HBMD-Net: Feature Fusion Based Breast Cancer Classification with Class Imbalance Resolution.

Breast cancer, a widespread global disease, represents a significant threat to women's health and lives, ranking as one of the most vulnerable malignant tumors they face. Many researchers have proposed their computer-aided diagnosis systems for classifying breast cancer. The majority of these approaches primarily utilize deep learning (DL) methods, which are not entirely reliable. These approaches overlook the crucial necessity of incorporating both local and global information for precise tumor detection, despite the fact that the subtle nuances are crucial for precise breast cancer classification. In addition, there are a limited number of publicly available breast cancer datasets, and the ones that are available tend to be imbalanced in nature. Therefore, this paper presents the hybrid breast mass detection-network (HBMD-Net) to address two critical challenges: class imbalance and the need to recognize that relying solely on either global or local features falls short in achieving precise tumor classification. To overcome the problem of class imbalance, HBMD-Net incorporates the borderline synthetic minority over-sampling technique (BSMOTE). Simultaneously, it employs a feature fusion approach, combining features by utilizing ResNet50 to extract deep features that provide global information, while handcrafted features are derived using histogram orientation gradient (HOG), that provide local information. In addition, an ROI segmentation has been implemented to avoid misclassifications. This integrated strategy substantially enhances breast cancer classification performance. Moreover, the proposed method integrates the block matching and 3D (BM3D) denoising filter to effectively eliminate multiplicative noise that has enhanced the performance of the system. The evaluation of the proposed HBMD-Net encompasses two breast ultrasound (BUS) datasets, namely BUSI and UDIAT. The proposed model has demonstrated a satisfactory performance, achieving accuracies of 99.14% and 94.49% respectively.

Importance of aspartate 4 in the Mg2+ dependent regulation of Leishmania major PAS domain-containing phosphoglycerate kinase.

Magnesium is an important divalent cation for the regulation of catalytic activity. Recently, we have described that the Mg2+ binding through the PAS domain inhibits the phosphoglycerate kinase (PGK) activity in PAS domain-containing PGK from Leishmania major (LmPAS-PGK) at neutral pH 7.5, but PGK activity is derepressed at acidic pH 5.5. The acidic residue within the PAS domain of LmPAS-PGK is expected to bind the cofactor Mg2+ ion at neutral pH, but which specific acidic residue(s) is/are responsible for the Mg2+ binding is still unknown. To identify the residues, we exploited mutational studies of all acidic (twelve Asp/Glu) residues in the PAS domain for plausible Mg2+ binding. Mg2+ ion-dependent repression at pH 7.5 is withdrawn by substitution of Asp-4 with Ala, whereas other acidic residue mutants (D16A, D22A, D24A, D29A, D43A, D44A, D60A, D63A, D77A, D87A, and E107A) showed similar features compared to the wild-type protein. Fluorescence spectroscopic studies and isothermal titration calorimetry analysis showed that the Asp-4 is crucial for Mg2+ binding in the absence of both PGK's substrates. These results suggest that Asp-4 residue in the regulatory (PAS) domain of wild type enzymes is required for Mg2+ dependent repressed state of the catalytic PGK domain at neutral pH.

Sentiment analysis: A survey on design framework, applications and future scopes.

Sentiment analysis is a solution that enables the extraction of a summarized opinion or minute sentimental details regarding any topic or context from a voluminous source of data. Even though several research papers address various sentiment analysis methods, implementations, and algorithms, a paper that includes a thorough analysis of the process for developing an efficient sentiment analysis model is highly desirable. Various factors such as extraction of relevant sentimental words, proper classification of sentiments, dataset, data cleansing, etc. heavily influence the performance of a sentiment analysis model. This survey presents a systematic and in-depth knowledge of different techniques, algorithms, and other factors associated with designing an effective sentiment analysis model. The paper performs a critical assessment of different modules of a sentiment analysis framework while discussing various shortcomings associated with the existing methods or systems. The paper proposes potential multidisciplinary application areas of sentiment analysis based on the contents of data and provides prospective research directions.

