Objective: To understand the nutritional literacy level and associated factors of primary and secondary school students in Beijing, so as to provide a scientific basis for improving student nutrition. Methods: From October 2022 to May 2023, a multi stage cluster random sampling method was employed to select a total of 14 568 primary, junior and senior high school students from 16 districts (ecluding the Economic Technological Development area) in Beijing. Through a survey questionnaire on nutritional literacy and dietary hehavior of school age children, basic information as well as data on nutritional literacy levels across four dimensions:nutrition related knowledge concepts, food selection, food preparation, and food intake dimensions were obtained. The Wilcoxon rank sum test, Kruskal-Wallis test, Spearman correlation analysis, Chi square test and binary Logistic regression were used for the analysis. Results: The median total score of nutritional literacy among primary and secondary school students in Beijing was 68.8. Approximately 26.0% of primary and secondary school students achieved nutritional literacy standards. The median scores and rates of meeting the standards for nutrition related knowledge concepts, food selection, food preparation and food intake dimensions were 23.0, 42.1%; 17.0, 27.4%; 6.5, 33.5%; 23.0, 33.3%, respectively. There were positive correlations between all pairs of the four dimensions ( r=0.33-0.49, P <0.05). The results of multiple Logistic regression analysis showed that primary school students, junior high school students, female students, suburban students, caregivers with a college education level and a bachelor s degree or above were the positive arrelation factors that promoted the achievement of nutritional literacy standards ( OR =2.21, 1.39, 1.18, 1.27, 1.42, 1.66, P <0.05). Conclusion The literacy level of primary and secondary school students in Beijing needs to be significantly improved. School stage, gender, region and caregiver s education level are associated factors.

[Objective] To analyze the characteristics of HLA-A, HLA-B, HLA-DRB1, HLA-C, HLA-DQB1 and HLA-DPB1 allele polymorphisms among cord blood donors in Guangdong population. [Methods] According to HLA high resolution genotyping data of 32 717 samples of cord blood donors from Guangdong Cord Blood Bank from January 2009 to December 2023, the allele frequencies were calculated by direct counting and the haplotype frequencies were calculated by using Arlequin software 3.5.2.2. [Results] A total of 102 HLA-A alleles, 160 HLA-B alleles and 96 HLA-DRB1 alleles were detected in 32 717 samples. Among them, 46 HLA-DPB1 alleles were detected in 5 377 samples, and 66 HLA-C alleles and 35 HLA-DQB1 alleles were detected in 13 310 samples. The most common alleles were HLA-A^*11∶01 (28.96%), HLA-B^*40∶01 (15.23%), HLA-DRB1^*09∶01 (15.72%), HLA-C^*01∶02 (19.40%), HLA-DQB1^*03∶01 (20.85%) and HLA-DPB1^*05∶01 (40.79%). The most common 3 loci haplotype and 6 loci haplotype were HLA-A^*02∶07-B^*46∶01-DRB1^*09∶01 (1.55%), HLA-C^*07∶02-DQB1^*03∶01-DPB1^*05∶01 (1.77%), HLA-DRB1^*09∶01-DQB1^*03∶03-DPB1^*05∶01 (3.31%) and HLA-A^*02∶07-B^*46∶01-C^*01∶02-DRB1^*09∶01-DQB1^*03∶03-DPB1^*05∶01 (0.30%). [Conclusion] In this study, the allele and haplotype frequencies of HLA-A, HLA-B, HLA-DRB1, HLA-C, HLA-DQB1 and HLA-DPB1 were obtained in the cord blood donors in Guangdong, which can provide important reference data for HLA gene related research and the selection of donors for clinical application.

