Article
Biochemistry & Molecular Biology
Clemens Rauer, Neeladri Sen, P. Vaishali Waman, Mahnaz Abbasian, A. Christine Orengo
Summary: Understanding protein function mechanisms is crucial for biological applications, but sparse experimental annotations require theoretical strategies to bridge the gap. The latest research focuses on building functional subclassifications and using evolutionary conservation to detect functional determinants, along with reviewing additional features and new machine learning strategies for functional site detection.
CURRENT OPINION IN STRUCTURAL BIOLOGY
(2021)
Article
Biochemical Research Methods
Anna Klimovskaia Susmelj, Yani Ren, Yann Vander Meersche, Jean-Christophe Gelly, Tatiana Galochkina
Summary: In the era of increasing protein data, a relevant and interpretable visualization is crucial. Poincare disk projection has shown its efficiency in visualizing single-cell RNAseq data. Here, we introduce PoincareMSA, a new method for visualizing complex relationships between protein sequences using Poincare maps embedding. It demonstrates efficiency in visualizing protein family topology and annotating unknown sequences. PoincareMSA is implemented in open source Python code with available interactive Google Colab notebooks.
BRIEFINGS IN BIOINFORMATICS
(2023)
Article
Biochemical Research Methods
Sayoni Das, Harry M. Scholes, Neeladri Sen, Christine Orengo
Summary: FunSite is a machine learning predictor that identifies catalytic, ligand-binding, and protein-protein interaction functional sites in proteins. Its prediction performance outperforms other publicly available functional site prediction methods, and conserved residues in FunFams are enriched in functional sites.
Article
Biochemistry & Molecular Biology
Yunxia Wang, Ziqi Pan, Minjie Mou, Weiqi Xia, Hongning Zhang, Hanyu Zhang, Jin Liu, Lingyan Zheng, Yongchao Luo, Hanqi Zheng, Xinyuan Yu, Xichen Lian, Zhenyu Zeng, Zhaorong Li, Bing Zhang, Mingyue Zheng, Honglin Li, Tingjun Hou, Feng Zhu
Summary: In this study, a task-specific encoding algorithm for RNAs and RNA-associated interactions was developed, which realized comprehensive RNA feature encoding by introducing novel features and enabled task-specific integration of interacting partners using convolutional autoencoder-directed feature embedding.
NUCLEIC ACIDS RESEARCH
(2023)
Article
Biochemistry & Molecular Biology
Gen Li, Shailesh Kumar Panday, Emil Alexov
Summary: SAAFEC-SEQ is a gradient boosting decision tree machine learning method for predicting the change of folding free energy caused by amino acid substitutions. It does not require the 3D structure of the corresponding protein, making it suitable for genome-scale investigations with sparse structural information.
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES
(2021)
Article
Biochemical Research Methods
Chengxin Zhang, Morgan Shine, Anna Marie Pyle, Yang Zhang
Summary: US-align is a universal protocol for aligning protein, RNA, and DNA molecules, which improves the accuracy and speed of structure comparison and alignment. It has significant importance in structural biology studies.
Article
Biochemistry & Molecular Biology
Fu-Ying Dao, Meng-Lu Liu, Wei Su, Hao Lv, Zhao-Yue Zhang, Hao Lin, Li Liu
Summary: CRISPR-Cas has attracted extensive attention as a gene editing tool. Anti-CRISPR (Acr) proteins can inhibit the CRISPR-Cas defense system and be utilized for gene editing regulation. The study developed a high-accuracy prediction model called AcrPred, based on a two-step model fusion strategy, which achieved an AUC of 0.952 with independent dataset validation. The model demonstrated strong generalization ability by correctly identifying 9 out of 10 new Acr proteins compared to published tools. Additionally, a user-friendly web-server AcrPred was established for easy identification of potential Anti-CRISPR proteins.
INTERNATIONAL JOURNAL OF BIOLOGICAL MACROMOLECULES
(2023)
Article
Biochemistry & Molecular Biology
Yunxia Wang, Zhen Chen, Ziqi Pan, Shijie Huang, Jin Liu, Weiqi Xia, Hongning Zhang, Mingyue Zheng, Honglin Li, Tingjun Hou, Feng Zhu
Summary: RNAincoder is a deep learning-based encoder that provides comprehensive RNA encoding features and enables representation of any RNA-associated interactions. It identifies the optimal performance in RNA-associated interaction prediction by scanning all possible feature combinations.
