Knowledge graph-based convolutional network coupled with sentiment analysis towards enhanced drug recommendation.

Recommending appropriate drugs to patients based on their history and symptoms is a complex real-world problem. Knowing whether a drug is useful without its consumption by a variety of people followed by proper evaluation is a challenge. Modern-day recommender systems can assist in this provided they receive large data to learn. Public reviews on various drugs are available for knowledge sharing. These reviews assist in recommending the best and most appropriate option to the user. The explicit feedback underpins the entire recommender system. This work develops a novel knowledge graph-based convolutional network for recommending drugs. The knowledge graph is coupled with sentiment analysis extracted from the public reviews on drugs to enhance drug recommendations. For each drug that has been used previously, sentiments have been analyzed to determine which one has the most effective reviews. The knowledge graph effectively captures user-item relatedness by mining its associated attributes. Experiments are performed on public benchmarks and a comparison is made with closely related state-of-the-art works. Based on the obtained results, the current work performs better than the past contributions by achieving up to 98.7% Area Under Curve (AUC) score.

Imagined character recognition through EEG signals using deep convolutional neural network.

Electroencephalography (EEG)-based brain computer interface (BCI) enables people to interact directly with computing devices through their brain signals. A BCI typically interprets EEG signals to reflect the user's intent or other mental activity. Motor imagery (MI) is a commonly used technique in BCIs where a user is asked to imagine moving certain part of the body such as a hand or a foot. By correctly interpreting the signal, one can perform a multitude of tasks such as controlling wheel chair, playing computer games, or even typing text. However, the use of motor-imagery-based BCIs outside the laboratory environment is limited due to the lack of their reliability. This work focuses on another kind of mental imagery, namely, the visual imagery (VI). VI is the manipulation of visual information that comes from memory. This work presents a deep convolutional neural network (DCNN)-based system for the recognition of visual/mental imagination of English alphabets so as to enable typing directly via brain signals. The DCNN learns to extract the spatial features hidden in the EEG signal. As opposed to many deep neural networks that use raw EEG signals for classification, this work transforms the raw signals into band powers using Morlet wavelet transformation. The proposed approach is evaluated on two publicly available benchmark MI-EEG datasets and a visual imagery dataset specifically collected for this work. The obtained results demonstrate that the proposed model performs better than the existing state-of-the-art methods for MI-EEG classification and yields an average accuracy of 99.45% on the two public MI-EEG datasets. The model also achieves an average recognition rate of 95.2% for the 26 English-language alphabets. Overall working of the proposed solution for imagined character recognition through EEG signals.

Orienting Conflicted Graph Edges Using Genetic Algorithms to Discover Pathways in Protein-Protein Interaction Networks.

Advanced computational techniques of the current era help to identify proteins from the complex biological network that interact with each other and with the cell's environment. Biological pathways are a chain of molecular actions that leads to a new molecular product creation or alters the cellular state. These pathways are helpful in the predication of many real-world issues. Rebuilding these pathways is a challenging task due to the fact that protein interactions are undirected, whereas pathways are directed. To discover these pathways in protein-protein interaction data from specified source and target, it is essential to orient protein interactions. Unfortunately, the edge orientation problem is NP-hard, which makes it challenging to develop effective algorithms. This work rebuilds biologically important pathways in a weighted network of protein interactions of yeast species. The proposed algorithm, pseudo-guided multi-objective genetic algorithm (PGMOGA) rebuilds pathways by assigning orientation to the edges of the weighted network. Extending the past research, mathematical modeling of single-objective and multi-objective functions is performed. The PGMOGA is compared with four state-of-the-art approaches, namely, random orientation plus local search (ROLS), single-objective genetic algorithm (SOGA), multi-objective genetic algorithm (MOGA), and multi random search (MRS). The comparison is based on three general and four path specific metrics. Results show that the current proposal performs better.

Status of insecticide resistance and its biochemical and molecular mechanisms in Anopheles stephensi (Diptera: Culicidae) from Afghanistan.

