SSIM can robustly identify changes in 3D genome conformation maps
Ing-Simmons, E.; Machnik, N.; Vaquerizas, J. M.
Show abstract
We previously presented Comparison of Hi-C Experiments using Structural Similarity (CHESS), an approach that applies the concept of the structural similarity index (SSIM) to Hi-C matrices1, and demonstrated that it could be used to identify both regions with similar 3D chromatin conformation across species, and regions with different chromatin conformation in different conditions. In contrast to the claim of Lee et al.2 that the SSIM output of CHESS is independent of the input data, here we confirm that SSIM depends on both local and global properties of the input Hi-C matrices. We provide two approaches for using CHESS to highlight regions of differential genome organisation for further investigation, and expanded guidelines for choosing appropriate parameters and controls for these analyses.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
Similar papers in this journal
Similar papers in this journal
- DeepC: Predicting chromatin interactions using megabase scaled deep neural networks and transfer learning. 96%
- Simultaneous profiling of chromatin accessibility and methylation on human cell lines with nanopore sequencing 94%
- SCENIC+: single-cell multiomic inference of enhancers and gene regulatory networks 93%
Similar papers in this journal
- Platypus: an open-access software for integrating lymphocyte single-cell immune repertoires with transcriptomes 93%
- HIPPIE2: a method for fine-scale identification of physically interacting chromatin regions 92%
- A Chinese hamster transcription start site atlas that enables targeted editing of CHO cells 92%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.