MyMedR

Displaying publications 1 - 20 of 62 in total

Abstract:

Sort:

Coccidial infections of goats in Selangor, peninsular Malaysia

Jalila A, Dorny P, Sani R, Salim NB, Vercruysse J

Vet Parasitol, 1998 Jan 31;74(2-4):165-72.
PMID: 9561704

Coccidial infections were studied in goats in the state of Selangor (peninsular Malaysia) during a 12-month period. The study included 10 smallholder farms on which kids were monitored for faecal oocyst counts from birth until 1-year old. Eimeria oocysts were found in 725 (89%) of 815 faecal samples examined. Nine species of Eimeria were identified. The most prevalent were E. arloingi, found in 71% of the samples, E. ninakohlyakimovae (67%), E. christenseni (63%) and E. alijevi (61%). The other species found were, E. hirci, E. jolchijevi, E. caprovina, E. caprina and E. pallida, present in 34, 22, 12, 9 and 4% of the samples, respectively. Oocyst counts were significantly higher in animals of less than 4-months old (P < 0.05). High oocyst counts were mainly caused by non-pathogenic species. Poor hygienic conditions were found to be associated with a higher intensity of coccidial infections. Mortality rates in kids could not be related to the intensity of coccidial infections.
Investigation and Optimization of Hydrogel Microneedles for Transdermal Delivery of Caffeine

Chandran R, Mohd Tohit ER, Stanslas J, Salim N, Tuan Mahmood TM

Tissue Eng Part C Methods, 2022 10;28(10):545-556.
PMID: 35485888 DOI: 10.1089/ten.TEC.2022.0045

Caffeine is therapeutically effective for treating apnea, cellulite formation, and pain management. It also exhibits neuroprotective and antioxidant activities in different models of Parkinson's disease and Alzheimer's disease. However, caffeine administration in a minimally invasive and sustainable manner through the transdermal route is challenging owing to its hydrophilic nature. Therefore, this study demonstrated a transdermal delivery approach for caffeine by utilizing hydrogel microneedle (MN) as a permeation enhancer. The influence of formulation parameters such as molecular weight (MW) of PMVE/MA (polymethyl vinyl ether/maleic anhydride) copolymer and sodium bicarbonate (NaHCO3) concentration on the swelling kinetics and mechanical integrity of the hydrogel MNs was investigated. In addition, the effect of different MN application methods and needle densities of hydrogel MN on the skin insertion efficiency and penetration depth was also evaluated. The swelling degree at equilibrium percentage (% Seq) recorded for hydrogels fabricated with Gantrez S-97 (MW = 1,500,000 Da) was significantly higher than formulation with Gantrez AN-139 (MW = 1,080,000 Da). Increasing the concentration of NaHCO3 also significantly increased the % Seq. Moreover, a 100% penetration was recorded for both the applicator and combination of applicator and thumb pressure compared with only 11% for thumb pressure alone. The average diameter of micropores created by the applicator method was 62.94 μm, which was significantly lower than the combination of both applicator and thumb pressure MN application (100.53 μm). Based on histological imaging, the penetration depth of hydrogel MN increased as the MN density per array decreased. The hydrogel MN with the optimized formulation and skin insertion parameters was tested for caffeine delivery in an in vitro Franz diffusion cell setup. Approximately 2.9 mg of caffeine was delivered within 24 h, and the drug release profile was best fitted to the Korsmeyer-Peppas model, displaying Super Case II kinetics. In conclusion, a combination of thumb and impact application methods and reduced needle density improved the skin penetration efficiency of hydrogel MNs. The results also show that hydrogel MNs fabricated from 3% w/w NaHCO3 and high MW of copolymer exhibit optimum physical and swelling properties for enhanced transdermal delivery.
Fulltext A new graph-based molecular descriptor using the canonical representation of the molecule

Hentabli H, Saeed F, Abdo A, Salim N

ScientificWorldJournal, 2014;2014:286974.
PMID: 25140330 DOI: 10.1155/2014/286974

