# Researchers release Tangermeme toolkit for interpreting genomic deep learning models

Digest AI · Research · published 2026-10-08T00:00:00Z

Canonical: https://digestai.news/story/researchers-release-tangermeme-toolkit-for-interpreting-genomic-deep-l

## Summary

A team of researchers has released Tangermeme, an open-source Python toolkit designed to help scientists interpret what genomic deep learning models have learned about cis-regulatory logic. Published in Nature Machine Learning, the software focuses on "everything-but-the-model" — providing optimized, modular tools for sequence manipulation, prediction, feature attribution, and sequence design that work across model architectures including convolutions, LSTMs, and transformers.

Tangermeme introduces a novel recursive seqlet-calling algorithm that identifies variable-length sequence motifs driving model predictions, along with tools for annotating these motifs against databases like JASPAR2024 and analyzing their pairwise occurrences and spacing. The authors demonstrate the toolkit by comparing BPNet and Beluga models trained on MYC transcription factor binding, revealing that BPNet relies almost exclusively on MYC motifs while Beluga learns a broader regulatory vocabulary. The package also includes optimized one-hot encoding that processes the entire human chromosome 1 in under 2 seconds, and built-in batching for DeepLIFT/SHAP attribution that avoids GPU memory bottlenecks. Tangermeme is available under the MIT license via pip and GitHub, with documentation at tangermeme.readthedocs.io.

## Key points

- Tangermeme is an open-source toolkit for interpreting genomic deep learning models, released under MIT license
- Includes novel recursive seqlet caller that identifies variable-length regulatory motifs from model attributions
- Demonstrated on BPNet and Beluga models showing different learned cis-regulatory logic for MYC binding

## Why it matters

Provides standardized, efficient tools for biologists to extract interpretable regulatory insights from black-box genomic models, enabling comparison across architectures and accelerating discovery of cis-regulatory rules.

## Sources

1. [Tangermeme: a toolkit for understanding cis-regulatory logic using deep learning models](https://nature.com/articles/s41592-026-03254-z) (Nature Machine Learning, 2026-10-08, primary source)

## Cite

Digest AI, "Researchers release Tangermeme toolkit for interpreting genomic deep learning models", 8 October 2026, https://digestai.news/story/researchers-release-tangermeme-toolkit-for-interpreting-genomic-deep-l

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/researchers-release-tangermeme-toolkit-for-interpreting-genomic-deep-l.json