TS-000874 — Currently, the process to perform analysis of proliferation and migration rates of cells in wound healing arrays is very hands-on and time consuming. The Wound Healing Automated Analysis Pipeline (WHAAP) is a fully automated pipeline that can track cell migration, proliferation, and density or confluency of a live culture. After setting the threshold for cell recognition, it enables the user to effortlessly analyze proliferation and migration rates of cells in wound healing assays. Users can specify both test and control groups, as well as replicate as many experimental trials as desired, all stemming from an input of microscopic images taken at regular intervals. Each set is evaluated with unbiased image recognition held at a constant state. The data collected is used for a variety of calculations and estimations. WHAAP efficiently conducts all stages of analysis without requiring the user to possess any advanced knowledge of computer programming or biology. The output of this program is publication-ready, which only requires the user to interpret the data provided quickly and efficiently.
Benefits:
WHAAP adopts previous ideas for the analysis of wound healing assays and constructs them in a novel pipeline that enables automated analysis. WHAAP produces more in-depth data analysis and the enhanced data visualizations, all in a shorter runtime. Our software has the potential for an array of applications that require tracking cell movement and proliferation in culture.
Stage of Development
Preliminary testing was successful. After positive demos to faculty, we decided to take the software to production environment. We are currently finalizing the backend code ,after which, the UI will be created that would allow use via interaction with a web app hosted in an AWS serverless environment. At a later date, use of Self-learning deep neural network might be implemented to further improve the cell recognition of the software and enable full automation (user need only submit images to application)
Potential Applications/Markets:
WHAAP reduces the time and effort spent analysing the results of wound healing assays, a very popular laboratory technique used for functional analysis. Due to the sheer number of images now able to be produced during live cell experiments, other groups have developed tools to try eliminating the need to manually count cells and measure the change in leading edge position in wound healing assays. These other methods are all exclusively based on a simplistic measurement of % confluency. The issue that our lab encountered (and I'm sure other labs have experienced as well) is that the use of% confluency as a measurement more often than not fails to provide meaningful results. Furthermore, combining the data of multiple replicates and then multiple experiments remains time consuming and difficult to perform.
WHAAP allows users to quickly and easily adjust cell recognition. In a future version of WHAAP, we plan to implement a machine learning based approach, specifically a self-learning deep neural network, to solve the problem of cellular detection to even more accurately track the rate of cell growth and movement in response to a wound. WHAAP introduces several new metrics that are captured during the assay, allowing generation of a wholistic data set that accurately captures the complete picture of the wound healing response. Our own preliminary data shows that without WHAAP's increased sensitivity and separation of multiple contributing features to wound healing, statistically significant changes in protein function (caused by genetic variation) would have gone undetected.
WHAAP has a number of additional features that we believe further add to the value of the product:
•eliminates the need for manual processing between steps of analysis (minimizing errors, bias, and need for background knowledge or expertise)
•analyzes images more rapidly than other comparable software
•performs statistical analysis on any combination of experimental conditions provided by the user
•creates figures, tables, and charts that are formatted such that they can be immediately interpreted and used for presentations, manuscripts, grant applications, etc.
Not only have the demonstrated improvements to the process of analyzing wound healing assays, but we predict that WHAAP will become invaluable to researchers performing these assays and has the potential to become the leading analysis tool in this market. Because wound healing assays are commonly used across a wide breadth of research concentrations, WHAAP has the potential for a high level of impact and a high number of customers.
As previously mentioned, future planned improvements include performing cell recognition using machine learning methods. We would also like to enable WHAAP to analyze different wound shapes (specifically, circular wounds) which would further improve WHAAP's utility and reach.
Seeking:
Development Partner
Commercial Partner
Licensing