Deep Learning for SARS COV-2 Genome Sequences

Albert Whata, Charles Chimedza

IEEE Access 2021 article cited by 56

Source Open-access PDF More in Biology & Life Sciences

importance 8/10 ai assisted Machine Learning in Bioinformatics infectious disease stage: research

Problem

During a novel virus outbreak, authorities must quickly determine whether the epidemic stems from a novel or a known virus; this work addresses classifying SARS-CoV-2 among coronaviruses from genome sequences.

Why it matters

Rapid pathogen identification guides outbreak response affecting millions of people.

What the AI did

A deep learning model combining a CNN and a Bi-LSTM classifies SARS-CoV-2 genome sequences among coronaviruses and flags candidate regulatory motifs.

Results

Peak classification accuracy of 99.95%; AUC ROC mentioned but value truncated in abstract.

Impact

Peer-reviewed IEEE Access paper with 56 citations indicates research uptake; no real-world deployment stated.

Record

Venue	IEEE Access
Published	2021
Work type	article
Authors	Albert Whata, Charles Chimedza
Citations	56 (OpenAlex, at import time)
References	65
Model or method	CNN-Bi-LSTM
Organization	not stated in source
Primary source	https://doi.org/10.1109/access.2021.3073728
Open access	gold
Keywords	SARS-CoV-2, deep learning, CNN, Bi-LSTM, genome classification, regulatory motifs

Importance rating

8 / 10

major — millions of lives, an industry or a field

Abstract states SARS-CoV-2 spread worldwide affecting millions; rapid novel-versus-known virus identification is crucial for outbreak response.

Basis: stated. The source itself states the scale. Stated scale: affecting millions of people worldwide. Method and limits.

More in Biology & Life Sciences

#	Paper	Year	Citations	Importance
1	Proteomics and Machine Learning Approaches Reveal a Set of Prognostic Markers for COVID-19 Severity With Drug Repurposing Potential Kruthi Suvarna, Deeptarup Biswas, Medha Gayathri J. Pai, Arup Acharjee...	2021	76	10
2	AlphaFold Protein Structure Database: massively expanding the structural coverage of protein-sequence space with high-accuracy models Mihály Váradi, Stephen Anyango, Mandar Deshpande, Sreenath Sasidharan...	2021	7,782	9
3	Evolutionary-scale prediction of atomic-level protein structure with a language model Zeming Lin, Halil Akin, Roshan Rao, Brian Hie, Zhongkai Zhu, Wenting L...	2023	5,455	9
4	Accurate prediction of protein structures and interactions using a three-track neural network Minkyung Baek, Frank DiMaio, Ivan V. Anishchenko, Justas Dauparas, Ser...	2021	5,468	9
5	De novo design of protein structure and function with RFdiffusion Joseph L. Watson, David Juergens, Nathaniel R. Bennett, Brian L. Tripp...	2023	2,294	9