Optimisation of mobile intelligent terminal data pre-processing methods for crowd sensing

Sensor data pre-processing is an essential phase of crowd sensing application. Existing studies do not effectively solve the problem, and there still exist various sensor data pre-processing optimisation problems at the acquisition end in crowd-sensing process. This study presents an improved sliding average method to achieve data compression and reduce the time complexity by using a dynamic window with improved processing time. Through adopting locally sorting and gradient change of the filter window, an improved extremum median filtering method is proposed to relieve the time- consuming problem when denoising high pixel images. A transmission strategy for optimisation is also proposed, in which only the demarcation points of each group of data and the data points with large differences when comparing with the demarcation points are recorded. This strategy reduces the storage pressure and the amount of data transmission of mobile terminal and improves the efficiency of data transmission. The experimental results show that their methods have higher speed and lower cost, and thus they can run better in crowd-sensing environment.

A proteomic landscape of pharmacologic perturbations for functional relevance

Pharmacological perturbation studies based on protein-level signatures are fundamental for drug discovery. In the present study, we used a mass spectrometry (MS)-based proteomic platform to profile the whole proteome of the breast cancer MCF7 cell line under stress induced by 78 bioactive compounds. The integrated analysis of perturbed signal abundance revealed the connectivity between phenotypic behaviors and molecular features in cancer cells. Our data showed functional relevance in exploring the novel pharmacological activity of phenolic xanthohumol, as well as the noncanonical targets of clinically approved tamoxifen, lovastatin, and their derivatives. Furthermore, the rational design of synergistic inhibition using a combination of histone methyltransferase and topoisomerase was identified based on their complementary drug fingerprints. This study provides rich resources for the proteomic landscape of drug responses for precision therapeutic medicine.

Digital twin driven and intelligence enabled content delivery in end-edge-cloud collaborative 5G networks

The rapid development of 5G/6G and AI enables an environment of Internet of Everything(IoE)which can support millions of connected mobile devices and applications to operate smoothly at high speed and low delay.However,these massive devices will lead to explosive traffic growth,which in turn cause great burden for the data transmission and content delivery.This challenge can be eased by sinking some critical content from cloud to edge.In this case,how to determine the critical content,where to sink and how to access the content correctly and efficiently become new challenges.This work focuses on establishing a highly efficient content delivery framework in the IoE environment.In particular,the IoE environment is re-constructed as an end-edge-cloud collaborative system,in which the concept of digital twin is applied to promote the collaboration.Based on the digital asset obtained by digital twin from end users,a content popularity prediction scheme is firstly proposed to decide the critical content by using the Temporal Pattern Attention(TPA)enabled Long Short-Term Memory(LSTM)model.Then,the prediction results are input for the proposed caching scheme to decide where to sink the critical content by using the Reinforce Learning(RL)technology.Finally,a collaborative routing scheme is proposed to determine the way to access the content with the objective of minimizing overhead.The experimental results indicate that the proposed schemes outperform the state-of-the-art benchmarks in terms of the caching hit rate,the average throughput,the successful content delivery rate and the average routing overhead.

AMicroseismic Signal Denoising Algorithm Combining VMD and Wavelet Threshold Denoising Optimized by BWOA

