Lightweight safflower cluster detection based on YOLOv5.

The effective detection of safflower in the field is crucial for implementing automated visual navigation and harvesting systems. Due to the small physical size of safflower clusters, their dense spatial distribution, and the complexity of field scenes, current target detection technologies face several challenges in safflower detection, such as insufficient accuracy and high computational demands. Therefore, this paper introduces an improved safflower target detection model based on YOLOv5, termed Safflower-YOLO (SF-YOLO). This model employs Ghost_conv to replace traditional convolution blocks in the backbone network, significantly enhancing computational efficiency. Furthermore, the CBAM attention mechanism is integrated into the backbone network, and a combined L C I O U + N W D loss function is introduced to allow for more precise feature extraction, enhanced adaptive fusion capabilities, and accelerated loss convergence. Anchor boxes, updated through K-means clustering, are used to replace the original anchors, enabling the model to better adapt to the multi-scale information of safflowers in the field. Data augmentation techniques such as Gaussian blur, noise addition, sharpening, and channel shuffling are applied to the dataset to maintain robustness against variations in lighting, noise, and visual angles. Experimental results demonstrate that SF-YOLO surpasses the original YOLOv5s model, with reductions in GFlops and Params from 15.8 to 13.2 G and 7.013 to 5.34 M, respectively, representing decreases of 16.6% and 23.9%. Concurrently, SF-YOLO's mAP0.5 increases by 1.3%, reaching 95.3%. This work enhances the accuracy of safflower detection in complex agricultural environments, providing a reference for subsequent autonomous visual navigation and automated non-destructive harvesting technologies in safflower operations.

Cryo-EM structures reveal two allosteric inhibition modes of PI3KαH1047R involving a re-shaping of the activation loop.

PI3Kα is a lipid kinase that phosphorylates PIP2 and generates PIP3. The hyperactive PI3Kα mutation, H1047R, accounts for about 14% of breast cancer, making it a highly attractive target for drug discovery. Here, we report the cryo-EM structures of PI3KαH1047R bound to two different allosteric inhibitors QR-7909 and QR-8557 at a global resolution of 2.7 Å and 3.0 Å, respectively. The structures reveal two distinct binding pockets on the opposite sides of the activation loop. Structural and MD simulation analyses show that the allosteric binding of QR-7909 and QR-8557 inhibit PI3KαH1047R hyper-activity by reducing the fluctuation and mobility of the activation loop. Our work provides a strong rational basis for a further optimization and development of highly selective drug candidates to treat PI3KαH1047R-driven cancers.