Although significant advances have been achieved in SAR land-cover classification, recent methods remain predominantly focused on supervised learning, which relies heavily on extensive labeled datasets. This dependency not only limits scalability and generalization but also restricts adaptability to diverse application scenarios. In this paper, a general-purpose foundation model for SAR land-cover classification is developed, serving as a robust cornerstone to accelerate the development and deployment of various downstream models. Specifically, a Dynamic Instance and Contour Consistency Contrastive Learning (DI3CL) pre-training framework is presented, which incorporates a Dynamic Instance (DI) module and a Contour Consistency (CC) module. DI module enhances global contextual awareness by enforcing local consistency across different views of the same region. CC module leverages shallow feature maps to guide the model to focus on the geometric contours of SAR land-cover objects, thereby improving structural discrimination. Additionally, to enhance robustness and generalization during pre-training, a large-scale and diverse dataset named SARSense, comprising 460,532 SAR images, is constructed to enable the model to capture comprehensive and representative features. To evaluate the generalization capability of our foundation model, we conducted extensive experiments across a variety of SAR land-cover classification tasks, including SAR land-cover mapping, water detection, and road extraction. The results consistently demonstrate that the proposed DI3CL outperforms existing methods. Our code and pre-trained weights are publicly available at: https://github.com/SARpre-train/DI3CL.

Nuclear localization signal (NLS) sequence from capsid protein of Venezuelan equine encephalitis virus (VEEV) binds to importin-α transport protein and clogs nuclear import. Prevention of viral NLS binding to importin-α may represent a viable therapeutic route. Here, we investigate the molecular mechanism by which two diffusively binding inhibitors, DP9 and DP9o, interfere with the binding of VEEV's NLS peptide to importin-α. Our study uses all-atom replica exchange molecular dynamics simulations, which probe the competitive binding of the VEEV NLS fragment, the coreNLS peptide, and the inhibitors to importin-α. Our previous simulations of non-competitive binding of the coreNLS, in which it natively binds to importin-α, are used as a reference. Both inhibitors abrogate native peptide binding and reduce the fraction of its native interactions, but they fail to prevent its non-native binding to importin-α. As a result, these inhibitors turn the coreNLS into diffusive binder, which adopts a manifold of non-native binding poses. Competition from the inhibitors compromises the free energy of coreNLS binding to importin-α showing that they reduce its binding affinity. The inhibition mechanism is based on masking the native binding interactions formed by the coreNLS amino acids. Surprisingly, ligand interference with the binding interactions formed by importin-α amino acids contributes little to inhibition. We show that DP9 is a stronger inhibitor than DP9o. By comparative analysis of DP9 and DP9o interactions we determine the atomistic reason for a relative "success" of DP9, which is due to the intercalation of this inhibitor between the side chains of NLS lysine residues. To test our simulations, we performed AlphaScreen experiments measuring IC50 values for the inhibitors. AlphaScreen data confirmed in silico ranking of the inhibitors. By combining our recent studies, we discuss the putative mechanism by which diffusively binding inhibitors impact protein-protein interactions.

Trip purpose is essential information supporting tasks in intelligent transportation systems, such as travel behaviour comprehension, location-based service, and urban planning. The observation of trip purpose is a necessary aspect of travel surveys. However, owing to the sampling volume, survey budget, and survey frequency, relying solely on travel surveys in the era of big data is a difficult task. There has long been a demand for an accurate, generalizable, and robust inference method for trip purposes. Although existing studies contributed significant efforts to improve the trip purpose inference, the potential of leveraging the trip chain is insufficient. The spatial correlations and chaining patterns hidden in travelled zones are worthy of further exploration. The unequal importance within trip chains has not been clearly represented. Additionally, complex activity-zone mutual interdependence has not been considered in previous models. Herein, we propose a framework-Dual-FlowAttentive Network with FeatureCrossing (DACross), specifically for inferring the chained trip purpose. We form trip chains innovatively that treat trip activities and travelled geographic zones as two chains with mutual interactions. We propose DACross, which consists of two parallel attentive branches and a co-attentive feature crossing module, for fully learning the intra- and inter-chain dependencies. We conducted extensive experiments on four large-scale real-world datasets to evaluate not only the performance of DACross but also the generalizability of the proposed framework among different cities and scenarios. Notably, the Experimental results prove the overall superiority of the proposed DACross.