Molecular similarity is a pervasive concept in drug design. The basic idea underlying molecular similarity is the similar property principle, which states that structurally similar molecules will exhibit similar physicochemical and biological properties. In this paper, a new graph-based molecular descriptor (GBMD) is introduced. The GBMD is a new method of obtaining a rough description of 2D molecular structure in textual form based on the canonical representations of the molecule outline shape and it allows rigorous structure specification using small and natural grammars. Simulated virtual screening experiments with the MDDR database show clearly the superiority of the graph-based descriptor compared to many standard descriptors (ALOGP, MACCS, EPFP4, CDKFP, PCFP, and SMILE) using the Tanimoto coefficient (TAN) and the basic local alignment search tool (BLAST) when searches were carried.
Fulltext Intelligent bar chart plagiarism detection in documents

Al-Dabbagh MM, Salim N, Rehman A, Alkawaz MH, Saba T, Al-Rodhaan M, et al.

ScientificWorldJournal, 2014;2014:612787.
PMID: 25309952 DOI: 10.1155/2014/612787

This paper presents a novel features mining approach from documents that could not be mined via optical character recognition (OCR). By identifying the intimate relationship between the text and graphical components, the proposed technique pulls out the Start, End, and Exact values for each bar. Furthermore, the word 2-gram and Euclidean distance methods are used to accurately detect and determine plagiarism in bar charts.
Fulltext Ligand-based virtual screening using Bayesian inference network and reweighted fragments

Ahmed A, Abdo A, Salim N

ScientificWorldJournal, 2012;2012:410914.
PMID: 22623895 DOI: 10.1100/2012/410914

Many of the similarity-based virtual screening approaches assume that molecular fragments that are not related to the biological activity carry the same weight as the important ones. This was the reason that led to the use of Bayesian networks as an alternative to existing tools for similarity-based virtual screening. In our recent work, the retrieval performance of the Bayesian inference network (BIN) was observed to improve significantly when molecular fragments were reweighted using the relevance feedback information. In this paper, a set of active reference structures were used to reweight the fragments in the reference structure. In this approach, higher weights were assigned to those fragments that occur more frequently in the set of active reference structures while others were penalized. Simulated virtual screening experiments with MDL Drug Data Report datasets showed that the proposed approach significantly improved the retrieval effectiveness of ligand-based virtual screening, especially when the active molecules being sought had a high degree of structural heterogeneity.
High-intensity interval training induced PGC-1∝ and AdipoR1 gene expressions and improved insulin sensitivity in obese individuals

Asilah Za'don NH, Amirul Farhana MK, Farhanim I, Sharifah Izwan TO, Appukutty M, Salim N, et al.

Med J Malaysia, 2019 12;74(6):461-467.
PMID: 31929469

INTRODUCTION: High-intensity interval training (HIIT) has been found to improve cardiometabolic health outcome as compared to moderate-intensity continuous exercise. However, there is still limited data on the benefits of HIIT on the expression of regulatory proteins that are linked to skeletal muscle metabolism and insulin sensitivity in obese adults. This study investigated the effects of HIIT intervention on expressions of peroxisome proliferatoractivated receptor-γ coactivator 1-∝ (PGC-1∝) and adiponectin receptor-1 (AdipoR1), insulin sensitivity (HOMAIR index), and body composition in overweight/obese individuals.
METHODS: Fifty overweight/obese individuals aged 22-29 years were assigned to either no-exercise control (n=25) or HIIT (n=25) group. The HIIT group underwent a 12-week intervention, three days/week, with intensity of 65-80% of age-based maximum heart rate. Anthropometric measurements, homeostatic model of insulin resistance (HOMA-IR) and gene expression analysis were conducted at baseline and post intervention.
RESULTS: Significant time-by-group interactions (p<0.001) were found for body weight, BMI, waist circumference and body fat percentage. The HIIT group had lower body weight (2.3%, p<0.001), BMI (2.7%, p<0.001), waist circumference (2.4%, p<0.001) and body fat percentage (4.3%, p<0.001) post intervention. Compared to baseline, expressions of PGC-1∝ and AdipoR1 were increased by approximately three-fold (p=0.019) and two-fold (p=0.003) respectively, along with improved insulin sensitivity (33%, p=0.019) in the HIIT group.
CONCLUSION: Findings suggest that HIIT possibly improved insulin sensitivity through modulation of PGC-1∝ and AdipoR1. This study also showed that improved metabolic responses can occur despite modest reduction in body weight in overweight/obese individuals undergoing HIIT intervention.
Ocular co-morbidities in patients with atopic dermatitis - a cross-sectional study from a tertiary referral hospital, Malaysia

