Fruit flies are one of the most harmful insect species to fruit yields. In AlertTrap, implementation of Single-Shot Multibox Detector (SSD) architecture with different state-of-the-art backbone feature extractors such as MobileNetV1 and MobileNetV2 appears to be potential solutions for the real-time detection problem. SSD-MobileNetV1 and SSD-MobileNetV2 perform well and result in AP at 0.5 of 0.957 and 1.0, respectively. You Only Look Once (YOLO) v4-tiny outperforms the SSD family with 1.0 in AP at 0.5; however, its throughput velocity is considerably slower, which shows SSD models are better candidates for real-time implementation. We also tested the models with synthetic test sets simulating expected environmental disturbances. The YOLOv4-tiny had better tolerance to these disturbances than the SSD models. The Raspberry Pi system successfully gathered environmental data and pest counts, sending them via email over 4 G. However, running the full YOLO version in real time on Raspberry Pi is not feasible, indicating the need for a lighter object detection algorithm for future research. Among model candidates, YOLOv4-tiny generally performs best, with SSD MobileNetV2 also comparable and sometimes better, especially in scenarios with synthetic disturbances. SSD models excel in processing time, enabling real-time, high-accuracy detection. TFLITE versions of SSD models also process faster than their inference graph on TPU hardware, suggesting real-time implementation on edge devices like the Google Coral Dev Board. The results demonstrate the feasibility of real-time implementation of the fruit fly detection models on edge devices with high performance. In addition, YOLOv4-tiny is shown to be the most probable candidate because YOLOv4-tiny demonstrates a robust testing performance toward citrus fruit fly detection. Nevertheless, SSD-MobileNetV2 will be the better model, considering the inference time.

The most recently identified class of actin nucleators, WASp homology domain 2 (WH2) nucleators, use tandem repeats of monomeric actin-binding WH2 domains to facilitate actin nucleation. WH2 domains are involved in a wide variety of actin regulatory activities. Structurally, they are expected to clash with interprotomer contacts within the actin filament. Thus, the discovery of their role in nucleation was surprising. Here we use Drosophila Spire (Spir) as a model system to investigate both how tandem WH2 domains can nucleate actin and what differentiates nucleating WH2-containing proteins from their non-nucleating counterparts. We found that the third WH2 domain in Spir (Spir-C or SC) plays a unique role. In the context of a short nucleation construct (containing only two WH2 domains), placement of SC in the N-terminal position was required for the most potent nucleation. We found that the native organization of the WH2 domains with respect to each other is necessary for binding to actin with positive cooperativity. We identified two residues within SC that are critical for its activity. Using this information, we were able to convert a weak synthetic nucleator into one with activity equal to a native Spir construct. Lastly, we found evidence that SC binds actin filaments, in addition to monomers.

Tubulins are essential for the reproduction of many eukaryotic viruses, but historically, bacteriophage were assumed not to require a cytoskeleton. Here, we identify a tubulin-like protein, PhuZ, from bacteriophage 201φ2-1 and show that it forms filaments in vivo and in vitro. The PhuZ structure has a conserved tubulin fold, with an unusual, extended C terminus that we demonstrate to be critical for polymerization in vitro and in vivo. Longitudinal packing in the crystal lattice mimics packing observed by EM of in-vitro-formed filaments, indicating how interactions between the C terminus and the following monomer drive polymerization. PhuZ forms a filamentous array that is required for positioning phage DNA within the bacterial cell. Correct positioning to the cell center and optimal phage reproduction only occur when the PhuZ filament is dynamic. Thus, we show that PhuZ assembles a spindle-like array that functions analogously to the microtubule-based spindles of eukaryotes.