7ee42571461ed5a384f3d1b628253a8773850cb2
max
  Wed Sep 9 08:54:16 2026 -0700
AlphaGenome track doc: preprint reference, threshold guidance from the authors

The AlphaGenome authors reviewed the description page and asked for the
peer-review status to be updated, for their threshold recommendation to
be stated, and for links to the Atlas preprint and the educational
guides.

diff --git src/hg/makeDb/trackDb/human/alphaGenome.html src/hg/makeDb/trackDb/human/alphaGenome.html
index 59165f3bf53..eba79ecd514 100644
--- src/hg/makeDb/trackDb/human/alphaGenome.html
+++ src/hg/makeDb/trackDb/human/alphaGenome.html
@@ -1,77 +1,100 @@
 <h2>Description</h2>
 <p>
 This track shows the AlphaGenome Variant Impact (AVI) score, a prediction from Google DeepMind
 of how likely a given substitution is to be disease causing. Scores are provided for every
 possible single-base substitution at every position in the genome, about 8.8 billion in total.
 Unlike predictors that only cover protein-coding changes, the AVI score is defined genome wide,
 so it also scores variants in introns and in intergenic regulatory regions.
 </p>
+<p>
+For an introduction to AlphaGenome and to the AVI score, see the
+<a href="https://deepmind.google.com/science/alphagenome/learning" target="_blank">AlphaGenome
+educational guides</a> at Google DeepMind. The resource and the score are described in detail in
+the
+<a href="https://storage.googleapis.com/deepmind-media/DeepMind.com/Blog/alphagenome-atlas-a-predictive-map-of-every-possible-dna-letter-change-in-the-human-genome/alphagenome-atlas.pdf"
+target="_blank">AlphaGenome Atlas preprint</a>.
+</p>
 
 <h2>Display Conventions and Configuration</h2>
 <p>
 Because there are three possible substitutions at each position, the scores are split across
 four separate graphs, one for each alternate allele. The graph labelled "Mutation: A" shows the
 score for changing the reference base to an A, and so on. At any given position only three of
 the four graphs carry a real prediction; the fourth is the one matching the reference base,
 where no substitution exists, and it is shown as zero.
 </p>
 <p>
 The source data gives two numbers per variant, a raw model score and a PHRED-scaled version of
 it. This track displays the PHRED-scaled score, which is easier to compare across variants: it
 is a rank in which 10 corresponds to the top 10 percent of the most impactful substitutions in
 the genome, 20 to the top 1 percent, and 30 to the top 0.1 percent. Higher values therefore
-indicate a variant predicted to be more damaging. Most positions score low, with a genome-wide
-median near 1.6, so the default view is scaled to 0 to 30 rather than to the observed maximum
-of about 89.
+indicate a variant predicted to be more damaging. Any score above 20 can be considered high, and
+the authors recommend treating 50 as the top of the useful range. Most positions score low, with
+a genome-wide median near 1.6, so the default view is scaled to 0 to 30 rather than to the
+observed maximum of about 89. Scores above the top of the range are drawn clipped at the top of
+the graph; the range can be changed on the track configuration page.
 </p>
 <p>
 Individual scores are only shown when the view is zoomed in far enough. At wider zoom levels the
 graph shows the range of scores in each screen pixel rather than a single value.
 </p>
 
 <h2>Methods</h2>
 <p>
 The AVI score comes from a machine learning model that combines several kinds of evidence about
 a variant: AlphaGenome regulatory predictions, AlphaMissense pathogenicity scores for changes
 that fall in coding sequence, measures of evolutionary sequence conservation, and further
 functional annotations. Google DeepMind precomputed the score for all single-base substitutions
 in GRCh38 and released it as a tab-separated, tabix-indexed table of chromosome, position,
-reference allele, alternate allele, raw score and PHRED score. Note that the score has not yet
-been described in a peer-reviewed publication.
+reference allele, alternate allele, raw score and PHRED score. The method is described in the
+AlphaGenome Atlas preprint (see References below), which has been submitted for peer review but
+is not yet published. The authors do not define a pathogenicity cutoff, but recommend that users
+adopt genomic region- or application-aware thresholds, and prefer ranking variants by score over
+applying a hard cutoff where possible.
 </p>
 <p>
 The scores can be downloaded from the
 <a href="https://deepmind.google.com/science/alphagenome/atlas" target="_blank">AlphaGenome
 Atlas</a>. At UCSC the table was split into one wig file per alternate allele and each was
 converted to bigWig. The PHRED column was copied through as text, so the values shown are
 exactly those in the source file. The commands are documented in the
 <a href="https://github.com/ucscGenomeBrowser/kent/blob/master/src/hg/makeDb/doc/hg38/alphaGenome.txt"
 target="_blank">makeDoc</a>, and the conversion program is in the
 <a href="https://github.com/ucscGenomeBrowser/kent/tree/master/src/hg/oneShot/alphaGenomeToWig"
 target="_blank">kent source tree</a>.
 </p>
 
 <h2>Data Access</h2>
 <p>
 Google DeepMind's terms do not allow UCSC to redistribute this dataset, so it is not available
 from the Table Browser, the Data Integrator, the Genome Browser API or our download server. The
 full set of precomputed scores can be obtained directly from the
 <a href="https://deepmind.google.com/science/alphagenome/atlas" target="_blank">AlphaGenome
 Atlas</a>, which provides the same tab-separated, tabix-indexed file that this track was built
 from. Scores for individual variants can also be read off the track in the browser by zooming in
 until single bases are visible.
 </p>
 <p>
 Use of the AlphaGenome Services and their output is subject to the
 <a href="https://deepmind.google.com/science/alphagenome/atlas" target="_blank">AlphaGenome
 Services Additional Terms of Service</a>. In summary, the Services are available only to
 individuals and to non-commercial organizations such as universities, non-profit research
 institutes, educational bodies and government bodies, or for journalism, and their output may not
 be used for clinical purposes or relied on for medical advice.
 </p>
 
 <h2>Credits</h2>
 <p>
 Thanks to Dhavanthi Hariharan, Francesca Pietra, Tom Ward and Elisa Wong at Google DeepMind for
 providing this dataset and for their help with the track description.
 </p>
+
+<h2>References</h2>
+<p>
+Cheng J, Taylor KR, Nicolaisen L, Pan J, Bycroft C, Perino M, Ward T, Hawkes G, Covill LE,
+Weilert M <em>et al</em>.
+<a href="https://storage.googleapis.com/deepmind-media/DeepMind.com/Blog/alphagenome-atlas-a-predictive-map-of-every-possible-dna-letter-change-in-the-human-genome/alphagenome-atlas.pdf"
+target="_blank">AlphaGenome Atlas: in silico mutagenesis of the entire human genome improves
+prioritization and interpretation of non-coding variants</a>. Preprint, 2026. Submitted for peer
+review.
+</p>