Gan TS, Juares Rizal A, Salim NL, Lau LL, Voo SYM

Med J Malaysia, 2022 Jan;77(1):6-11.
PMID: 35086988

INTRODUCTION: Atopic dermatitis (AD) is a chronic relapsing pruritic inflammatory skin disease that commonly occurs among children as well as adults. AD patients were reported to have high prevalence of ocular manifestations, which may be due to the disease nature or drug complications. This study aimed to determine the prevalence of ocular manifestations in patients with AD.
MATERIALS AND METHODS: Eighty patients who fulfilled the UK Working Party's Diagnostic Criteria for Atopic Dermatitis were included in the cross-sectional study. A standardized case report form was formulated to collect the demographic data and disease profile of the participants. AD severity was evaluated using the EASI and SCORAD score. All patients underwent a complete ophthalmological evaluation.
RESULTS: The prevalence of ocular manifestations among the patients with AD was 48.8%. Fifty-four (67.5%) patients had facial dermatitis and 37 (46.2%) showed periorbital signs. The mean AD disease duration was 10.99 ± 11.20 years. Majority of the patients had mild to moderate AD. The most frequent ocular manifestation was allergic conjunctivitis (18.75%) followed by cataract (8.75%) and ocular hypertension (8.75%). Among the patients with ocular manifestations, 27 (69.2%) patients regularly applied topical corticosteroids on the face. The use of systemic corticosteroids was seen in 19 (42.2%) patients. Prolonged AD duration was significantly associated with the development of ocular manifestations.
CONCLUSIONS: Nearly half of the patients with AD were complicated with ocular disease regardless of the AD severity, facial dermatitis and presence of periorbital signs. Long disease duration is associated with ocular manifestations, especially steroid related complications.
Fulltext Alteration of cell cytoskeleton and functions of cell recovery of normal human osteoblast cells caused by factors associated with real space flight

Kapitonova MY, Salim N, Othman S, Muhd Kamauzaman TM, Ali AM, Nawawi HM, et al.

Malays J Pathol, 2013 Dec;35(2):153-63.
PMID: 24362479 MyJurnal

Experiments involving short-term space flight have shown an adverse effect on the physiology, morphology and functions of cells investigated. The causes for this effect on cells are: microgravity, temperature fluctuations, mechanical stress, hypergravity, nutrient restriction and others. However, the extent to which these adverse effects can be repaired by short-term space flown cells when recultured in conditions of normal gravity remains unclear. Therefore this study aimed to investigate the effect of short-term spaceflight on cytoskeleton distribution and recovery of cell functions of normal human osteoblast cells. The ultrastructure was evaluated using ESEM. Fluorescent staining was done using Hoechst, Mito Tracker CMXRos and Tubulin Tracker Green for cytoskeleton. Gene expression of cell functions was quantified using qPCR. As a result, recovered cells did not show any apoptotic markers when compared with control. Tubulin volume density (p<0.001) was decreased significantly when compared to control, while mitochondria volume density was insignificantly elevated. Gene expression for IL-6 (p<0.05) and sVCAM-1 (p<0.001) was significantly decreased while alkaline phosphatase (p<0.001), osteocalcin and sICAM (p<0.05) were significantly increased in the recovered cells compared to the control ones. The changes in gene and protein expression of collagen 1A, osteonectin, osteoprotegerin and beta-actin, caused by short-term spaceflight, were statistically not significant. These data indicate that short term space flight causes morphological changes in osteoblast cells which are consistent with hypertrophy, reduced cell differentiation and increased release of monocyte attracting proteins. The long-term effect of these changes on bone density and remodeling requires more detailed studies.
Outcome of corticosteroid injection versus physiotherapy in the treatment of mild trigger fingers

Salim N, Abdullah S, Sapuan J, Haflah NH

J Hand Surg Eur Vol, 2012 Jan;37(1):27-34.
PMID: 21816888 DOI: 10.1177/1753193411415343

