Filtering by
- All Subjects: Cervical Cancer
- Creators: Anderson, Karen
Colorimetric assays are an important tool in point-of-care testing that offers several advantages to traditional testing methods such as rapid response times and inexpensive costs. A factor that currently limits the portability and accessibility of these assays are methods that can objectively determine the results of these assays. Current solutions consist of creating a test reader that standardizes the conditions the strip is under before being measured in some way. However, this increases the cost and decreases the portability of these assays. The focus of this study is to create a machine learning algorithm that can objectively determine results of colorimetric assays under varying conditions. To ensure the flexibility of a model to several types of colorimetric assays, three models were trained on the same convolutional neural network with different datasets. The images these models are trained on consist of positive and negative images of ETG, fentanyl, and HPV Antibodies test strips taken under different lighting and background conditions. A fourth model is trained on an image set composed of all three strip types. The results from these models show it is able to predict positive and negative results to a high level of accuracy.
Methods: We have designed a multiplexed magnetics programmable bead ELISA (MagProBE) to profile the immune responses of the proteins from 11 high-risk HPV types and 2 low-risk types—106 genes in total. HPV genes were optimized for human expression and either built with PCR or commercially purchased, and cloned into the Gateway-compatible pANT7_cGST vector for in vitro transcription/translation (IVTT) in a MagProBE array. Anti-GST antibody (Ab) labeling was then used to measure gene expression.
Results: 53/106 (50%) HPV genes have been cloned and tested for expression of protein. 91% of HPV proteins expressed at levels above the background control (MFI = 2288), and the mean expression was MFI = 4318. Codon-optimized genes have also shown a 20% higher expression over non-codon optimized genes.
Conclusion: Although this research is ongoing, it suggests that gene optimization may improve IVTT expression of HPV proteins in human HeLa lysate. Once the remaining HPV proteins have been expression confirmed, the cDNA for each gene will be printed onto slides and tested in serologic assays to identify potential Ab biomarkers to CIN3.