Field Of Computational Biology Research Articles

Expert Panel Discusses the Importance of Systems Medicine

Expert Panel Discusses the Importance of Systems Medicine

Inferring gene regulatory networks with hybrid of multi-agent genetic algorithm and random forests based on fuzzy cognitive maps

Inferring gene regulatory networks (GRNs) from expression data is an important and challenging problem in the field of computational biology. With the growth of high-throughput gene expression data, GRN inference has attracted much interest from researchers. In this paper, we focus on inferring large-scale GRNs using a fast and accurate algorithm. We first use fuzzy cognitive maps (FCMs) to model GRNs. Then, multi-agent genetic algorithm (MAGA) is used to determine regulatory links, and random forests (RF) are used as the feature selection algorithm to initialize the agents, which can reduce the search space of MAGA according to the gene ranking. We improve the genetic operators of MAGA to cope with GRN inference. The proposed algorithm is termed as MAGARFFCM-GRN. In the experiments, the performance of MAGARFFCM-GRN is validated on synthetic data and the well-known benchmark DREAM3 and DREAM4. The results show that MAGARFFCM-GRN can infer directed GRNs with high accuracy and efficiency.

Inferring Large-Scale Gene Regulatory Networks Using a Randomized Algorithm Based on Singular Value Decomposition.

Reconstructing large-scale gene regulatory networks (GRNs) is a challenging problem in the field of computational biology. Various methods for inferring GRNs have been developed, but they fail to accurately infer GRNs with a large number of genes. Additionally, the existing evaluation indexes for evaluating the constructed networks have obvious disadvantages because GRNs in most biological systems are sparse. In this paper, we develop a new method for inferring GRNs based on randomized singular value decomposition (RSVD) and ordinary differential equation (ODE)-based optimization, denoted as IGRSVD, from large-scale time series data with noise. The three major contributions of this paper are as follows. First, the IGRSVD algorithm uses the RSVD to handle the noise and reduce the original large-scale data into small-scale problems. Second, we propose two new evaluated indexes, the expected value accuracy (EVA) and the expected value error (EVE), to evaluate the performance of inferred networks by considering the sparse features in the network. Finally, the proposed IGRSVD algorithm is compared with the existing SVD algorithm and PCA_CMI algorithm using four subsets from E. coli and datasets from DREAM challenge. The experimental results demonstrate that the IGRSVD algorithm is effective and more suitable for reconstructing large-scale networks.

An optimization approach for agent-based computational models of biological development

Current research in the field of computational biology often involves simulations on high-performance computer clusters. It is crucial that the code of such simulations is efficient and correctly reflects the model specifications.In this paper, we present an optimization strategy for agent-based simulations of biological dynamics using Intel Xeon Phi coprocessors, demonstrated by a prize-winning entry of the “Intel Modern Code Developer Challenge” competition. These optimizations allow simulating various biological mechanisms, in particular the simulation of millions of cells, their proliferation, movements and interactions in 3D space. Overall, our results demonstrate a powerful approach to implement and conduct very detailed and large-scale computational simulations for biological research. We also highlight the main difficulties faced when developing such optimizations, in particular the assessment of the simulation accuracy, the dependencies between different optimization techniques and counter-intuitive effects in the speed of the optimized solution. The overall speedup of 595 × shows a good parallel scalability.

Interactive and coordinated visualization approaches for biological data analysis.

The field of computational biology has become largely dependent on data visualization tools to analyze the increasing quantities of data gathered through the use of new and growing technologies. Aside from the volume, which often results in large amounts of noise and complex relationships with no clear structure, the visualization of biological data sets is hindered by their heterogeneity, as data are obtained from different sources and contain a wide variety of attributes, including spatial and temporal information. This requires visualization approaches that are able to not only represent various data structures simultaneously but also provide exploratory methods that allow the identification of meaningful relationships that would not be perceptible through data analysis algorithms alone. In this article, we present a survey of visualization approaches applied to the analysis of biological data. We focus on graph-based visualizations and tools that use coordinated multiple views to represent high-dimensional multivariate data, in particular time series gene expression, protein-protein interaction networks and biological pathways. We then discuss how these methods can be used to help solve the current challenges surrounding the visualization of complex biological data sets.

