A review and comparative study of cancer detection using machine learning: SBERT and SimCSE application

Aug 3, 2026

Upload by Ivy

Using DNA sequence data as the only input source, this study reviews and compares machine learning approaches for cancer detection and then proposes a sentence-transformer-based methodology. It focuses on four highly prevalent cancers—lung, breast, prostate, and colorectal. Pretrained sentence transformers SBERT and unsupervised SimCSE learn DNA representations, which are fed into classifiers including XGBoost, Random Forest, LightGBM, and CNNs. Results show XGBoost achieves the best overall accuracy, with SimCSE embeddings improving performance only marginally.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages25

Reading Time1 h 3 min

AccessFree to download

Abstract

Background

Methods

Results

Introduction

Mokoatle etal. BMC Bioinformatics (2023) 24:112 BMC Bioinformatics [https://doi.org/10.1186/s12859-023-05235-x](https://doi.org/10.1186/s12859-023-05235-x) RESEARCH Open Access A review and comparative study of cancer detection using machine learning: SBERT and SimCSE application Mpho Mokoatle1*, Vukosi Marivate 1, Darlington Mapiye2, Riana Bornman4 and Vanessa. M. Hayes3,4 *Correspondence: [u19394277@tuks.co.za](u19394277@tuks.co.za) 1 Department of Computer Science, University of Pretoria, Pretoria, South Africa 2 CapeBio TM Technologies, Centurion, South Africa 3 School of Medical Sciences, The University of Sydney, Sydney, Australia 4 School of Health Systems and Public Health, University of Pretoria, Pretoria, South Africa Abstract Background: Using visual, biological, and electronic health records data as the sole input source, pretrained convolutional neural networks and conventional machine learning methods have been heavily employed for the identification of various malignancies. Initially, a series of preprocessing steps and image segmentation steps are performed to extract region of interest features from noisy features. Then, the extracted features are applied to several machine learning and deep learning methods for the detection of cancer. Methods: In this work, a review of all the methods that have been applied to develop machine learning algorithms that detect cancer is provided. With more than 100 types of cancer, this study only examines research on the four most common and prevalent cancers worldwide: lung, breast, prostate, and colorectal cancer. Next, by using state-of-the-art sentence transformers namely: SBERT (2019) and the unsupervised SimCSE (2021), this study proposes a new methodology for detecting cancer. This method requires raw DNA sequences of matched tumor/normal pair as the only input. The learnt DNA representations retrieved from SBERT and SimCSE will then be sent to machine learning algorithms (XGBoost, Random Forest, LightGBM, and CNNs) for classification. As far as we are aware, SBERT and SimCSE transformers have not been applied to represent DNA sequences in cancer detection settings. Results: The XGBoost model, which had the highest overall accuracy of 73 ± 0.13 % using SBERT embeddings and 75 ± 0.12 % using SimCSE embeddings, was the best performing classifier. In light of these findings, it can be concluded that incorporating sentence representations from SimCSE’s sentence transformer only marginally improved the performance of machine learning models. Keywords: Cancer detection, DNA, Machine learning, SentenceBert, SimCSE Introduction Cancer is a disease where some cells in the body grow destructively and may spread to other body organs [1]. Typically, cells grow and expand through a cell division process to create new cells that can be used to repair old and damaged ones. However, this © The Author(s) 2023. Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit [http://](http://)[ ](http://)[creativecommons.org/licenses/by/4.0/. The Creative Commons Public Domain Dedication waiver (](creativecommons.org/licenses/by/4.0/. The Creative Commons Public Domain Dedication waiver (http://creativecommons.org/publi)[http:/

FAQs

Which cancers does the study focus on?

The review examines four most common and prevalent cancers worldwide: lung, breast, prostate, and colorectal cancer.

How are SBERT and SimCSE used in the proposed cancer detection method?

SBERT and unsupervised SimCSE encode raw DNA sequences into learned representations, which are then provided to machine learning classifiers for cancer classification.

Which classifier performed best and what was the observed impact of SimCSE?

XGBoost performed best, reaching about 73% accuracy with SBERT embeddings and about 75% with SimCSE embeddings; incorporating SimCSE produced only marginal overall improvement.

Aug 3, 2026

Upload by Ivy