We compared the effectiveness of physiotherapy and corticosteroid injection treatment in the management of mild trigger fingers. Mild trigger fingers are those with mild crepitus, uneven finger movements and actively correctable triggering. This is a single-centred, prospective, block randomized study with 74 patients; 39 patients for steroid injection and 35 patients for physiotherapy. The study duration was from Jun 2009 until August 2010. Evaluation was done at 6 weeks, 3 months and 6 months post-treatment. At 3 months, the success rate (absence of pain and triggering) for those receiving steroid injection was 97.4% and physiotherapy 68.6%. The group receiving steroid injection also had lower pain score, higher rate of satisfaction, stronger grip strength and early recovery to near normal function (findings were all significant, p
The goat as a model for studies of pneumonic pasteurellosis caused by Pasteurella multocida

Zamri-Saad M, Effendy WM, Maswati MA, Salim N, Sheikh-Omar AR

Br. Vet. J., 1996 Jul;152(4):453-8.
PMID: 8791853

A model of pneumonic pasteurellosis has been established in goats using Pasteurella multocida harvested from pneumonic lungs of goats (types A and D), rabbits (type A) and sheep (type D). The resultant infections were acute, subacute or chronic. The gross and histological lesions of the subacute and chronic infections were typical of pneumonic pasteurellosis. P. multocida type D produced significantly (P < 0.01) more severe lesions when compared with other isolates. There were strong correlations between the clinical signs and the severity of lesions.
Shifting Paradigms and Arising Concerns in Severe Hemophilia A Treatment

Chandran R, Tohit ERM, Stanslas J, Salim N, Mahmood TMT, Rajagopal M

Semin Thromb Hemost, 2024 Jan 15.
PMID: 38224699 DOI: 10.1055/s-0043-1778103

The management of hemophilia A has undergone a remarkable revolution, in line with technological advancement. In the recent past, the primary concern associated with Factor VIII (FVIII) concentrates was the risk of infections, which is now almost resolved by advanced blood screening and viral inactivation methods. Improving patients' compliance with prophylaxis has become a key focus, as it can lead to improved health outcomes and reduced health care costs in the long term. Recent bioengineering research is directed toward prolonging the recombinant FVIII (rFVIII) coagulant activity and synthesising higher FVIII yields. As an outcome, B-domain deleted, polyethylene glycolated, single-chain, Fc-fused rFVIII, and rFVIIIFc-von Willebrand Factor-XTEN are available for patients. Moreover, emicizumab, a bispecific antibody, is commercially available, whereas fitusiran and tissue factor pathway inhibitor are in clinical trial stages as alternative strategies for patients with inhibitors. With these advancements, noninfectious complications, such as inhibitor development, allergic reactions, and thrombosis, are emerging concerns requiring careful management. In addition, the recent approval of gene therapy is a major milestone toward a permanent cure for hemophilia A. The vast array of treatment options at our disposal today empowers patients and providers alike, to tailor therapeutic regimens to the unique needs of each individual. Despite significant progress in modern treatment options, these highly effective therapies are markedly more expensive than conventional replacement therapy, limiting their access for patients in developing countries.
Fulltext Lipid-based nanoparticles for psoriasis treatment: a review on conventional treatments, recent works, and future prospects

Mohd Nordin UU, Ahmad N, Salim N, Mohd Yusof NS

RSC Adv, 2021 Aug 23;11(46):29080-29101.
PMID: 35478537 DOI: 10.1039/d1ra06087b

Psoriasis is a lingering inflammatory skin disease that attacks the immune system. The abnormal interactions between T cells, immune cells, and inflammatory cytokines causing the epidermal thickening. International guidelines have recommended topical treatments for mild to moderate psoriasis whilst systemic and phototherapy treatments for moderate to severe psoriasis. However, current therapeutic approaches have a wider extent to treat moderate to severe type of psoriasis especially since the emergence of diverse biologic agents. In the meantime, topical delivery of conventional treatments has prompted many unsatisfactory effects to penetrate through the skin (stratum corneum). By understanding the physiology of stratum corneum barrier functions, scientists have developed different types of lipid-based nanoparticles like solid lipid nanoparticles, nanostructured lipid carriers, nanovesicles, and nanoemulsions. These novel drug delivery systems help the poorly solubilised active pharmaceutical ingredient reaches the targeted site seamlessly because of the bioavailability feature of the nanosized molecules. Lipid-based nanoparticles for psoriasis treatments create a paradigm for topical drug delivery due to their lipids' amphiphilic feature to efficiently encapsulate both lipophilic and hydrophilic drugs. This review highlights different types of lipid-based nanoparticles and their recent works of nano formulated psoriasis treatments. The encapsulation of psoriasis drugs through lipid nanocarriers unfold numerous research opportunities in pharmaceutical applications but also draw challenges for the future development of nano drugs.
Extraction, anti-tyrosinase, and antioxidant activities of the collagen hydrolysate derived from Rhopilema hispidum

