Development of Automated Image Processing for High-Throughput Screening of Potential Anti-Chikungunya Virus Compounds

Chikungunya virus, a member of the Alphavirus genus, continues to present a global health challenge due to its widespread occurrence and the absence of specific antiviral therapies. Accurate detection of viral infections, such as chikungunya, is critical for antiviral research, yet traditional methods are time-consuming and prone to error. This study presents the development and validation of an automated image processing algorithm designed to improve the accuracy and speed of high-throughput screening for potential anti-chikungunya virus compounds. Using MvTec Halcon software (Version 22.11), the algorithm was developed to detect and classify infected and uninfected cells in viral assays, and its performance was validated against manual counts conducted by virology experts, showing a strong correlation with Pearson correlation coefficients of 0.9807 for cell detection and 0.9886 for virus detection. These values indicate a high correlation between the algorithm and manual counts performed by three virology experts, demonstrating that the algorithm's accuracy closely matches expert manual evaluations. Following statistical validation, the algorithm was applied to screen antiviral compounds, demonstrating its effectiveness in enhancing the throughput and accuracy of drug discovery workflows. This technology can be seamlessly integrated into existing virological research pipelines, offering a scalable and efficient tool to accelerate drug discovery and improve diagnostic workflows for vector-borne and emerging viral diseases. By addressing critical bottlenecks in speed and accuracy, it holds promise for tackling global virology challenges and advancing research into other viral infections.