With the rapid advancement of synthetic biology, CRISPR-Cas systems have emerged as a powerful tool for gene editing, demonstrating significant potential in various fields, including medicine, agriculture, and industrial biotechnology. This review comprehensively summarizes the significant progress in applying artificial intelligence (AI) technologies to the design, mining, and modification of CRISPR-Cas systems. AI technologies, especially machine learning, have revolutionized sgRNA design by analyzing high-throughput sequencing data, thereby improving the editing efficiency and predicting off-target effects with high accuracy. Furthermore, this paper explores the role of AI in sgRNA design and evaluation, highlighting its contributions to the annotation and mining of CRISPR arrays and Cas proteins, as well as its potential for modifying key proteins involved in gene editing. These advancements have not only improved the efficiency and precision of gene editing but also expanded the horizons of genome engineering, paving the way for intelligent and precise genome editing.
CRISPR-Cas Systems/genetics* ; Artificial Intelligence ; Gene Editing/methods* ; RNA, Guide, CRISPR-Cas Systems/genetics* ; Machine Learning ; Humans ; Genetic Engineering/methods* ; Synthetic Biology

Objective To compare and find an optimal model for predicting the risk of DKD occurrence in patients with type 2 diabetes mellitus(T2DM).Methods A total of 2005 patients with T2DM were enrolled in this study from The Second Hospital of Shijiazhuang City during December 2017 to December 2022.All the subjects were divided into a training set(n=1403)and a validation set(n=602)according to the ratio of 3∶1 by simple random sampling.With the occurrence of DKD as the outcome variablein the training set,important feature variables were screened by LASSO regression.Six different machine learning models were established according to the feature variables,thenthe optimal model was determined by comparison,and anonlinerisk predictor for DKD occurrence was constructed in patients with T2DM.Results Taking the occurrence of DKD as the outcome variable in the training set,the results of LASSO regression analysis showed that the optimal value of the model was 10-fold cross validation lambda.1se=0.01662473,and 15 characteristic variables with nonzero coefficient were screened out to be related to the occurrence of DKD.The data included sex,age,family history of DM,DM duration,LDL-C,HbA1c,WBC,PDW,Scr,urine α1-microglobulin,urine β2-microglobulin,urine microalbumin,hypertension,hypokalemia,and DR.In the training set and validation set,the prediction performance of XGBoost model was better than that of other models(AUC=0.872,0.893,95%CI 0.853～0.891,0.865～0.921),the sensitivity was 0.779,0.863,and the specificity was 0.721,0.758,respectively.The F1 scores were 0.774 and 0.787.DCA analysis showed that the XGBoost model had a greater net benefit and threshold probability.According to the XGBoost model,the online predictor of DKD risk in T2DM patients was laid out,and two patients were selected for application,the results showed that the predictive value of the model was 0.185 in non-DKD patients,and the predictive value was 0.510 in DKD patients.Conclusions The XGBoost model is the best model for predicting the occurrence of DKD in T2DM patients,and an online predictor was successfully built.

Objective To compare and find an optimal model for predicting the risk of DKD occurrence in patients with type 2 diabetes mellitus(T2DM).Methods A total of 2005 patients with T2DM were enrolled in this study from The Second Hospital of Shijiazhuang City during December 2017 to December 2022.All the subjects were divided into a training set(n=1403)and a validation set(n=602)according to the ratio of 3∶1 by simple random sampling.With the occurrence of DKD as the outcome variablein the training set,important feature variables were screened by LASSO regression.Six different machine learning models were established according to the feature variables,thenthe optimal model was determined by comparison,and anonlinerisk predictor for DKD occurrence was constructed in patients with T2DM.Results Taking the occurrence of DKD as the outcome variable in the training set,the results of LASSO regression analysis showed that the optimal value of the model was 10-fold cross validation lambda.1se=0.01662473,and 15 characteristic variables with nonzero coefficient were screened out to be related to the occurrence of DKD.The data included sex,age,family history of DM,DM duration,LDL-C,HbA1c,WBC,PDW,Scr,urine α1-microglobulin,urine β2-microglobulin,urine microalbumin,hypertension,hypokalemia,and DR.In the training set and validation set,the prediction performance of XGBoost model was better than that of other models(AUC=0.872,0.893,95%CI 0.853～0.891,0.865～0.921),the sensitivity was 0.779,0.863,and the specificity was 0.721,0.758,respectively.The F1 scores were 0.774 and 0.787.DCA analysis showed that the XGBoost model had a greater net benefit and threshold probability.According to the XGBoost model,the online predictor of DKD risk in T2DM patients was laid out,and two patients were selected for application,the results showed that the predictive value of the model was 0.185 in non-DKD patients,and the predictive value was 0.510 in DKD patients.Conclusions The XGBoost model is the best model for predicting the occurrence of DKD in T2DM patients,and an online predictor was successfully built.

