Conversation
…ry genomics, 5 tools wrapping Google DeepMind's alphagenome API
…ations across all 5 alphagenome tools
Each script gets a --test-fixture arg that loads pre-computed data from a JSON file and writes output through the normal formatting path, bypassing model creation and API calls. variant_effect exercises the full VCF read/write/INFO annotation pipeline with fixture scores; the 4 TSV tools write fixture rows through csv.writer or pandas. Fixture JSON files contain synthetic placeholder data for now.
bgruening
reviewed
Feb 14, 2026
| <credentials name="alphagenome" version="1.0" | ||
| label="AlphaGenome API" | ||
| description="API key from Google DeepMind AlphaGenome"> | ||
| <secret name="api_key" inject_as_env="ALPHAGENOME_API_KEY" |
Member
There was a problem hiding this comment.
Can you please look at the indentation or reformat it with the galaxy-language server?
| </when> | ||
| </conditional> | ||
|
|
||
| <param name="verbose" type="boolean" checked="false" truevalue="true" falsevalue="false" |
Member
There was a problem hiding this comment.
I would remove this param from the user-visible params, either enable or disable by default.
| <param name="verbose" type="boolean" checked="false" truevalue="true" falsevalue="false" | ||
| label="Verbose logging"/> | ||
|
|
||
| <param name="test_fixture" type="data" format="json" optional="true" |
Member
There was a problem hiding this comment.
this should also be removed I think, instead use type="hidden" set it to true and in the command section, when the hidden-param is set to true, use $__tool_directory__ to point to your test json.
| <param name="ontology_terms" type="text" value="" label="Ontology terms (optional)" | ||
| help="Comma-separated UBERON/CL terms for tissue context, e.g. UBERON:0002107,CL:0000746"/> | ||
|
|
||
| <param name="sequence_length" type="select" label="Prediction window size"> |
| <option value="mouse">Mouse (mm10)</option> | ||
| </param> | ||
|
|
||
| <param name="output_types" type="select" multiple="true" display="checkboxes" |
Comment on lines
+177
to
+183
| ----- | ||
|
|
||
| **Citation** | ||
|
|
||
| Avsec et al. (2025). "Predicting the impact of genetic variants on chromatin, | ||
| genes, and RNA processing with a unified model." *Nature*. | ||
| DOI: 10.1038/s41586-025-10014-0 |
Member
There was a problem hiding this comment.
Suggested change
| ----- | |
| **Citation** | |
| Avsec et al. (2025). "Predicting the impact of genetic variants on chromatin, | |
| genes, and RNA processing with a unified model." *Nature*. | |
| DOI: 10.1038/s41586-025-10014-0 |
Comment on lines
+29
to
+31
| #if $verbose | ||
| --verbose | ||
| #end if |
Member
There was a problem hiding this comment.
set by default and remove from user input?
| <option value="1MB">1 MB</option> | ||
| </param> | ||
|
|
||
| <param name="max_sequences" type="integer" value="20" min="1" max="1000" |
| <validator type="no_options" message="Select at least one output type"/> | ||
| </param> | ||
|
|
||
| <param name="ontology_terms" type="text" value="" label="Ontology terms (optional)" |
| <option value="mouse">Mouse (mm10)</option> | ||
| </param> | ||
|
|
||
| <param name="output_types" type="select" multiple="true" display="checkboxes" |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Galaxy tool wrappers for Google DeepMind's AlphaGenome genomic foundation model. Five tools covering the main API endpoints:
predict_variant()with max-abs log-fold-change scoring, VCF in/outscore_variant()with server-side gene-level aggregation and quantile normalizationscore_ism_variants()for in-silico saturation mutagenesispredict_interval()for baseline regulatory track characterizationpredict_sequence()for raw DNA sequence input (synbio, non-reference genomes)All tools use Galaxy vault-backed credentials for the API key and the
alphagenomebioconda package as the primary dependency.Tests use a fixture-based approach (
--test-fixtureflag) that loads pre-computed API response data from JSON files, bypassing the API while still exercising the output-writing pipeline. Fixtures were captured from real API runs against the test inputs.Caveat: I haven't written tools in forever, so I'm sure this needs additional work and I'm happy to address anything that pops up.