Swakkhar Shatabda

Memory-based local search for simplified protein structure prediction

Protein structure prediction is one of the most challenging problems in computational biology. Given a proteins amino acid sequence, a simplified version of the problem is to find an on-lattice self-avoiding walk that minimizes the interaction energy among the amino acids. In this paper, we present a memory-based local search method for the simplified problem using Hydrophobic-Polar energy model and Face Centered Cubic lattice. By memorizing local minima and then avoiding their neighbohood, our approach significantly improves the state-of-the-art local search method for protein structure prediction on a set of standard benchmark proteins.

The road not taken: retreat and diverge in local search for simplified protein structure prediction

BackgroundGiven a proteins amino acid sequence, the protein structure prediction problem is to find a three dimensional structure that has the native energy level. For many decades, it has been one of the most challenging problems in computational biology. A simplified version of the problem is to find an on-lattice self-avoiding walk that minimizes the interaction energy among the amino acids. Local search methods have been preferably used in solving the protein structure prediction problem for their efficiency in finding very good solutions quickly. However, they suffer mainly from two problems: re-visitation and stagnancy.ResultsIn this paper, we present an efficient local search algorithm that deals with these two problems. During search, we select the best candidate at each iteration, but store the unexplored second best candidates in a set of elite conformations, and explore them whenever the search faces stagnation. Moreover, we propose a new non-isomorphic encoding for the protein conformations to store the conformations and to check similarity when applied with a memory based search. This new encoding helps eliminate conformations that are equivalent under rotation and translation, and thus results in better prevention of re-visitation.ConclusionOn standard benchmark proteins, our algorithm significantly outperforms the state-of-the art approaches for Hydrophobic-Polar energy models and Face Centered Cubic Lattice.

Spiral search: a hydrophobic-core directed local search for simplified PSP on 3D FCC lattice

BackgroundProtein structure prediction is an important but unsolved problem in biological science. Predicted structures vary much with energy functions and structure-mapping spaces. In our simplified ab initio protein structure prediction methods, we use hydrophobic-polar (HP) energy model for structure evaluation, and 3-dimensional face-centred-cubic lattice for structure mapping. For HP energy model, developing a compact hydrophobic-core (H-core) is essential for the progress of the search. The H-core helps find a stable structure with the lowest possible free energy.ResultsIn order to build H-cores, we present a new Spiral Search algorithm based on tabu-guided local search. Our algorithm uses a novel H-core directed guidance heuristic that squeezes the structure around a dynamic hydrophobic-core centre. We applied random walks to break premature H-cores and thus to avoid early convergence. We also used a novel relay-restart technique to handle stagnation.ConclusionsWe have tested our algorithms on a set of benchmark protein sequences. The experimental results show that our spiral search algorithm outperforms the state-of-the-art local search algorithms for simplified protein structure prediction. We also experimentally show the effectiveness of the relay-restart.

An efficient encoding for simplified protein structure prediction using genetic algorithms

Protein structure prediction is one of the most challenging problems in computational biology and remains unsolved for many decades. In a simplified version of the problem, the task is to find a self-avoiding walk with the minimum free energy assuming a discrete lattice and a given energy matrix. Genetic algorithms currently produce the state-of-the-art results for simplified protein structure prediction. However, performance of the genetic algorithms largely depends on the encodings they use in representing protein structures and the twin removal technique they use in eliminating duplicate solutions from the current population. In this paper, we present a new efficient encoding for protein structures. Our encoding is nonisomorphic in nature and results into efficient twin removal. This helps the search algorithm diversify and explore a larger area of the search space. In addition to this, we also propose an approximate matching scheme for removing near-similar solutions from the population. Our encoding algorithm is generic and applicable to any lattice type. On the standard benchmark proteins, our techniques significantly improve the state-of-the-art genetic algorithm for hydrophobic-polar (HP) energy model on face-centered-cubic (FCC) lattice.

Random-walk: a stagnation recovery technique for simplified protein structure prediction

Protein structure prediction is a challenging optimisation problem to the computer scientists. A large number of existing (meta-)heuristic search algorithms attempt to solve the problem by exploring possible structures and finding the one with minimum free energy. However, these algorithms often get stuck in local minima and thus perform poorly on large sized proteins. In this paper, we present a random-walk based stagnation recovery approach. We tested our approach on tabu-based local search as well as population based genetic algorithms. The experimental results show that, random-walk is very effective for escaping from local minima for protein structure prediction on face-centred-cubic lattice and hydrophobic-polar energy model.

iDTI-ESBoost: Identification of Drug Target Interaction Using Evolutionary and Structural Features with Boosting

Prediction of new drug-target interactions is critically important as it can lead the researchers to find new uses for old drugs and to disclose their therapeutic profiles or side effects. However, experimental prediction of drug-target interactions is expensive and time-consuming. As a result, computational methods for predictioning new drug-target interactions have gained a tremendous interest in recent times. Here we present iDTI-ESBoost, a prediction model for identification of drug-target interactions using evolutionary and structural features. Our proposed method uses a novel data balancing and boosting technique to predict drug-target interaction. On four benchmark datasets taken from a gold standard data, iDTI-ESBoost outperforms the state-of-the-art methods in terms of area under receiver operating characteristic (auROC) curve. iDTI-ESBoost also outperforms the latest and the best-performing method found in the literature in terms of area under precision recall (auPR) curve. This is significant as auPR curves are argued as suitable metric for comparison for imbalanced datasets similar to the one studied here. Our reported results show the effectiveness of the classifier, balancing methods and the novel features incorporated in iDTI-ESBoost. iDTI-ESBoost is a novel prediction method that has for the first time exploited the structural features along with the evolutionary features to predict drug-protein interactions. We believe the excellent performance of iDTI-ESBoost both in terms of auROC and auPR would motivate the researchers and practitioners to use it to predict drug-target interactions. To facilitate that, iDTI-ESBoost is implemented and made publicly available at: http://farshidrayhan.pythonanywhere.com/iDTI-ESBoost/.

