Related Experiment Video
Updated: Aug 5, 2026
07:06
Prediction of HIV-1 Coreceptor Usage (Tropism) by Sequence Analysis using a Genotypic Approach
Published on: December 1, 2011
ViralMap: predicting features in viral proteins from primary sequence
Shrish Dwivedi1,2, Shaunak Kar2, Andrew P Horton2
1Systems, Synthetic, and Physical Biology, Rice University, Houston, Texas, USA.
Journal of Virology
|July 28, 2026
Summary
ViralMap is a new deep learning tool that annotates viral protein sequences to aid vaccine design. It predicts key protein features from sequence alone, accelerating antigen engineering for pandemic preparedness.
Area of Science:
- Virology
- Computational Biology
- Vaccine Development
Background:
- Viral proteins are key targets for vaccine development, requiring detailed characterization and engineering for enhanced immunogenicity.
- Current methods for viral protein annotation are fragmented, often requiring multiple tools and lacking specialization for diverse viral families.
- The emergence of novel pathogens necessitates rapid identification and annotation of viral protein features for swift vaccine design.
Purpose of the Study:
- To develop ViralMap, a multi-label deep learning model for comprehensive annotation of eukaryotic viral protein sequences.
- To provide a unified, sequence-based framework for predicting functionally relevant protein features essential for antigen engineering.
- To support rapid response to emerging viral threats and enhance vaccine development pipelines.
Main Methods:
- Developed ViralMap, a multi-label annotation model utilizing ESM-2 language model representations.
- Trained the model on eukaryotic viral proteins to predict 10 distinct annotation classes simultaneously from primary sequences.
- Evaluated model performance using residue-level precision-recall area under the curve (PR-AUC) and compared it with existing tools.
Main Results:
- ViralMap achieved a PR-AUC of 0.75 or greater for 7 out of 10 predicted annotation classes.
- The model demonstrated competitive performance against established tools across eight benchmarked classes.
- Case studies on SARS-CoV-2, HIV-1, Nipah, and Lassa viruses showed accurate prediction of residue-level profiles, including for novel viral families.
Conclusions:
- ViralMap offers a unified, sequence-based approach for multi-label annotation of viral proteins, crucial for antigen engineering.
- The model effectively bridges the gap between raw viral sequences and actionable annotation profiles for vaccine design.
- ViralMap enhances pandemic preparedness by enabling rapid characterization of viral proteins from newly identified pathogens.
Related Concept Videos
01:26Size and Structure of Viral Genomes
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...
00:56Viral Structure
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.
00:36Viral Mutations
A mutation is a change in the sequence of bases of DNA or RNA in a genome. Some mutations occur during replication of the genome due to errors made by the polymerase enzymes that replicate DNA or RNA. Unlike DNA polymerase, RNA polymerase is prone to errors because it is not capable of “proofreading” its work. Viruses with RNA-based genomes, like HIV, therefore accrue mutations faster than viruses with DNA-based genomes. Because mutation and recombination provide the raw material for adaptive...
02:28Leaky Scanning
During most eukaryotic translation processes, the small 40S ribosome subunit scans an mRNA from its 5' end until it encounters the first start AUG codon. The large 60S ribosomal subunit then joins the smaller one to initiate protein synthesis. The location of the translation initiation is largely determined by the nucleotides near the start codon as there may be multiple translation initiation sites present on the mRNA. Marilyn Kozak discovered that the sequence RCCAUGG (where R stands for...
01:29Viruses with RNA Genomes
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...
02:33Retroviruses
Retroviruses and retrotransposons both insert copies of their genetic elements into the genome of the host cell. Thus, the viral genes are passed on when the host genome is replicated or translated. A typical retroviral DNA sequence contains 3-4 genes that encode the different proteins required for its structural assembly and function as a molecular parasite. This DNA is transcribed into a single mRNA, which is very similar in structure to conventional mRNAs, i.e., it is capped at the 5’...