Ab Aziz NA, Salim N, Zarei M, Saari N, Yusoff FM

Prep Biochem Biotechnol, 2021;51(1):44-53.
PMID: 32701046 DOI: 10.1080/10826068.2020.1789991

The study was conducted to determine anti-tyrosinase and antioxidant activities of the extracted collagen hydrolysate (CH) derived from Malaysian jellyfish, Rhopilema hispidum. Collagen was extracted using 1:1 (w:v) 0.1 M NaOH solution at temperature 25 °C for 48 hr followed by treatment of 1:2 (w:v) distilled water for another 24 hr and freeze-dried. The extracted collagen was hydrolyzed using papain at optimum temperature, pH and enzyme/substrate ratio [E/S] of 60 °C, 7.0 and 1:50, respectively. CH was found to exhibit tyrosinase inhibitory activity, DPPH radical scavenging and metal ion-chelating assays up to 64, 28, and 83%, respectively, after 8 hr of hydrolysis process. The molecular weight of CH was found <10 kDa consisting of mainly Gly (19.219%), Glu (10.428%), and Arg (8.848%). The UV-visible spectrum analysis showed a major and minor peak at 218 and 276 nm, accordingly. The FTIR spectroscopy confirmed the amide groups in CH. The SEM images demonstrated spongy and porous structure of CH. In the cytotoxicity study, CH has no cytotoxicity against mouse embryonic 3T3 fibroblast cell line with IC50 value >500 µg/ml. Results revealed that the CH generated from this study has a potential to be developed as active ingredient in cosmeceutical application.
Fulltext The Power of Implicit Social Relation in Rating Prediction of Social Recommender Systems

Reafee W, Salim N, Khan A

PLoS One, 2016;11(5):e0154848.
PMID: 27152663 DOI: 10.1371/journal.pone.0154848

The explosive growth of social networks in recent times has presented a powerful source of information to be utilized as an extra source for assisting in the social recommendation problems. The social recommendation methods that are based on probabilistic matrix factorization improved the recommendation accuracy and partly solved the cold-start and data sparsity problems. However, these methods only exploited the explicit social relations and almost completely ignored the implicit social relations. In this article, we firstly propose an algorithm to extract the implicit relation in the undirected graphs of social networks by exploiting the link prediction techniques. Furthermore, we propose a new probabilistic matrix factorization method to alleviate the data sparsity problem through incorporating explicit friendship and implicit friendship. We evaluate our proposed approach on two real datasets, Last.Fm and Douban. The experimental results show that our method performs much better than the state-of-the-art approaches, which indicates the importance of incorporating implicit social relations in the recommendation process to address the poor prediction accuracy.
Fulltext Quality dimensions features for identifying high-quality user replies in text forum threads using classification methods

