Dataset Information

Chromatin Interaction Neural Network (ChINN): A machine learning-based method for predicting chromatin interactions from DNA sequences

ABSTRACT: Chromatin interactions play important roles in regulating gene expression. However, the availability of genome-wide chromatin interaction data is limited. Various computational methods have been developed to predict chromatin interactions. Most of these methods rely on large collections of ChIP-Seq/RNA-Seq/DNase-Seq datasets and predict only enhancer-promoter interactions. Some of the ‘state-of-the-art’ methods have poor experimental designs, leading to over-exaggerated performances and misleading conclusions. Here we developed a computational method, Chromatin Interaction Neural Network (CHINN), to predict chromatin interactions between open chromatin regions by using only DNA sequences of the interacting open chromatin regions. CHINN is able to predict CTCF-, RNA polymerase II- and HiC-associated chromatin interactions between open chromatin regions. CHINN also shows good across-sample performances and captures various sequence features that are predictive of chromatin interactions. We applied CHINN to 90 chronic lymphocytic leukemia (CLL) samples and detected systematic differences in the chromatin interactome between IGVH-mutated and IGVH-unmutated CLL samples.

ORGANISM(S): Homo sapiens

PROVIDER: GSE163896 | GEO | 2021/07/09

REPOSITORIES: GEO

ACCESS DATA

Similar Datasets

Project description:Several studies demonstrated IgVH mutation status and ZAP-70 expression as the most relevant prognostic markers in CLL, suggesting the separation of two patient subgroups: with good (MTZAP-70-) and poor prognosis (UMZAP-70+). We determined gene expression of B cells in 112 CLL patients divided into three classes: the first with IgVHMT and ZAP-70-, the second with IgVHUM and ZAP-70+, and the third included both IgVHUM ZAP-70- and IgVHMT ZAP-70+. We found LPL, AGPAT2, MBOAT1, CHPT1, AGPAT4, PLD1 genes encoding enzymes involved in lipid (glycerolipid/glycerophospholipid) metabolism overexpressed in UMZAP-70+. In addition, this study demonstrates the role of ARSD, a gene belonging to the sphingolipid metabolism, as a new gene significantly overexpressed in UMZAP-70+ in respect to MTZAP-70-. ARSD protein was found at significantly higher concentrations in UMZAP-70+ compared to MTZAP-70- CLL B cells and B cells from healthy individuals by Western blotting. Statistical analysis identified a strong correlation between ARSD and IgVH mutation status; ARSD protein level was associated with the requirement of therapy for CLL patients and for this purpose it is as good as IgVH mutational status. Our study highlights ARSD as a promising new prognostic factor in CLL and sphingolipid metabolism as a putative new biological mechanism in CLL. In this study we performed gene expression profiling of B cells on 112 CLL patients divided into three classes based on IgVH mutational status and ZAP-70 protein expression: class one with mutated IgVH and ZAP-70-, class two with unmutated IgVH and ZAP-70+, and class three included CLL patients with unmutated IgVH and ZAP-70-, or mutated IgVH and ZAP-70+, respectively. The decision to divide CLL patients in three categories was due to the clinical feature and the molecular heterogeneity of CLL, in order to elaborate different molecular signature capable of reveal biological mechanisms, and to identify new potential molecular predictors for prognostic assessment or genetic risk. RNA was extracted and quantified for high-density oligonucleotide microarrays Human Genome U133 Plus 2.0 GeneChip (Affymetrix, Santa Clara, CA). A first cohort of 62 subjects was analyzed using GeneChip Expression 3' Amplification One-Cycle Target Labeling Kit, while a second cohort of 50 subjects using GeneChip 3'IVT Express Kit, according to manufacturerM-bM-^@M-^Ys protocol (Affymetrix), respectively.

Dataset Information

Chromatin Interaction Neural Network (ChINN): A machine learning-based method for predicting chromatin interactions from DNA sequences

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure