TIPR: Transcription Initiation Pattern Recognition on a Genome Scale

Publication Online:
http://bioinformatics.oxfordjournals.org/content/early/2015/08/19/bioinformatics.btv464.long

About this study: 
In this work, we present the Transcription Initiation Pattern Recognizer (TIPR), a sequence-based machine learning model that identifies TSSs with high accuracy and resolution for multiple spatial distribution patterns along the genome, including broadly distributed TSS patterns that have previously been difficult to characterize. TIPR predicts not only the locations of TSSs but also the expected spatial initiation pattern each TSS will form along the chromosome-a novel capability for TSS prediction algorithms. As spatial initiation patterns are associated with spatiotemporal expression patterns and gene function, this capability has the potential to improve gene annotations and our understanding of the regulation of transcription initiation. The high nucleotide resolution of this model locates TSSs within 10 nucleotides or less on average.

Software

TIPR Model Scanning Tool

• TIPR_Software.tar.gz: TIPR Command Line Tool, Usage Instructions, and associated tools (TIPR-TFBS-Scanner and modified l1_logreg)

Installation Instructions

1. Download and extract TIPR software into directory:
   wget http://megraw.cgrb.oregonstate.edu/software/TIPR/TIPR_Software.tar.gz
tar xvzf TIPR_Software.tar.gz
cd TIPR_Software
2. Determine if l1_logreg needs to be recompiled:
   l1_logreg_modified/l1_logreg-0.8.1/
./src_c/l1_logreg_classify_bin
   l1_logreg_classify_bin should run without error and print a help message. If the executable does not run, recompile l1_logreg for your architecture:
   ./configure
make
3. Compile TIPR-TFBS-Scanner:
   cd LogLikScanner/src
./compile.sh
4. Run the run_test_example.sh script from the model scanning tool:
   cd Model
./run_test_example.sh

Please see the LICENSE file included in the archive file for copyright and distribution rights.

Supplementary Materials

TIPR_Supplementary_Materials.pdf

Supplementary Tables

1. Supplementary_Table_1-All_Model_ROEs.xls
2. Supplementary_Table_2-Cross-Validation_Scores.xls
3. Supplementary_Table_3-Feature_Weights.xls
4. Supplementary_Table_4-Confusion_Matrices.xls

Supplementary Data

1. Rach_Peak_Sets.tar.gz: FASTA files used to train and test the TIPR model used the data collected by Rach et al.

Citation

If any of these tools are used for work which results in a publication, we would appreciate citation of the following article:

Morton T, Wong WK, Megraw M. (2015). TIPR: transcription initiation pattern recognition on a genome scale. Bioinformatics, 31:3725-32.