Objective:To develop an artificial intelligence (AI)-based platelet review strategy to identify abnormal platelet histograms with no significant difference between initial impedance platelet count (PLT-I) and PLT-F results.Methods:This study included 5 119 routine blood analysis in Nanfang Hospital of Southern Medical University and its Ganzhou branch from July 2023 and March 2024. Specimens exhibiting abnormal platelet histograms and an initial platelet count >40×10?/L underwent review using the fluorescent platelet count (PLT-F) channel. Consistency of the results was defined as a difference between impedance platelet count (PLT-I) and PLT-F less than ±20% of the PLT-F results. A deep learning model was developed using platelet and red blood cell histogram data from a training set of 3 807 specimens. The model′s diagnostic performance was evaluated on an independent external validation set ( n=805) using receiver operating characteristic (ROC) curve analysis. Changes in the number of reviewed samples and sample turnaround time were analyzed to assess its clinical utility. Results:The deep learning model based on platelet and red blood cell histograms achieved an area under the ROC curve (AUC) of 0.854 in the training set. At a cutoff value of 0.1, the sensitivity was 0.954 and specificity was 0.358. The model could reduce review by 16.80% (190/1 131). In the validation set, the AUC was 0.805, with a sensitivity of 0.955 and specificity of 0.307, corresponding to a reduction of 17.41% (47/270) in reviewed specimens.Conclusion:The platelet review prediction model developed based on deep learning technology can efficiently identify samples with consistent results before and after review, reducing unnecessary reviews and shortening specimen testing time, thereby improving the efficiency of platelet test.

Liver diseases cannot be easily detected in the early stage， and although invasive diagnostic methods， such as liver biopsy， are relatively accurate， they tend to have a low degree of acceptance， which greatly limits the improvement in diagnosis and treatment techniques for liver diseases. Therefore， it is of great importance to search for new biomarkers and therapeutic targets. As an emerging biomarker for liquid biopsy， tRNA-derived small RNA （tsRNA） is abnormally expressed in various liver diseases including viral hepatitis， fatty liver disease， liver injury， and liver cancer， and it can affect the development and progression of liver diseases by regulating the biological functions such as gene expression， epigenetic regulation， and protein translation. This article reviews the origin， classification， and biological function of tsRNA， as well as the research advances in tsRNA as biomarkers and potential therapeutic targets for liver diseases， so as to provide ideas for the early diagnosis and treatment of liver diseases.

Antibody (Ab) humanization is critical to reduce immunogenicity and enhance efficacy in the preclinical phase of the development of therapeutic Abs originated from animal models. Computational suggestions have long been desired, but available tools focused on immunogenicity calculation of whole Ab sequences and sequence segments, missing the individual residue sites. This study introduces Site-specific Immunogenicity for Therapeutic Antibody (SITA), a novel computational framework that predicts B-cell immunogenicity score for not only the overall antibody, but also individual residues, based on a comprehensive set of amino acid descriptors characterizing physicochemical and spatial features for antibody structures. A transfer-learning-inspired framework was purposely adopted to overcome the scarcity of Ab-Ab structural complexes. On an independent testing dataset derived from 13 Ab-Ab structural complexes, SITA successfully predicted the epitope sites for Ab-Ab structures with a receiver operating characteristic (ROC)-area unver the ROC curve (AUC) of 0.85 and a precision-recall (PR)-AUC of 0.305 at the residue level. Furthermore, the SITA score can significantly distinguish immunogenicity levels of whole human Abs, therapeutic Abs and non-human-derived Abs. More importantly, analysis of an additional 25 therapeutic Abs revealed that over 70% of them were detected with decreased immunogenicity after modification compared to their parent variants. Among these, nearly 66% Abs successfully identified actual modification sites from the top five sites with the highest SITA scores, suggesting the ability of SITA scores for guide the humanization of antibody. Overall, these findings highlight the potential of SITA in optimizing immunogenicity assessments during the process of therapeutic antibody design.

