Article
Biochemical Research Methods
Fei-Liao Lai, Feng Gao
Summary: Recently, a novel post-translational modification called lysine lactylation (Kla) has been discovered, which regulates gene expression and life activities through lactate stimulation. The accurate identification of Kla sites is essential. Mass spectrometry is currently the primary method for identifying PTM sites, but it is costly and time-consuming. Therefore, we proposed a novel computational model, Auto-Kla, based on automated machine learning (AutoML), which can predict Kla sites in gastric cancer cells quickly and accurately.
BRIEFINGS IN BIOINFORMATICS
(2023)
Article
Biochemistry & Molecular Biology
Hao Tian, Rajas Ketkar, Peng Tao
Summary: The work presents an accurate ADMET prediction model using an ensemble of features and a tree-based machine learning model. The model performs well in the ADMET benchmark test and is ranked top 3 in most tasks. The trained machine learning models are integrated in a publicly available web server named ADMET boost.
JOURNAL OF MOLECULAR MODELING
(2022)
Article
Biochemical Research Methods
Sehwan Moon, Hyunju Lee
Summary: This article introduces a multi-task attention learning algorithm, MOMA, for multi-omics data, which achieves high diagnostic performance and interpretability by capturing important biological processes. Experimental results demonstrate the superior performance of MOMA in various classification tasks, and its utility is verified through comparison experiments and biological analysis.
Article
Chemistry, Analytical
Dominik Kopczynski, Nils Hoffmann, Nina Troppmair, Cristina Coman, Kim Ekroos, Michael R. Kreutz, Gerhard Liebisch, Dominik Schwudke, Robert Ahrends
Summary: Lipid analysis is important for understanding the various functions of lipids, and LipidSpace is a standalone tool that analyzes lipidomes by assessing their structural and quantitative differences. It offers a user-friendly GUI and support for multiple data formats, allowing for reanalysis and merging of datasets, and provides additional discoveries.
ANALYTICAL CHEMISTRY
(2023)
Article
Biochemical Research Methods
Ondrej Vavra, Jakub Beranek, Jan Stourac, Martin Surkovsky, Jiri Filipovic, Jiri Damborsky, Jan Martinovic, David Bednar
Summary: Access pathways are critical for substrate and product transport in enzymes. A Python3 API called pyCaverDock is introduced to enhance the user experience and facilitate ligand transport analysis. This API simplifies the steps needed to use CaverDock and allows for automation of setup processes.
Article
Biochemical Research Methods
Zhao-Yue Zhang, Yu-He Yang, Hui Ding, Dong Wang, Wei Chen, Hao Lin
Summary: The study obtained the optimal nonamer composition using binomial distribution and one-way analysis of variance, and developed a support vector machine predictor to identify mRNA subcellular localization with an accuracy of 90.12% for Homo sapiens. This predictor may be useful for studying mRNA localization mechanisms and translocation strategies.
BRIEFINGS IN BIOINFORMATICS
(2021)
Article
Biochemistry & Molecular Biology
Yu-He Yang, Cai-Yi Ma, Dong Gao, Xiao-Wei Liu, Shi-Shi Yuan, Hui Ding
Summary: 2'-O-methylation (2OM) is a common post-transcriptional modification in RNAs that plays important roles in RNA stability, mRNA splicing and translation, as well as innate immunity. We developed a two-step feature selection model based on four types of 2OM data and achieved an overall accuracy of 84.3% on an independent dataset. Additionally, we constructed an online tool called i2OM for convenient access to the prediction model, which may serve as a reference for the study of 2OM.
