Overview of Project Goals: Heat stress (HS) is an important stressor that is determinental to the welfare, production and the health status of poulty. Our research efforts in this seed grant seek to build experimental datasets (optical micrographs) that will processed through machine learning (ML)-based algorithms, to eventuate the development of rapid reporting techniques that inform on the presence of HS in poultry. The fundamental hypothesis that drives our research is that the cells overexpressing well-established intracellular stress chaperones such as heat shock proteins (HSP70) also undergo changes to their mechanical properties. We introduce the concept of rapidly characterizing mechanical properties of red blood cells (RBCs) of chickens using fluids called liquid crystals (LCs). A key aspect of the development of our LC-based platform involves building ML-based convolutional neural networks (CNNs) that can generate classifiers to separate image sets of RBCs dispersed within LCs into healthy ones those of chickens experiencing HS. The RBCs dispersed in LCs provide with value image features such as cell extension, cell orientation and LC texture which are all connected to our fundamental hypothesis and enable classification via CNN. The expression levels of HSP70 will be used to define our classes for the CNN framework which would then be used to classify the experimental micrographs. Through this seed grant, we seek to establish a strong preliminary dataset (both experimental and CNN) to test this fundamental hypothesis and enable us to apply for a standard grant in this program.Goals expanded:Current methods for monitoring stress rely on the identification of molecular and protein markers such as corticosterone and HSPs. Although methods that report on molecular and protein markers have increased our understanding of HS, these methods are usually time-intensive and are not immediately accessible to the end user (farmer, technician on a production line) seeking to make informed decisions on the health and stress levels of chicken. Therefore, there is a critical need to identify reliable, and rapid ways to monitor HS in poultry.A key innovation in the proposed work in our methodology is to connect the expression of HSP70 to rapid optical readouts which characterize the health of the blood cells of chickens. We seek to build a unified picture connecting protein markers of HS and rapid readouts of their mechanical properties. The PI has previously developed an LC-based technique and it was deployed to rapidly report on the health of human RBCs. Molecules of LC are perturbed from the preferred parallel orientation when an inclusion, for instance a colloidal particle is present withing the LC fluid. This creates an orientational strain within the LC. However, if the inclusion is soft, such as an RBC, the LC can stretch out the cell and release some of the strain contained within the fluid. This sharing of strain is intimately coupled to the mechanical properties of the RBCs which we expect to change as they experience HS. LCs enable rapid readouts of the mechanical properties of cells, for instance, a simple experiment of dispersing a few µl of blood in LCs can be used to understand the health status of over a thousand cells within a few minutes. Another key innovation of our approach is the development of CNNs algorithms that connect the micrographs of chicken RBCs dispersed in LCs to molecular expression of HSP70. Our preliminary data reveals that chicken RBCs dispersed in LCs exhibit several image features such as cell orientation, cell extension, texture of LC around the cell etc, which are all a function of the HS status of the cell. These feature-rich datasets are good candidates for developing our CNN algorithms and for classifying these features to the expression of HSP70. This will enable the development of a comprehensive picture from the molecular level to the cellular level of the state of chickens experiencing HS and enable rapid readouts with the LC-based technique.