---
title: What is the DiagAI score?
description: Learn about the SeqOne DiagAI suite, which helps prioritize causal germline variants with a cutting-edge machine learning approach based on pathogenicity, phenotypes and expert rules.
---
[Skip to content](https://hubspot.seqone.com/test_seqone/what-is-the-diagai-score#main-content)
English
Show submenu for translations
SeqOne
Open main navigation
Close main navigation
- English
Show submenu for translations
- Contact us
Contact us
How can we help you?
- There are no suggestions because the search field is empty.
1. [Test\_SeqOne](https://hubspot.seqone.com/test_seqone?hsLang=en)
2. [Analysis & Interpretation](https://hubspot.seqone.com/test_seqone/analysis-interpretation?hsLang=en)
3. [DiagAI](https://hubspot.seqone.com/test_seqone/analysis-interpretation?hsLang=en#diagai)
# What is the DiagAI score?
## This guide will walk you through what the DiagAI Score is, how it works, and how it can streamline your variant interpretation process.
### **What is the DiagAI Score?**
The [DiagAI Score](https://hubspot.seqone.com/hubfs/Ressources/SeqOne%20DiagAI%20WhitePaper.pdf?utm_medium=email&_hsenc=p2ANqtz-_kdCCBZv2bPoViexq3VasYdpSIrsnD63lceBLh2LQ_y-AgqTRkKntAmsGvZoUM9yUcUGwxbdFWBU7hCljGPKFBUD6RMg&_hsmi=96459724&utm_content=96459724&utm_source=hs_automation&hsLang=en) is a sophisticated ranking system for germline variants. It assigns a **score from 0 to 100** to each variant, indicating **how likely it is to be the cause of a disease**. The higher the score, the more likely the variant is to be clinically significant. This allows you to quickly focus on the variants that matter most, saving you valuable time during analysis.
The DiagAI Score is not just a single calculation; it's the result of a comprehensive assessment that combines three key components: **Pathogenicity**, **Phenotype**, and **Expert Rules**.
#### **The Three Pillars of the DiagAI Score**
##### **1. Pathogenicity (UP² Model)**
At its core, the DiagAI Score evaluates the inherent likelihood of a variant to be damaging. It does this using a powerful machine-learning model called the Universal Pathogenicity Predictor (UP²).
- **What it does:** The UP² model predicts a variant's pathogenicity. It's designed to work with both known and novel variants, which is crucial for identifying new disease-causing mutations.
- **How it works:** This model was trained on a massive dataset of over 2.5 million variants from ClinVar. It analyzes 72 distinct features for each variant to make its prediction.
- **High Accuracy:** The UP² model is highly accurate, predicting ACMG variant classifications with 97% accuracy when compared to ClinVar annotations. It can assess all types of variants, including missense, nonsense, and frameshift variants.
##### **2. Phenotype (PhenoGenius)**
Understanding the connection between a patient's symptoms (phenotype) and their genetic variants (genotype) is key to diagnosis. This is where PhenoGenius comes in.
- **What it does:** PhenoGenius is an innovative system that ranks genes based on the patient's reported symptoms (HPO terms). It goes beyond simple gene-symptom lists by modeling how different symptoms interact with each other.
- **How it works:** It pulls data from multiple sources like OMIM, PubMed, MedGen, and Orphanet to build a comprehensive map of gene-phenotype associations. It groups synonymous symptoms to account for the variability in how clinical information is often recorded.
- **Performance:** PhenoGenius significantly improves the ranking of diagnostic genes, outperforming other tools by a considerable margin.
##### **3. Expert Rules**
The final component of the DiagAI Score is a rule-based system designed in collaboration with genetics experts.
- **What it does:** This system prioritizes variants by considering inheritance patterns, the quality of the sequencing data, and gene relevance. For example, it evaluates the variant's zygosity and familial transmission patterns.
- **How it works:** The "weight" or importance of each rule has been optimized by training the system on real-world diagnostic cases. This ensures that the rules are not just theoretically sound but also clinically relevant.
- **Quality Matters:** The system also factors in important quality metrics like the VAF, frequency in the cohort and Phred score to ensure the reliability of the findings.
---
#### **The "Explainable AI" Approach**
A common concern with AI in clinical settings is the "black box" problem – not knowing how the AI arrived at its conclusion. SeqOne addresses this by making the DiagAI Score transparent.
For each component of the score, you can access a detailed breakdown of what influenced the result. **Simply click on your variant's DiagAI score in the Variant Table, to automatically open the side panel on the DiagAI tab.**
The tab provides information and graphs illustrating each of the score's components.
- **Pathogenicity:** On an intuitive graph, you can see how different molecular features contributed to the UP² pathogenicity score (up or down).
- **Phenotype:** A visual interface shows you exactly how the patient's symptoms map to specific genes.
- **Expert Rules:** The system clearly indicates which inheritance and quality rules were met for each variant.
This transparency allows you to critically evaluate the AI's recommendations and make more informed decisions.
#### **Practical Applications: ShortList and SmartPick**
To further speed up your workflow, the DiagAI platform includes two key features based on the DiagAI Score.
