SMFFX: a signal processing-inspired feature extraction framework for viral genomic sequences classification

In recent years, the coronavirus and other viral diseases increasing rate have attracted significant attention. Viral data can be analyzed at the intracellular level in the form of genomic sequences. This study introduced a signal processing approach applied to the corresponding signals of viral genomic sequences. The Mel-frequency cepstral coefficients (MFCC) algorithm, based on windowing techniques, enabled examination of genetic samples for feature extraction. Various statistical features were extracted from the resulting feature space, enabling classification algorithms to accurately identify and distinguish among the different virus types with high efficiency. The proposed approach was evaluated on 173,228 samples across 30 types of viruses using both binary and multi-class classification tasks. In the binary classification test, the proposed approach achieved accuracy and F1-scores of more than 0.99 using a decision tree classifier. In the multi-class classification mode, an accuracy of 0.99 and an F1-score exceeding 0.98 were achieved. In the one-versus-rest classes analysis, most classes achieved more than 99% F1-score, and AUC values. The high classification performance indicates the reliable predictive capability of the proposed approach. The feature-importance analysis provides the potential applicability to similar classification tasks involving other viruses or viral variants.

Authors

Institutions

Publication Details

Journal
Scientific Reports
Published
2026-11-16
DOI
https://doi.org/10.1038/s41598-026-78480-8
Primary Topic
Fractal and DNA sequence analysis
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

SMFFX: a signal processing-inspired feature extraction framework for viral genomic sequences classification

Amin Khodaei, Aida Shahriardoust, Yalda Mahmoudi
4 links
Scientific Reports
Fractal and DNA sequence analysis
article

SMFFX: a signal processing-inspired feature extraction framework for viral genomic sequences classification

Amin Khodaei, Aida Shahriardoust, Yalda Mahmoudi
article en

Abstract

In recent years, the coronavirus and other viral diseases increasing rate have attracted significant attention. Viral data can be analyzed at the intracellular level in the form of genomic sequences. This study introduced a signal processing approach applied to the corresponding signals of viral genomic sequences. The Mel-frequency cepstral coefficients (MFCC) algorithm, based on windowing techniques, enabled examination of genetic samples for feature extraction. Various statistical features were extracted from the resulting feature space, enabling classification algorithms to accurately identify and distinguish among the different virus types with high efficiency. The proposed approach was evaluated on 173,228 samples across 30 types of viruses using both binary and multi-class classification tasks. In the binary classification test, the proposed approach achieved accuracy and F1-scores of more than 0.99 using a decision tree classifier. In the multi-class classification mode, an accuracy of 0.99 and an F1-score exceeding 0.98 were achieved. In the one-versus-rest classes analysis, most classes achieved more than 99% F1-score, and AUC values. The high classification performance indicates the reliable predictive capability of the proposed approach. The feature-importance analysis provides the potential applicability to similar classification tasks involving other viruses or viral variants.

Scientific Reports
Islamic Azad University of Tabriz (IR), University of Tabriz (IR)
Good health and well-being
Fractal and DNA sequence analysis
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon