We love Sibe and the work Sibe does. We work closely with our colleagues to deliver the best possible solutions for their research.
Sie is a powerful digital engine, it can be used for biological science, particularly in protein folding & design, genomics, statistical calculation, deep learning, and optimization.
Sibe is an analytical and computational framework, and it aims to provide a powerful tool for biological science, such as sequence data analysis, in silico protein folding and design. Though much of the software suite is oriented toward basic research on protein sequence analysis, folding and design, Sibe is also designed for extracting meaningful information hidden behind `big data' based on machine learning. With the help of statistical analysis methods, Sibe can infer co-evolutionary information encoded in protein amino acids sequences for protein folding and design. Now, Sibe includes seven easy-interfaced modules, several physical- & chemical-principles and statistical analysis methods, as well as different optimization solvers.
The success of the software depends in part on the co-evolution derived method for detecting amino acid variations, and the easy-interface modules presented in Sibe lay the groundwork for drawing interpretable conclusions from protein sequence data to its folding and design studies in silico.
Generally, Sibe's power and perspicuous architecture are dependent on expressive and functional modules, which focus on extending methods specifically designed for the scientific applications in biophysics.
Sibe can provide an easy and rapid way for protein folding and design from analytical and computational inferences on protein sequences.
Computational protein design Statistical inference Co-Evolutionary information
Statistical analysis Functional genomics Structural genomics
Folding simulation Folding pathways Folding status
Residue-Contact prediction Secondary structure prediction Tertiray structure prediction
Analysis Calculations Demonstrations
Customized mathematical model Data-driven model Optimized model
Deep neural networks Auto-generated networks Deep learner
Quasi-Newton algorithms Swarm intelligence Monte Carlo methods