NUCLEIC ACIDS RESEARCH
(2023)
Article
Multidisciplinary Sciences
Sumera Zaib, Fatima Akram, Syed Talha Liaqat, Muhammad Zain Altaf, Imtiaz Khan, Ayed A. Dera, Jalal Uddin, Ajmal Khan, Ahmed Al-Harrasi
Summary: The aim of this study is to develop a specific vaccine using bioinformatics approaches to target SARS-CoV-2 infections. By predicting and selecting new epitopes, a vaccine subunit with immunogenic properties was constructed, and a good immune response was observed. The study identified this multi-epitope vaccine as a significant candidate for combating SARS-CoV-2 infections on a global scale.
SCIENTIFIC REPORTS
(2022)
Article
Multidisciplinary Sciences
V. K. Priya, Satish Prasad Rath, Parvin Abraham
Summary: By utilizing a computational approach, a peptide named Peptide 7 was designed to bind to the Receptor Binding Domain (RBD) of SARS-CoV, SARS-CoV-2 and MERS-CoV, preventing viral entry into host cells. Docking studies and molecular dynamic simulations demonstrated that Peptide 7 binds with higher affinity to the RBDs than native receptors, forming stable complexes and inhibiting viral-receptor interactions effectively. This peptide inhibitor shows promise as a potential candidate for peptide-based antiviral therapy against Coronaviruses.
Article
Chemistry, Multidisciplinary
Likun Yang, Xiaoli Liang, Na Zhang, Lu Lu
Summary: Protein engineering plays a significant role in various industries, and the combination of artificial intelligence with directed evolution is an innovative approach to research and development. To address the challenge of limited experience and coding skills, we have developed a web-based protein sequence recommendation system that utilizes Bayesian optimization and regression modeling to enhance the success rate of recommended sequences. In addition, we have incorporated an in silico-directed evolution approach to expand the exploration of the protein space.
Article
Biochemical Research Methods
Zahed Khatooni, Navid Teymourian, Heather L. Wilson
Summary: This study introduces a novel strategy for epitope prediction using molecular dynamics simulation, homology modeling, and docking simulations. By selecting diverse SLA-1 alleles, the study successfully identifies virus epitopes that bind with high affinity to these alleles.
Article
Biochemistry & Molecular Biology
R. Sanchez-Garcia, J. R. Macias, C. O. S. Sorzano, J. M. Carazo, J. Segura
Summary: Computational approaches for predicting protein-protein interfaces are important for understanding protein assemblies. The performance of these methods can be improved by selecting specific training datasets. BIPSPI+ is an upgraded version trained on carefully curated datasets, providing better predictions and new functionalities.
JOURNAL OF MOLECULAR BIOLOGY
(2022)
Article
Multidisciplinary Sciences
Paul L. Babb, Matjaz Gregoric, Nicholas F. Lahens, David N. Nicholson, Cheryl Y. Hayashi, Linden Higgins, Matjaz Kuntner, Ingi Agnarsson, Benjamin F. Voight
Summary: By studying the genomes and transcriptomes of Darwin's bark spider, researchers have identified at least 31 potential silk protein genes and analyzed the gene expression in different silk glands. This study expands the knowledge of silk protein sequences and gene expression, contributing to a better understanding of the biophysical properties of silks.
Article
Biotechnology & Applied Microbiology
Chloe Hsu, Hunter Nisonoff, Clara Fannjiang, Jennifer Listgarten
Summary: This study proposes a simple machine learning algorithm that combines evolutionary and experimental data for improved protein fitness prediction. They find that using ridge regression on site-specific amino acid features combined with a probability density feature from modeling the evolutionary data performs well on this task.
NATURE BIOTECHNOLOGY
(2022)
Article
Nutrition & Dietetics
Yongjian Zhu, Yanhua Liu, Wenjun Fu, Fangfang Zeng, Yuan Cao, Weifeng Dou, Dandan Duan, Yuming Chen, Quanjun Lyu, Xianlan Zhao
Summary: This study investigates the associations between dietary patterns and the odds of pre-eclampsia among Chinese pregnant women. The findings suggest that high fruit-vegetable and high protein dietary patterns are associated with a reduced risk of pre-eclampsia in this population.