INTERNATIONAL JOURNAL OF BIOLOGICAL MACROMOLECULES
(2023)
Article
Biochemistry & Molecular Biology
Spyros Tastsoglou, Athanasios Alexiou, Dimitra Karagkouni, Giorgos Skoufos, Elissavet Zacharopoulou, Artemis G. Hatzigeorgiou
Summary: DIANA-microT-CDS is an advanced miRNA target prediction algorithm that has been serving the scientific community since 2009. It is one of the first algorithms to predict miRNA binding sites in both the 3' Untranslated Region (3'-UTR) and the coding sequence (CDS) of transcripts, with improved performance. The current version, DIANA-microT 2023, provides updated interactions based on annotation information from Ensembl v102, miRBase 22.1, and MirGeneDB 2.1, resulting in over 83 million interactions in multiple species, as well as interactions between viral miRNAs and host transcripts. The webserver of DIANA-microT offers various features including smart filtering options, identification of abundance patterns, detection of known SNPs on binding sites, and access to miRNA-disease information.
NUCLEIC ACIDS RESEARCH
(2023)
Article
Multidisciplinary Sciences
Chowdhury Rafeed Rahman, Ruhul Amin, Swakkhar Shatabda, Md Sadrul Islam Toaha
Summary: The study developed a convolutional neural network tool capable of identifying DNA N6-methylation (6mA) sites in the rice genome. The model achieved an accuracy of 93.97% on benchmark dataset and demonstrated generalization ability on other plant genomes.
SCIENTIFIC REPORTS
(2021)
Article
Biochemical Research Methods
Wei He, Helen Wang, Yanjun Wei, Zhiyun Jiang, Yitao Tang, Yiwen Chen, Han Xu
Summary: This study developed an integrative prediction method GuidePro that prioritizes sgRNAs in protein knockouts by incorporating multiple factors. Tested on independent datasets, GuidePro demonstrated superior performance in predicting phenotypes caused by protein loss-of-function, suggesting its robustness in various applications of CRISPR/Cas9 knockouts.
Article
Biochemical Research Methods
Shun Liu, Jianchao Zhou, Ziyan Feng, Jiawen Zhang, Shuang Li, Zilong Jin, Chenfei Zhang, Shiliang Li, Gaoqi He, Honglin Li
Summary: In this study, a novel virtual screening tool called VRPharmer is proposed that enables users to perform the entire screening process in virtual reality environments. It provides both interactive and typical screening modes, editable pharmacophore models, and improved molecular rendering algorithms for precise representations.
Article
Biochemical Research Methods
Mihir Mongia, Romel Baral, Abhinav Adduri, Donghui Yan, Yudong Liu, Yuying Bian, Paul Kim, Bahar Behsaz, Hosein Mohimani
Summary: Microbial natural products are an important source of bioactive compounds for drug discovery, and nonribosomal peptides (NRPs) are a diverse class of NRPs that include antibiotics, immunosuppressants, anticancer agents, toxins, siderophores, pigments, and cytostatics. Prediction of the chemical structure and properties of NRPs, especially those composed of nonstandard amino acids, remains a challenge. In this article, we evaluated various machine learning algorithms and features for predicting the specificity of NRPs and showed that the extra trees model with one-hot encoding features outperforms existing approaches. Additionally, we developed novel techniques for predicting various properties of potentially novel amino acids found in A-domains using unsupervised clustering.
Article
Chemistry, Medicinal
Shahid Iqbal, Fang Ge, Fuyi Li, Tatsuya Akutsu, Yuanting Zheng, Robin B. Gasser, Dong-Jun Yu, Geoffrey Webb, Jiangning Song
Summary: PROST is a sequence-based predictor for protein stability changes caused by single-point missense mutations. It utilizes various sequence-based features, physicochemical properties, evolutionary information, and predicted structural features to accurately predict the protein stability changes. The performance of PROST is evaluated on multiple datasets and compared with state-of-the-art predictors, demonstrating its superiority.
JOURNAL OF CHEMICAL INFORMATION AND MODELING
(2022)
Article
Biochemical Research Methods
Jinuk Jung, Hyunwhan Joe, Kyungsik Ha, Jin-Muk Lim, Hong-Gee Kim
Summary: BEE is a web server that searches and explores different types of biomedical entities and their gene associations from multiple databases, allowing users to navigate search results clearly through set operations.
