Disease genes prediction by HMM based PU-learning using gene expression profiles.

Predicting disease candidate genes from human genome is a crucial part of nowadays biomedical research. According to observations, diseases with the same phenotype have the similar biological characteristics and genes associated with these same diseases tend to share common functional properties. Therefore, by applying machine learning methods, new disease genes are predicted based on previous ones. In recent studies, some semi-supervised learning methods, called Positive-Unlabeled Learning (PU-Learning) are used for predicting disease candidate genes. In this study, a novel method is introduced to predict disease candidate genes through gene expression profiles by learning hidden Markov models. In order to evaluate the proposed method, it is applied on a mixed part of 398 disease genes from three disease types and 12001 unlabeled genes. Compared to the other methods in literature, the experimental results indicate a significant improvement in favor of the proposed method.

VR-BFDT: A variance reduction based binary fuzzy decision tree induction method for protein function prediction.

In protein function prediction (PFP) problem, the goal is to predict function of numerous well-sequenced known proteins whose function is not still known precisely. PFP is one of the special and complex problems in machine learning domain in which a protein (regarded as instance) may have more than one function simultaneously. Furthermore, the functions (regarded as classes) are dependent and also are organized in a hierarchical structure in the form of a tree or directed acyclic graph. One of the common learning methods proposed for solving this problem is decision trees in which, by partitioning data into sharp boundaries sets, small changes in the attribute values of a new instance may cause incorrect change in predicted label of the instance and finally misclassification. In this paper, a Variance Reduction based Binary Fuzzy Decision Tree (VR-BFDT) algorithm is proposed to predict functions of the proteins. This algorithm just fuzzifies the decision boundaries instead of converting the numeric attributes into fuzzy linguistic terms. It has the ability of assigning multiple functions to each protein simultaneously and preserves the hierarchy consistency between functional classes. It uses the label variance reduction as splitting criterion to select the best "attribute-value" at each node of the decision tree. The experimental results show that the overall performance of the proposed algorithm is promising.

PCD-GED: Protein complex detection considering PPI dynamics based on time series gene expression data.

Detection of protein complexes from protein-protein interaction (PPI) networks is essential to understand the function of cell machinery. However, available PPIs are static, and cannot reflect the dynamics inherent in real networks. Our method uses time series gene expression data in addition to PPI networks to detect protein complexes. The proposed method generates a series of time-sequenced subnetworks (TSN) according to the time that the interactions are activated. It finds, from each TSN, the protein complexes by employing the weighted clustering coefficient and maximal weighted density concepts. The final set of detected protein complexes are obtained from union of all complexes from different subnetworks. Our findings suggest that by employing these considerations can produce far better results in protein complex detection problem.

Light-based solution for the dominating set problem.

In this paper, an optical solution for the dominating set problem is provided. The solution is based on long ribbon-shaped optical filters, on which some operations can be optically applied efficiently. The provided solution requires polynomial time, exponential length of filters, and exponential number of photons to solve the dominating set problem. The provided solution is implemented experimentally using lithographic sheets, on a graph with six vertices, to find all dominating sets with two vertices.

Comparison of Anesthesia Results between Wide Awake Local Anesthesia no Tourniquet (WALANT) and Forearm Tourniquet Bier Block in Hand Surgeries: A Randomized Clinical Trial.

BACKGROUND: There is still some debate regarding the most proper anesthetic technique in minor hand surgeries. We hypothesized that both the WALANT and forearm tourniquet Bier block methods provide effective anesthesia in minor hand surgeries without significant difference. METHODS: A total of 85 patients consented to participate in this study and were randomized into WALANT and single tourniquet forearm Bier block groups. In WALANT group, patients received adrenaline-contained lidocaine without tourniquet while lidocaine was administered accordingly after applying a forearm tourniquet in Bier group. Due to difference in intervention methods, the study was non-blinded. Need for additional analgesia during surgery, visual analogue scale (VAS) for pain intensity during operation and an hour later, amount of bleeding and active hand movements were evaluated and recorded. RESULTS: The need for analgesia and severity of pain (VAS) during surgery and one hour later were significantly less in WALANT group, whereas the amount of bleeding was less in Bier block group. The ability to move hand and fingers during the operation was the same in both groups. CONCLUSION: Both WALANT and single cuff forearm tourniquet Bier block are effective methods in minor hand surgeries, however, forearm Bier block provides less analgesia and pain control with a drier field than WALANT method.

DPCT: A Dynamic Method for Detecting Protein Complexes From TAP-Aware Weighted PPI Network.

