AlphaGenome
v0.7.0Predict RNA-seq variant effects on gene expression across returned tissues and cell types.
Predict RNA-seq variant effects on gene expression across returned tissues and cell types.
Bring Your Own Key (BYOK)
AlphaGenome is a deep learning model from Google DeepMind that predicts how genetic variants affect gene regulation. Its RNA-seq output contains 667 tracks spanning 285 unique biosamples at single base-pair resolution.
The model processes up to 1 million base pairs of DNA sequence and outputs predictions for gene expression (RNA-seq), splicing patterns, chromatin accessibility, and other regulatory features. Unlike models that focus on protein-coding regions (about 2% of the genome), AlphaGenome specializes in the non-coding 98% where most disease-associated variants reside.
AlphaGenome builds on DeepMind's earlier Enformer model and complements AlphaMissense, which predicts effects of variants within protein-coding regions.
Submit one VCF-style variant and a personal DeepMind API key to run AlphaGenome RNA-seq predictions online. ProteinIQ returns run details and track metadata for inspection, plus the paired reference and alternate full-resolution arrays for download without local Python setup.
AlphaGenome on ProteinIQ uses a Bring Your Own Key model. The DeepMind key supplies access to the model API. ProteinIQ credits still apply for job orchestration, result processing, and storage; the run form shows the current credit estimate before submission.
AlphaGenome is licensed by DeepMind for non-commercial research use only. This means ProteinIQ cannot host the model on its own servers or provide a shared API key. Doing so would violate the commercial use restrictions. By using a personal API key, researchers access AlphaGenome directly through DeepMind's infrastructure under their own non-commercial research agreement. Users are responsible for ensuring their use complies with DeepMind's Terms of Use.
The API key is free for academic and non-commercial research. Organizations seeking commercial access should contact DeepMind through their dedicated inquiry form.
ProteinIQ does not store API keys in its database. Keys are stripped from job records before storage and are only used transiently to communicate with DeepMind's API. However, the key does pass through ProteinIQ's processing servers during job execution.
| Field | Description |
|---|---|
Variant | One VCF variant record containing chromosome, 1-based position, ID, reference bases, and one alternate allele. Headered single-record VCF files are supported. |
AlphaGenome API Key | Personal API key from DeepMind (required). |
Job name | Optional label for identifying the job in history. |
| Setting | Description |
|---|---|
Window size | Analysis region: 16K bp (fastest), 128K bp, or 512K bp. Larger windows capture more regulatory context but produce larger output files. |
| Setting | Description |
|---|---|
Requested outputs | Prediction type. ProteinIQ currently runs RNA-seq (gene expression). |
Ontology terms | Optional comma-separated UBERON (tissue) or CL (cell type) codes for tissue-specific predictions. Example: UBERON:0002107 for liver, CL:0000057 for fibroblast. Unsupported terms are rejected so you can correct them. |
The output includes:
.npz file containing the reference and alternate RNA-seq arrays plus interval, variant, and track metadata payloadsThe downloadable .npz archive is intended for downstream analysis in Python, while the JSON metadata export helps map each returned track back to its ontology and biosample labels.
AlphaGenome uses a hybrid architecture combining convolutional neural networks and transformers:
The model was trained on thousands of experimental datasets measuring gene expression, chromatin accessibility, histone modifications, and transcription factor binding across diverse cell types. Training completed in four hours on TPUs—half the compute of the earlier Enformer model.
For variant effect prediction, AlphaGenome generates paired predictions for the reference and alternate sequence. ProteinIQ preserves both arrays so downstream analyses can calculate the effect measure appropriate for each track.
Predict intrinsically disordered regions and per-residue disorder probabilities from protein sequences.
Predict protein aggregation nucleation propensity from amino acid sequences.
Generate, score, and compare canonical DNA sequences with Carbon language models.
Score variants, rank DNA sequences and generate DNA with the Evo 2 genome language model
Screen paired antibody variable domains for low or high polyreactivity.
Predict protein solubility from sequence with feature-level and windowed profile outputs.
Predict MMP cleavage z-scores, evaluate substrates, and generate conditional peptides.
Identify CpG-rich DNA regions using GC content, CpG density, and observed-to-expected ratios.
Calculate GC content, AT content, GC/AT skew, melting temperature, and CpG islands for DNA or RNA, with a sliding-window GC plot.
Analyze independent DNA oligos or screen a bounded set for primer interactions with Primer3 thermodynamic conditions.