A5082857349- Machine Learning in Bioinformatics
- Protein Structure and Dynamics
- RNA and protein synthesis mechanisms
- Genomics and Phylogenetic Studies
- Computational Drug Discovery Methods
- Enzyme Structure and Function
- Chromosomal and Genetic Variations
- Artificial Intelligence in Healthcare
- Mass Spectrometry Techniques and Applications
- Protein purification and stability
- Biomedical Text Mining and Ontologies
- SARS-CoV-2 and COVID-19 Research
- Diatoms and Algae Research
- Enzyme Production and Characterization
- Advanced Condensed Matter Physics
- Advanced Proteomics Techniques and Applications
- Microbial Community Ecology and Physiology
- Catalytic Processes in Materials Science
- Radioactive element chemistry and processing
Soochow University
2011-2024
Suzhou City University
2024
Suzhou University of Science and Technology
2024
Shanghai Ocean University
2019
Lund University
2018
The advent of next-generation sequencing technologies is accompanied with the development many whole-genome sequence assembly methods and software, especially for de novo fragment assembly. Due to poor knowledge about applicability performance these software tools, choosing a befitting assembler becomes tough task. Here, we provide information adaptivity each program, then above all, compare eight distinct tools against groups simulated datasets from Solexa platform. Considering...
Thermophilic proteins have important value in the fields of biopharmaceuticals and enzyme engineering. Most existing thermophilic protein prediction models are based on traditional machine learning algorithms do not fully utilize sequence information. To solve this problem, a deep model self-attention multiple-channel feature fusion was proposed to predict proteins, called DeepTP. First, large new dataset consisting 20,842 constructed. Second, convolutional neural network bidirectional long...
Several methods have been developed to predict effects of amino acid substitutions on protein stability. Benchmark datasets are essential for method training and testing numerous requirements including that the data is representative investigated phenomenon. Available machine learning algorithms variant stability all trained with ProTherm data. We noticed a number issues contents, quality relevance database. There were errors, but also features had not clearly communicated. Consequently,...
The stability of proteins is an essential property that has several biological implications. Knowledge about protein important in many ways, ranging from purification and structure determination to cells biotechnological applications. Experimental thermal stabilities been tedious available data have limited. introduction limited proteolysis mass spectrometry approaches facilitated more extensive cellular production. We collected melting temperature information for 34,913 developed a machine...
Genetic variations have a multitude of effects on proteins. A substantial number affect protein–solvent interactions, either aggregation or solubility. Aggregation is often related to structural alterations, whereas solubilizable proteins in the solid phase can be made again soluble by dilution. Solubility central protein property and when reduced lead diseases. We developed prediction method, PON-Sol2, identify amino acid substitutions that increase, decrease, no effect The method machine...
The renaissance of research interests in actinide oxo clusters the past decade arises from both concerns radioactive contamination and their potential utility as nanoscale materials. Compared to uranium cluster, thorium (Th) cluster shows less coordination variation. Herein, we presented a unique Th (
The emergence of numerous variants SARS-CoV-2 has presented challenges to the global efforts control COVID-19 pandemic. major mutation is in viral envelope spike protein that responsible for virus attachment host, and main target host antibodies. It critically important study biological effects mutations understand mechanisms how alter functions. Here, we propose a co-conservation weighted network (PCCN) model only based on sequence characterize sites by topological features investigate from...
Proteins, as crucial macromolecules performing diverse biological roles, are central to numerous processes. The ability predict changes in protein thermal stability due mutations is vital for both biomedical research and industrial applications. However, existing experimental methods often costly labor-intensive, while structure-based prediction demand significant computational resources. In this study, we introduce PON-Tm, a novel sequence-based method predicting mutation-induced variations...
Most proteins fold into characteristic three-dimensional structures. The rate of folding and unfolding varies widely can be affected by variations in proteins. We developed a novel machine-learning-based method for the prediction effects amino acid substitutions two-state collected data set experimentally defined rates variants used them to train gradient boosting algorithm starting with 1161 features. Two predictors were designed. three-class classifier had, blind tests, specificity...
To reveal the working pattern of programmed cell death, knowledge subcellular location apoptosis proteins is essential. Besides costly and time-consuming method experimental determination, research into computational locating schemes, focusing mainly on innovation representation techniques protein sequences selection classification algorithms, has become popular in recent decades. In this study, a novel tri-gram encoding model proposed, which based using overlapping property matrix (POPM)...