Skip to main content Skip to main menu
UF Health University of Florida
College of Public Health & Health Professions University of Florida
Spring Graduation Information
About Overview

Dr Lins Research

Dr. Lin’s research interest is in the development and application of computational models for environmental chemicals, nanoparticles and drugs in animals and humans to address research questions related to nanomedicine, animal-derived food safety assessment, and human health risk assessment of xenobiotics, including per- and polyfluorinated substances (PFAS), pesticides, nanoparticles, and microplastics.

The computational models include traditional compartmental pharmacokinetic (PK) models, physiologically based pharmacokinetic (PBPK) models, and quantitative structure-activity relationship (QSAR) models. To build robust models, Dr. Lin’s team incorporates machine learning and artificial intelligence (AI) approaches into their models to build AI-based models. The long-term goal of Dr. Lin research is to develop AI-assisted computational approaches to support decision-making in human health, animal health, and environmental health (i.e., one health approach). Currently, Dr. Lin’s lab has the following projects.

1. Human Food Safety Assessment: The focus of this project is to build PK, PBPK, and QSAR models to help predict pharmacokinetics of drugs in food-producing animals, such as cattle, swine, sheep, goats, chickens, and turkeys. The objective of this project is to apply these computational models to predict withdrawal intervals of drugs in food animals following extralabel use, ultimately helping protect human food safety of animal-derived food products, such as meat, milk, and eggs. This project is supported by the United States Department of Agriculture (USDA) through the national Food Animal Residue Avoidance Databank (FARAD) program. Dr. Lin has been working in the FARAD program for more than 10 years. Dr. Lin was a PI and Regional Director at the Midwest Regional Center at Kansas State University from 2017 to 2021. From 2021 to the present, Dr. Lin is a Co-PI and Co-Regional Director of the Southeastern Regional Center of FARAD at the University of Florida.

Flowchart showing pharmacokinetic data, organ-based model, animal population analysis, and tissue residue graphs for withdrawal intervals.

2. Nanomedicine: The focus of this project is to build AI-based PBPK models to help determine the key physicochemical properties in the delivery of nanoparticles to the tumor site and other target organs. The objective of this project is to develop AI-assisted computational models to help design safe nanomedicine with improved targeting efficiency. This line of research has been funded by NIH since 2017. Dr. Lin’s lab members are working on several specific projects in this area: (1) expand the Nano-Tumor Database; (2) develop an AI-based QSAR model to predict delivery efficiency to tumor and major organs; and (3) develop an AI-based PBPK model to predict delivery efficiency to tumor and major organs.

The image shows a diagram combining human internal organs with a schematic of a neural network. On the left, there is an anatomical illustration of organs such as the liver, kidneys, heart, and blood vessels. On the right, there is a neural network model with labeled input, hidden, and output layers, indicating how medical or biological data might be processed using artificial intelligence.

3. Human Health Risk Assessment of Xenobiotics: The focus of this project is to develop PBPK models for xenobiotics, such as PFAS, pesticides, nanoparticles, and microplastics in animals and humans of different life stages, including fetal, neonatal, gestational, and lactational periods. In addition, Dr. Lin’s lab also develops machine learning-based QSAR models to predict chemicals’ toxicities, including carcinogenicity, liver toxicity, and neurotoxicity. The objective of these projects is to integrate these computational models with in vitro and in vivo animal toxicity data as well as human epidemiological data to inform exposure assessment, dose-response analysis, and risk assessment, and ultimately helping public health decision-making.

Diagram combining a human anatomical illustration with a neural network model. The left side shows a human torso with major organs and blood vessels highlighted in red and blue. The right side depicts a neural network with three sections: an input layer with six labeled nodes (TS, Size, Zeta, SH, TM, CT), a hidden layer with nine nodes (H1–H9), and an output layer with one node (O1) labeled “DE.” Two bias nodes (B1 and B2) connect to the hidden and output layers. A plus sign between the torso and the network indicates integration of physiological data with machine learning.
Diagram illustrating machine learning and QSAR modeling for chemical toxicity prediction. On the left, a box labeled “High-throughput screening (HTS) bioactivity in vitro data” contains a grid of pink dots, with a chemical structure diagram below showing atoms labeled N, C, O, and H. In the center, a “Deep neural network” is depicted with multiple interconnected nodes arranged in layers. To the right, an arrow points to “Chemical toxicity prediction,” represented by icons of a brain, lungs, stomach, and heart. A bullet list next to the neural network includes: Attribute selection, Training, Cross-validation, and Model assessment.