Antibody humanization is critical to reduce immunogenicity and enhance efficacy in the preclinical phase of the development of therapeutic antibodies originated from animal models.Computational suggestions have long been desired,but available tools focused on immunogenicity calculation of whole antibody sequences and sequence segments,missing the individual residue sites.This study introduces Site-specific Immunogenicity for Therapeutic Antibody(SITA),a novel computational framework that predicts B-cell immunogenicity score for not only the overall antibody,but also individual residues,based on a comprehensive set of amino acid descriptors characterizing physicochemical and spatial features for antibody structures.A transfer-learning-inspired framework was purposely adopted to overcome the scarcity of Antibody-Antibody structural complexes.On an independent testing dataset derived from 13 Antibody-Antibody structural complexes,SITA successfully predicted the epitope sites for Antibody-Antibody structures with a receiver operating characteristic(ROC)-area unver the ROC curve(AUC)of 0.85 and a precision-recall(PR)-AUC of 0.305 at the residue level.Furthermore,the SITA score can significantly distinguish immunogenicity levels of whole human antibodies,therapeutic antibodies and non-human-derived antibodies.More importantly,analysis of an additional 25 thera-peutic antibodies revealed that over 70％of them were detected with decreased immunogenicity after modification compared to their parent variants.Among these,nearly 66％antibodies successfully iden-tified actual modification sites from the top five sites with the highest SITA scores,suggesting the ability of SITA scores for guide the humanization of antibody.Overall,these findings highlight the potential of SITA in optimizing immunogenicity assessments during the process of therapeutic antibody design.

Objective:To explore the clinical and pathological features and survival outcomes of patients with early-onset intrahepatic cholangiocarcinoma (EOICC).Methods:This is a multicenter, retrospective cohort study. Data of 1 160 intrahepatic cholangiocarcinoma patients undergoing radical resection in 14 tertiary Grade A hospitals in China from January 2010 to November 2021 were retrospectively collected. The cohort included 632 males and 528 females, aged( M (IQR)) 61 (14) years (range: 22 to 93 years). ICC aged ≤50 years at the time of diagnosis was defined as EOICC and >50 years as late-onset intrahepatic cholangiocarcinoma (LOICC). Of these, there were 247 cases in the EOICC group and 913 cases in the LOICC. The clinical and pathological characteristics of both groups were analyzed and compared using the independent sample t-test, Mann-Whitney U test or Kaplan-Meier method. Univariate and multivariate Cox regression models for patient outcomes were constructed and forest graphed. Results:Compared with the patients in the LOICC group, patients in the EOICC group had lower carcinoembryonic antigen levels (2.5(4.0) μg/L vs. 3.1(5.2)μg/L, U=124 899, P=0.009) and CA19-9 level (63.4(524.7)U/ml vs. 77.9(611.3)U/ml, U=120 320, P=0.013), higher levels of ALT (29(35)U/L vs. 24(26)U/L, U=101 214, P=0.013), a lower score of the Eastern US Cooperative Oncology Group (0 score patients: 54.7% vs. 44.1%, χ2=12.472, P=0.014), higher TNM stage ( χ2=11.807, P=0.038), and proportion of lymph node dissection (62.3% vs. 54.1%, χ2=5.355, P=0.021). Patients in the two groups in sex, first diagnosis symptoms, intrahepatic bile duct stone history, nail protein, albumin, total bilirubin, transaminase, liver function Child-Pugh grade, T stage, stage, N stage, preoperative laparoscopic exploration proportion, tumor diameter, vascular invasion proportion, differentiation, margin, intraoperative bleeding, postoperative complications, postoperative hospital days were no statistical significance (all P>0.05). Patients in the EOICC group had better outcomes than the LOICC group (median survival time: 29.7 months vs. 25.0 months, 3-year overall survival: 45.1% vs. 37.8%, P=0.027). Conclusion:EOICC patients are better than LOICC patients in carcinoembryonic antigen, CA19-9, ALT, physical strength status and TNM stage, and the long-term prognosis is also better than LOICC patients.

