocessing for predictive genomics, informing future genetic research and possible personalized medicine applications while discussing ideas for improving classification accuracy.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages6

Reading Time15 min

AccessFree to download

Abstract

Introduction

Genomics and DNA sequence functional classification

Traditional and computational approaches

Machine learning methods and challenges

Research gap and hybrid modeling goal

Proposed contributions

Application of Traditional Machine Learning Techniques for the Classification of Human DNA Sequences: A Comparative Study of Random Forest and XGBoost Gregorius Airlangga1* 1Information System Study Program, Universitas Katolik Indonesia Atma Jaya, Jakarta, Indonesia [e-mail:](e-mail:1gregorius.airlangga@atmajaya.ac.id)[1](e-mail:1gregorius.airlangga@atmajaya.ac.id)[gregorius.airlangga@atmajaya.ac.id](e-mail:1gregorius.airlangga@atmajaya.ac.id) *Corresponding author Submitted Date: January 24th, 2024 Revised Date: February 27th, 2024 Reviewed Date: February 17th, 2024 Accepted Date: March 30th, 2024 Abstract This study evaluates the performance of hybrid machine learning models, specifically Random Forest and XGBoost, in classifying human DNA sequences into seven functional classes. Utilizing advanced feature vectorization techniques, this research addresses the challenges of analyzing high-dimensional genomic data. Both models were trained and tested on a dataset of annotated human DNA sequences, with an emphasis on generalizability to new, unseen data. Our results indicate that the Random Forest model achieved an accuracy of 87.98%, slightly outperforming the XGBoost model, which recorded an accuracy of 87.06% . These findings underscore the effectiveness of employing traditional machine learning techniques coupled with innovative data preprocessing for predictive modeling in genomics. The study not only enhances our understanding of genomic functionalities but also suggests robust methodologies for future genetic research and potential applications in personalized medicine. The implications of these results for improving classification accuracy and the recommendations for integrating more complex algorithms are also discussed. Keywords: Machine Learning; DNA Sequence Classification; Random Forest; XGBoost; Genomic Data Analysis 1. Introduction In the rapidly advancing field of genomics, the classification of human DNA sequences into their respective functional classes plays a pivotal role in understanding genetic functions and their implications in health and disease (Caudai et al., 2021; Jovic et al., 2022; Satam et al., 2023) . Traditional methods for classifying genetic material have heavily relied on direct biological experimentation, which is often costly and timeconsuming (He et al., 2022; Mobarak et al., 2023; Pan et al., 2022) . With the advent of computational biology, numerous techniques have been developed to expedite and enhance the accuracy of genetic classification, thereby providing significant insights into genomic functionalities more efficiently (Basso et al., 2020; Fu et al., 2022; Zhang et al., 2021) . Recent developments in machine learning have opened new avenues for analyzing and interpreting complex biological data (Dral & Barbatti, 2021; Rhodes et al., 2022; Tian et al., 2021) . The use of algorithms such as Random Forests and Gradient Boosting Machines has shown promise in various bioinformatics applications, including gene expression analysis and disease prediction (Raslan et al., 2023) . These methodologies, however, often encounter limitations in handling the high-dimensional and highly variable nature of DNA sequences (Thudumu et al., 2020) . This has prompted researchers to explore more robust and sophisticated machine learning techniques that can capture the inherent complexities of genetic data more effectively (Greener et al., 2022; Kunduru, 2023; Patra et al., 2023) . The urgency of developing improved computational tools for DNA sequence classification cannot be understated (Akbari Rokn Abadi et al., 2023) . As we delve deeper into the genomic era, the ability to classify DNA sequences quickly and accurately into their correct functional categories is essential for timely advancements in personalized medicine, genetic [http://openjournal.unpam.ac.id/index.php/informatika](http://openjournal.unpam.ac.id/index.php/informatika) 23 This work is licensed under a

FAQs

Which models are compared for human DNA sequence classification?

The study compares Random Forest and XGBoost hybrid machine learning models for classifying human DNA sequences into seven functional classes.

How many functional classes does the study classify DNA sequences into?

The research classifies DNA sequences into seven functional classes.

What accuracy results do the two models achieve?

Random Forest reaches 87.98% accuracy, slightly outperforming XGBoost with 87.06% accuracy.

Aug 5, 2026

Upload by Violet