CAGI Scientist Opening: apply here ☀️

Annotate all missense

Challenge: Annotate all missense 

Variant data: public

Last updated: 7 May 2018

This challenge is closed.

Make sure you understand our Data Use Agreement and Anonymity Policy


dbNSFP describes 81,084,849 possible protein-altering variants in the human genome. The challenge is to predict the functional effect of every such variant. For the vast majority of these missense and nonsense variants, the functional impact is not currently known, but experimental and clinical evidence are accruing rapidly. Rather than drawing upon a single discrete dataset as typical with CAGI, predictions will be assessed by comparing with experimental or clinical annotations made available after the prediction submission date, on an ongoing basis. If predictors assent, predictions will also incorporated into dbNSFP.


Currently, dozens of in silico methods for predicting the deleteriousness of a variant are available. In many cases, different methods may give opposite predictions for the same variant. dbNSFP is a database of human nonsynonymous single nucleotide variants (nsSNVs) and their functional predictions and annotations (Liu et al., 2011, 2013; Liu et al., 2016). It compiles 20 functional prediction scores and 6 conservation scores, as well as other related information including allele frequencies observed in different large datasets, various gene IDs from different databases, functional descriptions of genes, gene expression and gene interaction information.

Prediction challenge

A list of all possible nsSNVs based on the human reference sequence was created from dbNSFP (Liu et al., 2011, 2013; Liu et al., 2016). Predictors are asked to predict the functional effect predict each coding SNV.

Since the vast majority of these nsSNVs do not have experimental information, this challenge will assess in silico predictions with new experimental or clinical annotations as they appear in literature or databases. We anticipate making evaluations at the time of each CAGI experiment, approximately once a year.

Test File Format

Prediction submission format 

The prediction submission is a tab-delimited text file. Organizers provide a file template, which should be used for submission. In addition, a validation script is provided, and predictors should check the correctness of the format before submitting their predictions.

In the submitted file, each row must include the following tab-separated fields:

In the file, cells in columns 5-8 are marked with a "*". Submit your predictions by replacing the "*" with your value. No empty cells are allowed in the submission. You must submit predictions and standard deviation for all the variants; if you are not confident in a prediction for a variant, enter an appropriate large standard error for the prediction. Optionally, enter a brief comment on the basis of the prediction. If you do not enter a comment on a prediction, leave the "*" in those cells. Please make sure you follow the submission guidelines strictly.

In addition, your submission must include a detailed description of the method used to make the predictions, similar in style to the Methods section in a scientific article. This information will be submitted as a separate file.

If predictors assent, predictions will also be incorporated into dbNSFP. This must be explicitly specified in the document describing the method.

Given the large file that needs to be submitted for this challenge, submit your predictions and detailed description of the method by dropping the appropriate files into the Box upload widget on this page. The file submitted will go into a write-only folder for this challenge. Please name the files with group ID, submission ID and the date. 

Submit File to Annotate all missense Challenge CAGI5 Submission Folder (disabled)


Liu X, et al. dbNSFP: a lightweight database of human nonsynonymous snps and their functional predictions. Hum Mutat (2011) 32(8):894-899. PubMed 

Liu X, et al. dbNSFP v2.0:aA database of human non-synonymous SNVs and their functional predictions and annotations. Hum Mutat (2013) 34(9):E2393-2402. PubMed 

Liu X, et al. dbNSFP v3.0: a one-stop database of functional predictions and annotations for human nonsynonymous and splice-site SNVs. Hum Mutat (2016) 37(3):235-241. PubMed 

Download dataset 

Devided by chromosomes: (633.79 MB)

All chromosomes in one file: (633.79 MB)

Dataset providers

Xiaoming Liu from the University of Texas School of Public Health

Revision history 

30 November 2017: Initial release 

27 December 2017: Title fixed 

3 April 2018: Box folder for submission added 

7 April 2018: New box folder for submission link added 

9 May 2018: Challenge closed

24 September 2018: Dataset availability added