Metaheuristic integrated machine learning classification of colon cancer using STFT LASSO and EHO feature extraction from microarray gene expressions.

The microarray gene expression data poses a tremendous challenge due to their curse of dimensionality problem. The sheer volume of features far surpasses available samples, leading to overfitting and reduced classification accuracy. Thus the dimensionality of microarray gene expression data must be reduced with efficient feature extraction methods to reduce the volume of data and extract meaningful information to enhance the classification accuracy and interpretability. In this research, we discover the uniqueness of applying STFT (Short Term Fourier Transform), LASSO (Least Absolute Shrinkage and Selection Operator), and EHO (Elephant Herding Optimisation) for extracting significant features from lung cancer and reducing the dimensionality of the microarray gene expression database. The classification of lung cancer is performed using the following classifiers: Gaussian Mixture Model (GMM), Particle Swarm Optimization (PSO) with GMM, Detrended Fluctuation Analysis (DFA), Naive Bayes classifier (NBC), Firefly with GMM, Support Vector Machine with Radial Basis Kernel (SVM-RBF) and Flower Pollination Optimization (FPO) with GMM. The EHO feature extraction with the FPO-GMM classifier attained the highest accuracy in the range of 96.77, with an F1 score of 97.5, MCC of 0.92 and Kappa of 0.92. The reported results underline the significance of utilizing STFT, LASSO, and EHO for feature extraction in reducing the dimensionality of microarray gene expression data. These methodologies also help in improved and early diagnosis of lung cancer with enhanced classification accuracy and interpretability.

A community-based cervical cancer screening program in Alappuzha district of Kerala using camp approach.

Background: Cervical cancer is a major cause of preventable cancer related death in women, particularly in middle-income developing countries. Screening of cervical pre-cancer by cytology remains an effective strategy for prevention of mortality. However, there is paucity of community-based studies in Kerala. The aim of this study was to determine the prevalence of cervical precancerous lesions and to study the associated epidemiological factors through camp approach. Materials and Methods: A cross-sectional study was carried out among women in Alappuzha district, Kerala, by conducting community-based screening camps covering all the panchayaths from February 2017 to January 2019. Statistical Analysis Used: Descriptive statistics including mean for continuous variables and frequency along with their percentage for categorical variables were determined. Pearson's Chi-square test was used to determine the strength of the association between variables. Statistical significance was set at P value less than 0.05. Results: Out of 5241 women screened, majority (62.9%) were in the reproductive age group (31-50 years) with mean age of 47.1 ± 10.3 years. The prevalence of precancerous lesions of cervix was 6.37%, which consisted of low-grade squamous intraepithelial lesion (LSIL) in 2.2%, high-grade squamous intraepithelial lesion (HSIL) in 0.5% and Carcinoma-in-situ in 0.2%. Risk factors that had significant association with cervical precancerous lesions were lower education status, genital infections, early marriage age and high parity. Conclusion: Well planned community-based screening programs can help to identify the exact prevalence of cervical pre-cancer in a region and the associated epidemiological factors leading to formulation of effective elimination strategies.

Why are people dying due to tuberculosis? A study from Alappuzha District, Kerala, India.

BACKGROUND: Tuberculosis (TB)is a major killer disease worldwide. It is the ninth leading cause of death worldwide and the leading cause from a single infectious agent. In India also, TB kills about 480,000 persons every year and more than 1400 every day. Vision of the National TB Control Programme is TB-Free India with zero deaths, disease and poverty due to TB. Specific targets set in the End TB strategy include a 90% reduction in TB deaths and an 80% reduction in TB incidence by 2030, compared with 2015. Understanding about real cause of death is important to plan strategies to further prevent TB deaths. In the above circumstances we conducted a study, the objective of which was to find out the cause of deaths among patients registered in RNTCP unit of Alappuzha district of Kerala, India. METHODS: In RNTCP a patient who died during the course of treatment regardless of cause is declared as 'Died' due to TB. During the year 2015, 1618 cases were registered in RNTCP of Alappuzha district of which 90 patients died, showing a case fatality rate of 5.56%. Verbal autopsy can be considered as an essential public health tool for studying reasonable estimate of the cause of death at a community level even though not an accurate method at individual level. As part of the study, we visited the 4 RNTCP units of the district and collected the address of the TB patients who died in the area. With the help of the field staff we visited their houses and filled the death audit form of RNTCP along with the additional details. Verbal autopsy was conducted using WHO verbal autopsy format 2012 with immediate house hold contacts. RESULTS: Out of 90 deaths which occurred, three addresses could not be traced and another 15 patient relatives could not be contacted as they migrated out or were not available at their homes on two visits. Among them, mean age was found to be 62.6 years (SD+12.9). Males were 67 (77%) and rest 20 (23%)were females. Cause of death was analysed after Verbal autopsy for 72 deaths. Among 72 deaths, it was found that 29 (40.3%) had nothing other than TB, where as cause of death for 13 (18.1%) patients was myocardial infarction, 11 (15.3%) had cancer, 2 (2.8%) stroke and 17 (23.7%) other causes which include bronchiectasis, COPD, chicken pox, hepatitis, renal failure, and suicide. Only in 35 cases nothing other than TB could be suggested as a cause of death. Thus in 52 out of 87 (60%) cases, the causes of death were diseases other than TB. CONCLUSION: Among the TB deaths in Alappuzha district, 60% of deaths were due to diseases other than TB. Along with early diagnosis of all TB cases, screening for co-morbidity, appropriate management of co-morbidity and periodic clinical review of TB patients should also be part of the major strategies to prevent TB related deaths.

3DSwap: curated knowledgebase of proteins involved in 3D domain swapping.

Three-dimensional domain swapping is a unique protein structural phenomenon where two or more protein chains in a protein oligomer share a common structural segment between individual chains. This phenomenon is observed in an array of protein structures in oligomeric conformation. Protein structures in swapped conformations perform diverse functional roles and are also associated with deposition diseases in humans. We have performed in-depth literature curation and structural bioinformatics analyses to develop an integrated knowledgebase of proteins involved in 3D domain swapping. The hallmark of 3D domain swapping is the presence of distinct structural segments such as the hinge and swapped regions. We have curated the literature to delineate the boundaries of these regions. In addition, we have defined several new concepts like 'secondary major interface' to represent the interface properties arising as a result of 3D domain swapping, and a new quantitative measure for the 'extent of swapping' in structures. The catalog of proteins reported in 3DSwap knowledgebase has been generated using an integrated structural bioinformatics workflow of database searches, literature curation, by structure visualization and sequence-structure-function analyses. The current version of the 3DSwap knowledgebase reports 293 protein structures, the analysis of such a compendium of protein structures will further the understanding molecular factors driving 3D domain swapping.