Detecting protein complexes from the Protein-Protein interaction network (PPI) is the essence of discovering the rules of the cellular world. There is a large amount of PPI data available, generated from high throughput experimental data. The enormous size of the data persuaded us to use computational methods instead of experimental methods to detect protein complexes. In past years, many researchers presented their algorithms to detect protein complexes. Most of the presented algorithms use current static PPI networks. New researches proved the dynamicity of cellular systems, and so, the PPI is not static over time. In this paper, we introduce DPCT to detect protein complexes from dynamic PPI networks. In the proposed method, TAP and GO data are used to make a weighted PPI network and to reduce the noise of PPI. Gene expression data are also used to make dynamic subnetworks from PPI. A memetic algorithm is used to bicluster gene expression data and to create a dynamic subnetwork for each bicluster. Experimental results show that DPCT can detect protein complexes with better correctness than state-of-the-art detection algorithms. The source code and datasets of DPCT used can be found at https://github.com/alisn72/DPCT.

Comparison of effects of propofol and ketofol (Ketamine-Propofol mixture) on emergence agitation in children undergoing tonsillectomy.

BACKGROUND: The aim of this study was to compare the effect of propofol and ketofol (ketamine-propofol mixture) on EA in children undergoing tonsillectomy. METHOD: In this randomized clinical trial, 87 ASA class I and II patients, aged 3-12 years, who underwent tonsillectomy, were divided into two groups to receive either propofol 100 µg/kg/min (group p, n=44) or ketofol : ketamine 25 µg/kg/min + propofol 75 µg/kg/min (group k, n= 43). Incidence and severity of EA was evaluated using the Pediatric Anesthesia Emergence Delirium (PAED) scales on arrival at the recovery room, and 10 and 30 min after that time. RESULTS: There was no statistically significant difference in demographic data between the two groups. In the ketofol group, the need for agitation treatment and also mean recovery duration were lower than in the propofol group (30 and 41%, and 29.9 and 32.7 min), without statistically significant difference (P value=0.143 and P value=0.187). Laryngospasm or bronchospasm occurred in 2 patients in each group and bleeding was observed in only one individual in the ketofol group. CONCLUSION: Infusion of ketofol in children undergoing tonsillectomy provides shorter recovery time and lower incidence of EA despite the non significant difference with propofol.

C-PUGP: A cluster-based positive unlabeled learning method for disease gene prediction and prioritization.

Disease gene detection is an important stage in the understanding disease processes and treatment. Some candidate disease genes are identified using many machine learning methods Although there are some differences in these methods including feature vector of genes, the method used to selecting reliable negative data (non-disease genes), and the classification method, the lack of negative data is the most significant challenge of them. Recently, candidate disease genes are identified by semi-supervised learning methods based on positive and unlabeled data. These methods are reasonably accurate and achieved more desirable results versus preceding methods. In this article, we propose a novel Positive Unlabeled (PU) learning technique based upon clustering and One-Class classification algorithm. In this regard, unlike existing methods, we make a more Reliable Negative (RN) set in three steps: (1) Clustering positive data, (2) Learning One-Class classifier models using the clusters, and (3) Selecting intersection set of negative data as the Reliable Negative set. Next, we attempt to identify and rank the candidate disease genes using a binary classifier based on support vector machine (SVM) algorithm. Experimental results indicate that the proposed method yields to the best results, that is 92.8, 93.6, and 93.1 in terms of precision, recall, and F-measure respectively. Compared to the existing methods, the increase of performances of our proposed method is 11.7 percent better than the best method in terms of F-measure. Also, results show about 6% increase in the prioritization results.

BiCAMWI: A Genetic-Based Biclustering Algorithm for Detecting Dynamic Protein Complexes.

Considering the roles of protein complexes in many biological processes in the cell, detection of protein complexes from available protein-protein interaction (PPI) networks is a key challenge in the post genome era. Despite high dynamicity of cellular systems and dynamic interaction between proteins in a cell, most computational methods have focused on static networks which cannot represent the inherent dynamicity of protein interactions. Recently, some researchers try to exploit the dynamicity of PPI networks by constructing a set of dynamic PPI subnetworks correspondent to each time-point (column) in a gene expression data. However, many genes can participate in multiple biological processes and cellular processes are not necessarily related to every sample, but they might be relevant only for a subset of samples. So, it is more interesting to explore each subnetwork based on a subset of genes and conditions (i.e., biclusters) in a gene expression data. Here, we present a new method, called BiCAMWI to employ dynamicity in detecting protein complexes. The preprocessing phase of the proposed method is based on a novel genetic algorithm that extracts some sets of genes that are co-regulated under some conditions from input gene expression data. Each extracted gene set is called bicluster. In the detection phase of the proposed method, then, based on the biclusters, some dynamic PPI subnetworks are extracted from input static PPI network. Protein complexes are identified by applying a detection method on each dynamic PPI subnetwork and aggregating the results. Experimental results confirm that BiCAMWI effectively models the dynamicity inherent in static PPI networks and achieves significantly better results than state-of-the-art methods. So, we suggest BiCAMWI as a more reliable method for protein complex detection.

