Source: KANSAS STATE UNIV submitted to
FOOD ANIMAL RESIDUE AVOIDANCE DATABANK (FARAD)
Sponsoring Institution
National Institute of Food and Agriculture
Project Status
ACTIVE
Funding Source
Reporting Frequency
Annual
Accession No.
1033202
Grant No.
2024-41480-43679
Cumulative Award Amt.
$120,000.00
Proposal No.
2024-07942
Multistate No.
(N/A)
Project Start Date
Sep 1, 2024
Project End Date
Aug 31, 2027
Grant Year
2024
Program Code
[FARAD]- Food An. Res. Avoidance Database,FARAD
Project Director
Jaberi-Douraki, M.
Recipient Organization
KANSAS STATE UNIV
(N/A)
MANHATTAN,KS 66506
Performing Department
(N/A)
Non Technical Summary
The FARAD program, a national food safety initiative funded by the USDA for over 40 years since its inception in 1982, is a collaborative effort involving five regional centers: Kansas State University--Olathe (KSUO), North Carolina State University, the University of California--Davis, the University of Florida, and the Virginia-Maryland College of Veterinary Medicine. FARAD's primary objective is to provide the most up-to-date information and scientific tools to ensure the production of safe foods of animal origin. The program achieves this through two key objectives: (1) identifying, extracting, assembling, evaluating, and distributing reviewed information about residue avoidance and mitigation to stakeholders involved in residue avoidance programs; and (2) developing tools that enable the prediction of proper withdrawal intervals following extralabel drug use.To continue fulfilling FARAD's mission, the specific objectivesinclude: (1) developing interfaces that allow FARAD responders to access KSUO's comparative medicine databases and associated computational tools, along with relevant global data; (2) pursuing the development of novel AI technologies applicable to food-animal production for collecting, organizing, merging, and cleaning data, thereby facilitating the submission of queries for datasets on Global maximum residue limits (MRLs) and withdrawal periods (WDPs); and (3) conducting research to design a full-text retrieval system that will create an easily queried information retrieval database, performing metadata analysis on bibliographic records in veterinary medicine and those validated by the current FARAD database.
Animal Health Component
20%
Research Effort Categories
Basic
60%
Applied
20%
Developmental
20%
Classification

Knowledge Area (KA)Subject of Investigation (SOI)Field of Science (FOS)Percent
7115010118020%
7113910208020%
7113910209020%
5023910208020%
5023910209020%
Goals / Objectives
The national FARAD program aims to safeguard the American public by ensuring the production of safe, animal-derived human food products, such as milk, eggs, meat, honey, and more. These products must be free of violative or potentially unsafe chemical residues, including drugs, pesticides, environmental contaminants, natural toxins, and other harmful substances. Kansas State University Olathe (KSUO) will be tasked with developing interfaces for FARAD responders to access KSUO's comparative medicine databases and computational tools, as well as relevant global data. The KSUO team will focus on creating novel AI technologies applicable to food-animal production. These technologies will facilitate the collection, organization, merging, and cleaning of data, making it easier to submit queries regarding global drug clearance data, maximum residue limits (MRLs) and withdrawal periods (WDPs). The team will also research and design a full-text retrieval system to develop an information retrieval database that can be easily queried. This system will perform metadata analysis on bibliographic records in veterinary medicine, complementing the existing FARAD database. The information retrieval system will be instrumental in developing hybrid models that combine content-based and bibliometric features for machine learning applications. These applications will extract and clean data from various sources, forming an integral part of the next-generation FARAD program.
Project Methods
For the FARAD projects, we have been devleoping and employingmethods that involve comprehensive training for numerous students in data analytics techniques, with a particular focus on database curation, decision-making, and result interpretation. Students acquire the skills necessary to develop working hypotheses and design error correction techniques for data scrubbing and retrieval. They engage in data exploration techniques to visually analyze and understand the data's characteristics. Following this, data curation and annotation areconducted to organize and integrate data from various sources. This includes the annotation, organization, clustering, and presentation of data types from the 1DATA databank.Next, we integrate machine learning models to generate results from preprocessed and cleansed data, effectively reducing data size and eliminating insignificant and noise-driven reports. This integration enhances decision-making and interpretation through data-driven machine learning. The project also extensively utilizes statistical methods such as regression analysis, cohort and cluster analysis, feature reduction, and data visualization to analyze the data comprehensively.