Utilization of Synthetic Near-Infrared Spectra via Generative Adversarial Network to Improve Wood Stiffness Prediction.

Near-infrared (NIR) spectroscopy is widely used as a nondestructive evaluation (NDE) tool for predicting wood properties. When deploying NIR models, one faces challenges in ensuring representative training data, which large datasets can mitigate but often at a significant cost. Machine learning and deep learning NIR models are at an even greater disadvantage because they typically require higher sample sizes for training. In this study, NIR spectra were collected to predict the modulus of elasticity (MOE) of southern pine lumber (training set = 573 samples, testing set = 145 samples). To account for the limited size of the training data, this study employed a generative adversarial network (GAN) to generate synthetic NIR spectra. The training dataset was fed into a GAN to generate 313, 573, and 1000 synthetic spectra. The original and enhanced datasets were used to train artificial neural networks (ANNs), convolutional neural networks (CNNs), and light gradient boosting machines (LGBMs) for MOE prediction. Overall, results showed that data augmentation using GAN improved the coefficient of determination (R2) by up to 7.02% and reduced the error of predictions by up to 4.29%. ANNs and CNNs benefited more from synthetic spectra than LGBMs, which only yielded slight improvement. All models showed optimal performance when 313 synthetic spectra were added to the original training data; further additions did not improve model performance because the quality of the datapoints generated by GAN beyond a certain threshold is poor, and one of the main reasons for this can be the size of the initial training data fed into the GAN. LGBMs showed superior performances than ANNs and CNNs on both the original and enhanced training datasets, which highlights the significance of selecting an appropriate machine learning or deep learning model for NIR spectral-data analysis. The results highlighted the positive impact of GAN on the predictive performance of models utilizing NIR spectroscopy as an NDE technique and monitoring tool for wood mechanical-property evaluation. Further studies should investigate the impact of the initial size of training data, the optimal number of generated synthetic spectra, and machine learning or deep learning models that could benefit more from data augmentation using GANs.

Interpretable machine learning identification of arginine methylation sites.

Protein methylation is one of the most prominent posttranslation modifications that essentially regulates several biological processes in eukaryotes. Therefore, identification of the arginine methylation site is crucial in deciphering its characteristics and functions in cell biology, disease mechanisms, and guided drug development. The computation methods address the long-term bottleneck together with the cost, time, and labor required in experimental methods for large-scale identification of protein arginine methylation sites. In this study, we proposed a robust machine learning-based computational tool known as iIRMethyl, employing the primary sequence and physicochemical properties of protein along with a two-step feature selection method for optimal selection of feature descriptors. Moreover, the performance of iIRMethyl was comprehensively evaluated via k-fold cross-validation on a benchmark dataset and independent test dataset. iIRMethyl demonstrated a remarkably greater performance than the state-of-the-art method and achieved an average area under the curve value of 0.99 for both k-fold cross-validation and an independent test set in the identification of protein arginine methylation sites. Furthermore, the outcomes reveal that iIRMethyl is a robust and accurate computational tool for large-scale identification of arginine methylation sites and would facilitate the understanding of their functional mechanisms and accelerating their application in drug development and clinical therapy. Additionally, the prediction mechanism of the proposed model iIRMethyl is interpreted using the SHapley Additive exPlanation algorithm.

Identification of piRNA disease associations using deep learning.

Piwi-interacting RNAs (piRNAs) play a pivotal role in maintaining genome integrity by repression of transposable elements, gene stability, and association with various disease progressions. Cost-efficient computational methods for the identification of piRNA disease associations promote the efficacy of disease-specific drug development. In this regard, we developed a simple, robust, and efficient deep learning method for identifying the piRNA disease associations known as piRDA. The proposed architecture extracts the most significant and abstract information from raw sequences represented in a simplicated piRNA disease pair without any involvement of features engineering. Two-step positive unlabeled learning and bootstrapping technique are utilized to abstain from the false-negative and biased predictions dealing with positive unlabeled data. The performance of proposed method piRDA is evaluated using k-fold cross-validation. The piRDA is significantly improved in all the performance evaluation measures for the identification of piRNA disease associations in comparison to state-of-the-art method. Moreover, it is thus projected conclusively that the proposed computational method could play a significant role as a supportive and practical tool for primitive disease mechanisms and pharmaceutical research such as in academia and drug design. Eventually, the proposed model can be accessed using publicly available and user-friendly web tool athttp://nsclbio.jbnu.ac.kr/tools/piRDA/.

Identification of Functional piRNAs Using a Convolutional Neural Network.