The denoising of microseismic signals is a prerequisite for subsequent analysis and research.In this research,a new microseismic signal denoising algorithm called the Black Widow Optimization Algorithm(BWOA)optimized VariationalMode Decomposition(VMD)jointWavelet Threshold Denoising(WTD)algorithm(BVW)is proposed.The BVW algorithm integrates VMD and WTD,both of which are optimized by BWOA.Specifically,this algorithm utilizes VMD to decompose the microseismic signal to be denoised into several Band-Limited IntrinsicMode Functions(BLIMFs).Subsequently,these BLIMFs whose correlation coefficients with the microseismic signal to be denoised are higher than a threshold are selected as the effective mode functions,and the effective mode functions are denoised using WTD to filter out the residual low-and intermediate-frequency noise.Finally,the denoised microseismic signal is obtained through reconstruction.The ideal values of VMD parameters and WTD parameters are acquired by searching with BWOA to achieve the best VMD decomposition performance and solve the problem of relying on experience and requiring a large workload in the application of the WTD algorithm.The outcomes of simulated experiments indicate that this algorithm is capable of achieving good denoising performance under noise of different intensities,and the denoising performance is significantly better than the commonly used VMD and Empirical Mode Decomposition(EMD)algorithms.The BVW algorithm is more efficient in filtering noise,the waveform after denoising is smoother,the amplitude of the waveform is the closest to the original signal,and the signal-to-noise ratio(SNR)and the root mean square error after denoising are more satisfying.The case based on Fankou Lead-Zinc Mine shows that for microseismic signals with different intensities of noise monitored on-site,compared with VMD and EMD,the BVW algorithm ismore efficient in filtering noise,and the SNR after denoising is higher.

Early proactive monitoring of DNA-thioguanine in patients with Crohn’s disease predicts thiopurine-induced late leucopenia in NUDT15/TPMT normal metabolizers

BACKGROUND Thiopurine-induced leucopenia significantly hinders the wide application of thiopurines.Dose optimization guided by nudix hydrolase 15(NUDT15)has significantly reduced the early leucopenia rate,but there are no definitive biomarkers for late risk leucopenia prediction.AIM To determine the predictive value of early monitoring of DNA-thioguanine(DNATG)or 6-thioguanine nucleotides(6TGN)for late leucopenia under a NUDT15-guided thiopurine dosing strategy in patients with Crohn’s disease(CD).METHODS Blood samples were collected within two months after thiopurine initiation for detection of metabolite concentrations.Late leucopenia was defined as a leukocyte count<3.5×10^(9)/L over two months.RESULTS Of 148 patients studied,late leucopenia was observed in 15.6%(17/109)of NUDT15/thiopurine methyltransferase(TPMT)normal and 64.1%(25/39)of intermediate metabolizers.In patients suffering late leucopenia,early DNATG levels were significantly higher than in those who did not develop late leucopenia(P=4.9×10^(-13)).The DNATG threshold of 319.43 fmol/μg DNA could predict late leucopenia in the entire sample with an area under the curve(AUC)of 0.855(sensitivity 83%,specificity 81%),and in NUDT15/TPMT normal metabolizers,the predictive performance of a threshold of 315.72 fmol/μg DNA was much more remarkable with an AUC of 0.902(sensitivity 88%,specificity 85%).6TGN had a relatively poor correlation with late leucopenia whether in the entire sample(P=0.021)or NUDT15/TPMT normal or intermediate metabolizers(P=0.018,P=0.55,respectively).CONCLUSION Proactive therapeutic drug monitoring of DNATG could be an effective strategy to prevent late leucopenia in both NUDT15/TPMT normal and intermediate metabolizers with CD,especially the former.

Age-related secretion of grancalcin by macrophages induces skeletal stem/progenitor cell senescence during fracture healing

Skeletal stem/progenitor cell(SSPC)senescence is a major cause of decreased bone regenerative potential with aging,but the causes of SSPC senescence remain unclear.In this study,we revealed that macrophages in calluses secrete prosenescent factors,including grancalcin(GCA),during aging,which triggers SSPC senescence and impairs fracture healing.Local injection of human rGCA in young mice induced SSPC senescence and delayed fracture repair.Genetic deletion of Gca in monocytes/macrophages was sufficient to rejuvenate fracture repair in aged mice and alleviate SSPC senescence.Mechanistically,GCA binds to the plexin-B2 receptor and activates Arg2-mediated mitochondrial dysfunction,resulting in cellular senescence.Depletion of Plxnb2 in SSPCs impaired fracture healing.Administration of GCA-neutralizing antibody enhanced fracture healing in aged mice.Thus,our study revealed that senescent macrophages within calluses secrete GCA to trigger SSPC secondary senescence,and GCA neutralization represents a promising therapy for nonunion or delayed union in elderly individuals.

