AlphaFlipon
Flagship multimodal, multi-task model: the full repertoire of non-B conformations, conditioned on open chromatin.
Home / Models
Sequence-based and multimodal models for Z-DNA, G-quadruplexes, H-DNA and cruciforms. Each model is released with its trained weights and the genome-wide predictions it produced, versioned against the release, so a published analysis can be reproduced against the exact predictions it used.
Flagship multimodal, multi-task model: the full repertoire of non-B conformations, conditioned on open chromatin.
The companion architecture for G-quadruplex prediction.
Described in
Trained on
Genome-wide predictions
A deep learning framework for genome-wide Z-DNA prediction.
Described in
ADAR1 masks the cancer immunotherapeutic promise of ZBP1-driven necroptosis
Deep learning approach for predicting functional Z-DNA regions using omics data
Trained on
Z-DNA in promoters conserved between human and mouse.
Trained on
A DNA language model fine-tuned for G-quadruplex recognition.
Described in
Trained on
A transformer built on DNA language model pretraining, fine-tuned on experimental Z-DNA data.
Trained on