GILoop: Robust chromatin loop calling across multiple sequencing depths on Hi-C data

Wang, Fuzhou; Gao, Tingxiao; Lin, Jiecong; Zheng, Zetian; Huang, Lei; Toseef, Muhammad; Li, Xiangtao; Wong, Ka-Chun

doi:10.1016/j.isci.2022.105535

Cited by 5 publications

(4 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As an application that leverages the multi‐view nature of Hi‐C contact matrices, [ 43 ] scGSLoop adopted the graph view as the main data representation to operate on, while used the sequence view as an auxiliary source of information. Although the model is not sequence‐based, the information provided by the sequence view is crucial.…”

Section: Discussionmentioning

confidence: 99%

“…The data representation in this study was inspired by the multi‐view nature of bulk Hi‐C data, as described in ref. [43]. Bulk Hi‐C data, which typically have large sequencing depths, can be represented as either images or graphs (i.e., the image view and the graph view).…”

Section: Methodsmentioning

confidence: 99%

“…Although the augmentation step increased the density of interaction matrices, the augmented contact maps were still sparse, and therefore kept them suitable for graph‐based learning. [ 43 ] On the other hand, the sparse representation was preserved so that the data could fit into the memory of a normal workstation, which was a vital factor of the lightweight workflow.…”

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

A Lightweight Framework For Chromatin Loop Detection at the Single‐Cell Level

Wang,

Alinejad‐Rokny,

Lin

et al. 2023

Advanced Science

Self Cite

View full text Add to dashboard Cite

Single‐cell Hi‐C (scHi‐C) has made it possible to analyze chromatin organization at the single‐cell level. However, scHi‐C experiments generate inherently sparse data, which poses a challenge for loop calling methods. The existing approach performs significance tests across the imputed dense contact maps, leading to substantial computational overhead and loss of information at the single‐cell level. To overcome this limitation, a lightweight framework called scGSLoop is proposed, which sets a new paradigm for scHi‐C loop calling by adapting the training and inferencing strategies of graph‐based deep learning to leverage the sequence features and 1D positional information of genomic loci. With this framework, sparsity is no longer a challenge, but rather an advantage that the model leverages to achieve unprecedented computational efficiency. Compared to existing methods, scGSLoop makes more accurate predictions and is able to identify more loops that have the potential to play regulatory roles in genome functioning. Moreover, scGSLoop preserves single‐cell information by identifying a distinct group of loops for each individual cell, which not only enables an understanding of the variability of chromatin looping states between cells, but also allows scGSLoop to be extended for the investigation of multi‐connected hubs and their underlying mechanisms.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A Lightweight Framework For Chromatin Loop Detection at the Single‐Cell Level

Wang,

Alinejad‐Rokny,

Lin

et al. 2023

Advanced Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…RefHiC ( Zhang and Blanchette, 2022 ) is a deep learning method that uses high-quality Hi-C datasets with different cell types to study the topological structure annotation of samples. GILoop ( Wang et al, 2022 ) is a twin-branch neural network that utilizes the image view and graph view to identify interactions in the entire genome. Be-1DCNN ( Wu et al, 2023 ) utilizes a bagging ensemble learning strategy and one-dimensional convolutional neural network (1DCNN) to improve the accuracy and reliability of predictions by integrating multiple 1DCNN models.…”

Section: Introductionmentioning

confidence: 99%

CD-Loop: a chromatin loop detection method based on the diffusion model

Shen,

Wang,

Luo

2024

Front. Genet.

View full text Add to dashboard Cite

MotivationIn recent years, there have been significant advances in various chromatin conformation capture techniques, and annotating the topological structure from Hi-C contact maps has become crucial for studying the three-dimensional structure of chromosomes. However, the structure and function of chromatin loops are highly dynamic and diverse, influenced by multiple factors. Therefore, obtaining the three-dimensional structure of the genome remains a challenging task. Among many chromatin loop prediction methods, it is difficult to fully extract features from the contact map and make accurate predictions at low sequencing depths.ResultsIn this study, we put forward a deep learning framework based on the diffusion model called CD-Loop for predicting accurate chromatin loops. First, by pre-training the input data, we obtain prior probabilities for predicting the classification of the Hi-C contact map. Then, by combining the denoising process based on the diffusion model and the prior probability obtained by pre-training, candidate loops were predicted from the input Hi-C contact map. Finally, CD-Loop uses a density-based clustering algorithm to cluster the candidate chromatin loops and predict the final chromatin loops. We compared CD-Loop with the currently popular methods, such as Peakachu, Chromosight, and Mustache, and found that in different cell types, species, and sequencing depths, CD-Loop outperforms other methods in loop annotation. We conclude that CD-Loop can accurately predict chromatin loops and reveal cell-type specificity. The code is available at https://github.com/wangyang199897/CD-Loop.

show abstract