No abstract

Infrared small target detection is part of the key technologies in infrared precision-guided, search and track system.Resulting from the relative distance of the infrared image system and the target is far, the target becomes small, faint and obscure. Furthermore, the interference of background clutter and system noise is intense. To solve the problem of infrared small target detection in a complex background, this paper proposes a bilateral filtering algorithm based on similarity judgments for infrared image background prediction. The algorithm introduces gradient factor and similarity judgment factor into traditional bilateral filtering. The two factors can enhance the accuracy of the algorithm for smooth region. At the same time, spatial proximity coefficients and gray similarity coefficient in the bilateral filtering are all expressed by the first two of McLaughlin expansion, which aiming at reducing the time overhead. Simulation results show that the proposed algorithm can effectively suppress complex background clutter in the infrared image and enhance target signal compared with the improved bilateral filtering algorithm, and it also can improve the signal to noise ratio (SNR) and contrast. Besides, this algorithm can reduce the computation time. In a word, this algorithm has a good background rejection performance.

No abstract

No abstract

Structure-based lead optimization is an open challenge in drug discovery, which is still largely driven by hypotheses and depends on the experience of medicinal chemists. We here propose a pairwise binding comparison network (PBCNet) based on physics-informed graph attention mechanism, specifically tailored for ranking relative binding affinity among congeneric ligands. Benchmarking on two held-out sets (provided by Schrödinger, Inc. and Merck KGaA) containing over 460 ligands and 16 targets, PBCNet demonstrated significant advantages in terms of both prediction accuracy and computational efficiency. Equipped with a fine-tuning operation, the performance of PBCNet reaches that of Schrödinger's FEP+, which is much more computationally intensive and requires significant expert intervention. A further simulation-based experiment showed that active learning-optimized PBCNet may accelerate lead optimization campaigns by 30%. Finally, for the convenience of users, a web service (https://pbcnet.alphama.com.cn/index) for PBCNet is established to facilitate complex relative binding affinity prediction through an easy-to-operate graphical interface.