BRITISH JOURNAL OF NUTRITION
(2023)
Editorial Material
Cardiac & Cardiovascular Systems
Jiajun Guo, Yuanwei Xu, Ke Wan, Shi Chen, Yucheng Chen
CIRCULATION JOURNAL
(2023)
Article
Chemistry, Medicinal
Zhao-min Liu, Shu-yi Li, Qi Huang, Fang-fang Zeng, Bao-lin Li, Wen-ting Cao, Yu-ming Chen
Summary: Higher habitual intake of resveratrol and consumption of resveratrol-rich foods are associated with a reduced risk of hip fracture in Chinese elderly.
PHYTOTHERAPY RESEARCH
(2023)
Article
Biochemical Research Methods
Yu-Cheng Chen, Shan-Jing Yao, Dong-Qiang Lin
Summary: Mechanistic models are important in the development and optimization of ion-exchange chromatography (IEC). The steric mass action (SMA) model has led to a need for better estimation of the nonlinear parameter, steric shielding factor a. In this study, a combination of simplified linear approximation (SLA) and inverse method (IM) was proposed to initialize and determine a. The proposed method showed improved accuracy and reduced time complexity compared to previous methods.
JOURNAL OF CHROMATOGRAPHY A
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Jian Zhang, Yuanwei Xu, Weihao Li, Chao Zhang, Wentao Liu, Dong Li, Yucheng Chen
Summary: This study aimed to evaluate the prognostic value of magnetic resonance imaging (MRI) radiomics analysis of native T1 mapping in dilated cardiomyopathy (DCM). By developing multiple prediction models, it was found that the random forest model based on radiomics combined with clinical and conventional MRI parameters achieved the best performance.
JOURNAL OF MAGNETIC RESONANCE IMAGING
(2023)
Article
Optics
Song Zhu, Wenyu Wang, Linhao Ren, Chaoyang Gong, Yu-Cheng Chen, Lei Shi, Xinliang Zhang
Summary: The generation of EIT and EIA effects in optical cavity systems has various applications, including quantum interference effects, slow light, and light storage. This study proposes and demonstrates TGIT and TGIA effects in a single microcavity, induced by a unique temperature gradient. The platform also enables direct temperature readout with high resolution using photonic barcodes based on TGIT (or TGIA), offering a novel and efficient scheme for dynamic mode coupling in applications like light storage and temperature detection.
LASER & PHOTONICS REVIEWS
(2023)
Article
Environmental Sciences
Jing Yang, Qian Guo, Lei Li, Ruixue Wang, Yucheng Chen, Xingrun Wang
Summary: Compared to the concentration of Cr(VI), the distribution of specific Cr(VI) species in soil is often overlooked. This lack of attention may lead to inaccurate environmental risk assessment of Cr(VI) contaminated soil and hinder soil remediation efforts. This study systematically investigates the mechanisms and factors controlling the evolution of Cr(VI) species in soil by analyzing the distribution of Cr(VI) and Cr(III) species in soils with different particle sizes and textures. The results show that Cr(VI) can be adsorbed by minerals containing exchangeable calcium ions and metal oxide hydrates, forming stable adsorbed Cr(VI). Additionally, a small fraction of Cr(VI) precipitates as calcium chromate. The majority of Cr(VI) discharged into soil tends to be reduced by ferrous ions or minerals containing ferrous ions, resulting in the formation of Fe(III)-Cr(III) coprecipitate. The speciation of Cr in the soil is closely correlated to the contents of iron, exchangeable calcium ions, and metal oxide hydrates, which influence the reduction, precipitation, and adsorption of Cr(VI), respectively. After the equilibrium of these reactions is reached, the remaining Cr(VI) retains its original water-soluble state in soil.
SCIENCE OF THE TOTAL ENVIRONMENT
(2023)
Article
Green & Sustainable Science & Technology
Fu Cheng, Shanshan Ji, Yucheng Chen
Summary: Enterprise innovation is crucial for national economic growth. Employee Stock Ownership Plan (ESOP) is an effective means to stimulate employees' innovation vitality by linking their wealth with firm value. This study examines the impact of ESOP implementation and contract design on enterprise innovation investment in China. The findings highlight that ESOP implementation is beneficial for increasing innovation investment, and the effect varies with the design of incentive contracts.
