Exploring barriers to access to care following the 2021 socio-political changes in Afghanistan: a qualitative study.

BACKGROUND: Following the change of government in August 2021, the social and economic landscape of Afghanistan deteriorated into an economic and humanitarian crisis. Afghans continue to struggle to access basic healthcare services, making Universal Health Coverage (UHC) in the country a major challenge. The aim of this study was to perform a qualitative investigation into the main access to care challenges in Afghanistan and whether these challenges have been influenced by the recent socio-political developments, by examining the perspectives of health professionals and hospital directors working in the country. METHODS: Health professionals working in facilities run by an international non-government organisation, which has maintained continuous operations since 1999 and has become a key health reference point for the population, alongside the public health system, and hospital directors working in government hospitals were recruited to participate in an in-depth qualitative study using semi-structured interviews. RESULTS: A total of 43 participants from ten provinces were interviewed in this study. Four issues were identified as critical barriers to achieving UHC in Afghanistan: (1) the lack of quality human resources; (2) the suboptimal management of chronic diseases and trauma; (3) the inaccessibility of necessary health services due to financial hardship; (4) the unequal accessibility of care for different demographic groups. CONCLUSIONS: Health professionals and hospital directors shed light on weaknesses in the Afghan health system highlighting chronic issues and issues that have deteriorated as a result of the 2021 socio-political changes. In order to improve access to care, future healthcare system reforms should consider the perspectives of Afghan professionals working in the country, who are in close contact with Afghan patients and communities.

Access to care in Afghanistan after august 2021: a cross-sectional study exploring Afghans' perspectives in 10 provinces.

BACKGROUND: The Taliban takeover in August 2021 ended a decades-long conflict in Afghanistan. Yet, along with improved security, there have been collateral changes, such as the exacerbation of the economic crisis and brain drain. Although these changes have altered the lives of Afghans in many ways, it is unclear whether they have affected access to care. This study aimed to analyse Afghans' access to care and how this access has changed after August 2021. METHODS: The study relied on the collaboration with the non-governmental organisation EMERGENCY, running a network of three hospitals and 41 First Aid Posts in 10 Afghan provinces. A 67-item questionnaire about access to care changes after August 2021 was developed and disseminated at EMERGENCY facilities. Ordinal logistic regression was used to evaluate whether access to care changes were associated with participants' characteristics. RESULTS: In total, 1807 valid responses were returned. Most respondents (54.34%) reported improved security when visiting healthcare facilities, while the ability to reach facilities has remained stable for the majority of them (50.28%). Care is less affordable for the majority of respondents (45.82%). Female respondents, those who are unmarried and not engaged, and patients in the Panjshir province were less likely to perceive improvements in access to care. CONCLUSIONS: Findings outline which dimensions of access to care need resource allocation. The inability to pay for care is the most relevant barrier to access care after August 2021 and must therefore be prioritised. Women and people from the Panjshir province may require ad hoc interventions to improve their access to care.

DPI_CDF: druggable protein identifier using cascade deep forest.

BACKGROUND: Drug targets in living beings perform pivotal roles in the discovery of potential drugs. Conventional wet-lab characterization of drug targets is although accurate but generally expensive, slow, and resource intensive. Therefore, computational methods are highly desirable as an alternative to expedite the large-scale identification of druggable proteins (DPs); however, the existing in silico predictor's performance is still not satisfactory. METHODS: In this study, we developed a novel deep learning-based model DPI_CDF for predicting DPs based on protein sequence only. DPI_CDF utilizes evolutionary-based (i.e., histograms of oriented gradients for position-specific scoring matrix), physiochemical-based (i.e., component protein sequence representation), and compositional-based (i.e., normalized qualitative characteristic) properties of protein sequence to generate features. Then a hierarchical deep forest model fuses these three encoding schemes to build the proposed model DPI_CDF. RESULTS: The empirical outcomes on 10-fold cross-validation demonstrate that the proposed model achieved 99.13 % accuracy and 0.982 of Matthew's-correlation-coefficient (MCC) on the training dataset. The generalization power of the trained model is further examined on an independent dataset and achieved 95.01% of maximum accuracy and 0.900 MCC. When compared to current state-of-the-art methods, DPI_CDF improves in terms of accuracy by 4.27% and 4.31% on training and testing datasets, respectively. We believe, DPI_CDF will support the research community to identify druggable proteins and escalate the drug discovery process. AVAILABILITY: The benchmark datasets and source codes are available in GitHub: http://github.com/Muhammad-Arif-NUST/DPI_CDF .