Changes in Leaf Stomatal Properties in Rice with the Growing Season

Transplanting rice varieties grown in different seasons can lead to different yields due to different dry matterproduction. Early-season rice varieties transplanted in the late season can obtain high yields with short-growthduration and higher yields driven by higher dry matter production. To make clear the variations in dry matterproduction across seasons, four early-season rice varieties were chosen for late-season transplantation. The grainyield, dry matter accumulation, leaf photosynthetic, and leaf stomatal properties were studied. It was observedthat the average yields of these four varieties in the late season were 33% greater, despite a reduced growth periodof 13 days in comparison with the early season. Furthermore, there was a notable increase in both total and postheadingdry matter production during the late season. The leaf net photosynthetic rate, stomatal area, stomatalwidth, and stomatal length were higher in the late season. Despite no significant difference in stomatal densitybetween seasons, strong positive linear relationships were observed between net photosynthetic rate and stomatalconductance, and between stomatal conductance and area. These relationships demonstrate that the increase ofthe stomatal width and length of the leaves in the late season leads to an increase in the stomatal area, therebyincreasing the stomatal conductance and enhancing the photosynthesis of the leaves. Consequently, this leads togreater dry matter production and a higher yield compared to the early season. Therefore, when breeding newhigh-yielding and short-growing varieties, the large stomatal area can be used as a reference index.

Time-History Dynamic Characteristics of Reinforced Soil-Retaining Walls

Given the complexities of reinforced soil materials’constitutive relationships,this paper compares reinforced soil composite materials to a sliding structure between steel bars and soil and proposes a reinforced soil constitutive model that takes this sliding into account.A finite element dynamic time history calculation software for composite response analysis was created using the Fortran programming language,and time history analysis was performed on reinforced soil retaining walls and gravity retaining walls.The vibration time histories of reinforced soil retaining walls and gravity retaining walls were computed,and the dynamic reactions of the two types of retaining walls to vibration were compared and studied.The dynamic performance of reinforced earth retaining walls was evaluated.

Blockage of the habenular nucleus can eliminate dyspnea induced by electrostimulation of the insular cortex

BACKGROUND： The insular cortex and habenular nucleus may be a regulatory center for obstructive sleep apnea syndrome, and dyspnea may be caused by insular cortex activity. The insular cortex is a cortical representation of obstructive sleep apnea syndrome. The habenular nucleus is a station for descending insular cortex activity. OBJECTIVE： Through actively stimulating the rat insular cortex, to observe rat respiratory movement, myoelectric activities of genioglossus, arterial partial pressure of oxygen, partial pressure of carbon dioxide and acidity-alkalinity, and to verify a hypothesis that the insular cortex is a superior-position regulation center, and the habenular nucleus is an inferior-position nervous nuclei of the insular cortex in patients with obstructive sleep apnea syndrome. DESIGN, TIME AND SETTING： The randomized, controlled animal study was performed at the Laboratory of Electrophysiology, Department of Physiology, Norman Bathune College of Medicine, Jilin University, China from September 2004 to June 2008. MATERIALS： We used L-glutamic acid （Dingguo Biological Product Research Center, Beijing, China）, lidocaine hydrochloride （Seventh Pharmacy Co., Ltd., Wuxi, China）, electric stimulator （Nihon Kohden, Japan）, and an AVL-OPTI blood gas analyzer （AVL Scientific Co., Roswell, GA, USA）. METHODS： The insular cortex of healthy adult Wistar rats underwent electrostimulation and L-glutamic acid stimulation to record changes in the myoelectric activity of genioglossus and respiratory movement. Some rats were injected with lidocaine to block the habenular nucleus before electrostimulation or L-glutamic acid stimulation. L-glutamic acid and lidocaine were injected by microelectrodes embedded in nuclear groups. MAIN OUTCOME MEASURES： Myoelectric activities of genioglossus, arterial partial pressure of oxygen, partial pressure of carbon dioxide and acidity-alkalinity were measured following apnea in rats undergoing electrostimulation in the insular cortex and following blockade of the habenular nucleus. RESULTS： Following electrostimulation and L-glutamic acid stimulation, rats developed apnea or respiratory rhythm disorders. Simultaneously, the amplitude of myoelectric activity of the genioglossus was reduced （P 〈 0.01 ）, and the electromyogram integral was decreased （P 〈 0.01）. Arterial blood gas analysis showed arterial blood acidosis, a decrease in pH （P 〈 0.05）, and an increase in the negative value of alkaline reserve （P 〈 0.01）. Lidocaine in the habenular nuclear blocked respiratory and other index changes after insular cortex stimulation. CONCLUSION： Dyspnea induced by stimulating the insular cortex may require the habenular nucleus. Paralysis of the habenular nucleus can completely eliminate insular cortex stimulation-induced dyspnea.

