Photo by DeepMind on Unsplash

4D Nucleome (4DN) Dataset for Machine Learning

Install DagsHub:

pip install dagshub
Click on copy button to copy content

To stream this data directly on DagsHub

from dagshub.streaming import DagsHubFilesystem

fs = DagsHubFilesystem(".", repo_url="https://test.dagshub.com/DagsHub-Datasets/4dnucleome-dataset")

fs.listdir("s3://4dn-open-data-public")
Click on copy button to copy content

Description

The goal of the National Institutes of Health (NIH) Common Fund’s 4D Nucleome (4DN) program is to study the three-dimensional organization of the nucleus in space and time (the 4th dimension). The nucleus of a cell contains DNA, the genetic “blueprint” that encodes all of the genes a living organism uses to produce proteins needed to carry out life-sustaining cellular functions. Understanding the conformation of the nuclear DNA and how it is maintained or changes in response to environmental and cellular cues over time will provide insights into basic biology as well as aspects of human health and disease. The 4DN is an international consortium of researchers who generate data that include results from a variety of genomics and imaging assays with a focus on, but not exclusive to, those that demonstrate close contact between chromatin loci that are non-adjacent on the linear DNA sequence of chromosomes. Additional assays probe the nuclear landscape in the context of interactions of chromatin with specific proteins, RNAs and epigenetic changes.

Additional information

Update frequency

Daily

Managed by

4DN-DCIC

License

External data users may freely download, analyze, and publish results based on any 4DN data provided here without restrictions.

Related datasets

Allen Brain Observatory – Visual Coding AWS Public Data Set

Allen Cell Imaging Collections

Biological and Physical Sciences (BPS) Microscopy Benchmark Training Dataset

Cancer Cell Line Encyclopedia (CCLE)

Launch your ML development to new heights with DagsHub

Back to top