Coarse Graining of Data via Inhomogeneous Diffusion Condensation
Authors:
- Nathan BrugnoneNBNathan Brugnone
- Alex GonopolskiyAGAlex Gonopolskiy
- Mark W. MoyleMMMark W. Moyle
- Manik KuchrooMKManik Kuchroo
- David van DijkDDDavid van Dijk
- Kevin R. MoonKevin R. Moon
- Daniel Colon-RamosDCDaniel Colon-Ramos
- Guy WolfGWGuy Wolf
- Matthew J. HirnMHMatthew J. Hirn
- Smita KrishnaswamySKSmita Krishnaswamy
Preprint
Abstract
Big data often has emergent structure that exists at multiple levels of abstraction, which are useful for characterizing complex interactions and dynamics of the observations. Here, we consider multiple levels of abstraction via a multiresolution geometry of data points at different granularities. To construct this geometry we define a time-inhomogeneous diffusion process that effectively condenses data points together to uncover nested groupings at larger and larger granularities. This inhomogeneous process creates a deep cascade of intrinsic low pass filters on the data affinity graph that are applied in sequence to gradually eliminate local variability while adjusting the learned data geometry to increasingly coarser resolutions. We provide visualizations to exhibit our method as a continuously-hierarchical clustering with directions of eliminated variation highlighted at each step. The utility of our algorithm is demonstrated via neuronal data condensation, where the constructed multiresolution data geometry uncovers the organization, grouping, and connectivity between neurons.Keywords
All Related Versions
This publication has 17 references indexed in Scilit:
- Recovering Gene Interactions from Single-Cell Data Using Data DiffusionCell, 2018
- Manifold learning-based methods for analyzing single-cell RNA-sequencing dataCurrent Opinion in Systems Biology, 2018
- Comprehensive Classification of Retinal Bipolar Neurons by Single-Cell TranscriptomicsCell, 2016
- Data-Driven Phenotypic Dissection of AML Reveals Progenitor-like Cells that Correlate with PrognosisCell, 2015
- The Technology and Biology of Single-Cell RNA SequencingMolecular Cell, 2015
- Multiplexed ion beam imaging of human breast tumorsNature Medicine, 2014
- Highly multiplexed imaging of tumor tissues with subcellular resolution by mass cytometryNature Methods, 2014
- Clustering with a new distance measure based on a dual-rooted treeInformation Sciences, 2013
- Single-cell sequencing-based technologies will revolutionize whole-organism scienceNature Reviews Genetics, 2013
- Fast unfolding of communities in large networksJournal of Statistical Mechanics: Theory and Experiment, 2008