A5100397381- X-ray Diffraction in Crystallography
- Crystallization and Solubility Studies
- Computational Drug Discovery Methods
- Machine Learning in Bioinformatics
- Genomics and Phylogenetic Studies
- RNA and protein synthesis mechanisms
- Protein Structure and Dynamics
- Machine Learning in Materials Science
- Crystallography and molecular interactions
- Cell Image Analysis Techniques
- Esophageal Cancer Research and Treatment
- Advanced Electron Microscopy Techniques and Applications
- Advanced Image and Video Retrieval Techniques
- Gene expression and cancer classification
- Gastric Cancer Management and Outcomes
- Bioinformatics and Genomic Networks
- Retinal Imaging and Analysis
- Genomics and Chromatin Dynamics
- RNA modifications and cancer
- Metaheuristic Optimization Algorithms Research
- Single-cell and spatial transcriptomics
- Metabolomics and Mass Spectrometry Studies
- Advanced Multi-Objective Optimization Algorithms
- Esophageal and GI Pathology
- Radiomics and Machine Learning in Medical Imaging
Shanghai Municipal Education Commission
2016-2025
Shanghai Jiao Tong University
2016-2025
Shanghai Chest Hospital
2020-2025
West Anhui University
2025
Nanjing University of Chinese Medicine
2025
Zhejiang Cancer Hospital
2021-2024
Charité - Universitätsmedizin Berlin
2024
Chinese Academy of Sciences
2015-2024
Northeast Forestry University
2024
Tongren Hospital
2022-2024
The long non-coding RNA (lncRNA) studies have been hot topics in the field of biology. Recent shown that their subcellular localizations carry important information for understanding complex biological functions. Considering costly and time-consuming experiments identifying localization lncRNAs, computational methods are urgently desired. However, to best our knowledge, there no tools predicting lncRNA locations date.In this study, we report an ensemble classifier-based predictor,...
The standard self-consistent-charge density-functional-tight-binding (SCC-DFTB) method (Phys. Rev. B 1998, 58, 7260) is derived by a second-order expansion of the density functional theory total energy expression, followed an approximation charge fluctuations monopoles and effective damped Coulomb interaction between atomic net charges. central assumptions behind this charge−charge are inverse relation size chemical hardness use fixed parameter independent state. While these approximations...
Camrelizumab and chemotherapy demonstrated durable antitumor activity with a manageable safety profile as first-line treatment in patients advanced esophageal squamous cell carcinoma (ESCC). This study aimed to evaluate the efficacy of camrelizumab plus neoadjuvant chemotherapy, using pathologically complete response (pCR) primary endpoint, for locally ESCC.Patients but resectable thoracic ESCC, staged T1b-4a, N2-3 (≥3 stations), M0 or M1 lymph node metastasis (confined supraclavicular...
A novel coronavirus, called 2019-nCoV, was recently found in Wuhan, Hubei Province of China, and now is spreading across China other parts the world. Although there are some drugs to treat no proper scientific evidence about its activity on virus. It high significance develop a drug that can combat virus effectively save valuable human lives. usually takes much longer time using traditional methods. For it better rely alternative methods such as deep learning disease since 2019-nCoV highly...
Deep neural networks have been integrated into the whole clinical decision procedure which can improve efficiency of diagnosis and alleviate heavy workload physicians. Since most are supervised, their performance heavily depends on volume quality available labels. However, few such labels exist for rare diseases (e.g., new pandemics). Here we report a medical multimodal large language model (Med-MLLM) radiograph representation learning, learn broad knowledge image understanding, text...
Motivated by the long-term goal of understanding vectorial biological processes such as proton transport (PT) in biomolecular ion pumps, a number developments were made to establish combined quantum mechanical/molecular mechanical (QM/MM) methods suitable for studying chemical reactions involving significant charge separation condensed phase. These summarized and discussed with representative problems. Specifically, free energy perturbation boundary potential treating long-range...
Abstract Motivation Protein subcellular localization prediction has been an important research topic in computational biology over the last decade. Various automatic methods have proposed to predict locations for large scale protein datasets, where statistical machine learning algorithms are widely used model construction. A key step these predictors is encoding amino acid sequences into feature vectors. Many studies shown that features extracted from biological domains, such as gene...