Article
Computer Science, Artificial Intelligence
Wan Xiang Shen, Shu Ran Liang, Yu Yang Jiang, Yu Zong Chen
Summary: Researchers have developed an algorithm called MEGMA, which transforms metagenomic data into personalized multichannel microbiome 2D representations and improves disease prediction accuracy. This method analyzes microbial profiles through clustering and learning, and combined with ConvNet-based AggMapNet models, outperforms other commonly used machine learning and deep learning models. Additionally, the method reliably identifies disease-prediction microbes (biomarkers).
Article
Chemistry, Multidisciplinary
Xinyue Cao, Ying Wang, Xinran Song, Wanqing Lou, Xiaoyan Li, Weiping Lu, Kai Chen, Liang Chen, Yu Chen, Bingcang Huang
Summary: Sonodynamic therapy has the potential to revolutionize biomedicine with its non-invasiveness, deep tissue penetration, and controllability. However, the lack of suitable nanosonosensitizers with reactive oxygen species generation ability is a significant obstacle for its wider application. This study designs a bismuth-based nanosonosensitizer (Bi-HJ) that combines tumor therapy with metabolic regulation, photothermal therapy, and computed tomography imaging. The results demonstrate the effectiveness of Bi-HJ in achieving enhanced tumor therapy.
ADVANCED FUNCTIONAL MATERIALS
(2023)
Review
Chemistry, Multidisciplinary
Guocheng Fang, Yu-Cheng Chen, Hongxu Lu, Dayong Jin
Summary: Multicellular spheroids and organoids are promising models in personalized medicine and drug screening, replicating the structural and functional characteristics of human organs. Microfluidic technology and micro-nano fabrication meet the high requirements of engineering approaches in spheroids and organoids research. This review discusses how spheroids- and organoids-on-a-chip technology facilitates their establishment, expansion, and application through spatial-temporal control, mechanical cues modeling, high-throughput analysis, co-culture, multi-tissue interactions, biosensing, and bioimaging integration. The potential opportunities and challenges in developing spheroids- and organoids-on-a-chip technology are also highlighted.
ADVANCED FUNCTIONAL MATERIALS
(2023)
Article
Biology
Kai Ping Cheng, Wan Xiang Shen, Yu Yang Jiang, Yan Chen, Yu Zong Chen, Ying Tan
Summary: Clinical outcome prediction is crucial in stratified therapeutics, and machine learning and deep learning methods can predict therapeutic response based on transcriptomic profiles. However, the clinical transcriptomic data has challenges including low-sample sizes, high-dimensionality, and unordered nature. Existing methods have limited accuracy, and low-sample deep learning algorithms are needed for improved prediction capability.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Chemistry, Medicinal
Tianyi Wang, Ying Tan, Yu Zong Chen, Chunyan Tan
Summary: Infrared (IR) spectroscopy is a powerful tool for analyzing functional groups in organic compounds. This paper presents a new deep learning method for transforming IR spectral features into intuitive image-like feature maps and predicting major functional groups. The method successfully identifies 21 major functional groups for each molecule without expert guidance and feature selection, and it also shows potential for automated analysis in various fields.
JOURNAL OF CHEMICAL INFORMATION AND MODELING
(2023)
Article
Biochemistry & Molecular Biology
Yintao Zhang, Ying Zhou, Yuan Zhou, Xinyuan Yu, Xinyi Shen, Yanfeng Hong, Yuxin Zhang, Shanshan Wang, Minjie Mou, Jinsong Zhang, Lin Tao, Jianqing Gao, Yunqing Qiu, Yuzong Chen, Feng Zhu
Summary: Therapeutic biomarkers (ThMAR) play a crucial role in clinical development and practice, but their comprehensive information is lacking in existing databases. To address this, TheMarker database was constructed to provide different types of ThMAR used at different stages and comprehensively describe their information, aiming to enhance drug discovery and clinical practice.
NUCLEIC ACIDS RESEARCH
(2023)