NCBI Logo
GEO Logo
   NCBI > GEO > Accession DisplayHelp Not logged in | LoginHelp
GEO help: Mouse over screen elements for information.
          Go
Series GSE142238 Query DataSets for GSE142238
Status Public on Apr 22, 2020
Title Cross-species analysis of melanoma enhancer logic using deep learning
Organisms Danio rerio; Homo sapiens; Canis lupus familiaris; Equus caballus; Sus scrofa domesticus; Mus musculus
Experiment type Genome binding/occupancy profiling by high throughput sequencing
Summary Here, we combine comparative regulatory genomics with machine learning to investigate enhancer logic in melanoma. Through epigenomics profiling of 26 melanoma cell lines across six species, we examine the conservation of the two main melanoma states and underlying master regulators. By training a deep neural network on topic models derived from the human lines, we were able to classify not only human melanoma enhancers, but also regulatory regions in the other species. The deep learning model revealed important genomic features (i.e. TF binding motifs) for the different melanoma states, how they co-occur within melanoma enhancers, and where they are placed with respect to the central enhancer nucleosome. This in-depth analysis of the melanoma enhancer code allowed us to propose a mechanistic model of TF binding in MEL melanoma enhancers. Finally, by exploiting the deep layers of our model, we are able to identify causal mutations for melanoma enhancer loss and gain through evolution, not only affecting enhancer accessibility but also activity.
 
Overall design (omni)ATAC-seq on melanoma cell lines across six species, as well as OmniATAC-seq on knock-down of transcription factors in the human melanoma cell line MM001
 
Contributor(s) Minnoye L, Taskiran II, Aerts S, Zon L, Yang S
Citation(s) 32732264
Submission date Dec 17, 2019
Last update date Dec 15, 2020
Contact name Stein Aerts
E-mail(s) stein.aerts@kuleuven.vib.be
Organization name KU Leuven
Street address O&N4 Herestraat 49 PO Box 602
City Leuven
ZIP/Postal code 3000
Country Belgium
 
Platforms (7)
GPL14875 Illumina HiSeq 2000 (Danio rerio)
GPL18573 Illumina NextSeq 500 (Homo sapiens)
GPL19057 Illumina NextSeq 500 (Mus musculus)
Samples (23)
GSM4223577 OmniATAC-seq_MM034_BL
GSM4223578 OmniATAC-seq_MM052_BL
GSM4223579 OmniATAC-seq_MM116_BL
Relations
BioProject PRJNA596273
SRA SRP238021

Download family Format
SOFT formatted family file(s) SOFTHelp
MINiML formatted family file(s) MINiMLHelp
Series Matrix File(s) TXTHelp

Supplementary file Size Download File type/resource
GSE142238_RAW.tar 5.4 Gb (http)(custom) TAR (of BW)
SRA Run SelectorHelp
Raw data are available in SRA
Processed data provided as supplementary file

| NLM | NIH | GEO Help | Disclaimer | Accessibility |
NCBI Home NCBI Search NCBI SiteMap