The ISCB Student Council Internship Program: Expanding computational biology capacity worldwide.

Education and training are two essential ingredients for a successful career. On one hand, universities provide students a curriculum for specializing in one’s field of study, and on the other, internships complement coursework and provide invaluable training experience for a fruitful career. Consequently, undergraduates and graduates are encouraged to undertake an internship during the course of their degree. The opportunity to explore one’s research interests in the early stages of their education is important for students because it improves their skill set and gives their career a boost. In the long term, this helps to close the gap between skills and employability among students across the globe and balance the research capacity in the field of computational biology. However, training opportunities are often scarce for computational biology students, particularly for those who reside in less-privileged regions. Aimed at helping students develop research and academic skills in computational biology and alleviating the divide across countries, the Student Council of the International Society for Computational Biology introduced its Internship Program in 2009. The Internship Program is committed to providing access to computational biology training, especially for students from developing regions, and improving competencies in the field. Here, we present how the Internship Program works and the impact of the internship opportunities so far, along with the challenges associated with this program.

Robust breast cancer prediction system based on rough set theory at National Cancer Institute of Egypt

Background: Breast cancer is one of the major death causing diseases of the women in the world. Every year more than million women are diagnosed with breast cancer more than half of them will die because of inaccuracies and delays in diagnosis of the disease. High accuracy in cancer prediction is important to improve the treatment quality and the survivability rate of patients.Objectives: In this paper, we are going to propose a new and robust breast cancer prediction and diagnosis system based on the Rough Set (RS). Also, introducing the robust classification process based on some new and most effective attributes. Comparing and evaluating the performance of our proposed approach with the clinical, Radial Basis Function, and Artificial Neural Networks classification schemes.Methods: The dataset used in our experiments consists of 60 samples obtained from the National Cancer Institute (NCI) of Egypt. We have used the RS theory to robustly find dependence relationships among data, and evaluate the importance of attributes through:•Applying the Approximation Sets on this dataset to identify the patient’s cancer stage (0, IA, IB, IIA, IIB, IIIA, IIIB, IIIC, IV); and•Running the Reduction process on this dataset to identify which attributes (symptoms) are most effective for description and predict breast cancer stage.Results:•Our approach has classified the patients into 9 different stages, Stage 0 with accuracy 75%, Stage IA with accuracy 71%, Stage IB with zero patients, Stage IIA with accuracy 86%, Stage IIB with accuracy 67.5%, Stage IIIA with accuracy 85%, Stage IIIB with accuracy 100%, Stage IIIC with zero patients, and Stage IV with accuracy 100%;•The Reduction process gives as output, the most effective symptoms to early predict and accurately diagnosis the breast cancer. That are represented in Lymph Node Status, Tumor Size, Estrogen Receptor Status, Progesterone Receptor Status, and Metastasis; and•The last but not least, we have found two patients (patient No. 11 and 51 from our dataset) in High Risk Status, which requires intensive and special treatment.Conclusion: We have introduced the robustness of the RS theory in early predicting and diagnosing the breast cancer. This lay more importance to the contribution and efficiency of RS theory in the field of computational biology.