ML-Based Detection of DDoS Attacks Using Evolutionary Algorithms Optimization.

The escalating reliance of modern society on information and communication technology has rendered it vulnerable to an array of cyber-attacks, with distributed denial-of-service (DDoS) attacks emerging as one of the most prevalent threats. This paper delves into the intricacies of DDoS attacks, which exploit compromised machines numbering in the thousands to disrupt data services and online commercial platforms, resulting in significant downtime and financial losses. Recognizing the gravity of this issue, various detection techniques have been explored, yet the quantity and prior detection of DDoS attacks has seen a decline in recent methods. This research introduces an innovative approach by integrating evolutionary optimization algorithms and machine learning techniques. Specifically, the study proposes XGB-GA Optimization, RF-GA Optimization, and SVM-GA Optimization methods, employing Evolutionary Algorithms (EAs) Optimization with Tree-based Pipelines Optimization Tool (TPOT)-Genetic Programming. Datasets pertaining to DDoS attacks were utilized to train machine learning models based on XGB, RF, and SVM algorithms, and 10-fold cross-validation was employed. The models were further optimized using EAs, achieving remarkable accuracy scores: 99.99% with the XGB-GA method, 99.50% with RF-GA, and 99.99% with SVM-GA. Furthermore, the study employed TPOT to identify the optimal algorithm for constructing a machine learning model, with the genetic algorithm pinpointing XGB-GA as the most effective choice. This research significantly advances the field of DDoS attack detection by presenting a robust and accurate methodology, thereby enhancing the cybersecurity landscape and fortifying digital infrastructures against these pervasive threats.

Symptomatic post COVID patients have impaired alveolar capillary membrane function and high VE/VCO2.

BACKGROUND: Post COVID-19 syndrome is characterized by several cardiorespiratory symptoms but the origin of patients' reported symptomatology is still unclear. METHODS: Consecutive post COVID-19 patients were included. Patients underwent full clinical evaluation, symptoms dedicated questionnaires, blood tests, echocardiography, thoracic computer tomography (CT), spirometry including alveolar capillary membrane diffusion (DM) and capillary volume (Vcap) assessment by combined carbon dioxide and nitric oxide lung diffusion (DLCO/DLNO) and cardiopulmonary exercise test. We measured surfactant derive protein B (immature form) as blood marker of alveolar cell function. RESULTS: We evaluated 204 consecutive post COVID-19 patients (56.5 ± 14.5 years, 89 females) 171 ± 85 days after the end of acute COVID-19 infection. We measured: forced expiratory volume (FEV1) 99 ± 17%pred, FVC 99 ± 17%pred, DLCO 82 ± 19%, DM 47.6 ± 14.8 mL/min/mmHg, Vcap 59 ± 17 mL, residual parenchymal damage at CT 7.2 ± 3.2% of lung tissue, peakVO2 84 ± 18%pred, VE/VCO2 slope 112 [102-123]%pred. Major reported symptoms were: dyspnea 45% of cases, tiredness 60% and fatigability 77%. Low FEV1, Vcap and high VE/VCO2 slope were associated with persistence of dyspnea. Tiredness was associated with high VE/VCO2 slope and low PeakVO2 and FEV1 while fatigability with high VE/VCO2 slope. SPB was fivefold higher in post COVID-19 than in normal subjects, but not associated to any of the referred symptoms. SPB was negatively associated to Vcap. CONCLUSIONS: In patients with post COVID-19, cardiorespiratory symptoms are linked to VE/VCO2 slope. In these patients the alveolar cells are dysregulated as shown by the very high SPB. The Vcap is low likely due to post COVID-19 pulmonary endothelial/vasculature damage but DLCO is only minimally impaired being DM preserved.

Outcomes of Transcatheter Aortic Valve Replacement Patients With Different Transvalvular Flow-Gradient Patterns.

