Article
Biology
Grzegorz Skoraczynski, Anna Gambin, Blazej Miasojedow
Summary: This article introduces an algorithm called Alignstein for LC-MS retention time alignment, which effectively overcomes the limitations of traditional algorithms in dealing with retention time drift. It does not require a reference sample or prior signal identification, and it can detect the information contained in chromatograms.
Article
Forestry
Xinyu Miao, Jian Li, Yunjie Mu, Cheng He, Yunfei Ma, Jie Chen, Wentao Wei, Demin Gao
Summary: This study introduces an enhanced window-based Transformer time series forecasting model aimed at improving the precision of forest fire predictions. Using remote sensing satellite and GIS technologies, a myriad of forest fire influencing factors were identified, and their interrelationships were estimated through a multicollinearity test. The proposed model demonstrated superior predictive performance, harnessing spatial background information efficiently and effectively utilizing the periodicity of forest fire factors.
Article
Chemistry, Multidisciplinary
Constantino A. Garcia, Alberto Gil-de-la-Fuente, Coral Barbas, Abraham Otero
Summary: Retention time information is crucial for metabolite annotation in metabolomic experiments. By training machine learning models, the retention time for a specific chromatographic method can be accurately predicted, providing valuable support for metabolite annotation workflow.
JOURNAL OF CHEMINFORMATICS
(2022)
Article
Biochemistry & Molecular Biology
Dmitriy D. Matyushin, Anastasia Yu Sholokhova, Aleksey K. Buryak
Summary: The use of deep learning in predicting retention indices has significantly improved accuracy for non-polar stationary phases. This study demonstrates the first application of deep learning for retention index prediction on polar and mid-polar stationary phases, achieving high accuracy. Furthermore, the approach can be directly applied to predict the second dimension retention times if a large enough dataset is available.
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES
(2021)
Article
Environmental Sciences
Hongkang Chen, Tieding Lu, Jiahui Huang, Xiaoxing He, Kegen Yu, Xiwen Sun, Xiaping Ma, Zhengkai Huang
Summary: In this study, a dual variational modal decomposition long short-term memory (DVMD-LSTM) model is proposed to improve the accuracy of GNSS time series prediction. This model extracts fluctuation features from the residual terms obtained after VMD decomposition to reduce prediction errors. Experimental results show that compared to the VMD-LSTM model, the DVMD-LSTM model achieves significant improvements in prediction performance at all measurement stations.
Article
Biochemical Research Methods
Elizaveta S. Fedorova, Dmitriy D. Matyushin, Ivan Plyushchenko, Andrey N. Stavrianidi, Aleksey K. Buryak
Summary: This study investigates the prediction of retention time for small molecules in HPLC using deep learning models. By utilizing a large retention time data set from the METLIN database and representing molecules as SMILES strings, the proposed model achieved promising results in retention time prediction.
JOURNAL OF CHROMATOGRAPHY A
(2022)
Article
Biochemical Research Methods
Eunwoo Choi, Won Jun Yoo, Hwa-Yong Jang, Tae -Young Kim, Sung Ki Lee, Han Bin Oh
Summary: A standalone software with a user-friendly GUI is developed to predict LC-MS retention times of dansylated metabolites. The LC-RTs are predicted using an ANN machine-learning model trained on 315 dansylated urine metabolites. The LC-RT prediction model shows reliable results with a mean absolute deviation of 0.74 min for the 30 min LC run, making it useful for identifying nontargeted dansylated metabolites.
JOURNAL OF CHROMATOGRAPHY A
(2023)
Article
Biochemistry & Molecular Biology
Darien Yeung, Victor Spicer, Rene P. Zahedi, Oleg Krokhin
Summary: This study uses shallow convolutional neural network (CNN) and gated recurrent unit (GRU) models to predict peptide retention time, and finds that the spatial features obtained through CNN are correlated with real-world physicochemical properties. In addition, the study determines that the discovered parameters are micro-coefficients that contribute to the macro-coefficient (hydrophobicity). By embedding these features into the GRU model, peptide retention time can be highly accurately predicted with good interpretability.
COMPUTATIONAL AND STRUCTURAL BIOTECHNOLOGY JOURNAL
(2023)
Article
Mathematics, Interdisciplinary Applications
Ke Fu He Li, Pengfei Deng
Summary: In this paper, a deep learning model called DTIGNet is proposed for chaotic time series prediction. The model includes a hybrid deep neural network and an improved temporal-inception module. The model is validated on multiple chaotic time series and the results show that DTIGNet achieves higher accuracy and better performance compared to other methods.
