Description

This track collection shows ClinPred scores, a machine-learning predictor of pathogenicity for nonsynonymous (missense) single-nucleotide variants. ClinPred combines existing pathogenicity scores with population allele frequency from gnomAD, and was trained on confidently annotated disease-causing and benign variants from ClinVar. Pre-computed scores are provided for all possible human missense variants in the exome.

Scores range from 0 to 1, with higher values indicating greater predicted likelihood that a variant is disease-relevant. The authors recommend a score of ≥ 0.5 as evidence of pathogenicity. As with any pathogenicity prediction score, ClinPred is intended as supporting evidence rather than a stand-alone classifier.

Display Conventions and Configuration

There are four subtracks in this collection, one for each possible alternate nucleotide. At every exome position covered by ClinPred, three of the four subtracks show a score (one per non-reference base) and the fourth, corresponding to the reference base, is set to 0. Synonymous alternates — those that do not change the encoded amino acid — are also set to 0, since ClinPred only scores missense variants. Positions with no exome coverage are shown as gaps.

When using this track, zoom in until you can see every basepair at the top of the display. Otherwise, several nucleotides fall under each pixel and no score will be shown on the mouseover tooltip.

Track colors

Each subtrack is colored by score using the threshold recommended by the ClinPred authors:

Range Classification
≥ 0.5 Likely pathogenic
< 0.5 Likely benign

Data Access

ClinPred scores are available at the ClinPred website, which provides pre-computed scores for all possible human missense variants.

The ClinPred data on the UCSC Genome Browser can be explored interactively with the Table Browser or the Data Integrator. For automated download and analysis, the data are stored in bigWig files and can be downloaded from our download server. The files are named a.bw, c.bw, g.bw, t.bw. Individual regions can be obtained using bigWigToBedGraph, which can be compiled from source or downloaded as a precompiled binary; instructions are here. For example:
 
bigWigToBedGraph -chrom=chr1 -start=100000 -end=100500 http://hgdownload.soe.ucsc.edu/gbdb/$db/clinPred/a.bw stdout

Methods

Data were downloaded from the ClinPred website on May 5, 2026, and converted into four per-alternate-base bigWig files using a custom script. As with all other tracks, a full log of the commands used for the conversion is available in our source repository, for hg19 and hg38.

Data Use

ClinPred scores are freely available for non-commercial applications. For commercial use, please see the licensing information on the ClinPred website.

Credits

Thanks to the ClinPred authors for making the pre-computed scores available through their website.

References

Alirezaie N, Kernohan KD, Hartley T, Majewski J, Hocking TD. ClinPred: Prediction Tool to Identify Disease-Relevant Nonsynonymous Single-Nucleotide Variants. Am J Hum Genet. 2018 Oct 4;103(4):474-483. PMID: 30220433; PMC: PMC6174354