Internships

ResPred.AI

A hierarchical machine learning pipeline to classify Antimicrobial Resistance (AMR) gene families and functional categories of Virulence Factors from protein FASTA sequences of bacterial pathogens — combining supervised binary classifiers for initial detection with function prediction models for granular categorization.

Go to Respred.AI
View Publication
VERSION v1.0
CATEGORY AMR & Virulence Factor Classification
RELEASE DATE Aug 2026
INPUT Protein FASTA (*.fasta)
WEB SERVER Available Free
SUB-TOOLS AMRPred · VFPred
DATA HANDLING Processed securely, not retained

What ResPred.AI Does

ResPred.AI uses a multi-stage machine learning pipeline to classify antimicrobial resistance gene families and functionally annotate virulence factors — automating what would otherwise be slow, manual sequence curation.

01

Hierarchical Classification

Binary classifiers first detect AMR or virulence signal, then dedicated function-prediction models assign granular categories.

02

Physicochemical Profiling

Extracts physicochemical properties from each protein sequence as an early feature layer of the pipeline.

03

PTM Prediction

Predicts post-translational modification sites via MusiteDeep to enrich the feature set before embedding.

04

ESM2 Embeddings

Generates deep protein language model embeddings using ESM2 for high-resolution sequence representation.

05

Ensemble Learning

Combines supervised and ensemble learning techniques across pipeline stages for robust final predictions.

06

AMR Gene Family ID

Predicts resistance and AMR gene family directly from protein sequences using AI-powered models (AMRPred).

07

Virulence Annotation

Detects virulence factors and annotates their functional roles from protein sequence data (VFPred).

08

High-Throughput Ready

Built for high-throughput analysis in microbial genomics, antibiotic resistance surveillance, and pathogen virulence studies.

Prediction Pipeline

Upload a protein FASTA file and ResPred.AI classifies it through five sequential stages, with live progress shown on a run-tracking page.

01

FASTA Upload

User uploads a protein FASTA file (.fasta) via drag-and-drop or file picker. One file at a time; an example file and auto-load demo option are provided.
Input: Protein FASTA

02

Physicochemical Properties

The pipeline computes physicochemical properties for each sequence as an initial feature extraction layer.
Stage 2 of 5

03

Post-Translational Modifications

PTM sites are predicted from each sequence using MusiteDeep, adding a further layer of biologically informed features.
Engine: MusiteDeep

04

ESM2 Embeddings

Sequences are passed through the ESM2 protein language model to generate deep embeddings capturing sequence context.
Model: ESM2

05

Predictions

Combined features feed into the trained classifiers, returning AMR gene family or virulence factor functional category predictions per sequence.
Output: Class prediction per sequence

How to Use

ResPred.AI runs entirely as a web tool — no installation required for either module.

AMRPred

# No installation required
# Upload a protein FASTA file
 
Accepted format:
> *.fasta (protein only)
 
 
# Run Prediction, then track
# progress across 5 pipeline stages
✓ Data processed securely, not retained

VFPred

# No installation required
# Upload a protein FASTA file
 
Accepted format:
> *.fasta (protein only)
 
 
# Run Prediction, then track
# progress across 5 pipeline stages
✓ Data processed securely, not retained

Choose Your Plan

All plans are currently free. Pricing will be announced soon.

FREE

0$ / forever

Full access · No credit card needed

  • ✓ Web server (https://mgbio.asab.nust.edu.pk/respred/
  • ✓ AMRPred — AMR gene family prediction
  • ✓ VFPred — Virulence factor functional annotation
  • ✓ Hierarchical ML pipeline (binary detection + function classifiers)
  • ✓ FASTA protein input
  • ✓ Physicochemical + PTM + ESM2 feature extraction
  • ✓ Secure processing — data not retained
  •  
Go to ResPred.AI
PREMIUM

100$ / year

Advanced features for labs & institutions

Features coming soon. Stay tuned for updates.

Notify Me

Get Started

Free to use. No signup required for either module.

AMRPred

Predict AMR gene family from protein FASTA

Launch AMRPred
VFPred

Annotate virulence factor functional categories

Launch VFPred

How to Cite VacSol-ML

If VacSol-ML contributed to your research, please cite the original publication.

VacSol-ML(ESKAPE): Machine learning empowering vaccine antigen prediction for ESKAPE pathogens

PMID: 39126830

DOI: 10.1016/j.vaccine.2024.126204

AMA: Nasir S, Anwer F, Ishaq Z, Saeed MT, Ali A. VacSol-ML(ESKAPE): Machine learning empowering vaccine antigen prediction for ESKAPE pathogens. Vaccine. 2024 Sep 17;42(22):126204.
APA: Nasir, S., Anwer, F., Ishaq, Z., Saeed, M. T., & Ali, A. (2024). VacSol-ML(ESKAPE): Machine learning empowering vaccine antigen prediction for ESKAPE pathogens. Vaccine, 42(22), 126204.
MLA: Nasir, Samavi, et al. “VacSol-ML(ESKAPE): Machine Learning Empowering Vaccine Antigen Prediction for ESKAPE Pathogens.” Vaccine, vol. 42, no. 22, 2024, p. 126204.
NLM: Nasir S, Anwer F, Ishaq Z, Saeed MT, Ali A. VacSol-ML(ESKAPE): Machine learning empowering vaccine antigen prediction for ESKAPE pathogens. Vaccine. 2024 Sep 17;42(22):126204. Epub 2024 Aug 9. PMID: 39126830.

Contact Us

Email Address

Sales: sales@mgbio.tech

General: info@mgbio.tech

Call / WhatsApp

+92 308 0089944
09:00 AM – 05:00 PM

Find Us

NSTP, National University of Science and Technology, Sector H-12, Islamabad

Related Tools by MGBio

AbAMPdb

is the manually-curated database for antimicrobial peptides (AMPs) specifically against Acinetobacter baumannii.The database offers insights of antimicrobial potentials of these AMPs

Read More

Bacterial Immunogens Database

is the manually curated database, where you can find experimentally validated bacterial protective immunogens published and reported in literature. 

Read More

VacSol

a high throughput in silico pipeline to predict potential therapeutic targets in prokaryotic pathogens using subtractive reverse vaccinology

Read More

VacSol-ML

is a pipeline that uses machine learning algorithms to predict potential vaccine candidates in ESKAPE pathogens

Read More

Bvac-AI

expertly analyzes protein sequence data, providing unparalleled insights for the development of targeted vaccines against a wider spectrum of resistant bacteria.

Read More

PanRV

is a Linux based software package in JAVA language that uses both pangenome and reverse vaccinology approaches

Read More

B-Pan

is the updated version of PanRV, a software package for robust pan-genome analysis. B-Pan integrates functional annotations and algorithms for phylogenetic and evolutionary analysis

Read More