A5085156744- Cancer-related molecular mechanisms research
- RNA modifications and cancer
- Stock Market Forecasting Methods
- AI in cancer detection
- Financial Markets and Investment Strategies
- RNA and protein synthesis mechanisms
- Cancer-related gene regulation
- Advanced Bandit Algorithms Research
- Genomic variations and chromosomal abnormalities
- Energy Load and Power Forecasting
- Reinforcement Learning in Robotics
- Gene expression and cancer classification
- Domain Adaptation and Few-Shot Learning
- Chromosomal and Genetic Variations
- Hand Gesture Recognition Systems
- Time Series Analysis and Forecasting
- Bioinformatics and Genomic Networks
- Image Processing Techniques and Applications
- Retinal Imaging and Analysis
- Radiomics and Machine Learning in Medical Imaging
- Anomaly Detection Techniques and Applications
- Single-cell and spatial transcriptomics
- Digital Imaging for Blood Diseases
- Retinal and Optic Conditions
- Genomics and Chromatin Dynamics
Xi’an Jiaotong-Liverpool University
2016-2025
University of Saskatchewan
2024
Zhengzhou Children's Hospital
2024
Saskatoon Medical Imaging
2024
Shanghai Jiao Tong University
2023
University of Liverpool
2019-2021
University of California, Berkeley
2006-2021
Neusoft (China)
2019
Xiangya Hospital Central South University
2019
Central South University
2019
Abstract N 6-Methyladenosine (m6A) is the most prevalent RNA modification on mRNAs and lncRNAs. It plays a pivotal role during various biological processes disease pathogenesis. We present here comprehensive knowledgebase, m6A-Atlas, for unraveling m6A epitranscriptome. Compared to existing databases, m6A-Atlas features high-confidence collection of 442 162 reliable sites identified from seven base-resolution technologies quantitative (rather than binary) epitranscriptome profiles estimated...
N6-methyladenosine (m6A) is the most prevalent post-transcriptional modification in eukaryotes, and plays a pivotal role various biological processes, such as splicing, RNA degradation RNA–protein interaction. We report here prediction framework WHISTLE for transcriptome-wide m6A RNA-methylation site prediction. When tested on six independent datasets, our approach, which integrated 35 additional genomic features besides conventional sequence features, achieved major improvement accuracy of...
Abstract Motivation Recent progress in N7-methylguanosine (m7G) RNA methylation studies has focused on its internal (rather than capped) presence within mRNAs. Tens of thousands mRNA m7G sites have been identified mammalian transcriptomes, and a single resource to best share, annotate analyze the massive data generated recently are sorely needed. Results We report here m7GHub, comprehensive online platform for deciphering location, regulation pathogenesis m7G. The m7GHub consists four main...
Abstract Recent studies suggest that epi-transcriptome regulation via post-transcriptional RNA modifications is vital for all types. Precise identification of modification sites essential understanding the functions and regulatory mechanisms RNAs. Here, we present MultiRM, a method integrated prediction interpretation from sequences. Built upon an attention-based multi-label deep learning framework, MultiRM not only simultaneously predicts putative twelve widely occurring transcriptome (m 6...
Abstract 5-Methylcytosine (m5C) is one of the most prevalent covalent modifications on RNA. It known to regulate a broad variety RNA functions, including nuclear export, stability and translation. Here, we present m5C-Atlas, database for comprehensive collection annotation 5-methylcytosine. The contains 166 540 m5C sites in 13 species identified from 5 base-resolution epitranscriptome profiling technologies. Moreover, condition-specific methylation levels are quantified 351 bisulfite...
Deciphering the biological impacts of millions single nucleotide variants remains a major challenge. Recent studies suggest that RNA modifications play versatile roles in essential mechanisms, and are closely related to progression various diseases including multiple cancers. To comprehensively unveil association between disease-associated their epitranscriptome disturbance, we built RMDisease, database genetic can affect modifications. By integrating prediction results 18 different...
Psoriasis is a chronic inflammatory skin disease, which holds high incidence in China. However, professional dermatologists who can diagnose psoriasis early and correctly are insufficient China, especially the rural areas. A smart approach to identify by pictures would be highly adaptable countrywide could play useful role diagnosis regular treatment of psoriasis.Design evaluation identification system based on clinical images (without relying dermatoscope) that works effectively similar...
