AI Whole Genome Sequencing Analysis Research

Variant Calling Pipeline Development

Interns will develop and optimize bioinformatics pipelines for identifying genetic variants from whole genome sequencing data. They will work with tools like GATK and SAMtools to process raw sequencing reads, call single nucleotide polymorphisms (SNPs), and indels, while implementing quality control measures and validating results against known variants.

Machine Learning for Pathogenic Variant Classification

Interns will build and train machine learning models to classify genetic variants as pathogenic, benign, or of uncertain significance. They will utilize deep learning frameworks and feature engineering techniques on genomic datasets to improve prediction accuracy for clinical variant interpretation.

Copy Number Variation Detection Using AI

Interns will develop AI algorithms to detect and characterize copy number variations (CNVs) in whole genome sequencing data. This work involves implementing neural networks and statistical methods to identify duplications and deletions, analyze their breakpoints, and assess their potential clinical significance.

Genome Assembly and Sequence Alignment Optimization

Interns will research advanced algorithms for genome assembly and sequence alignment, focusing on improving accuracy and computational efficiency. They will work with long-read sequencing technologies and implement or optimize tools for handling complex genomic regions and structural variants.

Population Genomics and Ancestry Analysis

Interns will analyze whole genome data across diverse populations to understand genetic variation patterns, population structure, and ancestry. They will apply principal component analysis, admixture modeling, and statistical methods to characterize genomic diversity and identify population-specific variants of interest.