Early detection of Parkinson disease using stacking ensemble method.

Parkinson's disease (PD) is a common progressive neurodegenerative disorder that occurs due to corrosion of the substantianigra, located in the thalamic region of the human brain, and is responsible for the transmission of neural signals throughout the human body using brain chemical, termed as "dopamine." Diagnosis of PD is difficult, as it is often affected by the characteristics of the medical data of the patients, which include the presence of various indicators, imbalance cases of patients' data records, similar cases of healthy/affected persons, etc. Hence, sometimes the process of diagnosis may also be affected by human error. To overcome this problem some intelligent models have been proposed; however, most of them are single classifier-based models and due to this these models cannot handle noisy and imbalanced data properly and thus sometimes overfit the model. To reduce bias and variance, and to avoid overfitting of a single classifier-based model, this paper proposes an ensemble-based PD diagnosis model, named Ensembled Expert System for Diagnosis of Parkinson's Disease (EESDPD) with relevant features and a simple stacking ensemble technique. The proposed EESDPD aggregates diverse assumptions for making the prediction. The performance of the proposed EESDPD is compared with the performances of logistic regression, SVM, Naïve Bayes, Random Forest, XGBoost, simple Decision Tree, B-TDS-PD and B-TESM-PD in terms of classification accuracy, precision, recall and F1-score measures.

Detection of Diabetic Retinopathy using Convolutional Neural Networks for Feature Extraction and Classification (DRFEC).

Diabetic Retinopathy (DR) is caused as a result of Diabetes Mellitus which causes development of various retinal abrasions in the human retina. These lesions cause hindrance in vision and in severe cases, DR can lead to blindness. DR is observed amongst 80% of patients who have been diagnosed from prolonged diabetes for a period of 10-15 years. The manual process of periodic DR diagnosis and detection for necessary treatment, is time consuming and unreliable due to unavailability of resources and expert opinion. Therefore, computerized diagnostic systems which use Deep Learning (DL) Convolutional Neural Network (CNN) architectures, are proposed to learn DR patterns from fundus images and identify the severity of the disease. This paper proposes a comprehensive model using 26 state-of-the-art DL networks to assess and evaluate their performance, and which contribute for deep feature extraction and image classification of DR fundus images. In the proposed model, ResNet50 has shown highest overfitting in comparison to Inception V3, which has shown lowest overfitting when trained using the Kaggle's EyePACS fundus image dataset. EfficientNetB4 is the most optimal, efficient and reliable DL algorithm in detection of DR, followed by InceptionResNetV2, NasNetLarge and DenseNet169. EfficientNetB4 has achieved a training accuracy of 99.37% and the highest validation accuracy of 79.11%. DenseNet201 has achieved the highest training accuracy of 99.58% and a validation accuracy of 76.80% which is less than the top-4 best performing models.

The ChaC family of γ-glutamyl cyclotransferases is required for Leishmania to switch to a slow growth state and for long-term survival of the parasite.

The ChaC family of γ-glutamyl cyclotransferases is conserved throughout all Kingdoms and catalyzes the degradation of GSH. So far, the ChaC family proteins in trypanosomal parasites are missing in the literature. Here, we report two members of the ChaC family of γ-glutamyl cyclotransferases (LmChaC2a and LmChaC2b) in the unicellular pathogen Leishmania. Activity measurements suggest that these proteins catalyze degradation of GSH but no other γ-glutamyl peptides. Recombinant LmChaC2a protein shows ∼17-fold lower catalytic efficiency (kcat ∼ 0.9 s-1) than LmChaC2b (kcat ∼ 15 s-1), although they showed comparable Km values (∼1.75 mM for LmChaC2a and ∼2.0 mM for LmChaC2b) toward GSH. qRT-PCR and Western blot analyses suggest that the LmChaC2a protein was found to be constitutively expressed, whereas LmChaC2b was regulated by sulfur stress. To investigate its precise physiological function in Leishmania, we generated overexpressed, knockout, and complement cell lines. Flow cytometric analyses show the presence of a higher intracellular GSH concentration and lower intracellular ROS level, indicative of a more reductive environment in null mutants. We found LmChaC2-expressing cells grow in GSH-containing sulfur-limited media, while the null mutants failed to grow, suggesting that LmChaC2 is crucial for cell growth with GSH as the only sulfur source. Null mutants, although reach the stationary phase rapidly, display impaired long-term survival, indicating that LmChaC2-mediated GSH degradation is necessary for prolonged survival. In vivo studies suggest that LmChaC2-dependent controlled GSH degradation promotes chronic infection by the parasite. Altogether, these data indicate that LmChaC2 plays an important role in GSH homeostasis in Leishmania.

