About

Flipons are genomic elements that adopt left-handed Z-DNA, G-quadruplex, triplex (H-DNA) and cruciform conformations under torsional stress, acting as conformational switches in transcription, replication, repair and immune signalling. Their functional impact is condition-dependent: the same sequence may remain B-form in one cell type and flip in another, which makes experimental mapping expensive and inherently incomplete.

flipon.ai closes this gap computationally. We build sequence-based and multimodal deep learning models trained on high-throughput experimental maps (Z-DNA ChIP-seq, G4-seq and BG4 CUT&Tag, permanganate and S1-nuclease footprints), and we release them together with the genome-wide predictions they generate. Everything on this site — code, trained weights, whole-genome tracks, and the publications behind them — is intended to be used, checked and extended by the community.

We release genome-wide predictions as ready-to-use tracks (BED / bigWig, hg38 and T2T-CHM13, mouse where training data allow), downloadable in bulk. Maps are versioned against the model release that produced them, so any published analysis can be reproduced against the exact predictions it used. Cell-type-resolved AlphaFlipon tracks are provided for ENCODE reference cell lines and primary tissues with matched accessibility data.

flipon.ai is developed by an international group of researchers in computational genomics, structural biology and machine learning, working across academic laboratories and open collaboration. We welcome contributions, benchmark submissions and requests for cell types to be added to the AlphaFlipon release.

Centre for Biomedical Research and Technologies, Institute of Artificial Intelligence and Digital Sciences, HSE University, Russia
InsideOutBio, USA