Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
The paper introduces annbatch, a mini-batch loader for the anndata format, designed to alleviate the data access bottleneck in training machine learning models on large biological datasets. By enabling out-of-core training directly on disk-backed datasets, annbatch significantly improves data loading throughput by up to an order of magnitude. The result is a reduction in training time from days to hours across various biological data modalities, while maintaining compatibility with the scverse ecosystem.
Training AI on massive biological datasets just got way faster: annbatch slashes data loading times by up to 10x.
The scale of biological datasets now routinely exceeds system memory, making data access rather than model computation the primary bottleneck in training machine-learning models. This bottleneck is particularly acute in biology, where widely used community data formats must support heterogeneous metadata, sparse and dense assays, and downstream analysis within established computational ecosystems. Here we present annbatch, a mini-batch loader native to anndata that enables out-of-core training directly on disk-backed datasets. Across single-cell transcriptomics, microscopy and whole-genome sequencing benchmarks, annbatch increases loading throughput by up to an order of magnitude and shortens training from days to hours, while remaining fully compatible with the scverse ecosystem. Annbatch establishes a practical data-loading infrastructure for scalable biological AI, allowing increasingly large and diverse datasets to be used without abandoning standard biological data formats. Github: https://github.com/scverse/annbatch