Exploratory and Model-Based Analysis of ScHi-C Data

on YouTube ↗35m

" summary

Simple per-band scaling that adds back an average band decay (BandNorm) runs in ~15 minutes and often matches more complex methods on cell-type separation, but it degrades at very high sparsity (100 kb resolution or rare cell types). A deep generative, band-aware model (scVI-3D) uses a zero-inflated gamma with locus-specific zeros, needs GPU and ~hour runs, and preserves performance with imputation. Gene-level scGAD scores correlate with expression, enable CCA integration with RNA and ChIP, and hundreds of cells produce believable pseudo-bulk contact maps.

AI-written summary · about

" chapters (15)

1. 0:00Start
2. 1:38Hi-C for studying long-range interactions
3. 2:55Hi-C meets single cell sequencing
4. 3:23scHi-C data: sparsity
5. 4:34scHi-C specific genomic distance effect
6. 6:15BandNorm & SCVI-3D with band transformation of scHi-C data
7. 9:48Normalize and de-noise scHi-C data
8. 11:19Evaluation and impact on downstream
9. 12:44Cell type separation: Ramani2017
10. 13:17Cell type separation: Lee 2019
11. 14:43Evaluation of unsupervised clustering
12. 16:20Impact on downstream analysis: Pseudo- bulk ve bulk Hi-C
13. 17:18Similarity of the pseudo-bulk to bulk
14. 18:35Integrating scHi-C with other single cell data modalities
15. 24:49Acknowledgements

" related talks

• 35mMachine Learning for Single-Cell 3D EpigenomicsJian Ma · From Algorithms to Discovery in Genome-Scale Biology and Medicine 2022
• 28mSome Current Computational Challenges in BioinformaticsRon Shamir · KARPfest80
• 43mPanel on Interpretability in the Biological SciencesAnshul Kundaje, Jack Gallant, Debbie Marks · Interpretable Machine Learning in Natural and Social Sciences (2022)
• 57mBig Data and New Models Needed to Study DNA Variation in Evolution and CancerDavid Haussler · Symposium on Visions of the Theory of Computing 2013
• 42mHow Novel Compute Technology Transforms Life Science ResearchDenis C. Bauer · Agile India 2018
• 46mKeynote: Life Science Research at ScaleDenis C. Bauer · ODSC India 2018
• 47mBANKSY: A Spatial Omics Algorithm that Unifies Cell Type Clustering and Tissue Domain SegmentationShyam Prabhakar · From Algorithms to Discovery in Genome-Scale Biology and Medicine 2022
• 26mShiva Amiri, CEO, BioSymetrics at MLconf Seattle 2017Shiva Amiri · MLconf Seattle 2017