Elastic restricted Boltzmann machines for cancer data analysis

Restricted Boltzmann machines (RBMs) are endowed with the universal power of modeling (binary) joint distributions. Meanwhile, as a result of their confining network structure, training RBMs confronts less difficulties when dealing with approximation and inference issues. But little work has been developed to fully exploit the capacity of these models to analyze cancer data, e.g., cancer genomic, transcriptomic, proteomic and epigenomic data. On the other hand, in the cancer data analysis task, the number of features/predictors is usually much larger than the sample size, which is known as the “p ≫ N” problem and is also ubiquitous in other bioinformatics and computational biology fields. The “p ≫ N” problem puts the bias-variance trade-off in a more crucial place when designing statistical learning methods. However, to date, few RBM models have been particularly designed to address this issue. We propose a novel RBMs model, called elastic restricted Boltzmann machines (eRBMs), which incorporates the elastic regularization term into the likelihood function, to balance the model complexity and sensitivity. Facilitated by the classic contrastive divergence (CD) algorithm, we develop the elastic contrastive divergence (eCD) algorithm which can train eRBMs efficiently. We obtain several theoretical results on the rationality and properties of our model.We further evaluate the power of our model based on a challenging task — predicting dichotomized survival time using the molecular profiling of tumors. The test results show that the prediction performance of eRBMs is much superior to that of the state-of-the-art methods. The proposed eRBMs are capable of dealing with the “p ≫ N” problems and have superior modeling performance over traditional methods. Our novel model is a promising method for future cancer data analysis.

Weighted measures based on maximizing deviation for alignment-free sequence comparison

Alignment-free sequence comparison is becoming fairly popular in many fields of computational biology due to less requirements for sequence itself and computational efficiency for a large scale of sequence data sets. Especially, the approaches based on k-tuple like D2, D2S and D2∗ are used widely and effectively. However, these measures treat each k-tuple equally without accounting for the potential importance differences among all k-tuples. In this paper, we take advantage of maximizing deviation method proposed in multiple attribute decision making to evaluate the weights of different k-tuples. We modify D2, D2S and D2∗ with weights and test them by similarity search and evaluation on functionally related regulatory sequences. The results demonstrate that the newly proposed measures are more efficient and robust compared to existing alignment-free methods.

Pupylation sites prediction with ensemble classification model

Post-translational modification of protein is one of the most important biological processions in the field of proteomics and bioinformatics. Pupylation is a novel post translational modification which the small, intrinsically disordered prokaryotic ubiquitin-like protein is conjugated to lysine residues of potential segments. Both the experimental and computational prediction methods of such modified sites have proved to be a challenging issue. Computational methods mainly aimed at extracting effective features from the potential protein segments. In this paper, the statistical feature of adjacent amino acid residues has been proposed and the novel feature is combined appearance of adjacent amino acid and the BLOSUM62 matrix. The Neural Network and the Naïve Bayesian model have been employed as the classification model in this work. Such model will also be utilised to deal with many other issues in the field of computational biology.

基于可持续更新模板库的蛋白质二级结构预测器

蛋白质二级结构预测是计算生物学研究的重要领域。虽然现有优秀的机器学习方法的预测准确度已经超过80%，但是它们都有共同的缺陷：不能及时学习最新实测的蛋白质结构信息，不能持续修改模型和参数，从而满足人们在日新月异时代对蛋白质二级结构预测的要求。本文构建了基于可持续更新模板库的蛋白质二级结构预测器：SIPSS。我们的新方法以同源序列的结构保守性为基本原理。首先我们建立了一个可持续更新的模板库，每月自动从蛋白质数据库中下载新测定的蛋白质结构数据，经过筛选将新的序列和结构信息补充进模板库。然后对于查询序列，用多重同源比对与模板库比对，得到新的变量：SPSSM变量。最后，我们以SPSSM为变量，用条件随机场建模和预测。实际测试表明，SIPSS能够在线学习新的蛋白质结构信息，对新近测定的蛋白质二级结构预测准确度(80.6%)明显高于现有的预测器。SIPSS网站：http://cheminfo.tongji.edu.cn/SIPSS/，可供用户免费使用。 Protein secondary structure prediction is an important field of computational biology. Although the accuracies of the existed state-of-the-art approaches are more than 80% but these methods have a common limitation. They couldn’t learn new structure knowledge of currently measured proteins, and couldn’t change the used model and their parameters. Thus, they couldn’t satisfy our expecting in the changing world. Here, we present a predictor of protein secondary structure based on a con-tinuously updated templet library: SIPSS. The basic stone of our approach is structural similarity based on sequence homology. First, a continuously updated templet library is constructed, which can automatically download the measured protein structure data from PDB per-month. After screening, the new information of protein sequences and structures are supplied into the template library. Then a query sequence is aligned against the template library by using PSI BLAST, and a new variable-SPSSM variable is obtained. Last, the SPSSM variable is used in a conditional random field algorithm for modelling and prediction. Our experiments showed that SIPSS can online learn new protein structure information and its prediction accuracy (80.6%) of protein secondary struc-ture measured in recent times is significantly better than the state-of-the art approaches. SIPSS is available free of charge at http://cheminfo.tongji.edu.cn/SIPSS/.