Predicting metabolic syndrome using decision tree and support vector machine methods.

BACKGROUND: Metabolic syndrome which underlies the increased prevalence of cardiovascular disease and Type 2 diabetes is considered as a group of metabolic abnormalities including central obesity, hypertriglyceridemia, glucose intolerance, hypertension, and dyslipidemia. Recently, artificial intelligence based health-care systems are highly regarded because of its success in diagnosis, prediction, and choice of treatment. This study employs machine learning technics for predict the metabolic syndrome. METHODS: This study aims to employ decision tree and support vector machine (SVM) to predict the 7-year incidence of metabolic syndrome. This research is a practical one in which data from 2107 participants of Isfahan Cohort Study has been utilized. The subjects without metabolic syndrome according to the ATPIII criteria were selected. The features that have been used in this data set include: gender, age, weight, body mass index, waist circumference, waist-to-hip ratio, hip circumference, physical activity, smoking, hypertension, antihypertensive medication use, systolic blood pressure (BP), diastolic BP, fasting blood sugar, 2-hour blood glucose, triglycerides (TGs), total cholesterol, low-density lipoprotein, high density lipoprotein-cholesterol, mean corpuscular volume, and mean corpuscular hemoglobin. Metabolic syndrome was diagnosed based on ATPIII criteria and two methods of decision tree and SVM were selected to predict the metabolic syndrome. The criteria of sensitivity, specificity and accuracy were used for validation. RESULTS: SVM and decision tree methods were examined according to the criteria of sensitivity, specificity and accuracy. Sensitivity, specificity and accuracy were 0.774 (0.758), 0.74 (0.72) and 0.757 (0.739) in SVM (decision tree) method. CONCLUSION: The results show that SVM method sensitivity, specificity and accuracy is more efficient than decision tree. The results of decision tree method show that the TG is the most important feature in predicting metabolic syndrome. According to this study, in cases where only the final result of the decision is regarded significant, SVM method can be used with acceptable accuracy in decision making medical issues. This method has not been implemented in the previous research.

CAMWI: Detecting protein complexes using weighted clustering coefficient and weighted density.

Detection of protein complexes is very important to understand the principles of cellular organization and function. Recently, large protein-protein interactions (PPIs) networks have become available using high-throughput experimental techniques. These networks make it possible to develop computational methods for protein complex detection. Most of the current methods rely on the assumption that protein complex as a module has dense structure. However complexes have core-attachment structure and proteins in a complex core share a high degree of functional similarity, so it expects that a core has high weighted density. In this paper we present a Core-Attachment based method for protein complex detection from Weighted PPI Interactions using clustering coefficient and weighted density. Experimental results show that the proposed method, CAMWI improves the accuracy of protein complex detection.

Protein fold recognition with a two-layer method based on SVM-SA, WP-NN and C4.5 (TLM-SNC).

The structural knowledge of protein is crucial in understanding its biological role. An effort is made to assign a fold to a given protein in a protein fold recognition problem. A computational Two-Layer Method (TLM) based on the Support Vector Machine (SVM), the Neural Network (NN) and the Decision Tree (C4.5) has been developed in this study for the assignment of a protein sequence to a folding class in SCOP. Prediction accuracy is measured on a dataset and the accuracy of the proposed method is very promising in comparison with other classification methods.

RANGI: a fast list-colored graph motif finding algorithm.

Given a multiset of colors as the query and a list-colored graph, i.e., an undirected graph with a set of colors assigned to each of its vertices, in the NP-hard list-colored graph motif problem the goal is to find the largest connected subgraph such that one can select a color from the set of colors assigned to each of its vertices to obtain a subset of the query. This problem was introduced to find functional motifs in biological networks. We present a branch-and-bound algorithm named RANGI for finding and enumerating list-colored graph motifs. As our experimental results show, RANGI's pruning methods and heuristics make it quite fast in practice compared to the algorithms presented in the literature. We also present a parallel version of RANGI that achieves acceptable scalability.