In protein engineering, while computational models are increasingly used to predict mutation effects, their evaluations primarily rely on high-throughput deep mutational scanning (DMS) experiments that use surrogate readouts, which may not adequately capture the complex biochemical properties of interest. Many proteins and their functions cannot be assessed through high-throughput methods due to technical limitations or the nature of the desired properties, and this is particularly true for the real industrial application scenario. Therefore, the desired testing datasets, will be small-size (∼10-100) experimental data for each protein, and involve as many proteins as possible and as many properties as possible, which is, however, lacking. Here, we present VenusMutHub, a comprehensive benchmark study using 905 small-scale experimental datasets curated from published literature and public databases, spanning 527 proteins across diverse functional properties including stability, activity, binding affinity, and selectivity. These datasets feature direct biochemical measurements rather than surrogate readouts, providing a more rigorous assessment of model performance in predicting mutations that affect specific molecular functions. We evaluate 23 computational models across various methodological paradigms, such as sequence-based, structure-informed and evolutionary approaches. This benchmark provides practical guidance for selecting appropriate prediction methods in protein engineering applications where accurate prediction of specific functional properties is crucial.

Objective To investigate the risk factors and treatment efficiency for lung cancer patients with venous thromboembolism (VTE). Methods Total 282 cases of lung cancer patients with VTE were enrolled into two groups , including the VTE group and the non-VTE group , for comparation analysis based on a series of clinical data. Results The occupation rate of adenocarcinoma and Ⅳ period were 65.28% and 87.50% in VTE group, respectively, higher than those of 51.43% and 75.71% in the non-VTE group. The increased rate of blood viscosity and d-dimer respectively were 65.28% and 70.83%, higher than those of 51.43% and 56.67% in the non-VTE group, with significant differences (P < 0.05, respectively). Result of logistic regression analysis showed that tumor stage , d-dimer levels , smoking , age , and blood viscosity levels were highly correlated with venous thrombosis in patients with lung cancer, and the OR value among them was 3.802, 2.339, 5.814, 3.875 and 6.404, respectively, with significant differencees (P < 0.05, respectively). Conclusions Lung adenocarcinoma with stage Ⅳ, smoking , age and increase of blood viscosity and d-dimer were the important risk factors for VTE in patients with lung cancer chemotherapy. Timely assessment of risk factors and early anticoagulation therapy in lung cancer patients with venous thromboembolism associated with VTE can improve the treatment efficacy and reduce the complications.

Objective To explore the pathogenesis of juvenile disorders of spine facet joints and to clarify the diagnosis by concluding the clinical and imaging manifestations.Methods Retrospectively analyzed imaging data of 250 patients from 10～30 years with disorders of spine facet joints including X-ray and CT and MRI.Results Reasons of juvenile disorders of spine facet joints has unique imaging manifestations of asymmetric of small joints and joint surface hyperplasia like pen,of nonspecial inflammation in surrounding soft tissue.Conclusions Imaging can diagnose and differentiate diagnosis juvenile disorder of spine facet joints.X-ray is also the primary method.Not only.CT or MRI image can more clearly display the changes of spine facet joints and surrounding soft tissue,but also differentiate diagnosis disc henaiation and other diseases.