首页|Machine Learning Unravels Inherent Structural Patterns in Escherichia Coli Hi-C Matrices and Predicts DNA Dynamics
Machine Learning Unravels Inherent Structural Patterns in Escherichia Coli Hi-C Matrices and Predicts DNA Dynamics
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
“The large dimension of the Hi-C-derived chromosomal contact map, even for a bacterial cell, presentschallenges in extracting meaningful information related to its complex organization.“Here we first demonstrate that a machine-learnt (ML) low-dimensional embedding of a recently reportedHi-C interaction map of archetypal bacteria E. Coli can decode crucial underlying structural pattern.“In particular, a three-dimensional latent space representation of (928 x 928) dimensional Hi-C map, derivedfrom an unsupervised artificial neural network, automatically detects a set of spatially distinct domainsthat show close correspondences with six macro-domains (MDs) that were earlier proposed across E. Coligenome via recombination assay-based experiments. Subsequently, we develop a supervised random-forestregression model by machine-learning intricate relationship between large array of Hi-C-derived chromosomalcontact probabilities and diffusive dynamics of each individual chromosomal gene. The resultant MLmodel dictates that a minimal subset of important chromosomal contact pairs (only 30 %) out of full Hi-Cmap is sufficient for optimal reconstruction of the heterogenous, coordinate-dependent sub-diffusive motionsof chromosomal loci. Specifically the Ori MD was predicted to exhibit most substantial contributionin chromosomal dynamics among all MDs. Finally, the ML models, trained on wild-type E. Coli was testedfor its predictive capabilities on mutant bacterial strains, shedding light on the structural and dynamicnuances of deltaMatP30MM and deltaMukBEF22MM chromosomes. Overall our results illuminate thepower of ML techniques in unraveling the complex relationship between structure and dynamics of bacterialchromosomal loci, promising meaningful connections between our ML-derived insights and real-worldbiological phenomena.”
NETL
NSTL
