FineSplice is a Python wrapper to TopHat2 geared towards a reliable identification of expressed exon junctions from RNA-Seq data, at enhanced detection precision with small loss in sensitivity.

Following alignment with TopHat2 using known transcript annotations, FineSplice takes as input the resulting BAM file and outputs a confident set of expressed splice junctions with the corresponding read counts. Potential false positives arising from spurious alignments are filtered out via a semi-supervised anomaly detection strategy based on logistic regression. Multiple mapping reads with a unique location after filtering are rescued and reallocated to the most reliable candidate location.

FineSplice requires Python 2.x (>= 2.6) with the following modules installed: pysam (http://code.google.com/p/pysam/) and scikit-learn (http://scikit-learn.org/).

For further details check out our publication: Nucl. Acids Res. (2014) doi: 10.1093/nar/gku166

Features

  • Align with TopHat2 using transcript annotations for superior mapping performance
  • Run FineSplice to get rid of unreliable gapped alignments and improve splice junction detection precision
  • Outputs a confident set of exon-exon junctions with the corresponding read counts for downstream analyses

Project Samples

Project Activity

See All Activity >

Follow FineSplice

FineSplice Web Site

Other Useful Business Software
Ship AI Apps Faster with Vertex AI Icon
Ship AI Apps Faster with Vertex AI

Go from idea to deployed AI app without managing infrastructure. Vertex AI offers one platform for the entire AI development lifecycle.

Ship AI apps and features faster with Vertex AI—your end-to-end AI platform. Access Gemini 3 and 200+ foundation models, fine-tune for your needs, and deploy with enterprise-grade MLOps. Build chatbots, agents, or custom models. New customers get $300 in free credit.
Try Vertex AI Free

Additional Project Details

Programming Language

Python

Related Categories

Python Bio-Informatics Software, Python Machine Learning Software

Registered

2013-11-05