JOURNAL OF COMPUTATIONAL BIOLOGY
(2021)
Article
Biochemistry & Molecular Biology
Hao Wang, Zhaoyue Zhang, Haicheng Li, Jinzhao Li, Hanshuang Li, Mingzhu Liu, Pengfei Liang, Qilemuge Xi, Yongqiang Xing, Lei Yang, Yongchun Zuo
Summary: This study developed a computational biology method using single-cell transcriptome to identify and predict pathological cell subpopulations of early-onset preeclampsia (PE). The TURF_XGB method achieved high accuracy and recall rates in classifying healthy placenta subpopulations, revealing the heterogeneity of placental biology. Additionally, the analysis revealed the involvement of dendritic cells and the role of C1QB and C1QC in mediating inflammation and driving the development of PE. The study also developed a risk stratification card for preeclampsia classification.
CELL AND BIOSCIENCE
(2023)
Article
Computer Science, Information Systems
Zhao-Yue Zhang, Zi-Jie Sun, Yu-He Yang, Hao Lin
Summary: This study presents a support vector machine-based approach that incorporates mutual information algorithm and incremental feature selection strategy to improve the prediction performance of lncRNA subcellular localization.
FRONTIERS OF COMPUTER SCIENCE
(2022)
Article
Biochemical Research Methods
Zijie Sun, Qinlai Huang, Yuhe Yang, Shihao Li, Hao Lv, Yang Zhang, Hao Lin, Lin Ning
Summary: Many studies have shown the important roles of small nucleolar RNAs (snoRNAs) in the development of complex human diseases. However, traditional experimental approaches for uncovering associations between snoRNAs and diseases are costly and time-consuming. This study proposed a method called PSnoD, which achieved superior performance and computational efficiency in predicting snoRNA-disease associations.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Biochemistry & Molecular Biology
Xiaoming Song, Nan Li, Yingchao Zhang, Yi Liang, Rong Zhou, Tong Yu, Shaoqin Shen, Shuyan Feng, Yu Zhang, Xiuqing Li, Hao Lin, Xiyin Wang
Summary: Through transcriptomics and genomics analysis, this study identified and analyzed the genes related to chlorophyll and carotenoid in celery and other species. The study found that transcription factors play a role in regulating the expression of these genes. Expansion of carotenoid-related genes was observed in celery, while no notable expansion was found in chlorophyll biosynthesis genes.
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES
(2022)
Article
Biochemical Research Methods
Zhao-Yue Zhang, Lin Ning, Xiucai Ye, Yu-He Yang, Yasunori Futamura, Tetsuya Sakurai, Hao Lin
Summary: The location of miRNAs in cells plays a crucial role in their regulatory function. Current prediction algorithms for miRNA subcellular localization have limitations. In this study, a new data partitioning strategy and deep learning algorithm were proposed to accurately predict miRNA subcellular localization and explore the underlying mechanisms through motif analysis. Additionally, a user-friendly web server was established for convenient use.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Biology
Jianqiang Xiao, Mujiexin Liu, Qinlai Huang, Zijie Sun, Lin Ning, Junguo Duan, Siquan Zhu, Jian Huang, Hao Lin, Hui Yang
Summary: This study investigated the relationship between environmental, habits, parental vision, demographic factors and adolescent myopia by analyzing questionnaire data. Machine learning algorithms were used to classify the samples. The age variable and parental myopia status were found to be important risk factors, while measures taken by children and the distance between books and eyes during reading were identified as protective factors.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Biochemistry & Molecular Biology
Zahoor Ahmed, Hasan Zulfiqar, Lixia Tang, Hao Lin
Summary: The study found that polar amino acids, short bond length, wide DHA angle, and aromatic amino acids play important roles in the thermostability of proteins through statistical analysis on pairs of thermophilic proteins and their non-thermophilic orthologous.
