A5091465074- Machine Learning in Bioinformatics
- Biofuel production and bioconversion
- Protein Structure and Dynamics
- Genetics, Bioinformatics, and Biomedical Research
- RNA and protein synthesis mechanisms
- Computational Drug Discovery Methods
- Genomics and Phylogenetic Studies
- Glycosylation and Glycoproteins Research
- Bacterial Genetics and Biotechnology
National Yang Ming Chiao Tung University
2020-2021
Protein secondary structure prediction (SSP) has a variety of applications; however, there been relatively limited improvement in accuracy for years. With vision moving forward all related fields, we aimed to make fundamental advance SSP. There have many admirable efforts made improve the machine learning algorithm This work thus took step back by manipulating input features. A element-based position-specific scoring matrix (SSE-PSSM) is proposed, based on which new set features can be...
Secondary structure prediction (SSP) of proteins is an important structural biology technique with many applications. There have been ~300 algorithms published in the past seven decades fierce competition accuracy. In first 60 years, accuracy three-state SSP rose from ~56% to 81%; after that, it has long stayed at 81–86%. 1990s, theoretical limit had estimated be 88%. Thus, now generally considered not challenging or too improve. However, we found that might underestimated. Besides, there...
The secondary structure prediction of proteins is a classic topic computational structural biology with variety applications. During the past decade, accuracy achieved by state-of-the-art algorithms has been >80%; meanwhile, time cost increased rapidly because exponential growth fundamental protein sequence data. Based on literature studies and preliminary observations relationships between size/homology dataset speed/accuracy predictions, we raised two hypotheses that might be helpful to...
The secondary structure prediction (SSP) of proteins has long been an essential structural biology technique with various applications. Despite its vital role in many research and industrial fields, recent years, as the accuracy state-of-the-art predictors approaches theoretical upper limit, SSP considered no longer challenging or too to make advances. With belief that substantial improvement will move forward fields depending on it, we conducted this study, which focused three issues have...
Abstract Background This work aims to help develop new protein engineering techniques based on a structural rearrangement phenomenon called circular permutation (CP), equivalent connecting the native termini of followed by creating at another site. Although CP has been applied in many fields, its implementation is still costly because inevitable trials and errors. Results Here we present CirPred, structure modeling linker design method for circularly permuted proteins. Compared with...