Role of 5-hydroxytryptamine expression in cerebellar Purkinje cells in obstructive sleep apnea syndrome

In the present study, electrical stimulation to the rat insular cortex induced apnea or respiratory disturbance, reduced amplitude of genioglossal electromyogram, and decreased electromyogram integrals. In addition, arterial blood gas analysis showed arterial blood acidosis, reduced pH values, increased alkali reserve negative values, decreased peripheral blood 5-hydroxytryptamine content, and increased 5-hydroxytryptamine expression in cerebellar Purkinje cells. Following lidocaine injection to block the habenular nucleus, abnormalities in breath, genioglossal electromyogram, and blood gas values disappeared, and peripheral blood 5-hydroxytryptamine content returned to levels prior to electric stimulation. However, 5-hydroxytryptamine expression in cerebellar Purkinje cells remained high. The results suggested that 5-hydroxytryptamine expression in Purkinje cells did not correlate with ventilation function involving insular cortex and habenular nucleus.

5-hydroxytryptamine-mediated apnea caused by the habenular nucleus

5-hydroxytryptamine contributes to the control of activities of the dilator muscle in the upper respiratory tract, and is derived from the raphe nuclei, in which the habenular nucleus exerts a sustaJned inhibitory effect. In the present study, respiratory motion curve of the genJoglossus muscle and peripheral 5-hydroxytryptamine changes were observed following L-glutamate stimulation of the habenular nucleus of adult Wistar rats. Results showed that the rats had apnea and decreased plasma 5-hydroxytryptamine content after the neurons in habenular nucleus were excited. Genioglossus muscle electromyogram amplitude and integral were significantly reduced. The genioglossus myoelectric activity and respiratory motion curve were similar to obstructive sleep apnea syndrome, thus confirming that the habenular nucleus is the key nucleus involved in the pathogenesis of obstructive sleep apnea syndrome, and is the primary regulated center in the raphe nuclei. Stimulation of the habenular nucleus may suppress 5-hydroxytryptamine release and result in apnea, which is similar to obstructive sleep apnea syndrome.

Safety evaluation on the clinical application of Tenghuangjiangu tablet for osteoarthritis:a hospital registration study

To evaluate the treatment safety of Tenghuangjiangu tablet on osteoarthritis,3365 osteoarthritis patients whose prescription included Tenghuangjiangu tablet from 15 hospitals were involved in the prospective and multi-center clinical trial.Tenghuangjiangu tablet dosage was decided by instruction or doctors’experience.The course of treatment and observation was 4 weeks.The adverse drug reactions were observed in the treatment process.Results showed male and female patients were 1018(30.25%)and 2347(69.75%),respectively,and 528 patients had allergic history.The patients’average age was 58.30±8.99 years,and the average disease course was 33.29±37.40 months.The average score of WOMAC scale was 95.07±42.42,which indicated the light conditions.2275 patients were treated with combined drug regimen.There were two adverse drug reactions in this research.One reaction was skin rashes with itching and the interventions were stopped original drugs and give antianaphylactic treatment.The other reaction was stomach discomfort with disgusting and the intervention was stopped the original drugs temporarily,then continued to take two drugs after 3 days and the reaction didn’t appear.The accident rate of adverse drug reaction was 0.059%.The safety of Tenghuangjiangu tablet clinical application was good,and the mechanism of adverse drug reaction should be researched in-depth.