Objective To investigate the effect of Modified Renshen Wumei Decoction on the TLR4/MyD88/pNF-κBp65 signaling pathway and elucidate the potential mechanism by which this formula repairs the intestinal mucosal barrier in diarrheal rats.Methods Twelve rats were randomly selected from a total of 48 rats to serve as the blank control group(CK),while the remaining 36 rats were used to establish a disease model via a compound method.After 14 days of model preparation,the rats were randomly divided into three groups:the model group(MC),the western medicine group(MV),and the traditional Chinese medicine group(MRWD).Each of the four groups(including CK)received corresponding interventions for 7 days.The concentrations of serum diamine oxidase(DAO),D-lactic acid(D-Lac),interleukin-1β(IL-1β),IL-6,IL-10,tumor necrosis factor-α(TNF-α),mucin 2(MUC2),MUC4,MUC6,and colonic homogenate secretory immunoglobulin A(SIgA)were measured using ELISA.Additionally,the protein and gene expressions of colonic toll-like receptor 4(TLR4),myeloid differentiation primary response 88(MyD88),phosphorylated nuclear factor kappa-light-chain-enhancer of activated B cells p65(pNF-κBp65),occludin,claudin-1,and zonula occludens-1(ZO-1)were analyzed by Western blot and RT-PCR.Results(1)Intestinal mucosal injury markers:Compared with the blank group,the serum levels of DAO and D-Lac in the model group were significantly increased(P<0.05).Compared with the model group,both the Chinese medicine group and Western medicine group significantly decreased the serum levels of DAO(P<0.001),while the traditional Chinese medicine group also significantly reduced the serum levels of D-Lac(P<0.05).There was no significant difference in the changes of DAO and D-Lac serum levels between the Chinese medicine group and Western medicine group(P>0.05).(2)Inflammatory indicators:Compared with the blank group,the model group exhibited significant upregulation of TLR4,MyD88,pNF-κ Bp65 protein and gene expression,as well as serum levels of IL-1β,IL-6,and TNF-α(P<0.05),along with a significant decrease in IL-10 serum levels(P<0.05).Compared with the model group,both the Chinese medicine group and Western medicine group significantly downregulated TLR4,MyD88,pNF-κBp65 protein and gene expression,as well as serum levels of IL-1β,IL-6,and TNF-α(P<0.05),and significantly upregulated IL-10 serum levels(P<0.05).There was no significant difference in serum levels of TLR4,MyD88,pNF-κBp65 protein,gene expression,and IL-1β,IL-6,IL-10,and TNF-α between the Chinese medicine group and Western medicine group(P>0.05).(3)Intestinal mucosal barrier factors:Compared with the blank group,the model group exhibited significant downregulation in MUC2,MUC6,SIgA content,as well as Claudin-1,ZO-1 protein and gene expression,and Occludin protein expression(P<0.05).Compared with the model group,both Chinese and Western medicine groups significantly upregulated the content of MUC2 and SIgA,as well as the protein and gene expression of Claudin-1 and ZO-1(P<0.05).The traditional Chinese medicine group also significantly increased the content of MUC6 and Occludin protein expression(P<0.05).No significant differ-ences were observed between the Chinese and Western medicine groups in terms of MUC2,MUC6,SIgA serum content,and Claudin-1 and ZO-1 gene expression(P>0.05).However,the Western medicine group showed better Claudin-1 protein expression than the Chinese medicine group(P<0.05),while the ZO-1 protein expression was higher in the traditional Chinese medicine group compared to the Western medicine group(P<0.05).Conclusion Modified Renshen Wumei Decoction exerts an intestinal mucosal barrier repair effect in diarrhea rats by modulating the TLR4/MyD88/pNF-κBp65 signaling pathway.

