Research software

PolyAMiner-Bulk

A deep-learning method that decodes alternative polyadenylation dynamics from ordinary bulk RNA-seq, no specialized library prep required. Published in Cell Reports Methods (2024).

GitHub Paper Protocol

Genome-wide

Calls 3'UTR shortening and lengthening across every expressed gene, not just a curated panel.

Deep-learning core

A learned model separates true polyadenylation shifts from coverage noise, cutting false positives.

Interpretable

Per-gene APA indices and differential results you can take straight into a figure.

Reproducible

Published step by step in STAR Protocols so any lab can run it.

Get started

Install and run

# clone and install
git clone https://github.com/YalamanchiliLab/PolyAMiner-Bulk.git
cd PolyAMiner-Bulk
pip install -r requirements.txt

# example: compare two conditions
python PolyA-miner.py -mode bam -o results/ \
  -c1 control_1.bam control_2.bam \
  -c2 treatment_1.bam treatment_2.bam \
  -ref annotation/

Illustrative usage. See the repository README for the full set of options and a worked example.

The idea

What it detects

Most genes can end their messenger RNA in more than one place. PolyAMiner-Bulk reads ordinary RNA-seq coverage and infers which polyadenylation site a cell is using, then quantifies how that choice shifts between conditions. The interactive diagram on the research page walks through why that matters.

See the 3'UTR switch explainer

Cite

If PolyAMiner-Bulk helps your work

Cell Reports Methods · 2024

Jonnakuti VS, Wagner EJ, Maletić-Savatić M, Liu Z, Yalamanchili HK. PolyAMiner-Bulk is a deep learning-based algorithm that decodes alternative polyadenylation dynamics from bulk RNA-seq data. Cell Reports Methods. 2024;4(2):100707. doi:10.1016/j.crmeth.2024.100707

Using it in your research?

I am glad to help you get it running or talk through your data.

Get in touch