Dataset Information

Integrative Analysis of Transcription Factor Combinatorial Interactions Using a Bayesian Tensor Factorization Approach.

ABSTRACT: Transcription factors play a key role in transcriptional regulation of genes and determination of cellular identity through combinatorial interactions. However, current studies about combinatorial regulation is deficient due to lack of experimental data in the same cellular environment and extensive existence of data noise. Here, we adopt a Bayesian CANDECOMP/PARAFAC (CP) factorization approach (BCPF) to integrate multiple datasets in a network paradigm for determining precise TF interaction landscapes. In our first application, we apply BCPF to integrate three networks built based on diverse datasets of multiple cell lines from ENCODE respectively to predict a global and precise TF interaction network. This network gives 38 novel TF interactions with distinct biological functions. In our second application, we apply BCPF to seven types of cell type TF regulatory networks and predict seven cell lineage TF interaction networks, respectively. By further exploring the dynamics and modularity of them, we find cell lineage-specific hub TFs participate in cell type or lineage-specific regulation by interacting with non-specific TFs. Furthermore, we illustrate the biological function of hub TFs by taking those of cancer lineage and blood lineage as examples. Taken together, our integrative analysis can reveal more precise and extensive description about human TF combinatorial interactions.

SUBMITTER: Ye Y

PROVIDER: S-EPMC5625019 | biostudies-literature | 2017

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Integrative Analysis of Transcription Factor Combinatorial Interactions Using a Bayesian Tensor Factorization Approach.

Ye Yusen Y Gao Lin L Zhang Shihua S

Frontiers in genetics 20170928

Transcription factors play a key role in transcriptional regulation of genes and determination of cellular identity through combinatorial interactions. However, current studies about combinatorial regulation is deficient due to lack of experimental data in the same cellular environment and extensive existence of data noise. Here, we adopt a Bayesian CANDECOMP/PARAFAC (CP) factorization approach (BCPF) to integrate multiple datasets in a network paradigm for determining precise TF interaction lan ...[more]

PMID: 29033978

Similar Datasets

Project description:BackgroundDetermining which target to pursue is a challenging and error-prone first step in developing a therapeutic treatment for a disease, where missteps are potentially very costly given the long-time frames and high expenses of drug development. With current informatics technology and machine learning algorithms, it is now possible to computationally discover therapeutic hypotheses by predicting clinically promising drug targets based on the evidence associating drug targets with disease indications. We have collected this evidence from Open Targets and additional databases that covers 17 sources of evidence for target-indication association and represented the data as a tensor of 21,437 × 2211 × 17.ResultsAs a proof-of-concept, we identified examples of successes and failures of target-indication pairs in clinical trials across 875 targets and 574 disease indications to build a gold-standard data set of 6140 known clinical outcomes. We designed and executed three benchmarking strategies to examine the performance of multiple machine learning models: Logistic Regression, LASSO, Random Forest, Tensor Factorization and Gradient Boosting Machine. With 10-fold cross-validation, tensor factorization achieved AUROC = 0.82 ± 0.02 and AUPRC = 0.71 ± 0.03. Across multiple validation schemes, this was comparable or better than other methods.ConclusionIn this work, we benchmarked a machine learning technique called tensor factorization for the problem of predicting clinical outcomes of therapeutic hypotheses. Results have shown that this method can achieve equal or better prediction performance compared with a variety of baseline models. We demonstrate one application of the method to predict outcomes of trials on novel indications of approved drug targets. This work can be expanded to targets and indications that have never been clinically tested and proposing novel target-indication hypotheses. Our proposed biologically-motivated cross-validation schemes provide insight into the robustness of the prediction performance. This has significant implications for all future methods that try to address this seminal problem in drug discovery.

