Fig. 1
From: InvBFM: finding genomic inversions from high-throughput sequence data based on feature mining
Visualization of features in simulation and benchmark. All features involved in this image are processed by PCA. The red dots mean wild-type features from simulated data, and the blue dots mean the inversions’ features from simulated data. The green dots’ features come from benchmark of inversion in real data. The green and blue dots are clustered and separated from the red dots, which indicate the features mined by InvBFM are effective