BlockFormer applies a transformer architecture to localize centromeres from Hi-C maps by training on abundant synthetic interaction data generated by a custom simulator.
Physical tethering and volume exclusion determine higher-order genome organization in budding yeast
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
$\textit{BlockFormer}$ : Transformer-based inference from interaction maps
BlockFormer applies a transformer architecture to localize centromeres from Hi-C maps by training on abundant synthetic interaction data generated by a custom simulator.