Year: 2026
Type: preprint
Abstract: Motivation Sequence-to-function models predict genomic tracks from DNA sequence. AlphaGenome has been shown to outperform previous models, including Borzoi, on most track-prediction and variant-effect benchmarks. However, like its predecessors, it predicts tracks only for predefined, mostly bulk-derived cell types and tissues. While Scooby has extended Borzoi to single-cell resolution, a single-cell adaptation of AlphaGenome is still lacking. Results We present Scooby-2, which combines AlphaGenome with a cell-specific decoder to predict single-cell RNA-seq coverage and chromatin-accessibility genomic tracks from DNA sequence. The package provides the implementation, the parameter-efficient fine-tuning setup, the training pipeline and inference scripts. When evaluated on the NeurIPS bone marrow single-cell dataset, Scooby-2 achieved a Pearson correlation of 0.56 when predicting cell-type-specific gene expression differences, compared with 0.53 for Scooby. When using the distilled AlphaGenome backbone, variant effect prediction concordance of fine-mapped eQTLs from the OneK1K cohort improved from 0.37 to 0.47 Spearman’s rank correlation across all associations, an improvement consistent with that of AlphaGenome over Borzoi itself. Availability and implementation Scooby-2 alongside training code is available at github.com/gagneurlab/scooby under the MIT license. Trained weights ( huggingface.co/johahi/neurips-scooby-2 , huggingface.co/johahi/onek1k-scooby-2 ) are derivatives of AlphaGenome and are distributed under the AlphaGenome Model Parameters Terms of Use. Contact [email protected] ; [email protected]
Authors: Johannes Hingerl, Julien Gagneur
Language: English
Subfield: Molecular Biology
Domain: Life Sciences
Open Access status: green
Funder: Deutsche Forschungsgemeinschaft
OpenAlex ID: W7224454152