Objective:To analyze the sensitivity of cytoplasmic light-chain immunofluorescence with fluorescence in situ hybridization in bone marrow smears (new FISH) for detecting cytogenetic abnormalities in multiple myeloma (MM) .Methods:42 MM patients admitted to the First Affiliated Hospital of Nanjing Medical University from April 2022 to October 2023 were enrolled. The patients with MM were detected by new FISH and CD138 immunomagnetic bead sorting technology combined with FISH (MACS-FISH) or cytoplasmic immunoglobulin FISH (cIg-FISH) to analyze cytogenetic detection results using combination probes which included 1q21/1p32, p53, IgH, IgH/FGFR3 [t (4;14) ], and IgH/MAF [t (14;16) ].Results:In 23 patients with MM, the abnormality detection rates of cIg-FISH and new FISH were 95.7% and 100.0%, respectively ( P>0.05). The detection rates of 1q21+, 1p32-, p53 deletion, and IgH abnormalities by cIg-FISH and new FISH were consistent, which were 52.2%, 8.7%, 17.4%, and 65.2%, respectively. The results of the two methods further performed with t (4;14) and t (14;16) in patients with IgH abnormalities were identical. The positive rate of t (4;14) was 26.7%, whereas t (14;16) was not detected. In 19 patients with MM, the abnormality detection rates of MACS-FISH and new FISH were 73.7% and 63.2%, respectively ( P>0.05). The positivity rate of 1q21+, 1p32- and IgH abnormalities detected by MACS-FISH were slightly higher than those detected by new FISH; however, the differences were not statistically significant (all P values >0.05) . Conclusion:The new FISH method has a higher detection rate of cytogenetic abnormalities in patients with MM and has good consistency with MACS-FISH and cIg-FISH.

Objective:To explore the diagnostic value of ultrasound shear wave elastography and portal vein hemodynamic parameters for chronic hepatitis and liver fibrosis.Methods:The clinical data of 48 hospitalized patients with chronic hepatitis diagnosed in Fuyang Second People's Hospital from May 2019 to July 2020 were collected and analyzed retrospectively. The patients voluntarily received portal vein hemodynamics and ultrasonic shear wave elastography. According to Scheuer's method, 48 patients were classified into 5 stages of liver fibrosis, including 10 patients in S0 stage, 13 patients in S1 stage, 10 patients in S2 stage, 10 patients in S3 stage and 5 patients in S4 stage. The average velocity of portal vein, peak portal vein velocity (PVVmax), portal vein diameter (PVD), liver stiffness measurement (LSM) and Young's modulus of liver were compared. Pathological and liver biopsy was the gold standard to analyze the sensitivity and specificity of various detection methods. The normally distributed measurement data were expressed as xˉ± s, the comparison between multiple groups was performed by one-way ANOVA, and the pairwise comparison was performed by LSD-t test. Spearman method was used to analyze the correlation between liver function classification and various parameters. ROC curve was used to analyze the diagnostic value of ultrasonic shear wave elastography, portal vein hemodynamics and combined detection in predicting liver fibrosis in chronic hepatitis. Results:In the staging of liver fibrosis, the LSM of the patients in the S0 stage was (5.29±0.19) kPa, and the Young's modulus of the liver was (21.65±2.35) kPa; the LSM of the patients in the S1 stage was (6.38±1.25) kPa, and the Young's modulus of the liver ( 22.89±3.19) kPa, LSM (9.76±1.33) kPa and hepatic Young's modulus (23.77±3.52) kPa in S2 group, LSM (15.44±2.44) kPa, hepatic Young's modulus (25.14±2.29) in S3 group, LSM (18.08±1.22) kPa and hepatic Young's modulus (27.94±2.58) kPa in patients with S4 stage, the differences between groups were statistically significant (F values ??were 115.47, 4.84, P values?were <0.001, 0.003), and the difference was statistically significant (all P<0.05). The average flow velocity of patients in S0 stage was (20.56±4.21) cm/s, PVVmax (22.19±4.33) cm/s, the average flow velocity of S1 stage was (18.39±3.79) cm/s, PVVmax (20.69±3.12) cm/s, and the average of S2 stage Flow velocity (13.46±2.21) cm/s, PVVmax (16.65±2.54) cm/s, average flow velocity in S3 stage (10.56±2.85) cm/s, PVVmax (13.42±2.46) cm/s, average flow velocity in S4 stage (8.15±1.65) cm/s, PVVmax (11.89±2.89) cm/s, the difference between the groups was statistically significant (F values were 21.35, 16.96, all P<0.001), and the difference between the two groups was statistically significant (all P<0.05). Correlation analysis by Spearman method showed that liver function grades were negatively correlated with average flow velocity and PVVmax (r values ?were -0.75 and -0.88, respectively; all P<0.001), and were positively correlated with liver Young's modulus and LSM. (r values ??were 0.54 and 0.86, respectively; all P<0.001). According to the ROC curve analysis, the AUC predicted by ultrasonic shear wave elastography was 0.75, AUC predicted by portal vein hemodynamics predicts was 0.68, and AUC predicted by combined detection predicts was 0.94. Conclusion:The combination of portal vein hemodynamics and ultrasonic shear wave elastography has a certain diagnostic power for the assessment of chronic hepatitis and liver fibrosis, with high specificity and sensitivity.

