Related Experiment Video
Updated: Sep 29, 2025
08:40
Production of Pseudotyped Particles to Study Highly Pathogenic Coronaviruses in a Biosafety Level 2 Setting
Published on: March 1, 2019
59.2K
PWM2Vec: An Efficient Embedding Approach for Viral Host Specification from Coronavirus Spike Sequences.
Sarwan Ali1, Babatunde Bello1, Prakash Chourasia1
1Department of Computer Science, Georgia State University, Atlanta, GA 30303, USA.
Biology
|March 26, 2022
Summary
This study introduces PWM2Vec, a new method using coronavirus spike proteins to classify hosts. It helps understand virus origins and prevent future pandemics by identifying potential animal carriers.
Area of Science:
- Virology and Bioinformatics
- Genomic analysis of viral host specificity
Background:
- Understanding virus origins, like SARS-CoV-2, is crucial for pandemic prevention.
- Host specificity in coronaviruses is linked to their surface (spike) proteins.
- Previous studies highlight the role of animal hosts (e.g., bats, civets) in virus transmission.
Purpose of the Study:
- To classify coronavirus hosts based on spike protein sequences.
- To develop a novel feature embedding method for viral sequence analysis.
- To identify key amino acids involved in determining coronavirus host specificity.
Main Methods:
- Collected spike protein sequences from over 5,000 coronaviruses.
- Developed PWM2Vec, a feature embedding method inspired by Position Weight Matrices (PWMs).
- Applied machine learning classifiers to classify hosts using PWM2Vec-generated feature vectors.
Main Results:
- PWM2Vec effectively classifies coronavirus hosts into distinct clusters (birds, bats, camels, swine, humans, weasels).
- Machine learning models using PWM2Vec showed comparable or improved predictive performance and runtime versus baseline models.
- Identified specific amino acids crucial for predicting coronavirus host using information gain.
Conclusions:
- PWM2Vec offers a novel and effective approach for viral host classification using spike protein sequences.
- The method provides compact feature representations, aiding in understanding virus-host interactions.
- This research contributes to identifying potential pandemic origins and developing mitigation strategies.
Related Concept Videos
01:26Size and Structure of Viral Genomes
186
Viral genomes exhibit remarkable diversity in size, structure, and composition, influencing their replication strategies and interactions with host cells. These genomes consist of either DNA or RNA and may be linear or circular. Additionally, they can be single-stranded or double-stranded, with each configuration affecting how the virus propagates within a host. RNA viruses, for instance, generally have smaller genomes than DNA viruses, a factor that contributes to their high mutation rates and...
186
00:56Viral Structure
65.3K
Viruses are extraordinarily diverse in shape and size, but they all have several structural features in common. All viruses have a core that contains a DNA- or RNA-based genome. The core is surrounded by a protective coat of proteins called the capsid. The capsid is composed of subunits called capsomeres. The capsid and genome-containing core are together known as the nucleocapsid.
65.3K
01:29Viruses with RNA Genomes
180
RNA viruses are categorized into positive-strand, negative-strand, or double-stranded groups based on their genomic structure and replication mechanisms. This classification dictates how they exploit host cellular machinery for protein synthesis and replication. Some RNA viruses also utilize reverse transcription as part of their life cycle, further diversifying their replication strategies.Positive-Strand RNA VirusesPositive-strand RNA viruses have genomes that function directly as messenger...
180