Objective To investigate the application value of conventional MRI combined with diffusion tensor imaging(DTI)in evaluating the correlation between the texture composition of benign prostatic hyperplasia(BPH)and the International Prostate Symptom Score(IPSS).Methods Seventy patients with BPH confirmed by pathology were retrospectively analyzed and all patients underwent conventional MRI,DTI and IPSS before surgery.Evaluation metrics included:the mean signal intensity of T2WI(mean-SI-T2WI),apparent diffusion coefficient(ADC)and fractional anisotropy(FA)values.Independent samples t-test,partial correlation analysis,and receiver operating characteristic(ROC)curve were used to assess the correlation between the texture parameters of the prostate transition zone and IPSS.Results The mean-SI-T2WI was significantly negatively correlated with IPSS(r=-0.683,P<0.001);the average ADC value was slightly negatively correlated with IPSS(r=-0.467,P<0.001);and the average FA value was slightly positively correlated with IPSS(r=0.419,P<0.001).The predictive value of MRI texture parameters for IPSS in BPH patients,ranked from high to low,mean-SI-T2WI[area under the curve(AUC)=0.734],average ADC value(AUC=0.673),and average FA value(AUC=0.635);However,the combination of mean-SI-T2WI+ADC+FA(AUC=0.791)did not significantly improve the diagnostic efficacy by DeLong's test(P>0.05).Conclusion Mean-SI-T2WI,DWI and DTI can be used to evaluate the composition of the prostate,among which mean-SI-T2WI is the best,and the com-bination of them can not improve the diagnostic efficacy.

Objective To investigate the application value of conventional MRI combined with diffusion tensor imaging(DTI)in evaluating the correlation between the texture composition of benign prostatic hyperplasia(BPH)and the International Prostate Symptom Score(IPSS).Methods Seventy patients with BPH confirmed by pathology were retrospectively analyzed and all patients underwent conventional MRI,DTI and IPSS before surgery.Evaluation metrics included:the mean signal intensity of T2WI(mean-SI-T2WI),apparent diffusion coefficient(ADC)and fractional anisotropy(FA)values.Independent samples t-test,partial correlation analysis,and receiver operating characteristic(ROC)curve were used to assess the correlation between the texture parameters of the prostate transition zone and IPSS.Results The mean-SI-T2WI was significantly negatively correlated with IPSS(r=-0.683,P<0.001);the average ADC value was slightly negatively correlated with IPSS(r=-0.467,P<0.001);and the average FA value was slightly positively correlated with IPSS(r=0.419,P<0.001).The predictive value of MRI texture parameters for IPSS in BPH patients,ranked from high to low,mean-SI-T2WI[area under the curve(AUC)=0.734],average ADC value(AUC=0.673),and average FA value(AUC=0.635);However,the combination of mean-SI-T2WI+ADC+FA(AUC=0.791)did not significantly improve the diagnostic efficacy by DeLong's test(P>0.05).Conclusion Mean-SI-T2WI,DWI and DTI can be used to evaluate the composition of the prostate,among which mean-SI-T2WI is the best,and the com-bination of them can not improve the diagnostic efficacy.