Objective:To investigate the clinical significance of cc-chemokine receptor 7 (CCR7) as a potential diagnostic or differential marker for chronic lymphocytic leukemia (CLL).Methods:A total number of 643 patients with B-cell chronic lymphoproliferative diseases (B-CLPD) admitted to the First Affiliated Hospital of Nanjing Medical University from January 2015 to December 2018 were enrolled. The patients included 327 cases of CLL, 58 cases of mantle cell lymphoma (MCL), 34 cases of follicular lymphoma (FL), 36 cases of marginal zone lymphoma (MZL), 10 cases of hair-cell leukemia or its variants (HCL/HCLV-v), 40 cases of Waldorf′s macroglobulinemia (WM), 48 cases of CD5 +B-cell chronic lymphoproliferative disease unclassified (B-CLPD-U) and 90 cases of CD5 -B-CLPD-U. At the same time, 20 samples from healthy people from the medical examination center of our hospital were used as normal controls. Flow cytometry was used to detect the immune-phenotype and CCR7 expression level in B-CLPD patients, and Fluorescence in situ hybridization (FISH) was used to analyze the genomic alterations: the ataxia telangiectasia mutant gene (ATM) deletion, the 13q14 deletion, the P53 deletion and trisomy 12. Sanger sequencing was used to analyze gene mutations of splicing factor 3B subunit 1 (SF3B1), NOTCH1, tumor protein 53 (TP53) and immunoglobulin heavy chain variable region (IGHV). Measurement data were compared by Mann-Whitney test, and the positive rates were compared by chi-square test. The diagnostic value and optimal positive cutoff value of CCR7 were calculated using receiver operating characteristic (ROC) curve. Results:The positive rates of CCR7 expression in typical CLL and atypical CLL were 90.8% (257/283) and 84.1% (37/44), respectively, and there was no significant difference of the positive rates (χ 2=1.228, P=0.268) between groups. The positive expression rates of CCR7 in CLL, MCL, CD5 +B-CLPD-U, CD5 -B-CLPD-U, FL, WM, HCL/HCL-v and MZL were 89.9% (294/327), 10.3% (6/58), 6.3% (3/48), 8.9% (8/90), 0, 0, 0 and 13.9% (5/36) respectively, and the median mean fluorescence intensity (MFI) was 278 (246, 307), 114 (106, 128), 112 (106, 117), 110 (104, 121), 108 (105, 119), 111 (105, 124), 112 (108, 115) and 109 (105, 120) respectively. Compared with CLL, the positive expression rates of CCR7 in other types of B-CLPDs were lower significantly (χ 2=181.3, 177.8, 232, 164.7, 180.8, 62.6, 129, P<0.01). In addition, the sensitivity, specificity and accuracy of CCR7 for distinguishing CLL from other types of B-CLPD were 89.9%, 93.0% and 92.3%, respectively. The positive expression rate of CD49d in CCR7 +CLL patients was 13.9%, which was significantly lower than that in CCR7 -CLL patients (42.1%) (χ 2=7.6, P=0.01). The coincidence rate of 13q14 deletion was 50.3% in CCR7 +CLL patients, which was significantly higher than that in CCR7 -CLL patients (20%) (χ 2=6.56, P=0.01). Conclusions:The CC-chemokine receptor 7 (CCR7) antigen is an effective marker for the diagnosis and identification of chronic lymphocytic leukemia (CLL). The expression level of CCR7 in clinical specimens can distinguish CLL from other pathological subtypes of B-CLPDs.