This study was to present the 2016 prevalence estimates of Chinese school-aged children meeting physical fitness standards and examine differences by sex residence locales in who did not meet standards.We conducted cross-sectional analyses 171,991 adolescents (boy: 50.0%, Grades 1-12) participated Physical Activity Fitness China-The Youth Study. The main outcomes were measures, assessed 2014 revised National Student Standard (CNSPFS), covering areas aerobic capacity, upper body strength,...
Allosteric modulation provides exciting opportunities for drug discovery of enzymes, ion channels, and G protein-coupled receptors. As cation channels gated by extracellular ATP, P2X receptors have attracted wide attention as new targets. Although small molecules targeting entered into clinical trials rheumatoid arthritis, cough, pain, negative allosteric these remains largely unexplored. Here, combining X-ray crystallography, computational modeling, functional studies channel mutants, we...
Hepatocellular carcinoma (HCC) is a significant health problem worldwide with poor prognosis. Drug repositioning represents profitable strategy to accelerate drug discovery in the treatment of HCC. In this study, we developed new approach for predicting therapeutic drugs HCC based on tissue-specific pathways and identified three newly predicted that are likely be We validated these by analyzing their overlapping indications reported PubMed literature. By using cancer cell line data database,...
Many bioactive peptides demonstrated therapeutic effects over complicated diseases, such as antiviral, antibacterial, anticancer, etc. It is possible to generate a large number of potentially using deep learning in manner analogous the generation de novo chemical compounds acquired training set. Such generative techniques would be significant for drug development since are much easier and cheaper synthesize than compounds. Despite limited availability learning-based peptide-generating...
The development of the aviation industry is accompanied by continuous research high-performance aluminum alloys. Stuck in vast untapped composition space and routine trial-and-error method, efficiently discovering high-strength alloys remains a significant challenge. To address this issue, we proposed knowledge-aware design system (KADS) using machine learning (ML) methods to facilitate rational An alloy database containing 5113 samples was built based on Al–Zn–Mg–Cu, Al–Cu, Al–Li series...
The basal breast cancer subtype is enriched for triple-negative (TNBC) and displays consistent large chromosomal deletions. Here, we characterize evolution maintenance of chromosome 4p (chr4p) loss in cancer. Analysis Cancer Genome Atlas data shows recurrent deletion chr4p Phylogenetic analysis a panel 23 primary tumor/patient-derived xenograft cancers reveals early deletion. Mechanistically show that associated with enhanced proliferation. Gene function studies identify an unknown gene,...
Abstract Cancer is rarely the straightforward consequence of an abnormality in a single gene, but rather reflects complex interplay many genes, represented as gene modules. Here, we leverage recent advances model-agnostic interpretation approach and develop CGMega, explainable graph attention-based deep learning framework to perform cancer module dissection. CGMega outperforms current approaches prediction, it provides promising integrate multi-omics information. We apply breast cell line...
In most applications, component extraction is important when components of non-stationary multi-component signal are key features to be monitored and analyzed. Existing methods either sensitive noise or forced select a proper time-frequency representation for the considered signal. this paper, we present novel method The proposed combines parameterized de-chirping band-pass filter obtain signal, which avoids dealing with works well under heavy noise. addition, it able analyze whose have...
Developing machine learning models with high generalization capability for predicting chemical reaction yields is of significant interest and importance. The efficacy such depends heavily on the representation reactions, which has commonly been learned from SMILES or graphs molecules using deep neural networks. However, progression reactions inherently determined by molecular 3D geometric properties, have recently highlighted as crucial features in accurately properties reactions....
Benefiting from high-throughput experimental technologies, whole-genome analysis of microRNAs (miRNAs) has been more and common to uncover important regulatory roles miRNAs identify miRNA biomarkers for disease diagnosis. As a complementary information the data, domain knowledge like Gene Ontology KEGG pathway is usually used guide gene function analysis. However, functional annotation scarce in public databases. Till now, only few methods have proposed measuring similarity between based on...
The thermal conductivities of two groups silicon nanoribbons ∼20 and ∼30 nm thickness various widths have been measured analyzed through combining the Callaway model Fuchs-Sondheimer (FS) reduction function. results show that while data for thick ribbons can be well-explained by classical size effect, deviate from prediction remarkably, effects beyond phonon-boundary scattering must considered. measurements Young's modulus thin yield significantly lower values than corresponding bulk value,...