DPP-PseAAC: A DNA-binding protein prediction model using Chou’s general PseAAC

A DNA-binding protein (DNA-BP) is a protein that can bind and interact with a DNA. Identification of DNA-BPs using experimental methods is expensive as well as time consuming. As such, fast and accurate computational methods are sought for predicting whether a protein can bind with a DNA or not. In this paper, we focus on building a new computational model to identify DNA-BPs in an efficient and accurate way. Our model extracts meaningful information directly from the protein sequences, without any dependence on functional domain or structural information. After feature extraction, we have employed Random Forest (RF) model to rank the features. Afterwards, we have used Recursive Feature Elimination (RFE) method to extract an optimal set of features and trained a prediction model using Support Vector Machine (SVM) with linear kernel. Our proposed method, named as DNA-binding Protein Prediction model using Chous general PseAAC (DPP-PseAAC), demonstrates superior performance compared to the state-of-the-art predictors on standard benchmark dataset. DPP-PseAAC achieves accuracy values of 93.21%, 95.91% and 77.42% for 10-fold cross-validation test, jackknife test and independent test respectively. The source code of DPP-PseAAC, along with relevant dataset and detailed experimental results, can be found at https://github.com/srautonu/DNABinding. A publicly accessible web interface has also been established at: http://77.68.43.135:8080/DPP-PseAAC/.

iDNAProt-ES: Identification of DNA-binding Proteins Using Evolutionary and Structural Features

DNA-binding proteins play a very important role in the structural composition of the DNA. In addition, they regulate and effect various cellular processes like transcription, DNA replication, DNA recombination, repair and modification. The experimental methods used to identify DNA-binding proteins are expensive and time consuming and thus attracted researchers from computational field to address the problem. In this paper, we present iDNAProt-ES, a DNA-binding protein prediction method that utilizes both sequence based evolutionary and structure based features of proteins to identify their DNA-binding functionality. We used recursive feature elimination to extract an optimal set of features and train them using Support Vector Machine (SVM) with linear kernel to select the final model. Our proposed method significantly outperforms the existing state-of-the-art predictors on standard benchmark dataset. The accuracy of the predictor is 90.18% using jack knife test and 88.87% using 10-fold cross validation on the benchmark dataset. The accuracy of the predictor on the independent dataset is 80.64% which is also significantly better than the state-of-the-art methods. iDNAProt-ES is a novel prediction method that uses evolutionary and structural based features. We believe the superior performance of iDNAProt-ES will motivate the researchers to use this method to identify DNA-binding proteins. iDNAProt-ES is publicly available as a web server at: http://brl.uiu.ac.bd/iDNAProt-ES/.

How Good Are Simplified Models for Protein Structure Prediction

Protein structure prediction (PSP) has been one of the most challenging problems in computational biology for several decades. The challenge is largely due to the complexity of the all-atomic details and the unknown nature of the energy function. Researchers have therefore used simplified energy models that consider interaction potentials only between the amino acid monomers in contact on discrete lattices. The restricted nature of the lattices and the energy models poses a twofold concern regarding the assessment of the models. Can a native or a very close structure be obtained when structures are mapped to lattices? Can the contact based energy models on discrete lattices guide the search towards the native structures? In this paper, we use the protein chain lattice fitting (PCLF) problem to address the first concern; we developed a constraint-based local search algorithm for the PCLF problem for cubic and face-centered cubic lattices and found very close lattice fits for the native structures. For the second concern, we use a number of techniques to sample the conformation space and find correlations between energy functions and root mean square deviation (RMSD) distance of the lattice-based structures with the native structures. Our analysis reveals weakness of several contact based energy models used that are popular in PSP.

iPHLoc-ES: Identification of bacteriophage protein locations using evolutionary and structural features

Bacteriophage proteins are viruses that can significantly impact on the functioning of bacteria and can be used in phage based therapy. The functioning of Bacteriophage in the host bacteria depends on its location in those host cells. It is very important to know the subcellular location of the phage proteins in a host cell in order to understand their working mechanism. In this paper, we propose iPHLoc-ES, a prediction method for subcellular localization of bacteriophage proteins. We aim to solve two problems: discriminating between host located and non-host located phage proteins and discriminating between the locations of host located protein in a host cell (membrane or cytoplasm). To do this, we extract sets of evolutionary and structural features of phage protein and employ Support Vector Machine (SVM) as our classifier. We also use recursive feature elimination (RFE) to reduce the number of features for effective prediction. On standard dataset using standard evaluation criteria, our method significantly outperforms the state-of-the-art predictor. iPHLoc-ES is readily available to use as a standalone tool from: https://github.com/swakkhar/iPHLoc-ES/ and as a web application from: http://brl.uiu.ac.bd/iPHLoc-ES/.