Banana bunchy top virus (BBTV) was recently detected in Mozambique and appears to be limited to the provinces of Gaza, Maputo and Zambezia, but it has great potential to spread to other provinces. Despite its importance, nothing is known about the BBTV isolates that occur in Mozambique. In this study, the sequences of the S and R genes of 40 isolates chosen as representatives of samples collected previously from eleven farms of the four administrative posts of the district of Chóckwè, Gaza province, were sequenced and analyzed. The S-DNA nucleotide sequences of the analyzed isolates were highly conserved, with identity ranging from 97% to 100%. The same was observed for the R-DNA sequences, with most identities ranging between 98% and 100% among the isolates from Chókwè and above 90% when compared to the isolates from GenBank. The phylogenetic analysis showed that the Mozambican BBTV isolates belong to the Pacific-Indian Oceans (PIO) group, showing greater proximity to the isolate JQ820453 from Malawi than to the isolates from sub-Saharan countries, which were grouped in a distinct subclade. This is the first study conducted to determine the molecular characteristics of BBTV isolates present in Mozambique.

In this study, a diverse collection of images of myxozoans from the genera Henneguya and Myxobolus was created, providing a practical dataset for application in computer vision. Four versions of the YOLOv5 network were tested, achieving an average precision of 97.9%, a recall of 96.7%, and an F1 score of 97%, demonstrating the effectiveness of MLens in the automatic detection of these parasites. These results indicate that machine learning has the potential to make micro-parasite detection more efficient and less reliant on manual work in parasitology. The beta version of the MLens shows strong performance, and future improvements may include fine-tuning the WebApp hyperparameters, expanding to other myxosporean genera, and refining the model to handle more complex optical microscopy scenarios. This work represents a significant ad-vancement, opening new possibilities for the application of machine learning in parasitology and substantially accelerating parasite detection.