Phytoremediation of Rare Tailings-Contaminated Soil

In order to achieve the goal of circular economy and sustainable development of ecological environment,it is important to separate and recover associated elements from rare mineral resources.Compared with traditional physical and che-mical remediation methods of contaminated soil,phytoremediation is regarded as the most promising green in-situ restoration technology.The purpose of this review is to efctive alleviate the environmental problems caused by rare tailings contaminated soil through phytoremediation and realize the recovery of uranium-thorium,rare earth elements(REEs)and tantalum niobium.This review took rare tailings with uranium-thorium,REEs tantalum-niobium in China as the research object,then the background,significance,mechanisms and applcation strategies of phytoremediation were elaborated.In additon,the cases of spedies with tolerance to uranium thorium,tantalum niobium as well as REEs and their remediation mechanisms were summarized,respectively.Particularly,the typical plants represented by Bras-sica juncea,Sunflower,Phytolacca americana,Dicramopteris dichotoma,Salix SPP,etc,were very efctive in the reme-diation of rare tailings.The infuence factors of phytoremediation eficiency of tailings contaminated soil were discused.Two main factors were the mobility of heavy metals in soil(external cause)and the ennichment ability of species(inter-nal cause).Since the traditional phytoremediation also had some limitations in view of this,the work discussed some auxiliary methods(such as chelaing agents or microbial assisted restoration)to improve the effiency of phytoreme-diation.Finally,the future development of phytoremediation and potential applcation directions were explored.

Physiological Processes Contributing to the Difference in Grain Amino Acid Content Between Two Hybrid Rice(Oryza sativa L.)Cultivars

Improving grain amino acid content of rice(Oryza sativa L.)is essential for the health of consumers.This study was conducted to identify the physiological processes that contribute to the higher grain amino acid content in hybrid rice cultivar Lingliangyou 268 compared to Luliangyou 996.The results showed that total amino acid content in grains was 9%higher in Lingliangyou 268 than in Luliangyou 996.There was no significant difference in grain nitrogen(N)content between Lingliangyou 268 and Luliangyou 996,while ratio of amino acid to N was 6%higher in Lingliangyou 268 compared to Luliangyou 996.A total of 16 differentially expressed proteins related to amino acid metabolism(e.g.,erythronate-4-phosphate dehydrogenase domain containing protein)were identified in grains between Lingliangyou 268 and Luliangyou 996.The identified proteins were involved in 10 molecular functions.Six of the 10 defined functions were related to binding(heterocyclic compound binding,nucleoside phosphate binding,nucleotide binding,organic cyclic compound binding,protein binding,and small molecule binding)and the other 4 defined functions were catalytic activity,enzyme regulator activity,hydrolase activity,and transferase activity.These results indicate that the higher grain amino acid content in Lingliangyou 268 compared to Luliangyou 996 is attributed to increased efficiency of converting N to amino acid that results from altered expression of proteins related to amino acid metabolism.