Low-flow low-gradient (LF-LG) aortic stenosis (AS) may occur with preserved or depressed left ventricular ejection fraction (LVEF). Both situations represent the most challenging subset of patients to manage and generally have a poor prognosis. Few and controversial data exist on the outcomes of these patients compared with normal flow-high gradient (NF-HG) AS after transcatheter aortic valve replacement (TAVR). We sought to characterize different transvalvular flow-gradient patterns and to examine their prognostic value after TAVR. We enrolled 1,208 patients with severe AS and categorized as follow: 976 patients NF-HG (mean aortic pressure gradient [MPG] ≥40 mm Hg), 107 paradoxical LF-LG (pLF-LG, MPG <40 mm Hg, LVEF ≥50%, stroke volume index <35 ml/m2), and 125 classical LF-LG (cLF-LG) (MPG <40 mm Hg, LVEF <50%, stroke volume index <35 ml/m2). When compared with NF-HG and pLF-LG, cLF-LG had a worse symptomatic status (New York Heart Association III to IV 86% vs 62% and 67%, p <0.001), a higher prevalence of eccentric hypertrophy and a higher level of LV global afterload reflected by a higher valvuloarterial impedance. Valvular function after TAVR was excellent over time in all patients. While 30-day mortality (p = 0.911) did not differ significantly among groups, cLF-LG had a lower 5-year survival rate (LF-LG 50% vs pLF-LG 62% and NF-HG 68%, p <0.05). cLF-LG was associated with a hazard ratio for mortality of 2.41 (95% confidence interval 1.65 to 3.52, p <0.001). In conclusion, TAVR is an effective procedure regardless of transvalvular flow-gradient patterns. However, special care should be given to characterized hemodynamic of AS, as patients with pLF-LG had similar survival rates than patients with NF-HG, whereas cLF-LG is associated with a twofold increased risk of mortality at 5-year follow-up.

Early Biological Valve Failure: Structural Valve Degeneration, Thrombosis, or Endocarditis?

Biological valve failure (BVF) is an inevitable condition that compromises the durability of biological heart valves (BHVs). It stems from various causes, including rejection, thrombosis, and endocarditis, leading to a critical state of valve dysfunction. Echocardiography, cardiac computed tomography, cardiac magnetic resonance, and nuclear imaging play pivotal roles in the diagnostic multimodality workup of BVF. By providing a comprehensive overview of the pathophysiology of BVF and the diagnostic approaches in different clinical scenarios, this review aims to aid clinicians in their decision-making process. The significance of early detection and appropriate management of BVF cannot be overstated, as these directly impact patients' prognosis and their overall quality of life. Ensuring timely intervention and tailored treatments will not only improve outcomes but also alleviate the burden of this condition on patients' life. By prioritizing comprehensive assessments and adopting the latest advancements in diagnostic technology, medical professionals can significantly enhance their ability to manage BVF effectively.

Echocardiography vs. CMR in the Quantification of Chronic Mitral Regurgitation: A Happy Marriage or Stormy Divorce?

Quantification of chronic mitral regurgitation (MR) is essential to guide patients' clinical management and define the need and appropriate timing for mitral valve surgery. Echocardiography represents the first-line imaging modality to assess MR and requires an integrative approach based on qualitative, semiquantitative, and quantitative parameters. Of note, quantitative parameters, such as the echocardiographic effective regurgitant orifice area, regurgitant volume (RegV), and regurgitant fraction (RegF), are considered the most reliable indicators of MR severity. In contrast, cardiac magnetic resonance (CMR) has demonstrated high accuracy and good reproducibility in quantifying MR, especially in cases with secondary MR; nonholosystolic, eccentric, and multiple jets; or noncircular regurgitant orifices, where quantification with echocardiography is an issue. No gold standard for MR quantification by noninvasive cardiac imaging has been defined so far. Only a moderate agreement has been shown between echocardiography, either with transthoracic or transesophageal approaches, and CMR in MR quantification, as supported by numerous comparative studies. A higher agreement is evidenced when echocardiographic 3D techniques are used. CMR is superior to echocardiography in the calculation of the RegV, RegF, and ventricular volumes and can provide myocardial tissue characterization. However, echocardiography remains fundamental in the pre-operative anatomical evaluation of the mitral valve and of the subvalvular apparatus. The aim of this review is to explore the accuracy of MR quantification provided by echocardiography and CMR in a head-to-head comparison between the two techniques, with insight into the technical aspects of each imaging modality.