CHAOS SOLITONS & FRACTALS
(2022)
Article
Chemistry, Analytical
Alexander Kensert, Robbin Bouwmeester, Kyriakos Efthymiadis, Peter Van Broeck, Gert Desmet, Deirdre Cabooter
Summary: This study utilized graph convolutional networks (GCNs) to optimize molecular representations and predict the retention times of molecules in different chromatographic data sets. The performance of GCNs was found to be superior, significantly outperforming other benchmarks, or performing similarly to them. Saliency maps revealed significant differences in important molecular sub-structures for predictions in different chromatographic data sets.
ANALYTICAL CHEMISTRY
(2021)
Article
Biochemistry & Molecular Biology
Sara M. de Cripan, Adria Cereto-Massague, Pol Herrero, Andrei Barcaru, Nuria Canela, Xavier Domingo-Almenara
Summary: In this study, a rationalized framework for machine learning-based retention time prediction of trimethylsilyl derivatives of metabolites in gas chromatography was developed. Different machine learning paradigms were compared, and the influence of computational molecular structure representation on the prediction models was explored. The study demonstrated that machine learning can accurately predict retention time, providing insights into the true structure of unknown metabolites, and set the guidelines to assess confidence in metabolite identification using predicted retention time data.
Article
Biochemistry & Molecular Biology
Zhanbo Chen, Qiufeng Wei
Summary: This paper proposes an improved survival prediction model using deep forest and self-supervised learning to enhance the prediction performance of high-dimensional genomic data. Experimental results show that the proposed method outperforms other methods in survival analysis. The developed prediction model will facilitate personalized treatment decisions for doctors.
Article
Chemistry, Analytical
Petr Kozlik, Jana Vaclova, Kveta Kalikova
Summary: In this study, three recently developed HILIC columns were characterized in detail to compare their peptide retention mechanisms, revealing a multimodal retention mechanism in systems with these stationary phases. By balancing the properties of analytes and stationary phases, satisfactory retention and peak shape of peptides can be achieved. Buffer concentration and pH optimization was confirmed to be an effective tool for manipulating retention and peak symmetry, enhancing the potential applications of these columns in the analysis of diverse compounds.
MICROCHEMICAL JOURNAL
(2021)
Article
Biochemical Research Methods
Bailing Zhou, Maolin Ding, Jing Feng, Baohua Ji, Pingping Huang, Junye Zhang, Xue Yu, Zanxia Cao, Yuedong Yang, Yaoqi Zhou, Jihua Wang
Summary: Long non-coding RNAs (lncRNAs) are important in biological processes and diseases. This study developed deep learning algorithms to distinguish different types of lncRNAs from mRNAs, resulting in improved accuracy.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Biochemical Research Methods
Bailing Zhou, Maolin Ding, Jing Feng, Baohua Ji, Pingping Huang, Junye Zhang, Xue Yu, Zanxia Cao, Yuedong Yang, Yaoqi Zhou, Jihua Wang
Summary: Long non-coding RNAs (lncRNAs) are important in biological processes and disease. Algorithms have been developed to distinguish lncRNAs from mRNAs, resulting in the discovery of over 600,000 lncRNAs. However, only a small fraction of these have been validated through low-throughput experiments. To prioritize potentially functional lncRNAs and overcome the challenge of small datasets, deep learning algorithms were employed in this study.
BRIEFINGS IN BIOINFORMATICS
(2023)
Article
Biochemistry & Molecular Biology
Le Zhang, Tianming Lan, Chuyu Lin, Wenyuan Fu, Yaohua Yuan, Kaixiong Lin, Haimeng Li, Sunil Kumar Sahu, Zhaoyang Liu, Daqing Chen, Qunxiu Liu, Aishan Wang, Xiaohong Wang, Yue Ma, Shizhou Li, Yixin Zhu, Xingzhuo Wang, Xiaotong Ren, Haorong Lu, Yunting Huang, Jieyao Yu, Boyang Liu, Qing Wang, Shaofang Zhang, Xun Xu, Huanming Yang, Dan Liu, Huan Liu, Yanchun Xu
Summary: The South China tiger is critically endangered due to functional extinction in the wild and inbreeding depression among the captive population. This research assembled and characterized the genomes of the South China tiger and six other tiger subspecies, revealing the genomic signatures of inbreeding depression in the South China tiger. The study provides important information for genetic management policies for the South China tiger.
