FactorNet: A deep learning framework for predicting cell type specific transcription factor binding from nucleotide-resolution sequential data

Quang, Daniel; Xie, Xiaohui

doi:10.1016/j.ymeth.2019.03.020

Cited by 151 publications

(96 citation statements)

References 57 publications

(39 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This dearth in data availability is due to the di cult and expensive nature of the ChIP-seq experiments themselves [33]. One way to potentially incorporate histone modi cation and chromatin accessibility data is through the imputation of TF binding not directly measured by ChIP-seq experiments for a given cellular context through techniques like DeepSEA or FactorNet [34], [35]. In future work, these TF binding predictions could supplement the set of inputs to our GRN-based framework to produce better models.…”

Section: Discussionmentioning

confidence: 99%

Modeling Transcriptional Regulation Using Gene Regulatory Networks Based on Multi-Omics Data Sources

Patel

Bush²

2020

Preprint

View full text Add to dashboard Cite

BackgroundTranscriptional regulation is complex, requiring multiple cis(local) and trans acting mechanisms working in concert to drive gene expression, with disruption of these processes linked to multiple diseases. Previous computational attempts to understand the influence of regulatory mechanisms on gene expression have used prediction models containing input features derived from cis regulatory factors. However, local chromatin looping and trans-acting mechanisms are known to also influence transcriptional regulation, and their inclusion may improve model accuracy and interpretation. ResultsWe describe a computational framework to model gene expression for GM12878 and K562 cell lines. This framework weights the impact of transcription factor-based regulatory data using multi-omics gene regulatory networks to account for both cis and trans acting mechanisms, and the local chromatin context. These prediction models perform significantly better compared to models containing cis-regulatory features alone. Models that additionally integrate long distance chromatin interactions (or chromatin looping) between distal transcription factor binding regions and gene promoters also show improved accuracy. As a demonstration of their utility, effect estimates from these models were used to weight cis-regulatory rare variants for SKAT(sequence kernel association test) analyses of gene expression. ConclusionsOur models generate refined effect estimates for individual transcription factors, allow characterization of their roles across the genome, and provide a framework for integrating multiple data types into a single model of transcriptional regulation.

show abstract

Section: Discussionmentioning

confidence: 99%

Modeling Transcriptional Regulation Using Gene Regulatory Networks Based on Multi-Omics Data Sources

Patel

Bush²

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…For the CNNs, One possible way is to visualize the learned filters as a similar style of the position weight matrices. Therefore, we extracted the learned kernels from the first layers of our models and converted them to motifs following the procedure of Quang and Xie [21]. Using TOMTOM tool [42], we matched the obtained motifs with the RNAcompete database [43] and SPLICE motif dataset [44] that contains matrix profiles of human canonical and non-canonical splice sites.…”

Section: Models Interpretation and Discussionmentioning

confidence: 99%

“…In parallel, the use of deep neural networks (DNN) for the automatic extraction of features rather than handcrafted construction has improved the state-of-the-art performance for many genomics tasks [18,19], such as predicting transcription factor binding site [20,21], Branch point selection [22,23], RNA protein-coding [24], DNA methylation [25]. The most successful variant of DNN is convolution neural networks (CNN), which have been recently used for mapping the data through multiple layers, where deeper layers represent a higher level of abstraction.…”

Section: Introductionmentioning

confidence: 99%

Deep Splicing Code: Classifying Alternative Splicing Events Using Deep Learning

Louadi

Oubounyt

Tayara

et al. 2019

Genes

View full text Add to dashboard Cite

Alternative splicing (AS) is the process of combining different parts of the pre-mRNA to produce diverse transcripts and eventually different protein products from a single gene. In computational biology field, researchers try to understand AS behavior and regulation using computational models known as “Splicing Codes”. The final goal of these algorithms is to make an in-silico prediction of AS outcome from genomic sequence. Here, we develop a deep learning approach, called Deep Splicing Code (DSC), for categorizing the well-studied classes of AS namely alternatively skipped exons, alternative 5’ss, alternative 3’ss, and constitutively spliced exons based only on the sequence of the exon junctions. The proposed approach significantly improves the prediction and the obtained results reveal that constitutive exons have distinguishable local characteristics from alternatively spliced exons. Using the motif visualization technique, we show that the trained models learned to search for competitive alternative splice sites as well as motifs of important splicing factors with high precision. Thus, the proposed approach greatly expands the opportunities to improve alternative splicing modeling. In addition, a web-server for AS events prediction has been developed based on the proposed method and made available at https://home.jbnu.ac.kr/NSCL/dsc.htm.

show abstract

“…Most previous searches for features associated with cell type-specific TF binding sites have performed correlations with chromatin data measured when the TFs under study are already bound to DNA (i.e., “concurrent” chromatin information) [ 6 , 24 – 30 ]. But TFs and their recruited regulatory complexes often alter local chromatin landscapes [ 31 , 32 ].…”

Section: Introductionmentioning

confidence: 99%

An interpretable bimodal neural network characterizes the sequence and preexisting chromatin predictors of induced transcription factor binding

et al. 2021

View full text Add to dashboard Cite

Background Transcription factor (TF) binding specificity is determined via a complex interplay between the transcription factor’s DNA binding preference and cell type-specific chromatin environments. The chromatin features that correlate with transcription factor binding in a given cell type have been well characterized. For instance, the binding sites for a majority of transcription factors display concurrent chromatin accessibility. However, concurrent chromatin features reflect the binding activities of the transcription factor itself and thus provide limited insight into how genome-wide TF-DNA binding patterns became established in the first place. To understand the determinants of transcription factor binding specificity, we therefore need to examine how newly activated transcription factors interact with sequence and preexisting chromatin landscapes. Results Here, we investigate the sequence and preexisting chromatin predictors of TF-DNA binding by examining the genome-wide occupancy of transcription factors that have been induced in well-characterized chromatin environments. We develop Bichrom, a bimodal neural network that jointly models sequence and preexisting chromatin data to interpret the genome-wide binding patterns of induced transcription factors. We find that the preexisting chromatin landscape is a differential global predictor of TF-DNA binding; incorporating preexisting chromatin features improves our ability to explain the binding specificity of some transcription factors substantially, but not others. Furthermore, by analyzing site-level predictors, we show that transcription factor binding in previously inaccessible chromatin tends to correspond to the presence of more favorable cognate DNA sequences. Conclusions Bichrom thus provides a framework for modeling, interpreting, and visualizing the joint sequence and chromatin landscapes that determine TF-DNA binding dynamics.

show abstract

FactorNet: A deep learning framework for predicting cell type specific transcription factor binding from nucleotide-resolution sequential data

Cited by 151 publications

References 57 publications

Modeling Transcriptional Regulation Using Gene Regulatory Networks Based on Multi-Omics Data Sources

Modeling Transcriptional Regulation Using Gene Regulatory Networks Based on Multi-Omics Data Sources

Deep Splicing Code: Classifying Alternative Splicing Events Using Deep Learning

An interpretable bimodal neural network characterizes the sequence and preexisting chromatin predictors of induced transcription factor binding

Contact Info

Product

Resources

About