Nuclear and Morphological Alterations in Erythrocytes, Antioxidant Enzymes, and Genetic Disparities Induced by Brackish Water in Mrigal Carp (Cirrhinus mrigala).

Salinization of aquatic ecosystem, abrupt climate change, and anthropogenic activities cause adverse impact on agricultural land/soil as well as the aquaculture industry. This experimental study was designed to evaluate different biomarkers of oxidative stress, antioxidant enzymes, and genotoxic potential of diverse salinities of brackish water on freshwater fish. A total of 84 fresh water mrigal carp (Cirrhinus mrigala) were randomly segregated and maintained in four groups (T0, T1, T2, and T3) in a glass aquarium under similar laboratory conditions at various salinity levels (0, 3, 5, and 7 parts per thousand) to determine the pathological influence of brackish water. All the fish in groups T1, T2, and T3 were exposed to various salinity levels of brackish water for a period of 90 days while the fish of group T0 served as the control group. The experimental fish reared in different groups T1, T2, and T3 displayed various physical and behavioral ailments. The results revealed significantly augmented quantity of different oxidative stress indicators including reactive oxygen species (ROS) and thiobarbituric acid reactive substance (TBARS) in different visceral tissues (kidneys, liver, and gills) of exposed fish. Different antioxidant enzymes such as reduced glutathione (GSH), peroxidase (POD), superoxide dismutase (SOD), and catalase (CAT) along with total proteins were remarkably reduced in the kidneys, gills, and liver tissues. Results showed significantly increased values of different nuclear abnormalities (erythrocyte with micronucleus, erythrocyte with condensed nucleus, and erythrocyte with lobed nucleus) and morphological changes (pear shaped erythrocyte, spindle-shaped erythrocytes, and spherocyte) in red blood cells of experimental fish. The results on genotoxic effects exhibited significantly increased DNA damage in isolated cells of liver, kidneys, and gills of exposed fish. The findings of our experimental research suggested that brackish water causes adverse toxicological impacts on different visceral tissues of fresh water fish at higher salinity level through disruption and disorder of physiological and biochemical markers.

Leukemia segmentation and classification: A comprehensive survey.

Blood is made up of leukocytes (WBCs), erythrocytes (RBCs), and thrombocytes. The ratio of blood cancer diseases is increasing rapidly, among which leukemia is one of the famous cancer which may lead to death. Leukemia cancer is initiated by the unnecessary growth of immature WBCs present in the sponge tissues of bone marrow. It is generally analyzed by etiologists by perceiving slides of blood smear images under a microscope. The morphological features and blood cells count facilitated the etiologists to detect leukemia. Due to the late detection and expensive instruments used for leukemia analysis, the death rate has risen significantly. The fluorescence-based cell sorting technique and manual recounts using a hemocytometer are error-prone and imprecise. Leukemia detection methods consist of pre-processing, segmentation, features extraction, and classification. In this article, recent deep learning methodologies and challenges for leukemia detection are discussed. These methods are helpful to examine the microscopic blood smears images and for the detection of leukemia more accurately.

An optimized features selection approach based on Manta Ray Foraging Optimization (MRFO) method for parasite malaria classification.

Malaria is a serious and lethal disease that has been reported by the World Health Organization (WHO), with an estimated 219 million new cases and 435,000 deaths globally. The most frequent malaria detection method relies mainly on the specialists who examine the samples under a microscope. Therefore, a computerized malaria diagnosis system is required. In this article, malaria cell segmentation and classification methods are proposed. The malaria cells are segmented using a color-based k-mean clustering approach on the selected number of clusters. After segmentation, deep features are extracted using pre-trained models such as efficient-net-b0 and shuffle-net, and the best features are selected using the Manta-Ray Foraging Optimization (MRFO) method. Two experiments are performed for classification using 10-fold cross-validation, the first experiment is based on the best features selected from the pre-trained models individually, while the second experiment is performed based on the selection of best features from the fusion of extracted features using both pre-trained models. The proposed method provided an accuracy of 99.2% for classification using the linear kernel of the SVM classifier. An empirical study demonstrates that the fused features vector results are better as compared to the individual best-selected features vector and the existing latest methods published so far.