MOLECULAR ECOLOGY RESOURCES
(2023)
Correction
Multidisciplinary Sciences
Yilong Li, Nicola D. Roberts, Jeremiah A. Wala, Ofer Shapira, Steven E. Schumacher, Kiran Kumar, Ekta Khurana, Sebastian Waszak, Jan O. Korbel, James E. Haber, Marcin Imielinski, Joachim Weischenfeldt, Rameen Beroukhim, Peter J. Campbell
Correction
Multidisciplinary Sciences
Esther Rheinbay, Morten Muhlig Nielsen, Federico Abascal, Jeremiah A. Wala, Ofer Shapira, Grace Tiao, Henrik Hornshoj, Julian M. Hess, Randi Istrup Juul, Ziao Lin, Lars Feuerbach, Radhakrishnan Sabarinathan, Tobias Madsen, Jaegil Kim, Loris Mularoni, Shimin Shuai, Andres Lanzos, Carl Herrmann, Yosef E. Maruvka, Ciyue Shen, Samirkumar B. Amin, Pratiti Bandopadhayay, Johanna Bertl, Keith A. Boroevich, John Busanovich, Joana Carlevaro-Fita, Dimple Chakravarty, Calvin Wing Yiu Chan, David Craft, Priyanka Dhingra, Klev Diamanti, Nuno A. Fonseca, Abel Gonzalez-Perez, Qianyun Guo, Mark P. Hamilton, Nicholas J. Haradhvala, Chen Hong, Keren Isaev, Todd A. Johnson, Malene Juul, Andre Kahles, Abdullah Kahraman, Youngwook Kim, Jan Komorowski, Kiran Kumar, Sushant Kumar, Donghoon Lee, Kjong-Van Lehmann, Yilong Li, Eric Minwei Liu, Lucas Lochovsky, Keunchil Park, Oriol Pich, Nicola D. Roberts, Gordon Saksena, Steven E. Schumacher, Nikos Sidiropoulos, Lina Sieverling, Nasa Sinnott-Armstrong, Chip Stewart, David Tamborero, Jose M. C. Tubio, Husen M. Umer, Liis Uuskuela-Reimand, Claes Wadelius, Lina Wadi, Xiaotong Yao, Cheng-Zhong Zhang, Jing Zhang, James E. Haber, Asger Hobolth, Marcin Imielinski, Manolis Kellis, Michael S. Lawrence, Christian von Mering, Hidewaki Nakagawa, Benjamin J. Raphael, Mark A. Rubin, Chris Sander, Lincoln D. Stein, Joshua M. Stuart, Tatsuhiko Tsunoda, David A. Wheeler, Rory Johnson, Jueri Reimand, Mark Gerstein, Ekta Khurana, Peter J. Campbell, Nuria Lopez-Bigas, Joachim Weischenfeldt, Rameen Beroukhim, Inigo Martincorena, Jakob Skou Pedersen, Gad Getz
Review
Public, Environmental & Occupational Health
Xiaoping Cen, Fengao Wang, Xinhe Huang, Dragomirka Jovic, Fred Dubee, Huanming Yang, Yixue Li
Summary: This article reviews the role of omics technologies in studying COVID-19, including genomics, proteomics, single-cell multi-omics, and clinical phenomics. Large-scale sequencing and advanced analysis methods contribute to the understanding of virus evolution, prediction of severity risk, and identification of potential treatments. Omics technologies enable precise and global prevention and medicine for COVID-19 by utilizing big data capability and phenotypes refinement. Additionally, deep learning models can be used to decode the evolution rule of SARS-CoV-2, forecast new variants, and prevent future pandemics.
BIOSAFETY AND HEALTH
(2023)
Article
Chemistry, Analytical
Zhe Ren, Guoying Sun, Qianqian Zhang, Shaomin Zou, Jianhong Chen, Weining Zhao, Guixue Hou, Zeyan Zhong, Jialong Li, Yuhua Ye, Xiangmin Xu, Liang Lin
Summary: A LC-MS/MS-based approach was used to discover unique expression patterns of hemoglobin subunits in different alpha-thalassemia subtypes. Hemoglobin subunit mu showed significant upregulation in silent alpha-thalassemia patients, indicating its potential as a novel biomarker for clinical screening.
ANALYTICAL CHEMISTRY
(2023)
Article
Multidisciplinary Sciences
Xiaomin Liu, Leying Zou, Chao Nie, Youwen Qin, Xin Tong, Jian Wang, Huanming Yang, Xun Xu, Xin Jin, Liang Xiao, Tao Zhang, Junxia Min, Yi Zeng, Huijue Jia, Yong Hou
Summary: Although the association between human microbiome, especially gut microbiota, and longevity has been revealed in recent studies, the causality between them is still unclear. This study used bidirectional two-sample Mendelian randomization (MR) analyses to assess the relationship between the human microbiome (gut and oral microbiota) and longevity. The findings suggest that certain disease-protected gut microbiota and probiotics are associated with increased odds of longevity, while other gut microbiota are negatively associated with longevity.
