Pathogenicity Predictor: AI-Based Variant Risk Assessment and Classification

Home AI Assistant

Toolbox

Databases

Resources

About Us

AI Tools

RNA Splicer

ASO Designer

Pathogenicity Predictor

Bioinfo Tools

Sequence Viewer

Mutation Direct

Antibody Discovery

Target Insights

Computational Analysis

Databases

Learn

Explore

Contact

中文

About

Pathogenicity Predictor is a mutation site pathogenicity prediction tool based on an AI model, jointly developed by Cyagen Biosciences and the Artificial Intelligence Innovation Center of the Research Institute of Tsinghua University, Pearl River Delta.

This tool is capable of predicting single-base mutations (including insertions and deletions) in the human genome and evaluating whether they are likely to cause serious diseases, providing efficient and reliable pathogenicity analysis support for scientific research and clinical practice.

Predict genetic mutation pathogenicity instantly with our deep learning AI.

Mutation information is missing. The system will default to predicting based on absence of mutation. Please confirm to proceed or return to modify.

Home

Tools

Pathogenicity Predictor

Predict genetic mutation pathogenicity instantly with our deep learning AI.

Input

History

About

User Guide

Second base in codon

First base in codon

Last base in codon

Please enter the mutation site in the following input box for prediction.

Codon Chart

Input Mode:

1. Input mutation: Directly enter or paste standard mutation names.

2. Input transcript: Enter the mutation position and the base after mutation, and the reference base will be automatically filled.

3. Input protein: Enter the mutation position and the amino acid after mutation, and the reference amino acid will be automatically filled.

Standard Mutation Nomenclature:

Please enter a standard mutation name that conforms to the HGVS naming rules, for example:

（1）TP53: c.123T>A

（2）TP53: c.123_124TG>C

（3）TP53: c.169+2T>C

（4）TP53: c.45_46insGC

（5）COL4A5: c.36_38del

（6）COL4A5: c.45_47delinsTT

（7）COL4A5: c.-1G>T

（8）DMD: c.*16G>T

（9）DMD: c.23+4_23+5GG>CT

（10）DMD: p.Ser3435Ter

Note: If the system reports an error, it may be due to incorrect name format, failure to comply with HGVS rules, the site exceeding the transcript range, incorrect original base/amino acid, or exceeding the limit on the number of bases or amino acids before and after mutation, among other reasons.

Transcript ID:

MANE transcript is the default option. Please make careful to choose the right transcript ID depending on the mutation source, as wrong selection may result in mislocalization. The version number follows the decimal point in the transcript ID. This program uses the most recent NCBI data; using previous versions may not be compatible with this tool and may result in mislocalization.

Reference:

After determining the site, the eference base will be automatically filled in without the need for manual input.

Mutant:

1. In the case of a mutation, an empty base indicates the deletion of the corresponding base or sequence at the site.

2. Only the abbreviations for the four bases A/T/G/C are allowed, and the sequence length must not exceed 10.

Unfold Diagram

Concurrent RNA splicing prediction

Checking \"Concurrent RNA splicing prediction\" will conduct pathogenicity calculation and splicing change analysis simultaneously, which doubles the computing time.

History Record	Update Time	Status	Updater	Review
No data available

0 Results, 10 per Page

Confirm Delete

Are you sure you want to delete ‘--’?

iCyagen

User Agreement