A metal cluster stuck in a protein acts as a synthetic metalloenzyme for cancer-specific catalytic therapy.

To date, earlier diagnosis of Alzheimer’s disease (AD) is still challenging. Recent studies revealed the elevated expression of connective tissue growth factor (CTGF) in AD brain is an upstream regulator of amyloid-beta (Aβ) plaque, thus CTGF could be an earlier diagnostic biomarker of AD than Aβ plaque. Herein, we develop a peptide-coated gold nanocluster that specifically targets CTGF with high affinity (KD ~ 21.9 nM). The probe can well penetrate the blood-brain-barrier (BBB) of APP/PS1 transgenic mice at early-stage (earlier than 3-month-old) in vivo, allowing non-invasive NIR-II imaging of CTGF when there is no appearance of Aβ plaque deposition. Notably, this probe can also be applied to measuring CTGF on postmortem brain sections by multimodal analysis, including fluorescence imaging, peroxidase-like chromogenic imaging, and ICP-MS quantitation, which enables distinguishment between the brains of AD patients and healthy people. This probe possesses great potential for precise diagnosis of earlier AD before Aβ plaque formation.

Rationale: Bone is the most frequent site for breast cancer metastasis, which accounts for the leading cause of death in advanced breast cancer patients. Serious skeletal-related events (SREs) caused by bone metastasis have a decisive impact on the life expectancy of breast cancer patients, making breast cancer almost incurable. Metastatic breast cancer cell induced pathological osteoclastogenesis is a key driver of bone metastasis and osteolytic bone lesions. We previously reported that gold clusters can prevent inflammation induced osteoclastogenesis and osteolysis in vivo. In this study, we investigated the effects of a BSA-coated gold cluster on metastatic breast cancer-induced osteoclastogenesis in vitro and tumor-induced osteolysis in vivo, and elucidated its possible mechanism.

In drug design, the design and manufacture of safe and effective compounds is a long-term, complex, and complicated process. Therefore, developing a new rapid and generalizable drug design method is of great value. This study aimed to propose a general model based on reinforcement learning combined with drug-target interaction, which could be used to design new molecules according to different protein targets. The method adopted recurrent neural network molecular modeling and took the drug-target affinity model as the reward function of optimal molecular generation. It did not need to know the three-dimensional structure and active sites of protein targets but only required the information of a one-dimensional amino acid sequence. This approach was demonstrated to produce drugs highly similar to marketed drugs and design molecules with a better binding energy.

Background: Accurate localization and classification of intracerebral hemorrhage (ICH) lesions are of great significance for the treatment and prognosis of patients with ICH. The purpose of this study is to develop a symmetric prior knowledge based deep learning model to segment ICH lesions in computed tomography (CT).Methods: A novel symmetric Transformer network (Sym-TransNet) is designed to segment ICH lesions in CT images. A cohort of 1,157 patients diagnosed with ICH is established to train (n = 857), validate (n = 100), and test (n = 200) the Sym-TransNet. A healthy cohort of 200 subjects is added, establishing a test set with balanced positive and negative cases (n = 400), to further evaluate the accuracy, sensitivity, and specificity of the diagnosis of ICH. The segmentation results are obtained after data pre-processing and Sym-TransNet. The DICE coefficient is used to evaluate the similarity between the segmentation results and the segmentation gold standard. Furthermore, some recent deep learning methods are reproduced to compare with Sym-TransNet, and statistical analysis is performed to prove the statistical significance of the proposed method. Ablation experiments are conducted to prove that each component in Sym-TransNet could effectively improve the DICE coefficient of ICH lesions.Results: For the segmentation of ICH lesions, the DICE coefficient of Sym-TransNet is 0.716 ± 0.031 in the test set which contains 200 CT images of ICH. The DICE coefficients of five subtypes of ICH, including intraparenchymal hemorrhage (IPH), intraventricular hemorrhage (IVH), extradural hemorrhage (EDH), subdural hemorrhage (SDH), and subarachnoid hemorrhage (SAH), are 0.784 ± 0.039, 0.680 ± 0.049, 0.359 ± 0.186, 0.534 ± 0.455, and 0.337 ± 0.044, respectively. Statistical results show that the proposed Sym-TransNet can significantly improve the DICE coefficient of ICH lesions in most cases. In addition, the accuracy, sensitivity, and specificity of Sym-TransNet in the diagnosis of ICH in 400 CT images are 91.25%, 98.50%, and 84.00%, respectively.Conclusion: Compared with recent mainstream deep learning methods, the proposed Sym-TransNet can segment and identify different types of lesions from CT images of ICH patients more effectively. Moreover, the Sym-TransNet can diagnose ICH more stably and efficiently, which has clinical application prospects.