# Computer Predictors

The following is a list of computational tools Connected Insights uses to understand the functional impact of the variant on the protein function. This sectionis only available for variants.

### Computational Tools

| **Field Name**                       | **Description**                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                       |
| ------------------------------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Tool                                 | Description                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                           |
| REVEL                                | The Rare Exome Variant Ensemble Learner (REVEL) is an ensemble method for predicting the pathogenicity of rare missense variants. Scores range from 0 to 1 and variants with highers cores are predicted to be more likely to be pathogenic.                                                                                                                                                                                                                                                                          |
| SIFT                                 | The Sort Intolerant From Tolerant (SIFT) score predicts whether an amino acid substitution is likely to affect protein function based on sequence homology and the physicochemical similarity between the alternate amino acids. The qualitative prediction for substitutions with a score less than 0.05 are predicted to be deleterious. All other variants are considered tolerated.                                                                                                                               |
| PolyPhen-2                           | <p>Polymorphism Phenotyping-2, or PolyPhen-2, predicts the effect of an amino acid substitution on the structure and function of a protein using the following components:<br>• Sequence homology<br>• Pfam annotations<br>• 3D structures from PDB (where available)<br>• Other databases and tools (for example, DSSP and ncoils)<br>The PolyPhen-2 score represents the probability that a substitution is damaging, so values near1 are predicted to be deleterious, which is the opposite of the SIFT score.</p> |
| PrimateAI                            | PrimateAI is a deep residual neural network for classifying the pathogenicity of missense mutations. For more information, refer to [Acronyms and Terms](/connected-insights/resources-and-references/rar-acronyms-and-terms.md).                                                                                                                                                                                                                                                                                     |
| PrimateAI-3D                         | PrimateAI-3D is a three-dimensional (3D) convolutional neural network for classifying the pathogenicity of missense mutations. For more information, refer to [Acronyms and Terms](/connected-insights/resources-and-references/rar-acronyms-and-terms.md).                                                                                                                                                                                                                                                           |
| Nirvana Cross-SpeciesAA Conservation | Nirvana Cross-Species AA Conservation uses amino acid conservation scores that are obtained from multiple alignments of vertebrate exomes to the human ones. The score indicates the frequency with which a particular AA is observed in humans.                                                                                                                                                                                                                                                                      |
| PhyloP                               | PhyloP scores measure evolutionary conservation at individual alignment sites. For more information, refer to [Acronyms and Terms](/connected-insights/resources-and-references/rar-acronyms-and-terms.md).                                                                                                                                                                                                                                                                                                           |
| SpliceAI                             | SpliceAI is the delta score of a variant that can also be interpreted as the probability of the variant being splice-altering. For more information, refer to [Acronyms and Terms](/connected-insights/resources-and-references/rar-acronyms-and-terms.md).                                                                                                                                                                                                                                                           |
| gnomAD                               | <p>gnomAD consists of the following items:<br>• Constraint metrics<br>• LOEUF<br>• misZ<br>• pLi<br>• pNull<br>• pRec<br>• synZ<br>For more information, refer to <a href="/pages/cK1afbDR0LVjQqS79VgJ">Acronyms and Terms</a>.</p>                                                                                                                                                                                                                                                                                   |


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://help.connected.illumina.com/connected-insights/interpret-and-report/viewdetails-introduction/viewdetails-computer-predictors.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