SCIENTIFIC REPORTS
(2023)
Article
Biotechnology & Applied Microbiology
Xiangwei Hu, Kai Xia, Minhui Dai, Xiaofeng Han, Peng Yuan, Jia Liu, Shiwei Liu, Fuhuai Jia, Jiayu Chen, Fangfang Jiang, Jieyao Yu, Huanming Yang, Jian Wang, Xun Xu, Xin Jin, Karsten Kristiansen, Liang Xiao, Wei Chen, Mo Han, Shenglin Duan
Summary: Intermittent fasting is a promising weight loss method that modulates the gut microbiota. A three-week IF program resulted in an average weight loss of 3.67 kg and improved clinical parameters, regardless of initial BMI and gut microbiota status.
NPJ BIOFILMS AND MICROBIOMES
(2023)
Article
Ecology
Yang Zhou, Xiaoyu Zhan, Jiazheng Jin, Long Zhou, Juraj Bergman, Xuemei Li, Marjolaine Marie C. Rousselle, Meritxell Riera Belles, Lan Zhao, Miaoquan Fang, Jiawei Chen, Qi Fang, Lukas Kuderna, Tomas Marques-Bonet, Haruka Kitayama, Takashi Hayakawa, Yong-Gang Yao, Huanming Yang, David N. Cooper, Xiaoguang Qi, Dong-Dong Wu, Mikkel Heide Schierup, Guojie Zhang
Summary: A comparative analysis of Y chromosomes in 29 primate species reveals rapid evolution and different patterns of evolution in different regions. The Y chromosome plays a critical role in determining male sex and has unique sequence classes that have experienced distinct evolutionary trajectories. By generating and analyzing 19 new primate sex chromosome assemblies, along with 10 existing ones, this study reports the rapid evolution of the primate Y chromosome. Different primate lineages exhibit varying rates of gene loss, structural changes, and chromatin modifications on their Y chromosomes. The study also highlights the contribution of selection on Y-linked genes to the evolution of male traits across primates.
NATURE ECOLOGY & EVOLUTION
(2023)
Article
Biochemistry & Molecular Biology
Xiaoying Zhao, Kunli Qu, Benedetta Curci, Huanming Yang, Lars Bolund, Lin Lin, Yonglun Luo
Summary: Recent progress in CRISPR gene editing tools has expanded the possibilities for treating devastating genetic diseases. In this study, three methods of gene editing (NHBEJ, HDR, and PE) were compared for correcting loss-of-function mutations in Duchenne Muscular Dystrophy. The highest efficiency was achieved with NHBEJ, followed by HDR and PE2. The correction efficiency was increased with the use of PE3. This study demonstrates the potential for highly efficient correction of DMD mutations using CRISPR gene editing.
Article
Multidisciplinary Sciences
Zhuye Jie, Qian Zhu, Yuanqiang Zou, Qili Wu, Min Qin, Dongdong He, Xiaoqian Lin, Xin Tong, Jiahao Zhang, Zhu Jie, Wenwei Luo, Xiao Xiao, Shiyu Chen, Yonglin Wu, Gongjie Guo, Shufen Zheng, Yong Li, Weihua Lai, Huanming Yang, Jian Wang, Liang Xiao, Jiyan Chen, Tao Zhang, Karsten Kristiansen, Huijue Jia, Shilong Zhong
Summary: Through MWAS survey, a study found that individuals with ACVD have lower levels of Bacteroides cellulosilyticus, Faecalibacterium prausnitzii, and Roseburia intestinalis. Selected bacteria from healthy Chinese individuals were tested in Apoe(-/-) mice, showing that administration of these bacteria significantly improves cardiac function, reduces plasma lipid levels, and attenuates atherosclerotic plaque formation. Analysis of gut microbiota, plasma metabolome, and liver transcriptome revealed a beneficial modulation of the gut microbiota associated with a 7 alpha-dehydroxylation-LCA-FXR pathway. This study provides insights into the potential of specific bacteria for ACVD prevention and treatment.
