Dataset Information

Interpretable deep residual network uncovers nucleosome positioning and associated features.

ABSTRACT: Nucleosomes represent elementary building units of eukaryotic chromosomes and consist of DNA wrapped around a histone octamer flanked by linker DNA segments. Nucleosomes are central in epigenetic pathways and their genomic positioning is associated with regulation of gene expression, DNA replication, DNA methylation and DNA repair, among other functions. Building on prior discoveries that DNA sequences noticeably affect nucleosome positioning, our objective is to identify nucleosome positions and related features across entire genome. Here, we introduce an interpretable framework based on the concepts of deep residual networks (NuPoSe). Trained on high-coverage human experimental MNase-seq data, NuPoSe is able to learn sequence and structural patterns associated with nucleosome organization in human genome. NuPoSe can be also applied to unseen data from different organisms and cell types. Our findings point to 43 informative features, most of them constitute tri-nucleotides, di-nucleotides and one tetra-nucleotide. Most features are significantly associated with the nucleosomal structural characteristics, namely, periodicity of nucleosomal DNA and its location with respect to a histone octamer. Importantly, we show that features derived from the 27 bp linker DNA flanking nucleosomes contribute up to 10% to the quality of the prediction model. This, along with the comprehensive training sets, deep-learning architecture, and feature selection method, may contribute to the NuPoSe's 80-89% classification accuracy on different independent datasets.

SUBMITTER: Masoudi-Sobhanzadeh Y

PROVIDER: S-EPMC11347144 | biostudies-literature | 2024 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Interpretable deep residual network uncovers nucleosome positioning and associated features.

Masoudi-Sobhanzadeh Yosef Y Li Shuxiang S Peng Yunhui Y Panchenko Anna R AR

Nucleic acids research 20240801 15

Nucleosomes represent elementary building units of eukaryotic chromosomes and consist of DNA wrapped around a histone octamer flanked by linker DNA segments. Nucleosomes are central in epigenetic pathways and their genomic positioning is associated with regulation of gene expression, DNA replication, DNA methylation and DNA repair, among other functions. Building on prior discoveries that DNA sequences noticeably affect nucleosome positioning, our objective is to identify nucleosome positions an ...[more]

PMID: 39036965

Similar Datasets

Project description:Convolutional neural networks (CNNs) are revolutionizing digital pathology by enabling machine learning-based classification of a variety of phenotypes from hematoxylin and eosin (H&E) whole slide images (WSIs), but the interpretation of CNNs remains difficult. Most studies have considered interpretability in a post hoc fashion, e.g. by presenting example regions with strongly predicted class labels. However, such an approach does not explain the biological features that contribute to correct predictions. To address this problem, here we investigate the interpretability of H&E-derived CNN features (the feature weights in the final layer of a transfer-learning-based architecture). While many studies have incorporated CNN features into predictive models, there has been little empirical study of their properties. We show such features can be construed as abstract morphological genes ("mones") with strong independent associations to biological phenotypes. Many mones are specific to individual cancer types, while others are found in multiple cancers especially from related tissue types. We also observe that mone-mone correlations are strong and robustly preserved across related cancers. Importantly, linear mone-based classifiers can very accurately separate 38 distinct classes (19 tumor types and their adjacent normals, AUC = [Formula: see text] for each class prediction), and linear classifiers are also highly effective for universal tumor detection (AUC = [Formula: see text]). This linearity provides evidence that individual mones or correlated mone clusters may be associated with interpretable histopathological features or other patient characteristics. In particular, the statistical similarity of mones to gene expression values allows integrative mone analysis via expression-based bioinformatics approaches. We observe strong correlations between individual mones and individual gene expression values, notably mones associated with collagen gene expression in ovarian cancer. Mone-expression comparisons also indicate that immunoglobulin expression can be identified using mones in colon adenocarcinoma and that immune activity can be identified across multiple cancer types, and we verify these findings by expert histopathological review. Our work demonstrates that mones provide a morphological H&E decomposition that can be effectively associated with diverse phenotypes, analogous to the interpretability of transcription via gene expression values. Our work also demonstrates mones can be interpreted without using a classifier as a proxy.

Project description:Differential accessibility of DNA to nuclear proteins underlies the regulation of numerous cellular processes. Although DNA accessibility is primarily determined by the presence or absence of nucleosomes, differences in nucleosome composition or dynamics may also regulate accessibility. Methods for mapping nucleosome positions and occupancies genome-wide (MNase-seq) have uncovered the nucleosome landscapes of many different cell types and organisms. Conversely, methods specialized for the detection of large nucleosome-free regions of chromatin (DNase-seq, FAIRE-seq) have uncovered numerous gene regulatory elements. However, these methods are less successful in measuring the accessibility of DNA sequences within nucelosome arrays.Here we probe the genome-wide accessibility of multiple cell types in an unbiased manner using restriction endonuclease digestion of chromatin coupled to deep sequencing (RED-seq). Using this method, we identified differences in chromatin accessibility between populations of cells, not only in nucleosome-depleted regions of the genome (e.g., enhancers and promoters), but also within the majority of the genome that is packaged into nucleosome arrays. Furthermore, we identified both large differences in chromatin accessibility in distinct cell lineages and subtle but significant changes during differentiation of mouse embryonic stem cells (ESCs). Most significantly, using RED-seq, we identified differences in accessibility among nucleosomes harboring well-studied histone variants, and show that these differences depend on factors required for their deposition.Using an unbiased method to probe chromatin accessibility genome-wide, we uncover unique features of chromatin structure that are not observed using more widely-utilized methods. We demonstrate that different types of nucleosomes within mammalian cells exhibit different degrees of accessibility. These findings provide significant insight into the regulation of DNA accessibility.

Dataset Information

Interpretable deep residual network uncovers nucleosome positioning and associated features.

Publications

Interpretable deep residual network uncovers nucleosome positioning and associated features.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets