Peritumoral Radiomics Strategy Based on Ensemble Learning for the Prediction of Gleason Grade Group of Prostate Cancer.

RATIONALE AND OBJECTIVES: To develop and evaluate a peritumoral radiomic-based machine learning model to differentiate low-Gleason grade group (L-GGG) and high-GGG (H-GGG) prostate lesions. MATERIALS AND METHODS: In this retrospective study, a total of 175 patients with prostate cancer (PCa) confirmed by puncture biopsy were recruited and included 59 patients with L-GGG and 116 patients with H-GGG. The original PCa regions of interest (ROIs) were delineated on T2-weighted (T2WI), diffusion-weighted imaging (DWI), and apparent diffusion coefficient (ADC) maps, and then centra-tumoral and peritumoral ROIs were defined. Features were meticulously extracted from each ROI to establish radiomics models, employing distinct sequence datasets. Peritumoral radiomics models were specifically developed for both the peripheral zone (PZ) and transitional zone (TZ), utilizing dedicated PZ and TZ datasets, respectively. The performances of the models were evaluated by using the receiver operating characteristic (ROC) curve and precision-recall curve. RESULTS: The classification model with combined peritumoral features based on T2 + DWI + ADC sequence dataset demonstrated superior performance compared to the original tumor and centra-tumoral classification models. It achieved an area under the ROC curve (AUC) of 0.850 [95% confidence interval, 0.849, 0.860] and an average accuracy of 0.950. The combined peritumoral model outperformed the regional peritumoral models with AUC of 0.85 versus 0.75 for PZ lesions and 0.88 versus 0.69 for TZ lesions, respectively. The peritumoral classification models exhibit greater efficacy in predicting PZ lesions as opposed to TZ lesions. CONCLUSION: The peritumoral radiomics features showed excellent performance in predicting GGG in PCa patients and might be a valuable addition to the non-invasive assessment of PCa aggressiveness.

Radiomics-Based Machine Learning Models for Predicting P504s/P63 Immunohistochemical Expression: A Noninvasive Diagnostic Tool for Prostate Cancer.

Objective: To develop and validate a noninvasive radiomic-based machine learning (ML) model to identify P504s/P63 status and further achieve the diagnosis of prostate cancer (PCa). Methods: A retrospective dataset of patients with preoperative prostate MRI examination and P504s/P63 pathological immunohistochemical results between June 2016 and February 2021 was conducted. As indicated by P504s/P63 expression, the patients were divided into label 0 (atypical prostatic hyperplasia), label 1 (benign prostatic hyperplasia, BPH) and label 2 (PCa) groups. This study employed T2WI, DWI and ADC sequences to assess prostate diseases and manually segmented regions of interest (ROIs) with Artificial Intelligence Kit software for radiomics feature acquisition. Feature dimensionality reduction and selection were performed by using a mutual information algorithm. Based on screened features, P504s/P63 prediction models were established by random forest (RF), gradient boosting decision tree (GBDT), logistic regression (LR), adaptive boosting (AdaBoost) and k-nearest neighbor (KNN) algorithms. The performance was evaluated by the area under the ROC curve (AUC) and accuracy. Results: A total of 315 patients were enrolled. Among the 851 radiomic features, the 32 top features were derived from T2WI, in which the gray-level run length matrix (GLRLM) and gray-level cooccurrence matrix (GLCM) features accounted for the largest proportion. Among the five models, the RF algorithm performed best in general evaluations (microaverage AUC=0.920, macroaverage AUC=0.870) and provided the most accurate result in further sublabel prediction (the accuracies of label 0, 1, and 2 were 0.831, 0.831, and 0.932, respectively). In comparative sequence analyses, T2WI was the best single-sequence candidate (microaverage AUC=0.94 and macroaverage AUC=0.78). The merged datasets of T2WI, DWI, and ADC yielded optimal AUCs (microaverage AUC=0.930 and macroaverage AUC=0.900). Conclusions: The radiomic-based RF classifier has the potential to be used to evaluate the presurgical P504s/P63 status and further diagnose PCa noninvasively and accurately.

[Characterization of Schizosaccharomyces pombe secreted proteins].

