Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/BDB-Genomics/AlphaGenomeR/llms.txt

Use this file to discover all available pages before exploring further.

AlphaGenomeR is a Bioconductor-ready R package that wraps the Google DeepMind AlphaGenome API, giving R researchers access to transformer-based genomic predictions without leaving their native R environment. It bridges the official Python SDK via reticulate and returns results as R-native matrices and data frames ready for downstream analysis.

Installation

Install AlphaGenomeR from GitHub or Bioconductor and set up the Python dependency.

Quickstart

Make your first multimodal genomic prediction in minutes.

Modalities

Explore 11 supported genomic modalities including RNA-seq, ATAC, splicing, and 3D genome.

API Reference

Full function signatures, parameters, and return types for every exported function.

​
What is AlphaGenome?

AlphaGenome is a multimodal transformer model developed by Google DeepMind that predicts functional genomic features directly from DNA sequences at single-base resolution. Given a 1 MB genomic interval, it can predict RNA-seq signal, chromatin accessibility (ATAC-seq), transcription factor binding (ChIP-seq), splicing patterns, and 3D chromatin contact maps — simultaneously, for specific tissues or cell types. AlphaGenomeR makes these predictions accessible to the R/Bioconductor ecosystem by handling all gRPC communication through the official Python SDK and converting outputs into standard R data structures.

​
Key capabilities

Multimodal predictions

Query 11+ genomic modalities in a single API call — from gene expression to 3D genome architecture.

Tissue specificity

Filter predictions by tissue or cell type using UBERON and CL ontology terms.

Bioconductor-native output

Results come back as matrices and data frames that integrate directly with Bioconductor packages.

Single-base resolution

Predictions span 1 MB genomic intervals at base-pair resolution for precise regulatory analysis.

​
Get started in three steps

1

Install the package and Python dependency

# Install from GitHub
devtools::install_github("BDB-Genomics/AlphaGenomeR")

# Install the AlphaGenome Python SDK
pip install alphagenome
2

Query a genomic region

library(AlphaGenomeR)

results <- alphagenome_query(
  access_token = "YOUR_API_KEY",
  genomic_region = "chr17:42560601-43609177",
  ontology_terms = c("UBERON:0002048"),  # Lung
  requested_outputs = c("RNA_SEQ", "ATAC")
)
3

Extract and analyze predictions

rna_data <- alphagenome_get_rna_seq(results)

# Prediction matrix: positions x tracks
dim(rna_data$values)

# Track metadata: cell types, experiments
head(rna_data$metadata)
AlphaGenomeR requires Python >= 3.10 and the alphagenome Python package. See Installation for full setup instructions.

Build docs developers (and LLMs) love

Get started for freeTalk to us