Osman A, Salim N, Saeed F

PLoS One, 2019;14(5):e0215516.
PMID: 31091242 DOI: 10.1371/journal.pone.0215516

The Text Forum Threads (TFThs) contain a large amount of Initial-Posts Replies pairs (IPR pairs) which are related to information exchange and discussion amongst the forum users with similar interests. Generally, some user replies in the discussion thread are off-topic and irrelevant. Hence, the content is of different qualities. It is important to identify the quality of the IPR pairs in a discussion thread in order to extract relevant information and helpful replies because a higher frequency of irrelevant replies in the thread could take the discussion in a different direction and the genuine users would lose interest in this discussion thread. In this study, the authors have presented an approach for identifying the high-quality user replies to the Initial-Post and use some quality dimensions features for their extraction. Moreover, crowdsourcing platforms were used for judging the quality of the replies and classified them into high-quality, low-quality or non-quality replies to the Initial-Posts. Then, the high-quality IPR pairs were extracted and identified based on their quality, and they were ranked using three classifiers i.e., Support Vector Machine, Naïve Bayes, and the Decision Trees according to their quality dimensions of relevancy, author activeness, timeliness, ease-of-understanding, politeness, and amount-of-data. In conclusion, the experimental results for the TFThs showed that the proposed approach could improve the extraction of the quality replies and identify the quality features that can be used for the Text Forum Thread Summarization.
Fulltext Size-Controlled Preparation of Docetaxel- and Curcumin-Loaded Nanoemulsions for Potential Pulmonary Delivery

Asmawi AA, Salim N, Abdulmalek E, Abdul Rahman MB

Pharmaceutics, 2023 Feb 15;15(2).
PMID: 36839974 DOI: 10.3390/pharmaceutics15020652

Lung cancer is one of the deadliest pulmonary diseases in the world. Although docetaxel (DTX) has exhibited superior efficacy in lung cancer treatment, it has demonstrated numerous adverse effects and poor bioavailability. The natural product extract, curcumin (CCM), has reportedly reduced toxicity and synergistically improved DTX bioavailability. Nonetheless, the hydrophobic nature of DTX and CCM limits their clinical use. Nanoemulsion pulmonary delivery of DTX and CCM has demonstrated potential as a drug carrier to alleviate these drawbacks. The controlled preparation of inhalable DTX- and CCM-loaded nanoemulsions within the 100 to 200 nm range was explored in this study. A response surface methodology (RSM) based on a central composite design (CCD) was utilized to fabricate the desired size of the nanoemulsion under optimized conditions. Different process parameters were employed to control the size of the nanoemulsions procured through a high-energy emulsification technique. The size of the resultant nanoemulsions decreased with increasing energy input. The actual response according to the targeted sizes for DTX- and CCM-loaded nanoemulsion models exhibited excellent agreement with the predicted value at below 5% residual standard error under optimized conditions. The nanoemulsion of 100 nm particle size demonstrated better membrane permeability than their larger counterparts. Moreover, the formulations documented favorable physicochemical and aerodynamic pulmonary delivery properties and reduced toxicity in human lung fibroblast (MRC-5) cells. Hence, this tunable size of nanoemulsions could be a suitable alternative drug delivery for pulmonary diseases with increased local lung concentration.
Fulltext Nanoemulsions: A Review on the Conceptualization of Treatment for Psoriasis Using a 'Green' Surfactant with Low-Energy Emulsification Method

Dinshaw IJ, Ahmad N, Salim N, Leo BF

Pharmaceutics, 2021 Jul 06;13(7).
PMID: 34371716 DOI: 10.3390/pharmaceutics13071024

Psoriasis is a skin disease that is not lethal and does not spread through bodily contact. However, this seemingly harmless condition can lead to a loss of confidence and social stigmatization due to a persons' flawed appearance. The conventional methods of psoriasis treatment include taking in systemic drugs to inhibit immunoresponses within the body or applying topical drugs onto the surface of the skin to inhibit cell proliferation. Topical methods are favored as they pose lesser side effects compared to the systemic methods. However, the side effects from systemic drugs and low bioavailability of topical drugs are the limitations to the treatment. The use of nanotechnology in this field has enhanced drug loading capacity and reduced dosage size. In this review, biosurfactants were introduced as a 'greener' alternative to their synthetic counterparts. Glycolipid biosurfactants are specifically suited for anti-psoriatic application due to their characteristic skin-enhancing qualities. The selection of a suitable oil phase can also contribute to the anti-psoriatic effect as some oils have skin-healing properties. The review covers the pathogenic pathway of psoriasis, conventional treatments, and prospective ingredients to be used as components in the nanoemulsion formulation. Furthermore, an insight into the state-of-the-art methods used in formulating nanoemulsions and their progression to low-energy methods are also elaborated in detail.
Fulltext Aspect extraction on user textual reviews using multi-channel convolutional neural network