Perspective of AI system for COVID-19 detection using chest images: a review.

Coronavirus Disease 2019 (COVID-19) is an evolving communicable disease caused due to Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) which has led to a global pandemic since December 2019. The virus has its origin from bat and is suspected to have transmitted to humans through zoonotic links. The disease shows dynamic symptoms, nature and reaction to the human body thereby challenging the world of medicine. Moreover, it has tremendous resemblance to viral pneumonia or Community Acquired Pneumonia (CAP). Reverse Transcription Polymerase Chain Reaction (RT-PCR) is performed for detection of COVID-19. Nevertheless, RT-PCR is not completely reliable and sometimes unavailable. Therefore, scientists and researchers have suggested analysis and examination of Computing Tomography (CT) scans and Chest X-Ray (CXR) images to identify the features of COVID-19 in patients having clinical manifestation of the disease, using expert systems deploying learning algorithms such as Machine Learning (ML) and Deep Learning (DL). The paper identifies and reviews various chest image features using the aforementioned imaging modalities for reliable and faster detection of COVID-19 than laboratory processes. The paper also reviews and compares the different aspects of ML and DL using chest images, for detection of COVID-19.

A critical review on diagnosis of diabetic retinopathy using machine learning and deep learning.

Diabetic Retinopathy (DR) is a health condition caused due to Diabetes Mellitus (DM). It causes vision problems and blindness due to disfigurement of human retina. According to statistics, 80% of diabetes patients battling from long diabetic period of 15 to 20 years, suffer from DR. Hence, it has become a dangerous threat to the health and life of people. To overcome DR, manual diagnosis of the disease is feasible but overwhelming and cumbersome at the same time and hence requires a revolutionary method. Thus, such a health condition necessitates primary recognition and diagnosis to prevent DR from developing into severe stages and prevent blindness. Innumerable Machine Learning (ML) models are proposed by researchers across the globe, to achieve this purpose. Various feature extraction techniques are proposed for extraction of DR features for early detection. However, traditional ML models have shown either meagre generalization throughout feature extraction and classification for deploying smaller datasets or consumes more of training time causing inefficiency in prediction while using larger datasets. Hence Deep Learning (DL), a new domain of ML, is introduced. DL models can handle a smaller dataset with help of efficient data processing techniques. However, they generally incorporate larger datasets for their deep architectures to enhance performance in feature extraction and image classification. This paper gives a detailed review on DR, its features, causes, ML models, state-of-the-art DL models, challenges, comparisons and future directions, for early detection of DR.

Regulation of Leishmania major PAS domain-containing phosphoglycerate kinase by cofactor Mg2+ ion at neutral pH.