Piwi-interacting RNAs (piRNAs) are a distinct sub-class of small non-coding RNAs that are mainly responsible for germline stem cell maintenance, gene stability, and maintaining genome integrity by repression of transposable elements. piRNAs are also expressed aberrantly and associated with various kinds of cancers. To identify piRNAs and their role in guiding target mRNA deadenylation, the currently available computational methods require urgent improvements in performance. To facilitate this, we propose a robust predictor based on a lightweight and simplified deep learning architecture using a convolutional neural network (CNN) to extract significant features from raw RNA sequences without the need for more customized features. The proposed model's performance is comprehensively evaluated using k-fold cross-validation on a benchmark dataset. The proposed model significantly outperforms existing computational methods in the prediction of piRNAs and their role in target mRNA deadenylation. In addition, a user-friendly and publicly-accessible web server is available at http://nsclbio.jbnu.ac.kr/tools/2S-piRCNN/.

The Burden of Mental Disorders in the Eastern Mediterranean Region, 1990-2013.

The Eastern Mediterranean Region (EMR) is witnessing an increase in chronic disorders, including mental illness. With ongoing unrest, this is expected to rise. This is the first study to quantify the burden of mental disorders in the EMR. We used data from the Global Burden of Disease study (GBD) 2013. DALYs (disability-adjusted life years) allow assessment of both premature mortality (years of life lost-YLLs) and nonfatal outcomes (years lived with disability-YLDs). DALYs are computed by adding YLLs and YLDs for each age-sex-country group. In 2013, mental disorders contributed to 5.6% of the total disease burden in the EMR (1894 DALYS/100,000 population): 2519 DALYS/100,000 (2590/100,000 males, 2426/100,000 females) in high-income countries, 1884 DALYS/100,000 (1618/100,000 males, 2157/100,000 females) in middle-income countries, 1607 DALYS/100,000 (1500/100,000 males, 1717/100,000 females) in low-income countries. Females had a greater proportion of burden due to mental disorders than did males of equivalent ages, except for those under 15 years of age. The highest proportion of DALYs occurred in the 25-49 age group, with a peak in the 35-39 years age group (5344 DALYs/100,000). The burden of mental disorders in EMR increased from 1726 DALYs/100,000 in 1990 to 1912 DALYs/100,000 in 2013 (10.8% increase). Within the mental disorders group in EMR, depressive disorders accounted for most DALYs, followed by anxiety disorders. Among EMR countries, Palestine had the largest burden of mental disorders. Nearly all EMR countries had a higher mental disorder burden compared to the global level. Our findings call for EMR ministries of health to increase provision of mental health services and to address the stigma of mental illness. Moreover, our results showing the accelerating burden of mental health are alarming as the region is seeing an increased level of instability. Indeed, mental health problems, if not properly addressed, will lead to an increased burden of diseases in the region.

Health in times of uncertainty in the eastern Mediterranean region, 1990-2013: a systematic analysis for the Global Burden of Disease Study 2013.

BACKGROUND: The eastern Mediterranean region is comprised of 22 countries: Afghanistan, Bahrain, Djibouti, Egypt, Iran, Iraq, Jordan, Kuwait, Lebanon, Libya, Morocco, Oman, Pakistan, Palestine, Qatar, Saudi Arabia, Somalia, Sudan, Syria, Tunisia, the United Arab Emirates, and Yemen. Since our Global Burden of Disease Study 2010 (GBD 2010), the region has faced unrest as a result of revolutions, wars, and the so-called Arab uprisings. The objective of this study was to present the burden of diseases, injuries, and risk factors in the eastern Mediterranean region as of 2013. METHODS: GBD 2013 includes an annual assessment covering 188 countries from 1990 to 2013. The study covers 306 diseases and injuries, 1233 sequelae, and 79 risk factors. Our GBD 2013 analyses included the addition of new data through updated systematic reviews and through the contribution of unpublished data sources from collaborators, an updated version of modelling software, and several improvements in our methods. In this systematic analysis, we use data from GBD 2013 to analyse the burden of disease and injuries in the eastern Mediterranean region specifically. FINDINGS: The leading cause of death in the region in 2013 was ischaemic heart disease (90·3 deaths per 100 000 people), which increased by 17·2% since 1990. However, diarrhoeal diseases were the leading cause of death in Somalia (186·7 deaths per 100 000 people) in 2013, which decreased by 26·9% since 1990. The leading cause of disability-adjusted life-years (DALYs) was ischaemic heart disease for males and lower respiratory infection for females. High blood pressure was the leading risk factor for DALYs in 2013, with an increase of 83·3% since 1990. Risk factors for DALYs varied by country. In low-income countries, childhood wasting was the leading cause of DALYs in Afghanistan, Somalia, and Yemen, whereas unsafe sex was the leading cause in Djibouti. Non-communicable risk factors were the leading cause of DALYs in high-income and middle-income countries in the region. DALY risk factors varied by age, with child and maternal malnutrition affecting the younger age groups (aged 28 days to 4 years), whereas high bodyweight and systolic blood pressure affected older people (aged 60-80 years). The proportion of DALYs attributed to high body-mass index increased from 3·7% to 7·5% between 1990 and 2013. Burden of mental health problems and drug use increased. Most increases in DALYs, especially from non-communicable diseases, were due to population growth. The crises in Egypt, Yemen, Libya, and Syria have resulted in a reduction in life expectancy; life expectancy in Syria would have been 5 years higher than that recorded for females and 6 years higher for males had the crisis not occurred. INTERPRETATION: Our study shows that the eastern Mediterranean region is going through a crucial health phase. The Arab uprisings and the wars that followed, coupled with ageing and population growth, will have a major impact on the region's health and resources. The region has historically seen improvements in life expectancy and other health indicators, even under stress. However, the current situation will cause deteriorating health conditions for many countries and for many years and will have an impact on the region and the rest of the world. Based on our findings, we call for increased investment in health in the region in addition to reducing the conflicts. FUNDING: Bill & Melinda Gates Foundation.

