Postdoctoral Scholar-Pharmacology
Memphis, TN, USA
THIS IS A GRANT-FUNDED POSITION FUNDED UNTIL OCTOBER 1, 2030
The Department of Pharmacology, Addiction Science, and Toxicology at the University of Tennessee Health Sciences is seeking a Postdoctoral Scholar to lead the computational analysis and artificial intelligence (AI) integration for a major NIH funded grant. The successful candidate will be responsible for extracting biological insights from large-scale, high-dimensional sequencing data using a combination of conventional bioinformatics and cutting-edge machine learning methodologies.
The Department of Pharmacology, Addiction Science, and Toxicology at the University of Tennessee Health Sciences is seeking a Postdoctoral Scholar to lead the computational analysis and artificial intelligence (AI) integration for a major NIH funded grant. The successful candidate will be responsible for extracting biological insights from large-scale, high-dimensional sequencing data using a combination of conventional bioinformatics and cutting-edge machine learning methodologies.
EDUCATION: Ph.D. in Bioinformatics, Computational Biology, Computer Science, Neuroscience, or a related quantitative field.
EXPERIENCE: Experience in AI integration, extracting biological insights from large-scale high-dimensional sequencing data. Computational biology and AI preferred.
KNOWLEDGE, SKILLS, AND ABILITIES:
- Strong understanding of long-read sequencing technologies and multi-omics integration.
- Ability to work independently in a fast-paced, multi-disciplinary research environment.
- Excellent communication skills for collaborating with experimentalists and disseminating research outputs.
- Leads the analysis of foundational multi-omics datasets, including single-molecule long-read DNA methylation (CpG), direct RNA sequencing, and single-nucleus RNA-seq (snRNA-seq) generated across diverse rat strains and brain regions.
- Adapts and fine-tunes existing deep learning models (e.g., AlphaGenome, DeepSEA, DNA Hyena, scGPT) to improve variant effect prediction and automated cell-type annotation specifically for rat genomic data.
- Develops and implements a Retrieval-Augmented Generation (RAG) framework utilizing Large Language Models (LLMs) to synthesize information from biomedical literature and generate novel, testable hypotheses regarding Substance Use Disorder (SUD) mechanisms.
- Utilizes advanced statistical frameworks (e.g., Multi-Omics Factor Analysis) to integrate genomic, epigenomic, transcriptomic, and proteomic data.
- Drafts high-impact manuscripts for peer-reviewed journals and present research findings and resources at national and international conferences.
- Oversees the utilization of high-performance computational resources, including dedicated GPU workstations for LLM evaluation and testing.
- Performs other duties as assigned.