Objective To investigate the effect of Modified Renshen Wumei Decoction on the TLR4/MyD88/pNF-κBp65 signaling pathway and elucidate the potential mechanism by which this formula repairs the intestinal mucosal barrier in diarrheal rats.Methods Twelve rats were randomly selected from a total of 48 rats to serve as the blank control group(CK),while the remaining 36 rats were used to establish a disease model via a compound method.After 14 days of model preparation,the rats were randomly divided into three groups:the model group(MC),the western medicine group(MV),and the traditional Chinese medicine group(MRWD).Each of the four groups(including CK)received corresponding interventions for 7 days.The concentrations of serum diamine oxidase(DAO),D-lactic acid(D-Lac),interleukin-1β(IL-1β),IL-6,IL-10,tumor necrosis factor-α(TNF-α),mucin 2(MUC2),MUC4,MUC6,and colonic homogenate secretory immunoglobulin A(SIgA)were measured using ELISA.Additionally,the protein and gene expressions of colonic toll-like receptor 4(TLR4),myeloid differentiation primary response 88(MyD88),phosphorylated nuclear factor kappa-light-chain-enhancer of activated B cells p65(pNF-κBp65),occludin,claudin-1,and zonula occludens-1(ZO-1)were analyzed by Western blot and RT-PCR.Results(1)Intestinal mucosal injury markers:Compared with the blank group,the serum levels of DAO and D-Lac in the model group were significantly increased(P<0.05).Compared with the model group,both the Chinese medicine group and Western medicine group significantly decreased the serum levels of DAO(P<0.001),while the traditional Chinese medicine group also significantly reduced the serum levels of D-Lac(P<0.05).There was no significant difference in the changes of DAO and D-Lac serum levels between the Chinese medicine group and Western medicine group(P>0.05).(2)Inflammatory indicators:Compared with the blank group,the model group exhibited significant upregulation of TLR4,MyD88,pNF-κ Bp65 protein and gene expression,as well as serum levels of IL-1β,IL-6,and TNF-α(P<0.05),along with a significant decrease in IL-10 serum levels(P<0.05).Compared with the model group,both the Chinese medicine group and Western medicine group significantly downregulated TLR4,MyD88,pNF-κBp65 protein and gene expression,as well as serum levels of IL-1β,IL-6,and TNF-α(P<0.05),and significantly upregulated IL-10 serum levels(P<0.05).There was no significant difference in serum levels of TLR4,MyD88,pNF-κBp65 protein,gene expression,and IL-1β,IL-6,IL-10,and TNF-α between the Chinese medicine group and Western medicine group(P>0.05).(3)Intestinal mucosal barrier factors:Compared with the blank group,the model group exhibited significant downregulation in MUC2,MUC6,SIgA content,as well as Claudin-1,ZO-1 protein and gene expression,and Occludin protein expression(P<0.05).Compared with the model group,both Chinese and Western medicine groups significantly upregulated the content of MUC2 and SIgA,as well as the protein and gene expression of Claudin-1 and ZO-1(P<0.05).The traditional Chinese medicine group also significantly increased the content of MUC6 and Occludin protein expression(P<0.05).No significant differ-ences were observed between the Chinese and Western medicine groups in terms of MUC2,MUC6,SIgA serum content,and Claudin-1 and ZO-1 gene expression(P>0.05).However,the Western medicine group showed better Claudin-1 protein expression than the Chinese medicine group(P<0.05),while the ZO-1 protein expression was higher in the traditional Chinese medicine group compared to the Western medicine group(P<0.05).Conclusion Modified Renshen Wumei Decoction exerts an intestinal mucosal barrier repair effect in diarrhea rats by modulating the TLR4/MyD88/pNF-κBp65 signaling pathway.

Objective:To develop an artificial intelligence (AI)-based platelet review strategy to identify abnormal platelet histograms with no significant difference between initial impedance platelet count (PLT-I) and PLT-F results.Methods:This study included 5 119 routine blood analysis in Nanfang Hospital of Southern Medical University and its Ganzhou branch from July 2023 and March 2024. Specimens exhibiting abnormal platelet histograms and an initial platelet count >40×10?/L underwent review using the fluorescent platelet count (PLT-F) channel. Consistency of the results was defined as a difference between impedance platelet count (PLT-I) and PLT-F less than ±20% of the PLT-F results. A deep learning model was developed using platelet and red blood cell histogram data from a training set of 3 807 specimens. The model′s diagnostic performance was evaluated on an independent external validation set ( n=805) using receiver operating characteristic (ROC) curve analysis. Changes in the number of reviewed samples and sample turnaround time were analyzed to assess its clinical utility. Results:The deep learning model based on platelet and red blood cell histograms achieved an area under the ROC curve (AUC) of 0.854 in the training set. At a cutoff value of 0.1, the sensitivity was 0.954 and specificity was 0.358. The model could reduce review by 16.80% (190/1 131). In the validation set, the AUC was 0.805, with a sensitivity of 0.955 and specificity of 0.307, corresponding to a reduction of 17.41% (47/270) in reviewed specimens.Conclusion:The platelet review prediction model developed based on deep learning technology can efficiently identify samples with consistent results before and after review, reducing unnecessary reviews and shortening specimen testing time, thereby improving the efficiency of platelet test.