Article
Chemistry, Multidisciplinary
Zhiming Li, Yanmei Ju, Jingjing Xia, Zhe Zhang, Hefu Zhen, Xin Tong, Yuzhe Sun, Haorong Lu, Yang Zong, Peishan Chen, Kaiye Cai, Zhen Wang, Huanming Yang, Jiucun Wang, Jian Wang, Yong Hou, Xin Jin, Tao Zhang, Wenwei Zhang, Xun Xu, Liang Xiao, Ruijin Guo, Chao Nie
Summary: This study used deep-shotgun sequencing to analyze 450 facial samples and 2069 publicly available skin metagenomic datasets, and constructed a Unified Human Skin Genome (UHSG) catalog containing 813 prokaryotic species. The core functions of the skin microbiome were described based on the UHSG, and differences in amino acid metabolism, carbohydrate metabolism, and drug resistance functions among different phyla were identified. Additionally, analysis of near-complete genomes revealed 1220 putative novel secondary metabolites. The UHSG provides a convenient reference database for studying the role of skin microorganisms in the skin.
Article
Biotechnology & Applied Microbiology
Wenxi Li, Hewei Liang, Xiaoqian Lin, Tongyuan Hu, Zhinan Wu, Wenxin He, Mengmeng Wang, Jiahao Zhang, Zhuye Jie, Xin Jin, Xun Xu, Jian Wang, Huanming Yang, Wenwei Zhang, Karsten Kristiansen, Liang Xiao, Yuanqiang Zou
Summary: The study presents a Cultivated Oral Bacteria Genome Reference (COGR) consisting of 1089 high-quality genomes. COGR covers five phyla and contains 195 species-level clusters, with 315 genomes representing species with no taxonomic annotation. The oral microbiota differs between individuals, with person-specific clusters. The Streptococcus genus dominates COGR and many of these strains harbor quorum sensing pathways important for biofilm formation. Clusters containing unknown bacteria are enriched in individuals with rheumatoid arthritis, highlighting the importance of culture-based isolation for characterizing and exploiting oral bacteria.
NPJ BIOFILMS AND MICROBIOMES
(2023)
Article
Biology
Xi Dai, Honglian Shao, Nianqin Sun, Baiquan Ci, Jun Wu, Chuanyu Liu, Liang Wu, Yue Yuan, Xiaoyu Wei, Huanming Yang, Longqi Liu, Weizhi Ji, Bing Bai, Zhouchun Shang, Tao Tan
Summary: This study applied scATAC-seq technology to investigate the chromatin status of in vitro cultured cynomolgus monkey embryos. The findings provide insights into the chromatin reorganization and transcriptional regulatory mechanisms during early post-implantation development in primates, including the identification of regulatory factors and lineage specification.
Article
Cell Biology
Chentao Yang, Yang Zhou, Yanni Song, Dongya Wu, Yan Zeng, Lei Nie, Panhong Liu, Shilong Zhang, Guangji Chen, Jinjin Xu, Hongling Zhou, Long Zhou, Xiaobo Qian, Chenlu Liu, Shangjin Tan, Chengran Zhou, Wei Dai, Mengyang Xu, Yanwei Qi, Xiaobo Wang, Lidong Guo, Guangyi Fan, Aijun Wang, Yuan Deng, Yong Zhang, Jiazheng Jin, Yunqiu He, Chunxue Guo, Guoji Guo, Qing Zhou, Xun Xu, Huanming Yang, Jian Wang, Shuhua Xu, Yafei Mao, Xin Jin, Jue Ruan, Guojie Zhang
Summary: Since the release of the complete human genome, efforts in human genomic study have shifted towards closing gaps in ethnic diversity. In this study, a fully phased diploid human genome from a Han Chinese male individual (CN1) was presented, achieving the telomere-to-telomere (T2T) level. Comparisons with the CHM13 haploid T2T genome revealed significant variations in the centromere and numerous novel structural variations outside the centromere. CN1 outperformed CHM13 as a reference genome for the East Asian population, impacting rare SNP calling and uncovering East Asian specific introgression sequences.
Article
Ophthalmology
Wei Li, Xiang-Dong He, Zheng-Tao Yang, Dong-Ming Han, Yan Sun, Yan-Xian Chen, Xiao-Tong Han, Si-Cheng Guo, Yu-Ting Ma, Xin Jin, Huan-Ming Yang, Ya Gao, Zhuo-Shi Wang, Jian-Kang Li, Wei He
Summary: The aim of this study was to investigate the genetic characteristics and genotype-phenotype associations in a trio-based cohort of inherited eye diseases (IEDs). Through retrospective analysis of a large cohort of Chinese proband-parent trios, the researchers identified 108 IED-causative genes and found that the top 24 genes explained two-thirds of the genetically solved trios. The study also revealed the significant role of de novo mutations (DNMs) in IEDs and its association with paternal age at reproduction.
INVESTIGATIVE OPHTHALMOLOGY & VISUAL SCIENCE
(2023)