光热催化甲烷干重整研究进展

随着工业化的推进,化石能源的消耗产生大量温室气体,其中CH_(4)和CO_(2)占据温室气体排放的98%以上。将CH_(4)和CO_(2)转化为高附加值化学品具有重要的意义,一直受到工业界和学术界广泛关注。传统的热催化甲烷干重整(DRM)可实现将CH_(4)和CO_(2)转化为合成气,但该反应过程受热力学限制,需要很高的能量输入,并且由于反应温度较高,催化剂易发生积碳而失活。绿色环保的光催化技术可以使甲烷干重整反应在温和条件下进行,但是存在太阳光利用率和反应转化率较低等问题。最近光热协同催化受到学术界广泛关注。许多研究结果表明,在相对温和的条件下,光热催化DRM可以获得良好的催化效果,可有效实现太阳能转化为化学能。本文简要介绍近期光热催化甲烷干重整反应的研究进展,总结不同金属催化剂在光热催化甲烷干重整中的应用,同时提出了光热催化甲烷干重整存在的一些挑战及展望。

Parallel Learning:Overview and Perspective for Computational Learning Across Syn2Real and Sim2Real

The virtual-to-real paradigm,i.e.,training models on virtual data and then applying them to solve real-world problems,has attracted more and more attention from various domains by successfully alleviating the data shortage problem in machine learning.To summarize the advances in recent years,this survey comprehensively reviews the literature,from the viewport of parallel intelligence.First,an extended parallel learning framework is proposed to cover main domains including computer vision,natural language processing,robotics,and autonomous driving.Second,a multi-dimensional taxonomy is designed to organize the literature in a hierarchical structure.Third,the related virtual-toreal works are analyzed and compared according to the three principles of parallel learning known as description,prediction,and prescription,which cover the methods for constructing virtual worlds,generating labeled data,domain transferring,model training and testing,as well as optimizing the strategies to guide the task-oriented data generator for better learning performance.Key issues remained in virtual-to-real are discussed.Furthermore,the future research directions from the viewpoint of parallel learning are suggested.

DAO to HANOI via DeSci: AI Paradigm Shifts from AlphaGo to ChatGPT

From AlphaGo to ChatGPT,the field of AI has launched a series of remarkable achievements in recent years.Analyzing,comparing,and summarizing these achievements at the paradigm level is important for future AI innovation,but has not received sufficient attention.In this paper,we give an overview and perspective on machine learning paradigms.First,we propose a paradigm taxonomy with three levels and seven dimensions from a knowledge perspective.Accordingly,we give an overview on three basic and twelve extended learning paradigms,such as Ensemble Learning,Transfer Learning,etc.,with figures in unified style.We further analyze three advanced paradigms,i.e.,AlphaGo,AlphaFold and ChatGPT.Second,to enable more efficient and effective scientific discovery,we propose to build a new ecosystem that drives AI paradigm shifts through the decentralized science(DeSci)movement based on decentralized autonomous organization(DAO).To this end,we design the Hanoi framework,which integrates human factors,parallel intelligence based on a combination of artificial systems and the natural world,and the DAO to inspire AI innovations.

东洋区宽锤小叶蝉属Platfusa并记一新种(半翅目:叶蝉科)

宽锤小叶蝉属Platfusa Dworakowska,1993在中国首次报道,并记述该属1新种:片突宽锤小叶蝉P.lamellaris Kang&Zhang sp.nov.,绘制了形态特征图。文中还提供了种名录和检索表。

Knockdown of 11β-hydroxysteroid dehydrogenase type 1 alleviates LPS-induced myocardial dysfunction through the AMPK/SIRT1/PGC-1αpathway

Sepsis-induced myocardial dysfunction is primarily accompanied by severe sepsis,which is associated with high morbidity and mortality.11β-hydroxysteroid dehydrogenase type 1(11β-HSD1),encoded by Hsd11b1,is a reductase that can convert inactive cortisone into metabolically active cortisol,but the role of 11β-HSD1 in sepsis-induced myocardial dysfunction remains poorly understood.The current study aimed to investigate the effects of 11β-HSD1 on a lipopolysaccharide(LPS)-induced mouse model,in which LPS(10 mg/kg)was administered to wild-type C57BL/6J mice and 11β-HSD1 global knockout mice.We asscessed cardiac function by echocardiography,performed transmission electron microscopy and immunohistochemical staining to analyze myocardial mitochondrial injury and histological changes,and determined the levels of reactive oxygen species and biomarkers of oxidative stress.We also employed polymerase chain reaction analysis,Western blotting,and immunofluorescent staining to determine the expression of related genes and proteins.To investigate the role of 11β-HSD1 in sepsis-induced myocardial dysfunction,we used LPS to induce lentivirus-infected neonatal rat ventricular cardiomyocytes.We found that knockdown of 11β-HSD1 alleviated LPS-induced myocardial mitochondrial injury,oxidative stress,and inflammation,along with an improved myocardial function;furthermore,the depletion of 11β-HSD1 promoted the phosphorylation of adenosine 5′-monophosphate-activated protein kinase(AMPK),peroxisome proliferator-activated receptor gamma coactivator 1α(PGC-1α),and silent information regulator 1(SIRT1)protein levels both in vivo and in vitro.Therefore,the suppression of 11β-HSD1 may be a viable strategy to improve cardiac function against endotoxemia challenges.

Comparison and development of machine learning for thalidomideinduced peripheral neuropathy prediction of refractory Crohn’s disease in Chinese population

BACKGROUND Thalidomide is an effective treatment for refractory Crohn’s disease(CD).However,thalidomide-induced peripheral neuropathy(TiPN),which has a large individual variation,is a major cause of treatment failure.TiPN is rarely predictable and recognized,especially in CD.It is necessary to develop a risk model to predict TiPN occurrence.AIM To develop and compare a predictive model of TiPN using machine learning based on comprehensive clinical and genetic variables.METHODS A retrospective cohort of 164 CD patients from January 2016 to June 2022 was used to establish the model.The National Cancer Institute Common Toxicity Criteria Sensory Scale(version 4.0)was used to assess TiPN.With 18 clinical features and 150 genetic variables,five predictive models were established and evaluated by the confusion matrix receiver operating characteristic curve(AUROC),area under the precision-recall curve(AUPRC),specificity,sensitivity(recall rate),precision,accuracy,and F1 score.RESULTS The top-ranking five risk variables associated with TiPN were interleukin-12 rs1353248[P=0.0004,odds ratio(OR):8.983,95%confidence interval(CI):2.497-30.90],dose(mg/d,P=0.002),brainderived neurotrophic factor(BDNF)rs2030324(P=0.001,OR:3.164,95%CI:1.561-6.434),BDNF rs6265(P=0.001,OR:3.150,95%CI:1.546-6.073)and BDNF rs11030104(P=0.001,OR:3.091,95%CI:1.525-5.960).In the training set,gradient boosting decision tree(GBDT),extremely random trees(ET),random forest,logistic regression and extreme gradient boosting(XGBoost)obtained AUROC values>0.90 and AUPRC>0.87.Among these models,XGBoost and GBDT obtained the first two highest AUROC(0.90 and 1),AUPRC(0.98 and 1),accuracy(0.96 and 0.98),precision(0.90 and 0.95),F1 score(0.95 and 0.98),specificity(0.94 and 0.97),and sensitivity(1).In the validation set,XGBoost algorithm exhibited the best predictive performance with the highest specificity(0.857),accuracy(0.818),AUPRC(0.86)and AUROC(0.89).ET and GBDT obtained the highest sensitivity(1)and F1 score(0.8).Overall,compared with other state-of-the-art classifiers such as ET,GBDT and RF,XGBoost algorithm not only showed a more stable performance,but also yielded higher ROC-AUC and PRC-AUC scores,demonstrating its high accuracy in prediction of TiPN occurrence.CONCLUSION The powerful XGBoost algorithm accurately predicts TiPN using 18 clinical features and 14 genetic variables.With the ability to identify high-risk patients using single nucleotide polymorphisms,it offers a feasible option for improving thalidomide efficacy in CD patients.