Da'u A, Salim N

PeerJ Comput Sci, 2019;5:e191.
PMID: 33816844 DOI: 10.7717/peerj-cs.191

Aspect extraction is a subtask of sentiment analysis that deals with identifying opinion targets in an opinionated text. Existing approaches to aspect extraction typically rely on using handcrafted features, linear and integrated network architectures. Although these methods can achieve good performances, they are time-consuming and often very complicated. In real-life systems, a simple model with competitive results is generally more effective and preferable over complicated models. In this paper, we present a multichannel convolutional neural network for aspect extraction. The model consists of a deep convolutional neural network with two input channels: a word embedding channel which aims to encode semantic information of the words and a part of speech (POS) tag embedding channel to facilitate the sequential tagging process. To get the vector representation of words, we initialized the word embedding channel and the POS channel using pretrained word2vec and one-hot-vector of POS tags, respectively. Both the word embedding and the POS embedding vectors were fed into the convolutional layer and concatenated to a one-dimensional vector, which is finally pooled and processed using a Softmax function for sequence labeling. We finally conducted a series of experiments using four different datasets. The results indicated better performance compared to the baseline models.
MGACA-Net: a novel deep learning based multi-scale guided attention and context aggregation for localization of knee anterior cruciate ligament tears region in MRI images

Awan MJ, Mohd Rahim MS, Salim N, Nobanee H, Asif AA, Attiq MO

PeerJ Comput Sci, 2023;9:e1483.
PMID: 37547408 DOI: 10.7717/peerj-cs.1483

Anterior cruciate ligament (ACL) tears are a common knee injury that can have serious consequences and require medical intervention. Magnetic resonance imaging (MRI) is the preferred method for ACL tear diagnosis. However, manual segmentation of the ACL in MRI images is prone to human error and can be time-consuming. This study presents a new approach that uses deep learning technique for localizing the ACL tear region in MRI images. The proposed multi-scale guided attention-based context aggregation (MGACA) method applies attention mechanisms at different scales within the DeepLabv3+ architecture to aggregate context information and achieve enhanced localization results. The model was trained and evaluated on a dataset of 917 knee MRI images, resulting in 15265 slices, obtaining state-of-the-art results with accuracy scores of 98.63%, intersection over union (IOU) scores of 95.39%, Dice coefficient scores (DCS) of 97.64%, recall scores of 97.5%, precision scores of 98.21%, and F1 Scores of 97.86% on validation set data. Moreover, our method performed well in terms of loss values, with binary cross entropy combined with Dice loss (BCE_Dice_loss) and Dice_loss values of 0.0564 and 0.0236, respectively, on the validation set. The findings suggest that MGACA provides an accurate and efficient solution for automating the localization of ACL in knee MRI images, surpassing other state-of-the-art models in terms of accuracy and loss values. However, in order to improve robustness of the approach and assess its performance on larger data sets, further research is needed.
Fulltext A Quantum-Based Similarity Method in Virtual Screening

Al-Dabbagh MM, Salim N, Himmat M, Ahmed A, Saeed F

Molecules, 2015;20(10):18107-27.
PMID: 26445039 DOI: 10.3390/molecules201018107

One of the most widely-used techniques for ligand-based virtual screening is similarity searching. This study adopted the concepts of quantum mechanics to present as state-of-the-art similarity method of molecules inspired from quantum theory. The representation of molecular compounds in mathematical quantum space plays a vital role in the development of quantum-based similarity approach. One of the key concepts of quantum theory is the use of complex numbers. Hence, this study proposed three various techniques to embed and to re-represent the molecular compounds to correspond with complex numbers format. The quantum-based similarity method that developed in this study depending on complex pure Hilbert space of molecules called Standard Quantum-Based (SQB). The recall of retrieved active molecules were at top 1% and top 5%, and significant test is used to evaluate our proposed methods. The MDL drug data report (MDDR), maximum unbiased validation (MUV) and Directory of Useful Decoys (DUD) data sets were used for experiments and were represented by 2D fingerprints. Simulated virtual screening experiment show that the effectiveness of SQB method was significantly increased due to the role of representational power of molecular compounds in complex numbers forms compared to Tanimoto benchmark similarity measure.

Filters

Please provide feedback to Administrator (afdal@afpm.org.my)

External Links