BACKGROUND: Insecticide resistance of Anopheles stephensi, the main malaria vector in eastern Afghanistan, has been reported previously. This study describes the biochemical and molecular mechanisms of resistance to facilitate effective vector control and insecticide resistance management. METHODS: Mosquito larvae were collected from the provinces of Kunar, Laghman and Nangarhar from 2014 to 2017. The susceptibility of the reared 3-4 days old adults was tested with deltamethrin 0.05%, bendiocarb 0.1%, malathion 5%, permethrin 0.75% and DDT 4%. Cytochrome P450 content and general esterase, glutathione S-transferase (GST) and acetylcholinesterase (AChE) activities were measured in the three field populations and the results were compared with those of the laboratory susceptible An. stephensi Beech strain. Two separate allele-specific PCR assays were used to identify L1014, L1014F and L1014S mutations in the voltage gated sodium channel gene of An. stephensi. Probit analysis, ANOVA and Hardy-Weinberg equilibrium were used to analyse bioassay, biochemical assay and gene frequency data respectively. RESULTS: The population of An. stephensi from Kunar was susceptible to bendiocarb, apart from this, all populations were resistant to all the other insecticides tested. The differences between all values for cytochrome P450s, general esterases, GSTs and AChE inhibition rates in the Kunar, Laghman and Nangarhar populations were statistically significant when compared to the Beech strain, excluding GST activities between Kunar and Beech due to the high standard deviation in Kunar. The three different sodium channel alleles [L1014 (wild type), L1014F (kdr west) and L1014S (kdr east)] were all segregated in the Afghan populations. The frequencies of kdr east mutation were 22.9%, 32.7% and 35% in Kunar, Laghman and Nangarhar populations respectively. Kdr west was at the lowest frequency of 4.44%. CONCLUSIONS: Resistance to different groups of insecticides in the field populations of An. stephensi from Kunar, Laghman and Nangarhar Provinces of Afghanistan is caused by a range of metabolic and site insensitivity mechanisms, including esterases, cytochrome P450s and GSTs combined with AChE and sodium channel target site insensitivity. The intensity and frequency of these mechanisms are increasing in these populations, calling for urgent reorientation of vector control programmes and implementation of insecticide resistance management strategies.

Evidence of metabolic mechanisms playing a role in multiple insecticides resistance in Anopheles stephensi populations from Afghanistan.

BACKGROUND: Malaria is endemic in most parts of Afghanistan and insecticide-based vector control measures are central in controlling the disease. Insecticide resistance in the main malaria vector Anopheles stephensi from Afghanistan is increasing and attempts should be made to determine the underlying resistance mechanisms for its adequate management. METHODS: The contents of cytochrome P450s, esterases, glutathione S-transferases (GSTs) and acetylcholine esterase (AChE) activities were measured in the Kunar and Nangarhar populations of An. stephensi from Afghanistan and the results were compared with those of the susceptible Beech strain using the World Health Organization approved biochemical assay methods for adult mosquitoes. RESULTS: The cytochrome P450s enzyme ratios were 2.23- and 2.54-fold in the Kunar and Nangarhar populations compared with the susceptible Beech strain. The enzyme ratios for esterases with alpha-naphthyl acetate were 1.45 and 2.11 and with beta-naphthyl acetate were 1.62 and 1.85 in the Kunar and Nangarhar populations respectively compared with the susceptible Beech strain. Esterase ratios with para-nitrophenyl acetate (pNPA) were 1.61 and 1.75 in the Kunar and Nangarhar populations compared with the susceptible Beech strain. The GSTs enzyme ratios were 1.33 and 1.8 in the Kunar and Nangarhar populations compared with the susceptible Beech strain. The inhibition of AChE was 70.9 in the susceptible Beech strain, and 56.7 and 51.5 in the Kunar and Nangarhar populations. The differences between all values of the enzymes activities/contents and AChE inhibition rates in the Kunar and Nangarhar populations were statistically significant when compared with those of the susceptible Beech strain. CONCLUSIONS: Based on the results, the reported resistance to pyrethroid and organophosphate insecticides, and tolerance to bendiocarb in the Kunar and Nangarhar populations of An. stephensi from Afghanistan are likely to be caused by a range of metabolic mechanisms, including esterases, P450s and GSTs combined with target site insensitivity in AChE.

A Kinect-Based Sign Language Hand Gesture Recognition System for Hearing- and Speech-Impaired: A Pilot Study of Pakistani Sign Language.

Sign language provides hearing and speech impaired individuals with an interface to communicate with other members of the society. Unfortunately, sign language is not understood by most of the common people. For this, a gadget based on image processing and pattern recognition can provide with a vital aid for detecting and translating sign language into a vocal language. This work presents a system for detecting and understanding the sign language gestures by a custom built software tool and later translating the gesture into a vocal language. For the purpose of recognizing a particular gesture, the system employs a Dynamic Time Warping (DTW) algorithm and an off-the-shelf software tool is employed for vocal language generation. Microsoft(®) Kinect is the primary tool used to capture video stream of a user. The proposed method is capable of successfully detecting gestures stored in the dictionary with an accuracy of 91%. The proposed system has the ability to define and add custom made gestures. Based on an experiment in which 10 individuals with impairments used the system to communicate with 5 people with no disability, 87% agreed that the system was useful.