A machine learning framework for the prediction of chromatin folding inDrosophilausing epigenetic features

Abstract

Technological advances have lead to the creation of large epigenetic datasets, including information about DNA binding proteins and DNA spatial structure. Hi-C experiments have revealed that chromosomes are subdivided into sets of self-interacting domains called Topologically Associating Domains (TADs). TADs are involved in the regulation of gene expression activity, but the mechanisms of their formation are not yet fully understood. Here, we focus on machine learning methods to characterize DNA folding patterns in Drosophila based on chromatin marks across three cell lines. We present linear regression models with four types of regularization, gradient boosting, and recurrent neural networks (RNN) as tools to study chromatin folding characteristics associated with TADs given epigenetic chromatin immunoprecipitation data. The bidirectional long short-term memory RNN architecture produced the best prediction scores and identified biologically relevant features. Distribution of protein Chriz (Chromator) and histone modification H3K4me3 were selected as the most informative features for the prediction of TADs characteristics. This approach may be adapted to any similar biological dataset of chromatin features across various cell lines and species. The code for the implemented pipeline, Hi-ChiP-ML, is publicly available: https://github.com/MichalRozenwald/Hi-ChIP-ML

Review of deep learning: concepts, CNN architectures, challenges, applications, future directions

“…Author details 1 School of Computer Science, Queensland University of Technology, Brisbane, QLD 4000, Australia. 2…”

“…Recently, machine learning (ML) has become very widespread in research and has been incorporated in a variety of applications, including text mining, spam detection, video recommendation, image classification, and multimedia concept retrieval [1][2][3][4][5][6]. Among the different ML algorithms, deep learning (DL) is very commonly employed in these applications [7][8][9].…”

TAPIOCA: Topological Attention and Predictive Inference of Chromatin Arrangement Using Epigenetic Features

“…We compared TAPIOCA-network's performance on the task of TAD prediction to the performance of previously used models such as linear regression (Ulianov et al 2016), ridge and lasso regression (Ramírez et al 2018) and Bi-directional Long Short-Term Memory (BILSTM) (Rozenwald et al 2020) We observe visual similarity between the predictions of our network and Hi-C derived labels across all three metrics (Fig 4). TAPIOCA-network outperforms all previous approaches on the transitional gamma dataset (Table 1).…”

“…Transitional gamma is computed by performing TAD calling using the armatus tool with gamma values 1-10 and assigning the transitional gamma of a loci to be the first gamma value at which armatus identifies a TAD boundary (Figure 1a). In our experiments we use the transitional gamma values assigned to the feature dataset by (Rozenwald et al 2020).…”

“…The task was then reformulated as a linear regression problem in which epigenetic features were used to predict transitional gamma, a continuous metric created by the authors based on TAD identification tool Armatus. Recently the first application of neural networks, specifically LSTM obtained state-of-the are predictions (Rozenwald et al 2020) This paper provides two important contributions relative to prior research in this area. First we build upon the use of machine learning methods by applying self-attention through a variant of the state-of-the-art Transformer model which we call TAPIOCA (Topological Attention and Predictive Inference of Chromatin Arrangement).…”