Projects

• Led by Marcin Cieslik - Using GPT AI to classify germline variants as Benign, VUS, Pathogenic. The students are provided information about what is currently known about the variants in the list. It requires quite varied skills (genetics, programming, evaluation of predictive algorithms). 

• Led by Matt O’Meara - Spatial Analysis for Morphological profiling - cells in 384-well format are fixed and stained with multiple dyes, imaged using automated confocal microscopy, and then computationally analyzed at single cell resolution to evaluate treatment effects on cellular morphology. The aim is to develop methods to construct and analyze cell-adjacency networks, and use machine learning to estimate the mutual phenotypic information among adjacent cells.

• Led by Cristina Mitrea - Meta analysis of respiratory diseases datasets from GEO. Students would download and process select datasets (at least 5), pre-process and integrate the datasets and perform differential expression analysis and pathway analysis and GO analysis on the datasets to identify – genes and pathway and processes related to respiratory illnesses. Students will be provided with the dataset IDs and some code to start from and they would have to adapt the code. The idea came from the following tool: https://doi.org/10.1093/bioinformatics/bty721 that creates a report. See the attached report as an example.

  • • TCGA prostate cancer subtyping – using a similar approach the following paper provided “to integrate results from somatic mutations, gene fusions, somatic copy-number alterations (SCNA), gene expression, and DNA methylation to establish a molecular taxonomy of primary disease”: https://doi.org/10.1093/bioinformatics/bty133