Identification of the ubiquitin-proteasome pathway domain by hyperparameter optimization based on a 2D convolutional neural network.

The major mechanism of proteolysis in the cytosol and nucleus is the ubiquitin-proteasome pathway (UPP). The highly controlled UPP has an effect on a wide range of cellular processes and substrates, and flaws in the system can lead to the pathogenesis of a number of serious human diseases. Knowledge about UPPs provide useful hints to understand the cellular process and drug discovery. The exponential growth in next-generation sequencing wet lab approaches have accelerated the accumulation of unannotated data in online databases, making the UPP characterization/analysis task more challenging. Thus, computational methods are used as an alternative for fast and accurate identification of UPPs. Aiming this, we develop a novel deep learning-based predictor named "2DCNN-UPP" for identifying UPPs with low error rate. In the proposed method, we used proposed algorithm with a two-dimensional convolutional neural network with dipeptide deviation features. To avoid the over fitting problem, genetic algorithm is employed to select the optimal features. Finally, the optimized attribute set are fed as input to the 2D-CNN learning engine for building the model. Empirical evidence or outcomes demonstrates that the proposed predictor achieved an overall accuracy and AUC (ROC) value using 10-fold cross validation test. Superior performance compared to other state-of-the art methods for discrimination the relations UPPs classification. Both on and independent test respectively was trained on 10-fold cross validation method and then evaluated through independent test. In the case where experimentally validated ubiquitination sites emerged, we must devise a proteomics-based predictor of ubiquitination. Meanwhile, we also evaluated the generalization power of our trained modal via independent test, and obtained remarkable performance in term of 0.862 accuracy, 0.921 sensitivity, 0.803 specificity 0.803, and 0.730 Matthews correlation coefficient (MCC) respectively. Four approaches were used in the sequences, and the physical properties were calculated combined. When used a 10-fold cross-validation, 2D-CNN-UPP obtained an AUC (ROC) value of 0.862 predicted score. We analyzed the relationship between UPP protein and non-UPP protein predicted score. Last but not least, this research could effectively analyze the large scale relationship between UPP proteins and non-UPP proteins in particular and other protein problems in general and our research work might improve computational biological research. Therefore, we could utilize the latest features in our model framework and Dipeptide Deviation from Expected Mean (DDE) -based protein structure features for the prediction of protein structure, functions, and different molecules, such as DNA and RNA.

Selenium and mercury concentrations in biological samples from patients with COVID-19.

BACKGROUND: Coronavirus disease 2019 (COVID-19) is a systemic disease affecting multiple organs. Furthermore, viral infection depletes several trace elements and promotes complex biochemical reactions in the body. Smoking has been linked to the incidence of COVID-19 and associated mortality, and it may impact clinical effects, viral and bacterial conversion, and treatment outcomes. OBJECTIVES: To study the relationship between severe acute respiratory syndrome coronavirus type 2 and the elemental concentrations of selenium (Se) and mercury (Hg) in biological samples from smokers and nonsmokers infected with the virus and in healthy individuals. METHOD: We evaluated changes in the concentrations of essential (Se) and toxic (Hg) elements in biological samples (blood, nasal fluid, saliva, sputum, serum, and scalp hair) collected from male smokers and nonsmokers (aged 29-59 years) infected with COVID-19 and from healthy men in the same age group. The patients lived in different cities in Sindh Province, Pakistan. The Se and Hg concentrations were determined using atomic absorption spectrophotometry. RESULTS: Se concentrations in all types of biological samples from smokers and nonsmokers with COVID-19 were lower than those of healthy smokers and nonsmokers. Hg concentrations were elevated in both smokers and nonsmokers with COVID-19. CONCLUSIONS: In the current study, persons infected with COVID-19 had higher concentrations of toxic Hg, which could cause physiological disorders, and low concentrations of essential Se, which can also cause weakness. COVID-19 infection showed positive correlations with levels of mercury and selenium. Thus, additional clinical and experimental investigations are essential.