Motivation N6-methyladenosine (m6A) is the most prevalent RNA modification on mRNAs and lncRNAs. Evidence increasingly demonstrates its crucial importance in essential molecular mechanisms various diseases. With recent advances sequencing techniques, tens of thousands m6A sites are identified a typical high-throughput experiment, posing key challenge to distinguish functional from remaining 'passenger' (or 'silent') sites. Results: We performed comparative conservation analysis human mouse...
As the most pervasive epigenetic marker present on mRNAs and long non-coding RNAs (lncRNAs), N
Machine Learning algorithms and Neural Networks are widely applied to many different areas such as stock market prediction, facial recognition automatic machine translation. This paper introduces a novel strategy based on the classic Deep Reinforcement algorithm, QNetwork, for portfolio management. It is type of deep neural network which optimized by Q Learning. To adapt Q-Network production, we first discretize action space so that management becomes problem can solve. Following this,...
Abstract As the most pervasive epigenetic mark present on mRNA and lncRNA, N6-methyladenosine (m6A) RNA methylation regulates all stages of life in various biological processes disease mechanisms. Computational methods for deciphering modification have achieved great success recent years; nevertheless, their potential remains underexploited. One reason this is that existing models usually consider only sequence transcripts, ignoring regions (or geography) transcripts such as 3′UTR intron,...
Thoracic echocardiography (TTE) can provide sufficient cardiac structure information, evaluate hemodynamics and function, is an effective method for atrial septal defect (ASD) examination. This paper aims to study a deep learning based on ultrasound video assist in ASD diagnosis. We chose four standard views pediatric identify defects; the were as follows: subcostal sagittal view of atrium septum (subSAS), apical four-chamber (A4C), low parasternal (LPS4C), short-axis large artery (PSAX)....
Although sign language recognition aids non-hearing-impaired understanding, many hearing-impaired individuals still rely on alone due to limited literacy, underscoring the need for advanced production and translation (SLP SLT) systems. In field of production, lack adequate models datasets restricts practical applications. Existing face challenges in accuracy pose control, making it difficult provide fluent expressions across diverse scenarios. Additionally, data resources are scarce,...
Long-sequence causal reasoning seeks to uncover relationships within extended time series data but is hindered by complex dependencies and the challenges of validating links. To address limitations large-scale language models (e.g., GPT-4) in capturing intricate emotional causality dialogues, we propose CauseMotion, a long-sequence framework grounded Retrieval-Augmented Generation (RAG) multimodal fusion. Unlike conventional methods relying only on textual information, CauseMotion enriches...
Artificial intelligence has achieved notable results in sign language recognition and translation. However, relatively few efforts have been made to significantly improve the quality of life for 72 million hearing-impaired people worldwide. Sign translation models, relying on video inputs, involves with large parameter sizes, making it time-consuming computationally intensive be deployed. This directly contributes scarcity human-centered technology this field. Additionally, lack datasets...
In endovascular surgery, the precise identification of catheters and guidewires in X-ray images is essential for reducing intervention risks. However, accurately segmenting catheter guidewire structures challenging due to limited availability labeled data. Foundation models offer a promising solution by enabling collection similar domain data train whose weights can be fine-tuned downstream tasks. Nonetheless, large-scale training constrained necessity maintaining patient privacy. This paper...
Deep reinforcement learning (DRL) has been applied in financial portfolio management to improve returns changing market conditions. However, unlike most fields where DRL is widely used, the stock more volatile and dynamic as it affected by several factors such global events investor sentiment. Therefore, remains a challenge construct DRL-based framework with strong return capability, stable training, generalization ability. This study introduces new utilizing Memory Instance Gated...
Recent multimodal large language models (MLLMs) have demonstrated significant potential in open-ended conversation, generating more accurate and personalized responses. However, their abilities to memorize, recall, reason sustained interactions within real-world scenarios remain underexplored. This paper introduces MMRC, a Multi-Modal Real-world Conversation benchmark for evaluating six core of MLLMs: information extraction, multi-turn reasoning, update, image management, memory answer...
Artificial intelligence has achieved notable results in sign language recognition and translation. However, relatively few efforts have been made to significantly improve the quality of life for 72 million hearing-impaired people worldwide. Sign translation models, relying on video inputs, involves with large parameter sizes, making it time-consuming computationally intensive be deployed. This directly contributes scarcity human-centered technology this field. Additionally, lack datasets...