%0 Journal Article %1 Lahdesmaki:2008:PLoS-One:18364997 %A Lähdesmäki, H %A Rust, A G %A Shmulevich, I %D 2008 %J PLoS One %K imported probabilistic probtf proj:0915 tf %N 3 %R 10.1371/journal.pone.0001820 %T Probabilistic inference of transcription factor binding from multiple data sources %U http://www.ncbi.nlm.nih.gov/pubmed/18364997?dopt=Abstract %V 3 %X An important problem in molecular biology is to build a complete understanding of transcriptional regulatory processes in the cell. We have developed a flexible, probabilistic framework to predict TF binding from multiple data sources that differs from the standard hypothesis testing (scanning) methods in several ways. Our probabilistic modeling framework estimates the probability of binding and, thus, naturally reflects our degree of belief in binding. Probabilistic modeling also allows for easy and systematic integration of our binding predictions into other probabilistic modeling methods, such as expression-based gene network inference. The method answers the question of whether the whole analyzed promoter has a binding site, but can also be extended to estimate the binding probability at each nucleotide position. Further, we introduce an extension to model combinatorial regulation by several TFs. Most importantly, the proposed methods can make principled probabilistic inference from multiple evidence sources, such as, multiple statistical models (motifs) of the TFs, evolutionary conservation, regulatory potential, CpG islands, nucleosome positioning, DNase hypersensitive sites, ChIP-chip binding segments and other (prior) sequence-based biological knowledge. We developed both a likelihood and a Bayesian method, where the latter is implemented with a Markov chain Monte Carlo algorithm. Results on a carefully constructed test set from the mouse genome demonstrate that principled data fusion can significantly improve the performance of TF binding prediction methods. We also applied the probabilistic modeling framework to all promoters in the mouse genome and the results indicate a sparse connectivity between transcriptional regulators and their target promoters. To facilitate analysis of other sequences and additional data, we have developed an on-line web tool, ProbTF, which implements our probabilistic TF binding prediction method using multiple data sources. Test data set, a web tool, source codes and supplementary data are available at: http://www.probtf.org.

@article{Lahdesmaki:2008:PLoS-One:18364997, abstract = {An important problem in molecular biology is to build a complete understanding of transcriptional regulatory processes in the cell. We have developed a flexible, probabilistic framework to predict TF binding from multiple data sources that differs from the standard hypothesis testing (scanning) methods in several ways. Our probabilistic modeling framework estimates the probability of binding and, thus, naturally reflects our degree of belief in binding. Probabilistic modeling also allows for easy and systematic integration of our binding predictions into other probabilistic modeling methods, such as expression-based gene network inference. The method answers the question of whether the whole analyzed promoter has a binding site, but can also be extended to estimate the binding probability at each nucleotide position. Further, we introduce an extension to model combinatorial regulation by several TFs. Most importantly, the proposed methods can make principled probabilistic inference from multiple evidence sources, such as, multiple statistical models (motifs) of the TFs, evolutionary conservation, regulatory potential, CpG islands, nucleosome positioning, DNase hypersensitive sites, ChIP-chip binding segments and other (prior) sequence-based biological knowledge. We developed both a likelihood and a Bayesian method, where the latter is implemented with a Markov chain Monte Carlo algorithm. Results on a carefully constructed test set from the mouse genome demonstrate that principled data fusion can significantly improve the performance of TF binding prediction methods. We also applied the probabilistic modeling framework to all promoters in the mouse genome and the results indicate a sparse connectivity between transcriptional regulators and their target promoters. To facilitate analysis of other sequences and additional data, we have developed an on-line web tool, ProbTF, which implements our probabilistic TF binding prediction method using multiple data sources. Test data set, a web tool, source codes and supplementary data are available at: http://www.probtf.org.}, added-at = {2009-10-02T23:03:23.000+0200}, author = {L{\"a}hdesm{\"a}ki, H and Rust, A G and Shmulevich, I}, biburl = {https://www.bibsonomy.org/bibtex/207d562b2166f61fb42a0f5c3d9f557ac/wnpxrz}, description = {Probabilistic inference of transcription factor bi...[PLoS One. 2008] - PubMed Result}, doi = {10.1371/journal.pone.0001820}, interhash = {81240edab57d699ffc46d75e56938c99}, intrahash = {07d562b2166f61fb42a0f5c3d9f557ac}, journal = {PLoS One}, keywords = {imported probabilistic probtf proj:0915 tf}, number = 3, pmid = {18364997}, timestamp = {2009-10-02T23:03:23.000+0200}, title = {Probabilistic inference of transcription factor binding from multiple data sources}, url = {http://www.ncbi.nlm.nih.gov/pubmed/18364997?dopt=Abstract}, volume = 3, year = 2008 }