A Novel Gene Typing Scheme Based on Semi-Supervised Learning with No Human Intervention Reveals Hidden Diversity in Cryptosporidium parvum

The novel semi-supervised learning-based genotyping framework proposed in this study offers a new approach for investigating the genetic diversity of Cryptosporidium and provides effective tools for future genomic research and epidemiological investigations. With the continuous accumulation of global data and the ongoing optimization of analytical methods, this machine learning-based genotyping framework holds great potential for advancing research on Cryptosporidium and other pathogens, enabling more accurate and comprehensive insights into their genetic diversity, evolution, and transmission patterns.