Corpus ID: 54440737

FoldingZero: Protein Folding from Scratch in Hydrophobic-Polar Model

@article{Li2018FoldingZeroPF,
  title={FoldingZero: Protein Folding from Scratch in Hydrophobic-Polar Model},
  author={Yanjun Li and Hengtong Kang and Ketian Ye and Shuyu Yin and Xiaolin Li},
  journal={ArXiv},
  year={2018},
  volume={abs/1812.00967}
}
De novo protein structure prediction from amino acid sequence is one of the most challenging problems in computational biology. As one of the extensively explored mathematical models for protein folding, Hydrophobic-Polar (HP) model enables thorough investigation of protein structure formation and evolution. Although HP model discretizes the conformational space and simplifies the folding energy function, it has been proven to be an NP-complete problem. In this paper, we propose a novel protein… Expand
DEVELOPMENT OF A PROTEIN FOLDING ENVIRONMENT FOR REINFORCEMENT LEARNING
The prediction of the three-dimensional protein structures from amino acid sequences has been a long-standing challenge in computational biophysics. In the last decade, considerable progress has beenExpand
Deep Reinforcement Learning for Protein Folding in the Hydrophobic-Polar Model with Pull Moves
The protein folding problem of predicting folded protein structure given an amino acid sequence is a challenging and extensively studied NP-hard problem in computational biology. One common approachExpand
Solving the protein folding problem in hydrophobic-polar model using deep reinforcement learning
TLDR
A comparison between the DRL approach and other notable approaches shows that the approach outperforms other approaches in finding the minimum value of the free energy, which is the main factor in the protein folding problem, in less time in any available case. Expand
The New Geometric “State-Action” Space Representation for Q-Learning Algorithm for Protein Structure Folding Problem
TLDR
The article proposes a new geometric “state-action” space representation which significantly differs from all alternative representations used for this problem and analyzes existing approaches of different states and actions spaces representations for Q-learning algorithm for protein structure folding problem to reveal their advantages and disadvantages. Expand
DeepAtom: A Framework for Protein-Ligand Binding Affinity Prediction
TLDR
It is demonstrated that the less feature engineering dependent DeepAtom approach consistently outperforms the other state-of-the-art scoring methods and is potentially adopted in computational drug development protocols such as molecular docking and virtual screening. Expand
RetailNet : Enhancing Retails of Perishable Products with Multiple Selling Strategies via PairWise Multi-Q Learning
We propose RetailNet, an end-to-end reinforcement learning (RL)-based neural network, to achieve efficient selling strategies for perishable products in order to maximize retailers’ long-term profit.Expand

References

SHOWING 1-10 OF 29 REFERENCES
The Protein-Folding Problem, 50 Years On
Protein Folding: Past and Future Fifty years ago the Nobel Prize in chemistry was awarded to Max Perutz and John Kendrew for determining the structure of globular proteins. Since first viewing theirExpand
Fast Protein Folding in the Hydrophobic-Hydrophillic Model within Three-Eights of Optimal
TLDR
These algorithms are the first approximation algorithms in the literature with guaranteed performance for this model and achieve a three-dimensional protein conformation that has a guaranteed free energy no worse than three-eighths of optimal. Expand
A Constraint-Based Approach to Fast and Exact Structure Prediction in Three-Dimensional Protein Models
TLDR
This approach is the first one that can be applied to two three-dimensional lattices, namely the cubic lattice and the face-centered-cubic (FCC) lattice, and it is the only exact method for the FCC lattice. Expand
An ant colony optimisation algorithm for the 2D and 3D hydrophobic polar protein folding problem
TLDR
The application of ACO to this bioinformatics problem compares favourably with specialised, state-of-the-art methods for the 2D and 3D HP protein folding problem; the empirical results indicate that the rather simple ACO algorithm scales worse with sequence length but usually finds a more diverse ensemble of native states. Expand
A hybrid approach to protein folding problem integrating constraint programming with local search
TLDR
A novel hybrid approach to simulate the protein folding problem using constraint programming technique integrated within local search and encouraging results obtained show that these two approaches can be combined efficiently to obtain better quality solutions within acceptable time. Expand
Finding low-energy conformations of lattice protein models by quantum annealing
TLDR
This report presents a benchmark implementation of quantum annealing for lattice protein folding problems (six different experiments up to 81 superconducting quantum bits) and paves the way towards studying optimization problems in biophysics and statistical mechanics using quantum devices. Expand
A fast conformational search strategy for finding low energy structures of model proteins
  • T. Beutler, K. Dill
  • Mathematics, Medicine
  • Protein science : a publication of the Protein Society
  • 1996
TLDR
A new computer algorithm for finding low‐energy conformations of proteins that uses a heuristic bias function to help assemble a hydrophobic core, the Core‐directed chain Growth method (CG), which has the potential advantage that it should have nonexponential scaling with chain length. Expand
Exploration of two-dimensional hydrophobic-polar lattice model by combining local search with elastic net algorithm.
TLDR
A novel hybrid of elastic net algorithm and local search method (ENLS) is applied successfully to simulations of protein folding on two-dimensional hydrophobic-polar lattice model and the numerical results show that it is drastically superior to other methods in finding the ground state of a protein. Expand
A novel state space representation for the solution of 2D-HP protein folding problem using reinforcement learning methods
TLDR
The proposed state space representation reduces the dependency of the size of the state-action space to the amino acid sequence length and allows the agent to find the optimal fold of any sequence of a certain length. Expand
Combinatorial Algorithms for Protein Folding in Lattice Models: A Survey of Mathematical Results
TLDR
It is shown how work on 2D self-avoiding walks contact-map decomposition can build upon the exact RNA contacts counting formula by Mike Waterman and collaborators which lead to renewed hope for analytical closed-form approximations for statistical mechanics of protein folding in lattice models. Expand
...
1
2
3
...