Binglan Li Email & Phone Number

West Hollywood, California, United States

Stanford, California, United States

1. LLM - Benchmarked the performance of the state-of-the-art LLMs (GPT-4o, GPT-4-turbo, Gemini Pro 1.5, and Llama 3) for pharmacogenomics Q&A towards better clinical AI. - Red-teaming/stress-testing the LLMs' behavior in real-world medicine.2. Clinical software - Pharmacogenomics Clinical Annotation Tool (PharmCAT) - Maintaining and improving PharmCAT. - Responding to PharmCAT users' requests - Developed a Nextflow pipeline to automate 500K WGS UK Biobank analysis in one click and improve efficiency by > 80% - Designing and generating PharmCAT tutorials and YouTube videos

San Francisco Bay Area

Genomic medicine and clinical tool development, supervised by Professor Teri E. Klein1. Pharmacogenomics Clinical Annotation Tool (PharmCAT) - PharmCAT translates patients' genetic data to genotype-based prescribing recommendations. - Contributed to PharmCAT development and maintenance. - Developed and maintained a Python-based data preprocessor and reduced ~95% PharmCAT runtime. - Developed a validation tool to ensure PharmCAT accuracy and optimized the computing runtime from ~3,000 hrs to ~1hr.2. UK Biobank - Investigated the PGx frequencies in 200K UK Biobank participants. - Analyzed 200K Whole-Exome Sequencing VCF and gVCF, imputed data, and genotype arrays.3. Facilitating the development of a machine-learning method to identify latent gene-trait-drug map for drug repurposing.4. Genomic medicine - Investigated the possibility of Genomic Medicine that takes care of patients from disease diagnosis to drug prescribing and adherence. - Identified overlapping genes and variants between drug responses and disease genetics by data mining in ClinGen, ClinVar, and PharmGKB (drug guidelines, FDA drug labels, etc.).

Philadelphia, Pennsylvania

Genomics and Computational Biology PhD program supervised by Professor Marylyn D. Ritchie.Thesis- Identified genes underlying complex traits using machine learning and gene-based analytic approaches.1. Multi-ancestry gene-trait association landscape - Designed and developed an efficient ML and statistical analysis framework on HPC. - Investigated gene-trait associations for 3 populations, 308 disease codes, and 20k+ genes across 49 tissues. - Analyzed EHR-linked UK Biobank, Penn Medicine Biobank, and the eMERGE network phase III data.2. Translational biomedical research - Collaborated with physicians to identify clinical biomarkers for age-related hearing impairment (ARHI).3. Power and type I error rates using simulated datasets - Investigated how tissue-specificity influenced regression models' capacity to identify disease-related genes. - Developed an efficient (multivariate normal distribution-based) simulation algorithm to emulate eQTL-gene-trait relationships in multiple tissues. - Evaluated the performance metrics (power and type I error rates) of various regression models, regularization approaches, and set-based inference methods. - Designed a tissue specificity-aware TWAS (TSA-TWAS) analytic framework.4. Feature selection of potential causal variants in GWAS using regression models.

State College, Pennsylvania Area

Student of Dr. Marylyn D. Ritchie Doctoral candidate in Bioinformatics & Genomics program

Shanghai City, China

Machine Learning in Systems Biology and Cancer- Used machine learning methods to identify cancer subtypes using TCGA datasets.- Investigated regulatory microRNAs on the transcriptome in the hypoxic placenta samples for its impact on fetus developmentSupervised by Dr. Weidong Tian

Doctor Of Philosophy - Phd, Genomics And Computational Biology

Dissertation titled "identifying complex trait-related genes via regulation-informed gene-based analyses"

Biomathematics, Bioinformatics, And Computational Biology

Activities and Societies: Huck Graduate Student Advisory CommitteeSupervised by Dr. Marylyn D. Ritchie and Transferred to University.

Bachelor Of Science (Bs), Life Sciences

Worked with Dr. Weidong Tian on macromolecular network interactions

High School Diploma, 4.0