Software we developed
EagleC: A deep-learning approach to predict structure variants in cancer genomes. (Wang et al., Science Advances, 2022). Github.
NeoLoopFinder: A computational framework to identify copy number variations (CNVs) and predict enhancer-hijacking events genome-wide in the cancer genome. (Wang et al., Nature Methods, 2021). Github.
Peakachu: A supervised machine learning framework to predict chromatin loops from a genome-wide contact map (such as Hi-C and HiChIP). (Salameh and Wang et al., Nature Communications, 2020). Github.
HiCPlus: The first machine learning strategy to computationally enhance the chromatin contact maps.(Zhang et al., Nature Communications, 2018). Github.
HiCRep: One of the first and most widely used software to assess the reproducibility of Hi-C data. (Yang et al., Genome Research, 2017). Github.
The 3D Genome Browser: Visualize published chromatin interaction data such as Hi-C and HiChIP in different species, different assembly and different resolution. This website has been visited by more than 120,000 users from all over the world for over 1,200,000 times. (Wang et al., Genome Biology 2018).Link.