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES
(2022)
Review
Biochemical Research Methods
Li Liu, Kaiyuan Han, Huimin Sun, Lu Han, Dong Gao, Qilemuge Xi, Lirong Zhang, Hao Lin
Summary: This review provides an overview of loop-calling tools for various 3C-based techniques. It categorizes and summarizes these tools, discusses background biases and denoising algorithms, and helps researchers select the most appropriate method for loop calling and downstream analysis. It is also useful for bioinformatics scientists aiming to develop new loop-calling algorithms.
BRIEFINGS IN BIOINFORMATICS
(2023)
Article
Biochemical Research Methods
Xiang Feng, Hongqi Zhang, Hao Lin, Haixia Long
Summary: In this study, a directed graph neural network called scDGAE was developed for scRNA-seq analysis, using graph autoencoders and graph attention network. The experiment results showed that the scDGAE model achieved promising performance in gene imputation and cell clustering prediction, and it can be applied to general scRNA-Seq analyses.
Article
Chemistry, Medicinal
Xiao-Wei Liu, Tian-Yu Shi, Dong Gao, Cai-Yi Ma, Hao Lin, Dan Yan, Ke-Jun Deng
Summary: Diabetes mellitus is a chronic metabolic disease that disrupts blood glucose homeostasis and leads to severe complications. The development of artificial intelligence has provided a powerful tool, iPADD, for accelerating the discovery of potential antidiabetic drugs. iPADD achieved high accuracy in drug prediction by using molecular fingerprints and machine learning algorithms.
JOURNAL OF CHEMICAL INFORMATION AND MODELING
(2023)
Article
Medicine, General & Internal
Wen Zhu, Shi-Shi Yuan, Jian Li, Cheng-Bing Huang, Hao Lin, Bo Liao
Summary: This study provides the first recognition framework for accurately identifying HBP based on machine learning. By using four sequence descriptors, HBP and non-HBP samples were represented by discrete numbers and input into SVM and RF algorithms for comparison. The SVM-based classifier was found to have the greatest potential for identifying HBP.
Review
Biochemistry & Molecular Biology
Hasan Zulfiqar, Zhiling Guo, Bakanina Kissanga Grace-Mercure, Zhao-Yue Zhang, Hui Gao, Hao Lin, Yun Wu
Summary: Hormone binding proteins (HBPs) belong to soluble carrier proteins that interact selectively and non-covalently with hormones, promoting growth hormone signaling in humans and other animals. The identification of HBPs is crucial for understanding these proteins and their applications in medical and commercial fields. Computational prediction methods, using sequence information and machine learning algorithms, have played a significant role in recognizing HBPs, offering a time-saving and cost-effective alternative to experimental methods.
COMPUTATIONAL AND STRUCTURAL BIOTECHNOLOGY JOURNAL
(2023)
Article
Biodiversity Conservation
Wenfei Liao, Hao Lin
Summary: Urbanisation has complex effects on the morphological traits of aquatic insect species, with different species exhibiting different strategies and abilities to cope with movement barriers caused by urbanisation.
INSECT CONSERVATION AND DIVERSITY
(2023)
Article
Biology
Liping Ren, Lin Ning, Yu Yang, Ting Yang, Xinyu Li, Shanshan Tan, Peixin Ge, Shun Li, Nanchao Luo, Pei Tao, Yang Zhang
Summary: Researchers have developed a manually curated database of metabolite markers related to COVID-19, which includes significantly altered metabolites associated with early diagnosis, disease severity, prognosis, and drug response. This database facilitates both basic and clinical research on COVID-19.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Biology
Jie Gao, Yongxian Feng, Yan Yang, Yuetong Shi, Junjie Liu, Hao Lin, Lirong Zhang
Summary: This study systematically identified and analyzed key CpG sites closely related to differential expression of genes in LUSC through a two-step correlation analysis method, and found that these sites and genes can serve as effective biomarkers for LUSC.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)