Objective To investigate the prevalence and risk factors of diabetes and prediabetes in Jingyuan County in Ningxia. Methods A cross-sectional survey including 10 639 participants (18-88 years of age) with a multistage sampling was conducted in Jingyuan County between January, 2014 and April, 2015. Questionnaires, physical examinations, and laboratory tests were included in the survey. Results Among all the subjects, 10 491 participants (men: 4 826, women: 5 665) with complete data were included in the analysis. The standardized prevalence of diabetes and prediabetes was 4.2% (men: 3.9%, women: 4.5%) and 8.8% (men: 7.6%, women 10.3%), respectively, in which the standardized prevalence of diabetes was higher in Hui (4.5%) than that in Han (3.5%) (P<0.05). Logistic regression analyses showed that age, family history of diabetes, overweight/obesity, hypertriglyceridemia and hypertension were positively associated with prediabetes and diabetes with the odds ratios being 1.60 and 2.14 (age, P<0.001), 1.40 and 3.32 (family history, P< 0.05), 1.47 and 1.57 (overweight/obesity, P< 0.001), 1.88 and 2.55 (hypertriglyceridemia, P<0.001), 1.44 and 1.89 (hypertension, P<0.001), respectively. Conclusions The prevalence of diabetes was relatively low in the rural area in Ningxia. However, it is still essential to take active interventions in people at high risk of diabetes in order to prevent the incident diabetes.

Objective To investigate the safety of autologous bone marrow mesenchymal stem cells (ABMSCs) transplantation into the subretinal space for the treatment of proliferative diabetic retinopathy (PDR). Methods The clinical data of four PDR patients ( four eyes ) who received ABMSCs transplantation into the subretinal space were collected in Army Medical University,Southwest Eye Hospital from March 2014 to December 2015,including 3 males and 1 female;the average age was 55 years old;the average course of diabetes was 10 years, and the blood glucoses were all well controlled before treatment. All the patients underwent conventional ophthalmologic examination,and visual acuity,slit lamp microscope,color fundus photography,fluorescein angiography (FFA) and optical coherence tomography ( OCT) examination were performed at 1 week,1 month,3 months,6 months,9 months and 12 months after surgery. This study protocol was approved by Ethic Committee of Army Medical University,Southwest Eye Hospital (No. 2013-34). Results Four patients diagnosed as PDR were enrolled in this study. All patients were performed ABMSC transplantation,and no one felt discomfort after treatment. FFA and OCT showed that the transplanted cells were present in the subretinal space until 1 month after transplantation. The macular edema of one patient diagnosed as macular edema preoperatively was relived gradually after transplantation,and the effects lasted 3 months after transplantation. The preoperative best corrected visual acuity (BCVA) of the two patients were improved from hand movement and finger counting to 20/20 ( 84 ETDRS) and 20/200 ( 38 ETDRS) after transplantation,respectively,and the visual acuities of the other two eyes were both stable. All patients underwent panretinal photocoagulatio 3 months after transplantation, and the follow-up treatment complied with the routine of post-vitrectomy for DR, no complications occurred during the follow-up period. Conclusions Subretinal transplantation of ABMSCs for PDR is safe. The transplanted cells show local anti-inflammatory effect,and no effect on cell proliferation or circulatory improvement are observed.

Objective To explore the application effect of risk management in the continuous renal replacement therapy ( CRRT ) of patients in emergency intensive care unit ( EICU ) . Methods Totally 74 critical patients with CRRT that admitted in the EICU of Xuanwu Hospital of Capital Medical University from February 2010 to December 2015 were selected by random number table method and were divided into the observation group and the control group, with 37 cases in each group. Patients in the control group received routine nursing, while patients in the observation group received risk management based on the routine nursing method. The treatment time, the situation of anxiety and depression, and family members′satisfaction to nursing between two groups were compared. Results In the observation, the CRRT treatment time of patients was (12. 73±3.13) d, the score of self-rating anxiety scale (SAS) was (33.12±6.94), and the score of self-rating depression scale (SDS) was (38.21±5.56);while in the control group, the treatment time was (12.73±3.13) d, the SAS score was (51.56±1.81), and the SDS score was (52.37±1.36) (t=10.235,8.274,9.024;P<0. 05) . Family members′satisfaction to nursing in the observation group was 97. 30%, and it was 81.08% in the control group (χ2=5.045,P<0.05). Conclusions Risk management can shorten the CRRT treatment time, relieve patients′negative emotions, and improve family members′satisfaction.

Objective: To explore the effect of ulinastatin on anti-inflammation and pulmonary function protection with its mechanism for infants at cardiopulmonary bypass surgery. Methods: A total of 38 infants with ventricular septal defect undergoing cardiac operation were randomly divided into 2 groups. Ulinastatin group, the patients received uliastatin 20 000 U/kg,n=20 and Control group, the patients received the same volume of normal saline,n=18. The serum levels of TNF-α, IL-2, IL-l0 were examined at 4 time points: 5 min before skin incision (T1), immediate opening of aorta (T2), 4 hours after operation (T3) and 24 hours after operation (T4). The expressions of CD4+CD45+ T cells and CD4+Foxp3+ T cells were measured at T4. The respiratory index and oxygenation index at 4 time points were compared between 2 groups. Results: Compared with Control group, Ulinastatin group had the lower levels of TNF-α, IL-2 and higher level of IL-l0 at T2, T3, T4; Ulinastatin group also had the higher oxygenation index and lower respiratory index at T2, T3, T4, allP<0.05. Ulinastatin group had less expression of CD4+CD45+ T cells (35.98 ± 3.67)% than Control group (41.94 ± 4.56)% , and more expression of CD4+Foxp3+ T cells (19.65 ± 3.45)% than Control group (6.45 ± 1.47)%,P<0.05-P<0.01. Conclusion: Ulinastatin may improve the differentiation from CD4+CD45+ T cell to Foxp3+CD4+ T cell, down regulating inlfammatory response and protecting pulmonary function for infants at cardiopulmonary bypass surgery.