Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userPrediction of amino acid side chain conformation using a deep neural network
106
0
0.0
(
0
)
Authors
Ke Liu
Ask ChatGPT about the research
No Arabic abstract
A deep neural network based architecture was constructed to predict amino acid side chain conformation with unprecedented accuracy. Amino acid side chain conformation prediction is essential for protein homology modeling and protein design. Current widely-adopted methods use physics-based energy functions to evaluate side chain conformation. Here, using a deep neural network architecture without physics-based assumptions, we have demonstrated that side chain conformation prediction accuracy can be improved by more than 25%, especially for aromatic residues compared with current standard methods. More strikingly, the prediction method presented here is robust enough to identify individual conformational outliers from high resolution structures in a protein data bank without providing its structural factors. We envisage that our amino acid side chain predictor could be used as a quality check step for future protein structure model validation and many other potential applications such as side chain assignment in Cryo-electron microscopy, crystallography model auto-building, protein folding and small molecule ligand docking.
rate research
Read More
Protein secondary structure (SS) prediction is important for studying protein structure and function. When only the sequence (profile) information is used as input feature, currently the best predictors can obtain ~80% Q3 accuracy, which has not been improved in the past decade. Here we present DeepCNF (Deep Convolutional Neural Fields) for protein SS prediction. DeepCNF is a Deep Learning extension of Conditional Neural Fields (CNF), which is an integration of Conditional Random Fields (CRF) and shallow neural networks. DeepCNF can model not only complex sequence-structure relationship by a deep hierarchical architecture, but also interdependency between adjacent SS labels, so it is much more powerful than CNF. Experimental results show that DeepCNF can obtain ~84% Q3 accuracy, ~85% SOV score, and ~72% Q8 accuracy, respectively, on the CASP and CAMEO test proteins, greatly outperforming currently popular predictors. As a general framework, DeepCNF can be used to predict other protein structure properties such as contact number, disorder regions, and solvent accessibility.
The correlations of primary and secondary structures were analyzed using proteins with known structure from Protein Data Bank. The correlation values of amino acid type and the eight secondary structure types at distant position were calculated for distances between -25 and 25. Shapes of the diagrams indicate that amino acids polarity and capability for hydrogen bonding have influence on the secondary structure at some distances. Clear preference of most of the amino acids towards certain secondary structure type classifies amino acids into four groups: alpha-helix admirers, strand admirers, turn and bend admirers and the others. Group four consists of His and Cis, the amino acids that do not show clear preference for any secondary structure. Amino acids from a group have similar physicochemical properties, and the same structural characteristics. The results suggest that amino acid preference for secondary structure type is based on the structural characteristics at Cb and Cg atoms of amino acid. alpha-helix admirers do not have polar heteroatoms on Cb and Cg atoms, nor branching or aromatic group on Cb atom. Amino acids that have aromatic groups or branching on Cb atom are strand admirers. Turn and bend admirers have polar heteroatom on Cb or Cg atoms or do not have Cb atom at all. Our results indicate that polarity and capability for hydrogen bonding have influence on the secondary structure at some distance, and that amino acid preference for secondary structure is caused by structural properties at Cb or Cg atoms.
The Machine Recognition of Crystallization Outcomes (MARCO) initiative has assembled roughly half a million annotated images of macromolecular crystallization experiments from various sources and setups. Here, state-of-the-art machine learning algorithms are trained and tested on different parts of this data set. We find that more than 94% of the test images can be correctly labeled, irrespective of their experimental origin. Because crystal recognition is key to high-density screening and the systematic analysis of crystallization experiments, this approach opens the door to both industrial and fundamental research applications.
This note represents the further progress in understanding the determination of the genetic code by Golden mean (Rakocevic, 1998). Three classes of amino acids that follow from this determination (the 7 golden amino acids, 7 of their complements, and 6 non-complements) are observed now together with two further possible splittings into 4 x 5 and 5 x 4 amino acids.
We investigate the effectiveness of different machine learning methodologies in predicting economic cycles. We identify the deep learning methodology of Bi-LSTM with Autoencoder as the most accurate model to forecast the beginning and end of economic recessions in the U.S. We adopt commonly-available macro and market-condition features to compare the ability of different machine learning models to generate good predictions both in-sample and out-of-sample. The proposed model is flexible and dynamic when both predictive variables and model coefficients vary over time. It provided good out-of-sample predictions for the past two recessions and early warning about the COVID-19 recession.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
