A5018731800- Mass Spectrometry Techniques and Applications
- Advanced Proteomics Techniques and Applications
- Biometric Identification and Security
- Machine Learning in Bioinformatics
- Face and Expression Recognition
- Face recognition and analysis
- Metabolomics and Mass Spectrometry Studies
- Complex Systems and Time Series Analysis
- Advanced Steganography and Watermarking Techniques
- Traditional Chinese Medicine Studies
- Medical Image Segmentation Techniques
- Stock Market Forecasting Methods
- Image Processing Techniques and Applications
- Image and Signal Denoising Methods
- Digital Media Forensic Detection
- Financial Markets and Investment Strategies
Xiamen University
2022-2024
Capital University of Economics and Business
2022
Northeast Electric Power University
2019-2021
Data-independent acquisition (DIA) technology for protein identification from mass spectrometry and related algorithms is developing rapidly. The spectrum-centric analysis of DIA data without the use spectra library data-dependent represents a promising direction. In this paper, we proposed an untargeted method, Dear-DIAXMBD, direct data. Dear-DIAXMBD first integrates deep variational autoencoder triplet loss to learn representations extracted fragment ion chromatograms, then uses k-means...
In shotgun proteomics, the proteome search engine analyzes mass spectra obtained by experiments, and then a peptide-spectra match (PSM) is reported for each spectrum. However, most of PSMs identified are incorrect, therefore various postprocessing software have been developed reranking peptide identifications. Yet these methods suffer from issues such as dependency on distribution, reliance shallow models, limited effectiveness. this work, we propose AttnPep, deep learning model rescoring...
OpenSWATH is an analysis toolkit commonly used for data independent acquisition (DIA). Although the output of controlled at 1% false discovery rate (FDR), report still contains many peptide precursors with low similarity fragments. At last step quantification, researchers usually need to manually check extracted ion chromatograms (XICs) fragments distinguish high confidence and precursors. Here we developed algorithm a Graphic User Interface named MSSort-DIAXMBD, which combines deep...
Machine learning methods have been used in multifactor stock strategy for years. This paper uses three machine and linear regression method to find the most appropriate approach. First, a framework is established 10 style factors 30 industry are chosen. Second, four forecast portfolio returns compared by predicting returns, successful rate, Sharpe ratio. Finally, this draws conclusion. The main findings as follows: support vector has stable rate predicting, while ridge unstable with more...
Abstract Data-independent acquisition (DIA) technology for protein identification from mass spectrometry and related algorithms is developing rapidly. The spectrum-centric analysis of DIA data without the use spectra library data-dependent (DDA) represents a promising direction. In this paper, we proposed an untargeted method, Dear-DIA XMBD , direct data. first integrates deep variational autoencoder triplet loss to learn representations extracted fragment ion chromatograms, then uses...