Objective: To explore the clinical characteristics and diagnosis and treatment plans of neurofibromatosis type 1 (NF1), and to provide references for clinical diagnosis and treatment. Methods : The clinical manifestations and treatment of an 8-year-old female patient with NF1 was reported. A literature review was conducted to summarize the clinical characteristics and therapeutic strategies of NF1. Multiple NF1s occurred on the right cheek, orbit, and eyelid, and recurred after surgical resection. The tumor caused ptosis, incomplete closure, and vision loss in the upper eyelid of the right eye. After a multidisciplinary assessment determined that radical resection was not feasible, selumetinib sulfate targeted therapy was adopted (25 mg, Po, bid), 28 days constitute one treatment course, and 14 courses have been completed, combined with symptomatic ocular treatments, such as Befusu. Result: The follow-up showed that the tumor volume did not continue to increase (stable disease), the uncorrected vision of the right eye improved (0.05 vs 0.1), and no drug-related adverse reactions occurred during the treatment period. The literature review summarizes the diverse clinical manifestations of NF1, with café-au-lait macules, multiple neurofibromas, and Lisch nodules being hallmark features. Currently, surgical intervention remains the most commonly employed and primary therapeutic approach for NF1; however, for patients who do not meet the criteria for surgery, alternative treatment strategies should be considered. MEK inhibitors, such as selumetinib, demonstrate significant efficacy in inhibiting the growth of NF1-associated plexiform neurofibromas, with tumor volume reductions of at least 20% observed in 70% of pediatric patients in the SPRINT clinical trial. Furthermore, these inhibitors exhibit favorable long-term safety profiles. Conclusion Café-au-lait macules, multiple neurofibromas, and Lisch nodules are hallmark features of NF1. Selumetinib is safe and effective for NF1 in the head and neck of children, and it is the preferred treatment option for patients who are not suitable for surgery. Long-term follow-up monitoring of tumor changes and drug safety is required.

Objective To investigate the value of CT imaging texture analysis in predicting simplified pathological types of thymic epithelial tumors(TETs).Methods The CT data from 114 patients with TETs confirmed by surgical or pathology were analyzed retrospectivel,and the types of TETs were divided into three groups,including low-risk thymoma(LRT)group,high-risk thymoma(HRT)group,and thymic carcinoma(TC)group.First,the texture parameters of CT images were extracted,and then the weighted Rad-score values were obtained,and the predictive performance of the texture features was evaluated by using the receiver operating characteristic(ROC)curve.Results There were 114 TETs patients,including 45 patients with LRT,44 patients with HRT,and 25 patients with TC.Based on CT imaging texture analysis,the area under the curve(AUC)in differentiating LRT and HRT or TC via CT plain scan,arterial phase,and venous phase were 0.776,0.885,and 0.761,respectively.In differentiating HRT from TC,the AUC of CT plain scan,arterial phase,and venous phase were 0.828,0.808,and 0.804,respectively.In differentiating thymoma from TC,the AUC of CT plain scan,arterial phase,and venous phase were 0.808,0.769,and 0.774,respectively.Conclusion CT imaging texture analysis can serve as an effective auxiliary tool for predicting the simplified pathological types of TETs,helping to develop personal-ized treatment plans for TETs patients.CT enhanced scanning of arterial phase texture parameters has the highest differential diag-nostic efficiency.

Alternative polyadenylation(APA)is a crucial step in post-transcriptional regulation.Previous bioinformatic studies have mainly focused on the recognition of polyadenylation sites(PASs)in a given genomic sequence,which is a binary classification problem.Recently,computa-tional methods for predicting the usage level of alternative PASs in the same gene have been pro-posed.However,all of them cast the problem as a non-quantitative pairwise comparison task and do not take the competition among multiple PASs into account.To address this,here we propose a deep learning architecture,Deep Regulatory Code and Tools for Alternative Polyadenylation(DeeReCT-APA),to quantitatively predict the usage of all alternative PASs of a given gene.To accommodate different genes with potentially different numbers of PASs,DeeReCT-APA treats the problem as a regression task with a variable-length target.Based on a convolutional neural network-long short-term memory(CNN-LSTM)architecture,DeeReCT-APA extracts sequence features with CNN layers,uses bidirectional LSTM to explicitly model the interactions among com-peting PASs,and outputs percentage scores representing the usage levels of all PASs of a gene.In addition to the fact that only our method can quantitatively predict the usage of all the PASs within a gene,we show that our method consistently outperforms other existing methods on three different tasks for which they are trained:pairwise comparison task,highest usage prediction task,and rank-ing task.Finally,we demonstrate that our method can be used to predict the effect of genetic variations on APA patterns and sheds light on future mechanistic understanding in APA regulation.

The accurate annotation of transcription start sites(TSSs)and their usage are critical for the mechanistic understanding of gene regulation in different biological contexts.To fulfill this,specific high-throughput experimental technologies have been developed to capture TSSs in a genome-wide manner,and various computational tools have also been developed for in silico pre-diction of TSSs solely based on genomic sequences.Most of these computational tools cast the problem as a binary classification task on a balanced dataset,thus resulting in drastic false positive predictions when applied on the genome scale.Here,we present DeeReCT-TSS,a deep learning-based method that is capable of identifying TSSs across the whole genome based on both DNA sequence and conventional RNA sequencing data.We show that by effectively incorporating these two sources of information,DeeReCT-TSS significantly outperforms other solely sequence-based methods on the precise annotation of TSSs used in different cell types.Furthermore,we develop a meta-learning-based extension for simultaneous TSS annotations on 10 cell types,which enables the identification of cell type-specific TSSs.Finally,we demonstrate the high precision of DeeReCT-TSS on two independent datasets by correlating our predicted TSSs with experimentally defined TSS chromatin states.The source code for DeeReCT-TSS is available at https://github.-com/JoshuaChou2018/DeeReCT-TSS_release and https://ngdc.cncb.ac.cn/biocode/tools/BT007316.