**ShortList:** This feature narrows down thousands of variants to a manageable list of about 8, with a 95% probability of containing the disease-causing variant.
- - - - Variants in the shortlist have a distinct icon next to their score.
- Use the preset “DiagAI” filter profile on your variant table to focus on just the Shortlist.
**SmartPick:** For cases with HPO terms or family studies, this feature goes a step further and suggests the most likely causative variant with 90% specificity.
- - - - SmartPick variants are variants from the ShortList with an exceptionally high combined pathogenicity and phenotypе relevance score.
- SmartPick variants also have a distinct icon next to their score.
#### **Further reading: DiagAI Whitepaper**
For more information on DiagAI models and performances, read [our White Paper](https://hubspot.seqone.com/hubfs/Ressources/SeqOne%20DiagAI%20WhitePaper.pdf?utm_medium=email&_hsenc=p2ANqtz-_kdCCBZv2bPoViexq3VasYdpSIrsnD63lceBLh2LQ_y-AgqTRkKntAmsGvZoUM9yUcUGwxbdFWBU7hCljGPKFBUD6RMg&_hsmi=96459724&utm_content=96459724&utm_source=hs_automation&hsLang=en)!
- [Releases](https://hubspot.seqone.com/test_seqone/releases?hsLang=en#main-content)
- [Spring 2026](https://hubspot.seqone.com/test_seqone/releases?hsLang=en#spring-2026)
- [Release Notes 2025](https://hubspot.seqone.com/test_seqone/releases?hsLang=en#release-notes-2025)
- [What's new in Preview?](https://hubspot.seqone.com/test_seqone/releases?hsLang=en#whats-new-in-preview)
- [Analysis & Interpretation](https://hubspot.seqone.com/test_seqone/analysis-interpretation?hsLang=en#main-content)
- [Variant table](https://hubspot.seqone.com/test_seqone/analysis-interpretation?hsLang=en#variant-table)
- [Workflow Management](https://hubspot.seqone.com/test_seqone/analysis-interpretation?hsLang=en#workflow-management)
- [Annotation and Scores](https://hubspot.seqone.com/test_seqone/analysis-interpretation?hsLang=en#annotation-and-scores)
- [Reporting](https://hubspot.seqone.com/test_seqone/analysis-interpretation?hsLang=en#reporting)
- [DiagAI](https://hubspot.seqone.com/test_seqone/analysis-interpretation?hsLang=en#diagai)
- [Coverage and Metrics](https://hubspot.seqone.com/test_seqone/analysis-interpretation?hsLang=en#coverage-and-metrics)
- [CNV](https://hubspot.seqone.com/test_seqone/analysis-interpretation?hsLang=en#cnv)
- [Getting started](https://hubspot.seqone.com/test_seqone/getting-started?hsLang=en#main-content)
- [General Platform Usage](https://hubspot.seqone.com/test_seqone/getting-started?hsLang=en#general-platform-usage)
- [Intro to worksets](https://hubspot.seqone.com/test_seqone/getting-started?hsLang=en#intro-to-worksets)
- [Video Tutorials](https://hubspot.seqone.com/test_seqone/getting-started?hsLang=en#video-tutorials)
- [Files](https://hubspot.seqone.com/test_seqone/getting-started?hsLang=en#files)
- [Intro to Platform Features](https://hubspot.seqone.com/test_seqone/getting-started?hsLang=en#intro-to-platform-features)
- [Troubleshooting](https://hubspot.seqone.com/test_seqone/troubleshooting?hsLang=en#main-content)
- [General](https://hubspot.seqone.com/test_seqone/troubleshooting?hsLang=en#general)
- [Credentials](https://hubspot.seqone.com/test_seqone/troubleshooting?hsLang=en#credentials)
- [Error and info messages](https://hubspot.seqone.com/test_seqone/troubleshooting?hsLang=en#error-and-info-messages)
- [Information Security & Compliance](https://hubspot.seqone.com/test_seqone/information-security-compliance?hsLang=en#main-content)
- [General](https://hubspot.seqone.com/test_seqone/information-security-compliance?hsLang=en#general)
- [AI Systems Documentation](https://hubspot.seqone.com/test_seqone/ai-systems-documentation?hsLang=en#main-content)
- [DiagAI Autofill](https://hubspot.seqone.com/test_seqone/ai-systems-documentation?hsLang=en#diagai-autofill)
- [DiagAI HPO](https://hubspot.seqone.com/test_seqone/ai-systems-documentation?hsLang=en#diagai-hpo)
- [Technical Information](https://hubspot.seqone.com/test_seqone/technical-information?hsLang=en#main-content)
- [Workflows - Somatic](https://hubspot.seqone.com/test_seqone/technical-information?hsLang=en#workflows-somatic)
- [Technical details](https://hubspot.seqone.com/test_seqone/technical-information?hsLang=en#technical-details)
- [Databases](https://hubspot.seqone.com/test_seqone/technical-information?hsLang=en#databases)
# SeqOne
[mailto:email@email.com](mailto:email@email.com)
Copyright © 2026, SeqOne