Numerical Characterization of Protein Sequences Based on the Generalized Chou’s Pseudo Amino Acid Composition

The technique of comparison and analysis of biological sequences is playing an increasingly important role in the field of Computational Biology and Bioinformatics. One of the key steps in developing the technique is to identify an appropriate manner to represent a biological sequence. In this paper, on the basis of three physical–chemical properties of amino acids, a protein primary sequence is reduced into a six-letter sequence, and then a set of elements which reflect the global and local sequence-order information is extracted. Combining these elements with the frequencies of 20 native amino acids, a ( 21 + λ ) dimensional vector is constructed to characterize the protein sequence. The utility of the proposed approach is illustrated by phylogenetic analysis and identification of DNA-binding proteins.

Tumor purity and differential methylation in cancer epigenomics.

DNA methylation is an epigenetic modification of DNA molecule that plays a vital role in gene expression regulation. It is not only involved in many basic biological processes, but also considered an important factor for tumorigenesis and other human diseases. Study of DNA methylation has been an active field in cancer epigenomics research. With the advances of high-throughput technologies and the accumulation of enormous amount of data, method development for analyzing these data has gained tremendous interests in the fields of computational biology and bioinformatics. In this review, we systematically summarize the recent developments of computational methods and software tools in high-throughput methylation data analysis with focus on two aspects: differential methylation analysis and tumor purity estimation in cancer studies.

Filogenia de malware orientada al análisis de librerías

In the field of computational biology, phylogeny is used to recognize the existing similarity between various species as well as the evolution engine (force) that has enabled these species to show modifications as time goes by. The use of these phylogeny techniques with a focus on computer viruses has allowed the finding of similarities between different malware families. This study presents the implementation of a proof of concept through the application of a technique used in the bioinformatics field, as is the case of the Neighbor Joining algorithm designed for the analysis of a group of computer samples. The aim will be to detect the similarity between the gathered samples, considering the similarity between the libraries of the system that uses this kind of programs.

A Multilevel Framework for Sparse Optimization with Application to Inverse Covariance Estimation and Logistic Regression

Solving $l_1$ regularized optimization problems is common in the fields of computational biology, signal processing, and machine learning. Such $l_1$ regularization is utilized to find sparse minimizers of convex functions. A well-known example is the least absolute shrinkage and selection operator (LASSO) problem, where the $l_1$ norm regularizes a quadratic function. A multilevel framework is presented for solving such $l_1$ regularized sparse optimization problems efficiently. We take advantage of the expected sparseness of the solution, and create a hierarchy of problems of similar type, which is traversed in order to accelerate the optimization process. This framework is applied for solving two problems: (1) the sparse inverse covariance estimation problem, and (2) $l_1$ regularized logistic regression. In the first problem, the inverse of an unknown covariance matrix of a multivariate normal distribution is estimated, under the assumption that it is sparse. To this end, an $l_1$ regularized log-dete...