XGB-DrugPred: computational prediction of druggable proteins using eXtreme gradient boosting and optimized features set.

Accurate identification of drug-targets in human body has great significance for designing novel drugs. Compared with traditional experimental methods, prediction of drug-targets via machine learning algorithms has enhanced the attention of many researchers due to fast and accurate prediction. In this study, we propose a machine learning-based method, namely XGB-DrugPred for accurate prediction of druggable proteins. The features from primary protein sequences are extracted by group dipeptide composition, reduced amino acid alphabet, and novel encoder pseudo amino acid composition segmentation. To select the best feature set, eXtreme Gradient Boosting-recursive feature elimination is implemented. The best feature set is provided to eXtreme Gradient Boosting (XGB), Random Forest, and Extremely Randomized Tree classifiers for model training and prediction. The performance of these classifiers is evaluated by tenfold cross-validation. The empirical results show that XGB-based predictor achieves the best results compared with other classifiers and existing methods in the literature.

Human drug-pathway association prediction based on network consistency projection.

We present a novel computational method for drug-pathway association prediction based on known drug-pathway associations. The association between a drug and a pathway needs to be examined to not only explain the cause and enable the identification, therapy, and diagnosis of a human disease. Though, biological studies and clinical trials require substantial time and resources to identify drug-pathway associations. Considerable research attention has been devoted to many scientists have developed computer models to predict the future interactions of drug-pathway organizations. We proposed a novel computing approach known as the Network Consistency Projection for Human Drug-Pathway Association (NCPHDPA). This method was based on the drug pathway target wherein biologically related drugs appear to interact with pathway targets in identical diseases and vice versa. We computed the pathway-pathway-interaction similarity of drugs sharing similarities on the basis of pairwise Jaccard similarity and then computed the drug-drug-interaction similarity of drugs sharing similar drug targets based on Jaccard similarity. The system was combined because of the cosine similarity drug network, the pathway cosine resemblance network, and the interaction network for recognized drug-pathway. NCPHDPA was a parameter less solution and did not require negative tests. Notably, NCPHDPA could be used to predict drugs without any known related pathway. Test results showed that our proposed NCPHDPA method with LOOCV achieved a high ROC of AUC = 0.7479, and with10-fold CV obtained ROC of AUC = 0.7566. The Result of ROC (AUC) comparison of NCPHDPA with other methods, such as SIMCCDA LOOCV (AUC = 0.7364), LOMDA LOOCV (AUC = 0.6729) and DMTHNDM LOOCV (AUC = 0.50.00) obtained. The robust predictive capability of the NCPHDPA was demonstrated in three case studies on drugs involved in pathways, cancer pathways, and hepatocellular carcinoma. Few attempts have been made to compared with other methods, our proposed NCPHDPA method had reliable predictive performance. The results yielded some interesting findings as that interaction of these proteins can cause a change in its associated pathway, leading to the onset of cancer.

The Role of Multimodality Imaging in Left-Sided Prosthetic Valve Dysfunction.

Prosthetic valve (PV) dysfunction (PVD) is a complication of mechanical or biological PV. Etiologic mechanisms associated with PVD include fibrotic pannus ingrowth, thrombosis, structural valve degeneration, and endocarditis resulting in different grades of obstruction and/or regurgitation. PVD can be life threatening and often challenging to diagnose due to the similarities between the clinical presentations of different causes. Nevertheless, identifying the cause of PVD is critical to treatment administration (thrombolysis, surgery, or percutaneous procedure). In this report, we review the role of multimodality imaging in the diagnosis of PVD. Specifically, this review discusses the characteristics of advanced imaging modalities underlying the importance of an integrated approach including 2D/3D transthoracic and transesophageal echocardiography, fluoroscopy, and computed tomography. In this scenario, it is critical to understand the strengths and weaknesses of each modality according to the suspected cause of PVD. In conclusion, for patients with suspected or known PVD, this stepwise imaging approach may lead to a simplified, more rapid, accurate and specific workflow and management.

3D echocardiography in mitral valve prolapse.

