​   Research


  • Machine Learning

  • Computational Biology

  • Bioinformatics

  • Alternative splicing quantification

  • Post-transcriptional regulation

  • Regulatory elements modeling

  • Genetic variations effect on RNA processing

  • Personalized medicine based on clinical, genetic, and genomic profiling


Regulatory Elements Modeling

We develop computational models for DNA/RNA regulatory sequence elements to improve identification of underlying regulatory mechanisms.

In collaboration with

Kristen Lynch, Shane Jensen

Quantification and Visualization of RNA splicing

We develop methods to address

the computational challenges posed by high throughput data for accurately quantifying and visualizting splice variants and how these change across different conditions.

Lab member

Jordi Vaquero, CJ Green,

Scott Norton

Alternative Splicing Prediction

A main focus of the lab is developing algorithms and tools for predicting and analzying splicing outcome under varying conditions.

Splicing Regulatory


The lab iterates between computational splicing regulatory models and experimental verifications.

In collaboration with

Kristen Lynch, Russ Carstens,

David Elliot

Genetic Variations Effect on Splicing 

We study how genetic variations affect splicing and how these changes correlate with maligant state and phenotipic diversity.

In collaboration with

Andrei Thomas-Tikhonenko, Doug Epstein, Morthy Chavali, Kostas Koumenis

Predicting Individualized Risk of Metastasis in Uveal Melanoma

We developed PRiMIUM, a predictive model + matching web-tool that allows clinicians to assess individualized risk of metastasis in Uveal Melanoma given a patient's clinical and genetic profile.

In collaboration with

Arupa Ganguly


© BIOCIPHERS - 2020 · Department of Genetics Perelman School of Medicine Department of Computer and Information Science School of Engineering University of Pennsylvania