Objective:The clinical characteristics and prognosis of 20 patients with small B-lymphocyte proliferative disease with t (14;19) (q32; q13) were analyzed to improve the understanding of such rare cases.Methods:The clinical data of 20 patients with t (14; 19) (q32; q13) small B lymphocyte proliferative disease treated in the First Affiliated Hospital of Nanjing Medical University from April 2013 to December 2020 were retrospectively collected and analyzed. Among them, 10 cases were chronic lymphocytic leukemia (CLL) and 10 cases were other small B-cell malignancies.Results:Among the 20 cases, 10 were male and 10 were female, and the median age at diagnosis was 53.5 (35-88) years old. All patients had absolute lymphocytosis, 19 patients had lymphadenopathy, and 10 patients had splenomegaly. With a median follow-up of 36 (4-163) months, three patients died, and 11 patients had a time to treatment (TTT) ≤12 months. Ten patients (50%) were accompanied by +12, two patients (2/17, 12%) were accompanied by 13q-. Moreover, we found that t (14;19) was associated with unmutated immunoglobulin heavy-chain variable (IGHV) somatic mutation (17/19, 89%) and a biased use of IGHV4-39 (7/17, 41%) was observed. Next-generation sequencing detected one or more gene mutations in 14 (14/17, 82%) cases and a total of 25 gene mutations had been revealed, of which the most frequent were NOTCH1 (35%) , followed by SF3B1 (24%) and KMT2D (18%) . For 10 CLL patients, five (50%) were defined as Rai Ⅲ/Binet C. It is noteworthy that among the 20 cases, two cases actually involved Richter transformation.Conclusions:Small B-cell malignant tumors with abnormal t (14; 19) show unique clinical biological characteristics, often accompanied by a variety of adverse prognostic factors, and tend to have an aggressive clinical course.

Objective:To explore the clinical features of acute pancreatitis (AP) complicated with portal vein system thrombosis (PVST) and the clinical prediction of symptomatic PVST.Methods:From January 2014 to December 2019, at First Affiliated Hospital and Second Affiliated Hospital of Kunming Medical University, 152 hospitalized patients who met the diagnostic criteria of AP complicated with PVST and had complete clinical data were retrospectively analyzed, and the clinical characteristics of them were analyzed. According to whether there were clinical manifestations caused by PVST (esophago-gastric variceal bleeding, persistent ascites, intestinal ischemia), AP patients complicated with PVST were divided into symptomatic group ( n=48) and asymptomatic group ( n=104). The differences in general information, laboratory test indicators, acute physiology and chronic health evaluation Ⅱ (APACHE Ⅱ), Balthazar computed tomography (CT) score, local and systemic complications were compared between symptomatic group and asymptomatic group. Two independent sample t test, two sample rank sum test, and chi-square test were used for statistical analysis. The binary logistic regression was used for multivariate analysis. Results:The severe acute pancreatitis (SAP) complicated with PVST was common, accounted for 73.0% (111/152), and the hospital mortality rate was 14.5% (22/152). The splenic vein (46.1%, 70/152) was the most common single vessel involved. The hospital stay of the symptomatic group was longer than that of the asymptomatic group, the hospitalization costs and hospital mortality of the symptomatic group were both higher than those of the asymptomatic group ((26.31±19.38) d vs. (15.11±9.31) d, (103 463.68±15 312.74) yuan vs. (37 199.38±4 647.17) yuan, 25.0%, 12/48 vs. 9.6%, 10/104, respectively), and the differences were statistically significant ( t=-3.809 and -4.141, χ2=6.280; all P<0.05). The lactic acid dehydrogenase, C-reactive protein, and prothrombin time of the symptomatic group were all higher than those of the asymptomatic group (4.78 μmol·s -1·L -1, 2.96 μmol·s -1·L -1 to 7.82 μmol·s -1·L -1 vs. 4.42 μmol·s -1·L -1, 3.29 μmol·s -1·L -1 to 9.30 μmol·s -1·L -1; 69.53 mg/L, 29.49 mg/L to 147.14 mg/L vs. 40.90 mg/L, 8.88 mg/L to 104.89 mg/L; (16.88±8.23) s vs. (14.12±1.59) s), however the hematocrit and blood calcium in the symptomatic group were both lower than those of the asymptomatic group ((34.97±8.96)% vs. (39.18±7.17)%, (2.01±0.32) mmol/L vs. (2.17±0.19) mmol/L), and the differences were all statistically significant ( Z=-2.067 and -1.977, t=-2.281, 3.072 and 3.083; all P<0.05). The scores of APACHE Ⅱand Balthazar CT, the rate of local complications of pancreatic necrosis, and systemic complications including abdominal hemorrhage, septic shock, acute respiratory distress syndrome, lung infection and pleural effusion of the symptomatic group were higher than those of the asymptomatic group (7.21±3.84 vs. 5.27±2.31, 7.10±1.57 vs. 4.83±1.87, 87.5%, 42/48 vs. 28.8%, 30/104; 10.4%, 5/48 vs. 1.9%, 2/104; 18.8%, 9/48 vs. 1.9%, 2/104; 25.0%, 12/48 vs. 3.8%, 4/104; 91.7%, 44/48 vs. 60.6%, 63/104; 85.4%, 41/48 vs. 49.0%, 51/104; respectively), and the differences were statistically significant ( t=-3.241 and -7.331, χ2=45.320, 5.393, 13.852, 15.604, 15.323 and 18.191; all P<0.05). The results of binary logistic regression showed that Balthazar CT score was an independent risk factor for symptomatic PVST ( P<0.01), and odds ratio (95% confidence interval) was 1.79 (1.41 to 2.29). Conclusions:Balthazar CT score is an influencing factor of symptomatic PVST in AP patients, and patients with high scores should be treated early to improve the prognosis.

