ESEvyatar Sar-Shalom

Evyatar Sar-Shalom

*This is an algorithmically generated author record based on publicly available information.

Evyatar Sar-Shalom has a total of 17 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    YOLito: A generalizable model for automated mosquito detection

    by Evyatar Sar-Shalom, Ziv Kassner, Arad Sarig, Clément Vinauger, Iliano Coutinho-Abreu, Merybeth F. Triana, Lucía I. Bouzada, R. Jason Pitts, Marcus C. Stensmyr, Omar S. Akbari, et al.

    Understanding mosquito behavior is key to advancing research in ecology, evolution, and disease control, yet most behavioral assays rely on human-dependent methods, such as real-time observation or manual frame-by-frame annotation, limiting throughput and reproducibility. We present YOLito, a domain-generalized AI model for automated mosquito detection and behavioral quantification. Built on the Ultralytics YOLO framework and enhanced with Slicing-Aided Hyper Inference (SAHI), YOLito accurately detects multiple mosquitoes across diverse backgrounds and imaging conditions. Trained on a globally assembled dataset of 38,547 annotated images from 35 experimental setups across six laboratories and three public datasets, YOLito achieved high performance on unseen data (precision = 0.95; recall = 0.91) and generalized across mosquito species ( Aedes, Anopheles, Culex ) and assay types, including blood-feeding, sugar-feeding, and oviposition. By automating behavioral scoring, YOLito transforms traditional assays into scalable and reproducible experimental platforms. The accompanying open-source toolkit enables high-throughput extraction of metrics such as visit frequency, duration, and distance traveled, providing a standardized and extensible framework that bridges computer vision and vector biology.


  • Open Access

    An OpIE2 -DsRed marker disrupts female blood-feeding and shortens lifespan in the malaria vector Anopheles gambiae

    by Arad Sarig, Evyatar Sar-Shalom, Ebrima Sm Kolley, Elad Shmuel Yonah, Lee Benjamin Lamdan, Ariel Roselin Lewin, Tamir Partosh, Gur Pines, Jonathan D. Bohbot, Philippos Aris Papathanos

    Anopheles gambiae is one of the principal vectors of human malaria. Over the past two decades, transgenic mosquito strains have been essential tools for studying mosquito biology and developing genetic control strategies such as gene drives. Mosquito transformants are typically identified using fluorescent markers, which are assumed to be phenotypically neutral. While generating CRISPR-based gene drive strains carrying an OpIE2 -DsRed marker we unexpectedly found that transgenic females were unable to blood-feed and were consequently sterile, whereas males initially appeared normal and fertile. Given the potential utility of dominant, female-specific sterility for mosquito control, we established additional strains controlling for transgene content and integration site, confirming that the OpIE2 -DsRed cassette caused the defect. Behavioral assays showed that females exhibited normal attraction to a membrane feeder but failed to initiate blood-feeding, performing repeated cycles of probing and proboscis grooming in rapid succession before ultimately leaving the feeder unfed. Microscopy showed that both sexes possessed a distally curved proboscis, providing a morphological explanation for the blood-feeding defect of females and the reduced male lifespan. A second promoter variant ( OpIE2b ), differing in flanking sequences at the IE-2 junction, drove strong marker expression without impairing blood-feeding or longevity. These findings demonstrate that minor differences in promoter architecture can produce major, unexpected phenotypic effects. OpIE2b provides a robust, phenotypically neutral marker for An. gambiae research, while OpIE2a highlights the need for rigorous validation of transgenic components intended for research and applied releases.