Predicting transcription factor binding using ensemble random forest models

Assessing phylogenetic motif models for predicting transcription factor binding sites

MOTIVATION A variety of algorithms have been developed to predict transcription factor binding sites (TFBSs) within the genome by exploiting the evolutionary information implicit in multiple alignments of the genomes of related species. One such approach uses an extension of the standard position-specific motif model that incorporates phylogenetic information via a phylogenetic tree and a model...

Random Forest Ensemble Visualization

The Random forest model for machine learning has become a very popular data mining algorithm due to its high predictive accuracy as well as simiplicity in execution. The downside is that the model is difficult to interpret. The model consists of a collection of classification trees. Our proposed visualization aggregates the collection of trees based on the number of feature appearances at node ...

Predicting Transcription Factor Binding Sites Using Structural Knowledge

Current approaches for identification and detection of transcription factor binding sites rely on an extensive set of known target genes. Here we describe a novel structure-based approach applicable to transcription factors with no prior binding data. Our approach combines sequence data and structural information to infer context-specific amino acid-nucleotide recognition preferences. These are...

Predicting Transcription Factor Binding Sites Using a Bayesian Allocation Method

Using Hidden Markov Models to Model Multiple Transcription Factor Binding

Transcription is a cellular process leading to protein synthesis. The process is activated through the binding of proteins to specific sequences of the DNA strand. These proteins are referred to as transcription factors, and their DNA binding sites are called motifs. Computational techniques are used to predict and study such motifs. The two transcription factors Oct4 and Sox9 are known to be c...