Vitamin D deficiency and possible link with Bony pain and onset of Osteoporosis.

OBJECTIVE: To explore if vitamin D deficiency had a direct correlation with bone pain or if it contributes in any way to the onset of osteoporosis. METHODS: The cross sectional Study was conducted from February to May 2014, presented at Liaquat National Hospital, Karachi, and comprised Orthopaedic outpatients. Who were questioned, examined and counselled, before a questionnaire was filled that included questions about their complaint, and its severity. Several blood test reports were incorporated including serum Vitamin D, to evaluate kidney and liver functions. Dual energy X-ray absorptiometry scans of the lumber and hip regions were also included. Data was collected manually and analysed using SPSS version 16. RESULTS: The mean age of the 65 subjects, was 52.±16 SD years, and 54(83.1%) were overweight with body mass index of 29.7kg/m2. Besides, 61(93.8%) had a positive association of low vitamin D levels as a causative agent for bone pain with mean pain severity index 6±1 SD. On the other hand 25(38.5%) were diagnosed as cases of osteoporosis, and, of them, 21(84%) had low vitamin D levels. CONCLUSIONS: Deficiency of vitamin D was directly related to the intensity of bone pain. Some patients had vitamin D deficiency along with osteoporosis, which may have aggravating effect in this context.

Functional outcome of ACL reconstruction using patellar bone tendon bone graft.

PURPOSE: To evaluate the mid-term functional outcome using Lysholm score of anterior cruciate ligamentreconstruction using bone patella-tendon bone graft. METHODS: The retrospective study of prospectively collected data was conducted at Liaquat National Hospital, Karachi, from June 2010to June 2013, and comprised patients with complete anterior cruciate ligamenttear who were treated with diagnostic arthroscopy and open reconstruction using bone patella-tendon bone graft. All patients were operated under tourniquet control and knee immobiliser was applied. Straight leg raise procedure was started on 2nd postoperative day. One year after surgery, functional outcome was assessed using Lysholm score. RESULTS: All the 36(100%) patients in the study were males. Four (11%) patients were lost to follow-up and were excluded, while 32(89%) completed the study. Right knee was involved in 16(50%) patients while left knee was involved in 16(50%) patients. Overall, 31(97%) patients had history of contact sports injury. The average age of patients was 28.25±8.32 years. All patients were operated at an average of 17.5±10.3 weeks. The ligament tear was associated with medial meniscal tear in 16(50%) patients, while lateral meniscal tear was noted in 10(31.25%). The mean Lysholm score was 83.06±4.17at 1 year (fair to good outcome). The average range of motion 1 year after surgery was 127.5±11.25. Loss of extension <3o was noted in 20(62.5%) patients, while >3o was noted in 12(37.5%). The average loss of extension was 3.5±2.3 degrees. Two (6.25%) patients developed superficial infection which subsided with oral antibiotics. Anterior knee pain was reported by 8(25%) patients. CONCLUSIONS: Patellar bone tendon bone graft was a reliable method for reconstruction of anterior cruciate ligament.

Common presentation uncommon diagnosis primary omental torsion.

Primary omental torsion is a rare cause of acute abdomen and mimics common acute abdominal condition like appendicitis. Torsion of the greater omentum may be primary or secondary. Here we present 2 cases admitted through emergency with the pain in right iliac fossa with this unusual diagnosis.