Secreted proteins play a vital physiological role. Schizosaccharomyces pombe is an important model organism for cell cycle study and a potential useful drug screen model. Secreted proteins also initiate the mating. However, few global studies concerning the secreted proteins of S. pombe was reported. To address this issue, bioinformatics were used to reveal the global secreted proteins of S. pombe. The 4997 proteins deduced from the S. pombe genome were analyzed by combined several programs. One hundred and sixty proteins were identified carrying an NH2-terminal secretory signal peptide by signalP3.0. Among them, 117 proteins are integral membrane proteins (TMpred), 13 proteins are lipoproteins (PrositeS-can), and 66 proteins are secreted proteins. The location of the secreted proteins was also predicted by Target P. Some of the secreted proteins are involved in the nutrition, reproduction, as well as the communication between cells and environment. The global information of the secreted proteins of S. pombe will benefit further studies in drug screening model and host searching for heterologous gene expression.

[Comparison of the rescue efficiency of Sendai virus minigenome mediated by CMV and T7 promoter].

In this study, we constructed the plasmid of Sendai virus (SeV) BB1 strain minigenome with Gaussia luciferase (Gluc) as reporter and compared the rescue efficiency of SeV minigenome mediated by T7 promoter with that by CMV promoter. Firstly, the sequence was designed and synthesized which contained hammerhead ribozyme, sequence composed of the trailer, untranslated region of L gene, untranslated region of N gene, and the leader from SeV, and mutant hepatitis delta virus ribozyme sequence. Then, the synthesized sequence was inserted into pVAX1 containing CMV and T7 promoters and the general vector for SeV minigenome pVAX-miniSeV was obtained. Furthermore, pVAX-miniSeV-Gluc (+) and pVAX-miniSeV-Gluc(-) were obtained by inserting Gluc gene into pVAX-miniSeV. From the supernatant of BHK-21 cell transfected with pVAX-miniSeV-Gluc(+), high level of Gluc expression was detection indicating the normal transcription function of CMV promoter. pVAX-SeV-miniGluc(-) and plasmids expressing N,P and L protein of SeV were co-transfected into BST T7/5 cell which derived from BHK-21 and expressed T7 RNA polymerase stably. And high expression of Gluc was found, which indicated that SeV minigenome was efficiently rescued. However, we failed to repeat the result on BHK-21 cell, implying that T7 promoter and CMV promoter may have different effects on the rescue efficiency of SeV minigenome. Therefore, we further constructed SeV minigenome vectors pT7-miniSeV-Gluc (-) and pCMV-miniSeV-Gluc(-) with single promoter of T7 or CMV. Then, these vectors were transfected into BSR T7/ 5 cells respectively accompanied with the N, P, and L protein expression vectors. The result demonstrated that high expression of Gluc was found in the group of pT7-miniSeV-Gluc(-), which failed in the group of pCMV-miniSeV-Gluc(-). It indicated that T7 promoter significantly increased the rescue efficiency of SeV minigenome. We successfully constructed a SeV minigenome vector with secreted luciferase gene as report er and proved T7 promoter can enhance the rescue efficiency of SeV minigenome, which provides basis for construction of infectious clone containing SeV full-length genome.

[Deletion of IV a2 gene from adenoviral genome by lambda-Red recombinase system and packaging of the recombinant adenovirus].

This investigation is to delete the most of the coding sequence (1104 bp) of the IV a2 gene in an adenovirus genome by a lambda-Red recombinase system-mediated PCR-targeting approach and rescue a recombinant adenovirus with IV a2 deletion. First, the template pAK of PCR targeting, containing kanamycin cassette, was constructed. Then, a linear fragment for PCR targeting, which had 39 bp homologous arms at both of its terminus, was amplified by PCR from the pAK. The pFG140 and the linear fragment were electroporated into E. coli BW25113/pIJ790 sequentially and the recombinant pFG140-deltaIV a2 (1104) was established by homologous recombination between the linear fragment and the pFG140 with aid of X-Red recombinase. The precise deletion of 1 104 bp fragment from IV a2 was confirmed by restriction endonucleases digestion and DNA sequencing. ORF of IV a2 was amplified by PCR from pFG140 and then cloned into the pAAV2neo vector. The recombinant adenovirus Ad5delta IV a2 (1104) was rescued by co-transfection of pFG140-deltaIV a2 (1104) and pAAV2neo-IV a2 into HEK293 cells. It was shown by Western Blot that IV a2 could not be detected in the Ad5deltaIV a2 (1104)- infected HEK293 cells. This study established a PCR-targeting strategy for manipulating adenovirus genome directly by a lambda-Red recombinase system, and a recombinant adenovirus with IV a2 deletion was obtained.