A fixed-parameter algorithm for the maximum agreement forest problem on multifurcating trees

The Maximum Agreement Forest (MAF) problem on two given phylogenetic trees is an important NP-hard problem in the field of computational biology. In this paper, we study the parameterized version of the MAF problem: given two unrooted (multifurcating) phylogenetic trees T1 and T2 with the same leaf-label set L, and a parameter k, either construct an agreement forest of at most k trees for T1 and T2, or report that no such a forest exists. Whether there is a fixed-parameter tractable algorithm for this problem was posed as an open problem several times in the literature. In this paper, we resolve this open problem by presenting a parameterized algorithm of running time O(4kn5) for the problem.

A New Heuristic Approach for DNA Sequences Alignment

The problem of comparing DNA sequences is one of the most significant tasks in the field of computational biology. It helps locating the similarities and differences between pairs of DNA sequences. This task can be achieved by finding the longest common substrings between DNA sequences and consequently aligning them. The complexity of this task is due to the high computational power and huge space consuming. Comparing DNA sequences leads to infer the cause of a certain disease beside many significant biological applications. This paper introduces a new Heuristic Approach for DNA Sequences Alignment between two DNA sequences. The new approach is based on three processing phases: the first phase finds the multiple common substrings in the two sequences, the second one sorts the obtained common substrings descending according to their lengths, and the last phase generates the optimal two aligned sequences. The modules of the new approach have been implemented and tested in C# language under Windows platform. The obtained results manifest a reduction in both time of processing and memory requirements.

Hybrid Dynamic Optimization Methods for Systems Biology with Efficient Sensitivities

In recent years, model optimization in the field of computational biology has become a prominent area for development of pharmaceutical drugs. The increased amount of experimental data leads to the increase in complexity of proposed models. With increased complexity comes a necessity for computational algorithms that are able to handle the large datasets that are used to fit model parameters. In this study the ability of simultaneous, hybrid simultaneous, and sequential algorithms are tested on two models representative of computational systems biology. The first case models the cells affected by a virus in a population and serves as a benchmark model for the proposed hybrid algorithm. The second model is the ErbB model and shows the ability of the hybrid sequential and simultaneous method to solve large-scale biological models. Post-processing analysis reveals insights into the model formulation that are important for understanding the specific parameter optimization. A parameter sensitivity analysis reveals shortcomings and difficulties in the ErbB model parameter optimization due to the model formulation rather than the solver capacity. Suggested methods are model reformulation to improve input-to-output model linearity, sensitivity ranking, and choice of solver.

An Integer Programming Formulation of the Minimum Common String Partition Problem.

We consider the problem of finding a minimum common string partition (MCSP) of two strings, which is an NP-hard problem. The MCSP problem is closely related to genome comparison and rearrangement, an important field in Computational Biology. In this paper, we map the MCSP problem into a graph applying a prior technique and using this graph, we develop an Integer Linear Programming (ILP) formulation for the problem. We implement the ILP formulation and compare the results with the state-of-the-art algorithms from the literature. The experimental results are found to be promising.

Message from the ISCB: 2015 ISCB Accomplishment by a Senior Scientist Award: Cyrus Chothia.

The International Society for Computational Biology (ISCB; http://www.iscb.org) honors a senior scientist annually for his or her outstanding achievements with the ISCB Accomplishment by a Senior Scientist Award. This award recognizes a leader in the field of computational biology for his or her significant contributions to the community through research, service and education. Cyrus Chothia, an emeritus scientist at the Medical Research Council Laboratory of Molecular Biology and emeritus fellow of Wolfson College at Cambridge University, England, is the 2015 ISCB Accomplishment by a Senior Scientist Award winner.Chothia was selected by the Awards Committee, which is chaired by Dr Bonnie Berger of the Massachusetts Institute of Technology. He will receive his award and deliver a keynote presentation at 2015 Intelligent Systems for Molecular Biology/European Conference on Computational Biology in Dublin, Ireland, in July 2015. dkovats@iscb.org.