Objective:To establish and internally validate a visualized model for predicting the severity of acute pancreatitis (AP).Methods:From September 1st 2017 to August 31st 2020, 600 patients with AP diagnosed in the First Affiliated Hospital of Kunming Medical University were enrolled. According to the Atlanta classification of AP, the 600 patients were divided into severe acute pancreatitis (SAP) group (128 cases) and non-severe acute pancreatitis (NSAP) group (472 cases). The general clinical data (age, gender, body mass index, etc), laboratory indicators (fasting blood glucose, urea nitrogen, creatinine, etc.), complicated with ascites or pleural effusion, acute physiology and chronic health evaluation Ⅱ (APACHE Ⅱ) scores and bedside index of severity in acute pancreatitis (BISAP) score between the two groups were compared. The potential predictors of SAP were screened with least absolute shrinkage and selection operator (LASSO). The screened predictors were included in the multivariate logistic regression analysis to establish the logistic regression model. The operation characteristic curves of the model, APACHE Ⅱ scores and BISAP were drawn, the discriminative capability of the model was evaluated by comparing the area under the curve (AUC). Calibration, Hosmer-Lemesshow test and decision curve analysis (DCA) were used to evaluate the accuracy and clinical practicability of the prediction model. Bootstrap was used for internally validation of the model. Independent sample t test, Wilcoxon test and chi-square test were used for statistical analysis. Results:The difference of gender composition ratio between SAP and NSAP group was statistically significant ( χ2=4.092, P<0.05). The fatality rate of SAP group was higher than that of NSAP group(21.1%, 27/128 vs. 0, 0/472); the length of hospital stay of SAP group was longer than that of NSAP group((20.33±16.21) d vs. (8.42±4.26) d); the hospitalization cost, fasting blood glucose level, urea nitrogen level, creatinine level, C-reactive protein(CRP) level, D-dimer level, fibrinogen level, white blood cell count, percentage of neutrophils, neutrophil-lymphocyte ratio, APACHEⅡ and BISAP scores, the incidence of complicated with pleural effusion or ascites and the constituent ratio of alcoholic etiology of SAP group were all higher than those of NASP group (44 837.58 yuan (23 017.73 yuan, 102 579.77 yuan) vs. 12 301.46 yuan (8 649.26 yuan, 18 823.88 yuan); (10.48±4.84) mmol/L vs. (8.45±4.80) mmol/L; (8.80±6.50) mmol/L vs. (4.90±2.33) mmol/L; (139.56±127.75) mmol/L vs. (80.05±38.54) mmol/L; (187.33±87.25) mg/L vs. (90.81±82.53) mg/L; 5.19 mg/L (2.96 mg/L, 8.52 mg/L) vs.1.29 mg/L (0.53 mg/L, 2.87 mg/L); 6.13 mg/L (4.64 mg/L, 7.31 mg/L) vs. 4.58 mg/L (3.50 mg/L, 5.98 mg/L); (14.87±5.82)×10 9/L vs. (11.79±4.86)×10 9/L; 0.84±0.12 vs.0.78±0.12; 13.16±7.57 vs. 8.77±7.28; 9.80±6.09 vs. 3.79±2.59; 2.12±0.89 vs. 1.04±0.78; 65.6%, 84/128 vs. 12.9%, 61/472; 70.3%, 90/128 vs. 20.3%, 96/472; 18.8%, 24/128 vs. 11.4%, 54/472); serum albumin level, blood calcium level, and hematocrit level of SAP group were all lower than those of NSAP group ((30.86±4.95) g/L vs. (37.14±5.44) g/L; (1.98±0.31) mmol/L vs. (2.16±0.20) mmol/L; (42.40±8.67)% vs.