Recently, we described the PAS domain-containing phosphoglycerate kinase (PGK) from Leishmania major (LmPAS-PGK) that shows acidic pH (5.5)-dependent optimum catalytic activity. The PAS domain of LmPAS-PGK is expected to regulate PGK activity during catalysis, but the mechanism of regulation by PAS domain at the molecular level is uncharacterized. In this work, we have utilized the full-length, PAS domain-deleted, and mutant enzymes to measure the enzymatic activity in the presence of divalent cation at various pH values. Catalytic activity measurement indicates that Mg2+ binding through PAS domain inhibits the PGK activity at pH 7.5, and this inhibition is withdrawn at pH 5.5. To identify the Mg2+ binding residues of the PAS domain, we exploited a systematic mutational analysis of all (four) His residues in the PAS domain for potential divalent cation binding. Replacement of His-57 with alanine resulted in depression in the presence of Mg2+ at pH 7.5, but H71A, H89A, and H111A showed similar characteristics with respect to the wild-type protein. Fluorescence and isothermal titration calorimetry studies revealed that H57 is responsible for Mg2+ binding in the absence of substrates. Thus, the protonated form of His57 at acidic pH 5.5 destabilizes the Mg2+ binding in the PAS domain, which is an essential requirement in the wild-type LmPAS-PGK for a conformational alteration in the sensor domain that, sequentially, activates the PGK domain, resulting in the synthesis of higher amounts of ATP.

PAS domain-containing phosphoglycerate kinase deficiency in Leishmania major results in increased autophagosome formation and cell death.

Per-Arnt-Sim (PAS) domains are structurally conserved and present in numerous proteins throughout all branches of the phylogenetic tree. Although PAS domain-containing proteins are major players for the adaptation to environmental stimuli in both prokaryotic and eukaryotic organisms, these types of proteins are still uncharacterized in the trypanosomatid parasites, Trypanosome and Leishmania In addition, PAS-containing phosphoglycerate kinase (PGK) protein is uncharacterized in the literature. Here, we report a PAS domain-containing PGK (LmPAS-PGK) in the unicellular pathogen Leishmania The modeled structure of N-terminal of this protein exhibits four antiparallel ß sheets centrally flanked by α helices, which is similar to the characteristic signature of PAS domain. Activity measurements suggest that acidic pH can directly stimulate PGK activity. Localization studies demonstrate that the protein is highly enriched in the glycosome and its presence can also be seen in the lysosome. Gene knockout, overexpression and complement studies suggest that LmPAS-PGK plays a fundamental role in cell survival through autophagy. Furthermore, the knockout cells display a marked decrease in virulence when host macrophage and BALB/c mice were infected with them. Our work begins to clarify how acidic pH-dependent ATP generation by PGK is likely to function in cellular adaptability of Leishmania.

Loss of virulence in NAD(P)H cytochrome b5 oxidoreductase deficient Leishmania major.

Leishmania promastigotes have the ability to synthesize essential polyunsaturated fatty acids de novo and can grow in lipid free media. Recently, we have shown that NAD(P)H cytochrome b5 oxidoreductase (Ncb5or) enzyme in Leishmania acts as the redox partner for Δ12 fatty acid desaturase, which catalyses the conversion of oleate to linoleate. So far, the exact role of Leishmania derived linoleate synthesis is still incomplete in the literature. The viability assay by flow cytometry as well as microscopic studies suggests that linoleate is an absolute requirement for Leishmania promastigote survival in delipidated media. Western blot analysis suggested that infection with log phase linoleate deficient mutant (KO) results in increased level of NF-κBp65, IκB and IKKß phosphorylation in RAW264.7 cells. Similarly, the log phase KO infected RAW264.7 cells show dramatic increment of COX-2 expression and TNF-α secretion, compared to control or Ncb5or complement (CM) cell lines. The activation of inflammatory signaling pathways by KO mutant is significantly reduced when the RAW264.7 cells are pre-treated with BSA bound linoleate. Together, these findings confirmed that the leishmanial linoleate inhibits both COX-2 and TNF-α expression in macrophage via the inactivation of NF-κB signaling pathway. The stationary phase of KO promastigotes shows avirulence after infection in macrophages as well as inoculation into BALB/c mice; whereas CM cell lines show virulence. Collectively, these data provide strong evidence that de novo linoleate synthesis in Leishmania is an essential for parasite survival at extracellular promastigote stage as well as intracellular amastigote stage.