Discovery of non-sulfonamide carbonic anhydrase IX inhibitors through structure-based virtual screening.

Carbonic anhydrase IX (CA IX) is a subtype of the human carbonic anhydrase (hCA) family and exhibits high expression in various solid tumors, rendering it a promising target for tumor therapy. Currently, marketed carbonic anhydrase inhibitors (CAIs) are primarily composed of sulfonamides derivatives, which may have impeded their potential for further expansion. Therefore, we have developed a structure-based virtual screening approach to explore novel CAIs exhibiting distinctive structures and anti-tumor potential in the FDA database. In vitro experiments demonstrated that 3-pyridinemethanol (0.42 µM), procodazole (8.35 µM) and pamidronic acid (8.51 µM) exhibited inhibitory effects on CA IX activity. The binding stability and interaction mode between the CA IX and the hit compounds are further investigated through molecular dynamics simulations and binding free energy calculations. Furthermore, the ADME/Tox prediction results indicated that these compounds exhibited favorable pharmacological properties and minimal toxic side effects. Our study successfully applied computational strategies to discover three non-sulfonamide inhibitors of carbonic anhydrase IX (CA IX) that demonstrate inhibitory activity in vitro. These findings have significant implications for the development of CA IX inhibitors and anti-tumor drugs, contributing to their progress in the field.

Deep High-Resolution Representation Learning for Visual Recognition.

High-resolution representations are essential for position-sensitive vision problems, such as human pose estimation, semantic segmentation, and object detection. Existing state-of-the-art frameworks first encode the input image as a low-resolution representation through a subnetwork that is formed by connecting high-to-low resolution convolutions in series (e.g., ResNet, VGGNet), and then recover the high-resolution representation from the encoded low-resolution representation. Instead, our proposed network, named as High-Resolution Network (HRNet), maintains high-resolution representations through the whole process. There are two key characteristics: (i) Connect the high-to-low resolution convolution streams in parallel and (ii) repeatedly exchange the information across resolutions. The benefit is that the resulting representation is semantically richer and spatially more precise. We show the superiority of the proposed HRNet in a wide range of applications, including human pose estimation, semantic segmentation, and object detection, suggesting that the HRNet is a stronger backbone for computer vision problems. All the codes are available at https://github.com/HRNet.

Bayesian Cycle-Consistent Generative Adversarial Networks via Marginalizing Latent Sampling.

Recent techniques built on generative adversarial networks (GANs), such as cycle-consistent GANs, are able to learn mappings among different domains built from unpaired data sets, through min-max optimization games between generators and discriminators. However, it remains challenging to stabilize the training process and thus cyclic models fall into mode collapse accompanied by the success of discriminator. To address this problem, we propose an novel Bayesian cyclic model and an integrated cyclic framework for interdomain mappings. The proposed method motivated by Bayesian GAN explores the full posteriors of cyclic model via sampling latent variables and optimizes the model with maximum a posteriori (MAP) estimation. Hence, we name it Bayesian CycleGAN. In addition, original CycleGAN cannot generate diversified results. But it is feasible for Bayesian framework to diversify generated images by replacing restricted latent variables in inference process. We evaluate the proposed Bayesian CycleGAN on multiple benchmark data sets, including Cityscapes, Maps, and Monet2photo. The proposed method improve the per-pixel accuracy by 15% for the Cityscapes semantic segmentation task within origin framework and improve 20% within the proposed integrated framework, showing better resilience to imbalance confrontation. The diversified results of Monet2Photo style transfer also demonstrate its superiority over original cyclic model. We provide codes for all of our experiments in https://github.com/ranery/Bayesian-CycleGAN.