flipon.ai

Home / Models / Z-DNABERT

In production

Z-DNABERT

A transformer built on DNA language model pretraining, fine-tuned on experimental Z-DNA data.

WHOLE-GENOME PREDICTIONS
Z-DNABERT

Attention-based interpretation recovers known Z-forming motifs — alternating purine–pyrimidine repeats, CA/TG and CG dinucleotide tracts — directly from the learned representations, without motif engineering.

Trained on Kouzine et al. 2018.

Downloads

Genome-wide predictions

Described in

Z-flipon variants reveal the many roles of Z-DNA and Z-RNA in health and disease Umerenkov D, Herbert A, Konovalov D, Danilova A, Beknazarov N, Kokh V, Fedorov A, Poptsova M · Life Sci Alliance, 2023 · doi:10.26508/lsa.202301962

Trained on

Z-DNA_Kouzine_hg19 Kouzine et al. 2018