Project description:Green tea (Camellia sinensis, Cs) abundantly produces a diverse array of phenylpropanoid compounds benefiting human health. To date, the regulation of the phenylpropanoid biosynthesis in tea remains to be investigated. Here, we report a cDNA isolated from leaf tissues, which encodes a R2R3-MYB transcription factor. Amino acid sequence alignment and phylogenetic analysis indicate that it is a member of the MYB4-subgroup and named as CsMYB4a. Transcriptional and metabolic analyses show that the expression profile of CsMYB4a is negatively correlated to the accumulation of six flavan-3-ols and other phenolic acids. GFP fusion analysis shows CsMYB4a's localization in the nucleus. Promoters of five tea phenylpropanoid pathway genes are isolated and characterized to contain four types of AC-elements, which are targets of MYB4 members. Interaction of CsMYB4a and five promoters shows that CsMYB4a decreases all five promoters' activity. To further characterize its function, CsMYB4a is overexpressed in tobacco plants. The resulting transgenic plants show dwarf, shrinking and yellowish leaf, and early senescence phenotypes. A further genome-wide transcriptomic analysis reveals that the expression levels of 20 tobacco genes involved in the shikimate and the phenylpropanoid pathways are significantly downregulated in transgenic tobacco plants. UPLC-MS and HPLC based metabolic profiling reveals significant reduction of total lignin content, rutin, chlorogenic acid, and phenylalanine in CsMYB4a transgenic tobacco plants. Promoter sequence analysis of the 20 tobacco genes characterizes four types of AC-elements. Further CsMYB4a-AC element and CsMYB4a-promoter interaction analyses indicate that the negative regulation of CsMYB4a on the shikimate and phenylpropanoid pathways in tobacco is via reducing promoter activity. Taken together, all data indicate that CsMYB4a negatively regulates the phenylpropanoid and shikimate pathways. Highlight: A tea (Camellia sinensis) MYB4a is characterized to encode a R2R3-MYB transcription factor. It is shown to repressively control the phenylpropanoid and shikimate pathway.

Project description:BackgroundComputational fusion approaches to drug-target interaction (DTI) prediction, capable of utilizing multiple sources of background knowledge, were reported to achieve superior predictive performance in multiple studies. Other studies showed that specificities of the DTI task, such as weighting the observations and focusing the side information are also vital for reaching top performance.MethodWe present Variational Bayesian Multiple Kernel Logistic Matrix Factorization (VB-MK-LMF), which unifies the advantages of (1) multiple kernel learning, (2) weighted observations, (3) graph Laplacian regularization, and (4) explicit modeling of probabilities of binary drug-target interactions.ResultsVB-MK-LMF achieves significantly better predictive performance in standard benchmarks compared to state-of-the-art methods, which can be traced back to multiple factors. The systematic evaluation of the effect of multiple kernels confirm their benefits, but also highlights the limitations of linear kernel combinations, already recognized in other fields. The analysis of the effect of prior kernels using varying sample sizes sheds light on the balance of data and knowledge in DTI tasks and on the rate at which the effect of priors vanishes. This also shows the existence of "small sample size" regions where using side information offers significant gains. Alongside favorable predictive performance, a notable property of MF methods is that they provide a unified space for drugs and targets using latent representations. Compared to earlier studies, the dimensionality of this space proved to be surprisingly low, which makes the latent representations constructed by VB-ML-LMF especially well-suited for visual analytics. The probabilistic nature of the predictions allows the calculation of the expected values of hits in functionally relevant sets, which we demonstrate by predicting drug promiscuity. The variational Bayesian approximation is also implemented for general purpose graphics processing units yielding significantly improved computational time.ConclusionIn standard benchmarks, VB-MK-LMF shows significantly improved predictive performance in a wide range of settings. Beyond these benchmarks, another contribution of our work is highlighting and providing estimates for further pharmaceutically relevant quantities, such as promiscuity, druggability and total number of interactions.

Dataset Information

Integrative Analysis of Transcription Factor Combinatorial Interactions Using a Bayesian Tensor Factorization Approach.

Publications

Integrative Analysis of Transcription Factor Combinatorial Interactions Using a Bayesian Tensor Factorization Approach.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets