A5022647677- Manufacturing Process and Optimization
- Bioinformatics and Genomic Networks
- Cancer Genomics and Diagnostics
- Gene expression and cancer classification
- Radiomics and Machine Learning in Medical Imaging
- Advanced Numerical Analysis Techniques
- 3D Shape Modeling and Analysis
- Advanced Manufacturing and Logistics Optimization
- Advanced machining processes and optimization
- Image Processing and 3D Reconstruction
- Computational Drug Discovery Methods
- Injection Molding Process and Properties
- Scheduling and Optimization Algorithms
- Additive Manufacturing and 3D Printing Technologies
- Cancer-related molecular mechanisms research
- Product Development and Customization
- Industrial Technology and Control Systems
- Machine Learning in Bioinformatics
- 3D Surveying and Cultural Heritage
- Computer Graphics and Visualization Techniques
- Genetic factors in colorectal cancer
- Epigenetics and DNA Methylation
- Ferroptosis and cancer prognosis
- Robotics and Sensor-Based Localization
- Simulation and Modeling Applications
Shanghai Jiao Tong University
2016-2025
Huazhong Agricultural University
2016-2024
Obstetrics and Gynecology Hospital of Fudan University
2020-2024
Ministry of Agriculture and Rural Affairs
2024
Third Xiangya Hospital
2022-2024
Central South University
2022-2024
City University of Macau
2023
University of Macau
2023
Baoji University of Arts and Sciences
2023
Cincinnati Children's Hospital Medical Center
2020-2022
In many microarray studies, classifiers have been constructed based on gene signatures to predict clinical outcomes for various cancer sufferers. However, originating from different studies often suffer poor robustness when used in the classification of data sets independent which they were generated from. this paper, we present an unsupervised feature learning framework by integrating a principal component analysis algorithm and autoencoder neural network identify characteristics expression...
Drug combinations have exhibited promise in treating cancers with less toxicity and fewer adverse reactions. However, vitro screening of synergistic drug is time-consuming labor-intensive because the combinatorial explosion. Although a number computational methods been developed for predicting combinations, multi-way relations between cell lines existing synergy data not well exploited.We propose relation-enhanced hypergraph representation learning method to predict anti-cancer synergy,...
Long intergenic non-coding RNAs (lincRNAs) may play widespread roles in gene regulation and other biological processes, however, a systematic examination of the functions lincRNAs responses rice to phosphate (Pi) starvation has not been performed. Here, we used computational method predict Pi-starved rice. Overall, 3,170 lincRNA loci were identified using RNA sequencing data from roots shoots control A competing endogenous (ceRNA) network was constructed for each tissue by considering...
It has been proved and widely acknowledged that messenger RNAs can talk to each other by competing for a limited pool of miRNAs. The endogenous are called as ceRNAs. Although some researchers have recently used ceRNAs do biological function annotations, few them investigated the ceRNA network on specific disease systematically. In this work, using both miRNA expression data mRNA breast cancer patient well target relations, authors proposed computational method construct...
Corona Virus Disease 2019 (COVID-19), an acute respiratory infectious disease caused by severe syndrome coronavirus-2 (SARS-CoV-2), has spread rapidly worldwide, resulting in a pandemic with high mortality rate. In clinical practice, we have noted that many critically ill or patients COVID-19 present typical sepsis-related manifestations, including multiple organ dysfunction syndrome, coagulopathy, and septic shock. addition, it been demonstrated some pathological similarities sepsis, such...
Cell-free DNA (cfDNA) fragmentation patterns have immense potential for early cancer detection. However, the definition of varies, ranging from entire genome to specific genomic regions. These not been systematically compared, impeding broader research and practical implementation. Here, 1382 plasma cfDNA sequencing samples 8 types are collected. Considering that within open chromatin regions is more susceptible fragmentation, 10 as features employed machine learning techniques evaluate...
Abstract Background cfDNA fragmentomics-based liquid biopsy is a potential option for noninvasive bladder cancer (BLCA) detection that remains an unmet clinical need. Methods We assessed the diagnostic performance of hotspot-driven machine-learning models in cohort 55 BLCA patients, 51 subjects with benign conditions, and 11 healthy volunteers. further performed functional bioinformatics analysis biological understanding interpretation tool’s capability. Results Urinary hotspots-based model...
As the leading cause of cancer death, lung seriously endangers human health and quality life. Although many studies have reported intestinal microbial composition cancer, little is known about interplay between microbiome metabolites how they affect development cancer. Herein, we combined 16S ribosomal RNA (rRNA) gene sequencing liquid chromatography-mass spectrometry (LC-MS) technology to analyze microbiota serum metabolism profile in a cohort 30 patients with different stages 15 healthy...
Background: Bladder cancer is a common malignancy that affects the human urinary tract. Muscle-invasive bladder (MIBC) aggressive and has poor prognosis. Previous studies have reported tumor-infiltrating lymphocytes (TILs) were associated with MIBC outcome; however, inconsistency remains mRNA level TIL markers' prognostic significance in unclear. Materials methods: In present study, we reanalyzed data from four public datasets (the Cancer Genome Atlas for investigation; CIT, GSE5287,...
Abstract The fine-scale cell-free DNA fragmentation patterns in early-stage cancers are poorly understood. We developed a de novo approach to characterize the hotspots from plasma whole-genome sequencing. Hotspots enriched open chromatin regions, and, interestingly, 3′end of transposons. showed global hypo-fragmentation liver and associated with genes involved initiation hepatocellular carcinoma cancer stem cells. varied across multiple demonstrated high performance for diagnosis...
Cancer is a major global health threat, and early detection of cancer crucial for improving patient outcomes. DNA methylation in circulating cell-free (cfDNA) has emerged as promising biomarker non-invasive diagnosis. However, the integration utilization existing cfDNA data have been limited, hindering comprehensive research efforts, especially discovery biomarkers. To address this challenge, we introduce cfMethDB, database dedicated to that encompasses 4828 publicly available datasets....
The geometric structure design of three-layer hollow fan blades is extremely complex, which not only directly related to the blade quality and manufacturing cost but also has a significant impact on engine performance. Based algorithms combined with rules process constraints, an intelligent method for proposed: A new cross-section curve based non-equidistant offset presented enable rapid wall plate structure. An innovative parametric corrugation in cross-sections driven by constraints such...