Mitral valve prolapse (MVP) is the leading cause of mitral valve surgery. Echocardiography is the principal imaging modality used to diagnose MVP, assess the mitral valve morphology and mitral annulus dynamics, and quantify mitral regurgitation. Three-dimensional (3D) echocardiographic (3DE) imaging represents a consistent innovation in cardiovascular ultrasound in the last decades, and it has been implemented in routine clinical practice for the evaluation of mitral valve diseases. The focus of this review is the role and the advantages of 3DE in the comprehensive evaluation of MVP, intraoperative and intraprocedural monitoring.

Identification of Enzymes-specific Protein Domain Based on DDE, and Convolutional Neural Network.

Predicting the protein sequence information of enzymes and non-enzymes is an important but a very challenging task. Existing methods use protein geometric structures only or protein sequences alone to predict enzymatic functions. Thus, their prediction results are unsatisfactory. In this paper, we propose a novel approach for predicting the amino acid sequences of enzymes and non-enzymes via Convolutional Neural Network (CNN). In CNN, the roles of enzymes are predicted from multiple sides of biological information, including information on sequences and structures. We propose the use of two-dimensional data via 2DCNN to predict the proteins of enzymes and non-enzymes by using the same fivefold cross-validation function. We also use an independent dataset to test the performance of our model, and the results demonstrate that we are able to solve the overfitting problem. We used the CNN model proposed herein to demonstrate the superiority of our model for classifying an entire set of filters, such as 32, 64, and 128 parameters, with the fivefold validation test set as the independent classification. Via the Dipeptide Deviation from Expected Mean (DDE) matrix, mutation information is extracted from amino acid sequences and structural information with the distance and angle of amino acids is conveyed. The derived feature maps are then encoded in DDE exploitation. The independent datasets are then compared with other two methods, namely, GRU and XGBOOST. All analyses were conducted using 32, 64 and 128 filters on our proposed CNN method. The cross-validation datasets achieved an accuracy score of 0.8762%, whereas the accuracy of independent datasets was 0.7621%. Additional variables were derived on the basis of ROC AUC with fivefold cross-validation was achieved score is 0.95%. The performance of our model and that of other models in terms of sensitivity (0.9028%) and specificity (0.8497%) was compared. The overall accuracy of our model was 0.9133% compared with 0.8310% for the other model.

AFP-CMBPred: Computational identification of antifreeze proteins by extending consensus sequences into multi-blocks evolutionary information.

In extremely cold environments, living organisms like plants, animals, fishes, and microbes can die due to the intracellular ice formation in their bodies. To sustain life in such cold environments, some cold-blooded species produced Antifreeze proteins (AFPs), also called ice-binding proteins. AFPs are not only limited to the medical field but also have diverse significance in the area of biotechnology, agriculture, and the food industry. Different AFPs exhibit high heterogeneity in their structures and sequences. Keeping the significance of AFPs, several machine-learning-based models have been developed by scientists for the prediction of AFPs. However, due to the complex and diverse nature of AFPs, the prediction performance of the existing methods is limited. Therefore, it is highly indispensable for researchers to develop a reliable computational model that can accurately predict AFPs. In this connection, this study presents a novel predictor for AFPs, named AFP-CMBPred. The sequences of AFPs are formulated via four different feature representation methods, such as Amphiphilic pseudo amino acid composition (Amp-PseAAC), Dipeptide Deviation from Expected Mean (DDE), Multi-Blocks Position Specific Scoring Matrix (MB-PSSM), and Consensus Sequence-based on Multi-Blocks Position Specific Scoring Matrix (CS-MB-PSSM) to collect local and global descriptors. In the next step, the extracted feature vectors are evaluated via Support Vector Machine (SVM) and Random Forest (RF) based classification learners. The prediction performance of both classifiers is further assessed using three validation methods i.e., jackknife test, 10-fold cross-validation test, and independent test. After examining the prediction rates of all validation tests, it was found that our proposed model achieved the higher prediction accuracies of ∼2.65%, ∼2.84%, and ∼3.37% using jackknife, K-fold, and independent test, respectively. The experimental outcomes validate that our proposed "AFP-CMBPred" predictor secured the highest prediction results than the existing models for the identification of AFPs. It is further anticipated that our proposed AFP-CMBPred model will be considered a valuable tool in the research academia and drug development.