(44.30±6.45)%), and the differences were all statistically significant ( χ2=99.403, t=8.235, Z=-13.330, t=4.239, 10.759, 5.207 and 11.227, Z=-11.406 and -6.234, t=6.097, 4.829, 6.011, 10.899 and 12.395, χ2=152.604, 117.563 and 4.757, t=-11.788, -6.180 and -2.310, all P<0.05). LASSO regression analysis screened out four predictors of CRP, urea nitrogen, D-dimer and ascites. The results of multivariate logistic regression analysis showed that CRP (odds ratio ( OR)=1.009, 95% (confidence interval) CI 1.006 to 1.012), urea nitrogen( OR=1.185, 95% CI 1.097 to 1.280), D-dimer( OR=1.166 95% CI 1.082 to 1.256), ascites ( OR= 4.848, 95% CI 2.829 to 8.307) were the independent predictors of SAP (all P<0.01). The AUC of the model (0.895 , 95% CI 0.865 to 0.926) was higher than those of the APACHE Ⅱ(AUC=0.835, 95% CI 0.791 to 0.878)and BISAP score (AUC=0.803, 95% CI 0.760 to 0.846), and the differences were statistically significant ( Z=2.578 and 4.466, both P<0.05). The results predicted by the model in the calibration chart and the Hosmer-Lemesshow test were highly consistent with the results of actual clinical observation. When the probability of SAP in the model was 10% to 95%, the DCA curve of the model was higher than the two extreme lines, which had certain clinical practical value. After bootstrap internal validation, the model had a high discrimination ability (AUC=0.892), and its predicted AP severity curve was still in good agreement with the actual clinical AP severity curve. Conclusion:The prediction model established based on CRP, urea nitrogen, D-dimer and ascites can predict the severity of AP, and help doctors to make more scientific clinical decision.

The etiology and pathogenesis of autoimmune hepatitis (AIH) remain unclear and are currently considered to be associated with genetic susceptibility and environmental factors. Regulatory T (Treg) cells play an immunosuppressive role by secreting IL-10 and TGFβ, while T helper 17 (Th17) cells mainly promote inflammatory response, suggesting that Treg cells, Th17 cells, and the dynamic balance between them may be involved in the development and progression of AIH; however, further studies are needed to explore related participation mechanisms. This article reviews the association between Treg/Th17 cells and AIH in recent years and elaborates on their mechanism of action and therapeutic targets.

The establishment of a landscape of enhancers across human cells is crucial to deciphering the mechanism of gene regulation, cell differentiation, and disease development. High-throughput experimental approaches, which contain successfully reported enhancers in typical cell lines, are still too costly and time-consuming to perform systematic identification of enhancers specific to different cell lines. Existing computational methods, capable of predicting regulatory elements purely relying on DNA sequences, lack the power of cell line-specific screening. Recent studies have suggested that chromatin accessibility of a DNA segment is closely related to its potential function in regulation, and thus may provide useful information in identifying regulatory elements. Motivated by the aforementioned understanding, we in-tegrate DNA sequences and chromatin accessibility data to accurately predict enhancers in a cell line-specific manner. We proposed DeepCAPE, a deep convolutional neural network to predict enhancers via the integration of DNA sequences and DNase-seq data. Benefitting from the well-designed feature extraction mechanism and skip connection strategy, our model not only consistently outperforms existing methods in the imbalanced classification of cell line-specific enhancers against background sequences, but also has the ability to self-adapt to different sizes of datasets. Besides, with the adoption of auto-encoder, our model is capable of making cross-cell line predictions. We further visualize kernels of the first convolutional layer and show the match of identified sequence signatures and known motifs. We finally demonstrate the potential ability of our model to explain functional implications of putative disease-associated genetic variants and discriminate disease-related enhancers. The source code and detailed tutorial of DeepCAPE are freely available at https://github.com/Sheng-quanChen/DeepCAPE.