Perspectives of gene combinations in phenotype presentation

Machine Learning-Based Alzheimer's Disease Stage Diagnosis Utilizing Blood Gene Expression and Clinical Data: A Comparative Investigation

Background/Objectives: This study presents a comparative analysis of the multistage diagnosis of Alzheimer's disease (AD), including mild cognitive impairment (MCI), utilizing two distinct types of biomarkers: blood gene expression and clinical biomarker samples. Both of these samples, obtained from participants in the Alzheimer's Disease Neuroimaging Initiative (ADNI), were independently analyzed utilizing machine learning (ML)-based multiclassifiers. This study applied novel machine learning-based data augmentation techniques to gene expression profile data that are high-dimensional, low-sample-size (HDLSS) and inherently highly imbalanced. The investigation obtained the highest multiclassification performance to date in the multistage diagnosis of Alzheimer's disease utilizing the blood gene expression profiles of Alzheimer's Disease Neuroimaging Initiative (ADNI) participants. Based on the performance results obtained, and other factors such as early prediction capabilities, this study compares the efficacies of the two types of biomarkers for multistage diagnosis. This study presents the sole investigation in which multiclassification-based AD stage diagnosis was conducted utilizing blood gene expression data. We obtained the best multiclassification result in both modalities of the ADNI data in terms of F1-score and were able to identify new genetic biomarkers. Methods: The combination of the XGBoost and SFBS (Sequential Floating Backward Selection) methods was used to select the features. We were able to select the 95 most effective gene probe sets out of 49,386. For the clinical study data, eight of the most effective biomarkers were selected using SFBS. A deep learning (DL) classifier was used to identify the stages-cognitive normal (CN), mild cognitive impairment (MCI), and Alzheimer's disease (AD)/dementia. DL, support vector machine (SVM), gradient boosting (GB), and random forest (RF) classifiers were used for the AD stage detection from gene expression profile data. Because of the high data imbalance in genomic data, borderline oversampling/data augmentation was applied in the model training and original samples for validation. Results: Utilizing clinical data, the highest ROC AUC scores attained were 0.989, 0.927, and 0.907 for the identification of the CN, MCI, and dementia stages, respectively. The highest F1 scores achieved were 0.971, 0.939, and 0.886. Employing gene expression data, we obtained ROC AUC scores of 0.763, 0.761, and 0.706 for the CN, MCI, and dementia stages, respectively, and F1 scores of 0.71, 0.77, and 0.53 for CN, MCI, and dementia, respectively. Conclusions: This represents the best outcome to date for AD stage diagnosis from ADNI blood gene expression profile data utilizing multiclassification techniques. The results indicated that our multiclassification model effectively manages the imbalanced data of a high-dimension, low-sample-size (HDLSS) nature to identify samples of the minority class. MAPK14, PLG, FZD2, FXYD6, and TEP1 are among the novel genes identified as being associated with AD risk.

Origin of cells and network information

All cells are derived from one cell, and the origin of different cell types is a subject of curiosity. Cells construct life through appropriately timed networks at each stage of development. Communication among cells and intracellular signaling are essential for cell differentiation and for life processes. Cellular molecular networks establish cell diversity and life. The investigation of the regulation of each gene in the genome within the cellular network is therefore of interest. Stem cells produce various cells that are suitable for specific purposes. The dynamics of the information in the cellular network changes as the status of cells is altered. The components of each cell are subject to investigation.

Reprogramming of human somatic cells by bacteria

In general, it had been believed that the cell fate restriction of terminally differentiated somatic cells was irreversible. In 1952, somatic cell nuclear transfer (SCNT) was introduced to study early embryonic development in frogs. So far, various mammalian species have been successfully cloned using the SCNT technique, though its efficiency is very low. Embryonic stem (ES) cells were the first pluripotent cells to be isolated from an embryo and have a powerful potential to differentiate into more than 260 types of cells. The generation of induced pluripotent stem (iPS) cells was a breakthrough in stem cell research, and the use of these iPS cells has solved problems such as low efficiency and cell fate restriction. These cells have since been used for clinical application, disease investigation, and drug selection. As it is widely accepted that the endosymbiosis of Archaea into eukaryotic ancestors resulted in the generation of eukaryotic cells, we examined whether bacterial infection could alter host cell fate. We previously showed that when human dermal fibroblast (HDF) cells were incorporated with lactic acid bacteria (LAB), the LAB-incorporated HDF cells formed clusters and expressed a subset of common pluripotent markers. Moreover, LAB-incorporated cell clusters could differentiate into cells derived from each of the three germinal layers both in vivo and in vitro, indicating successful reprogramming of host HDF cells by LAB. In the current review, we introduce the existing examples of cellular reprogramming by bacteria and discuss their nuclear reprogramming mechanisms.

Regulated genes in mesenchymal stem cells and gastric cancer

AIM

To investigate the genes regulated in mesenchymal stem cells (MSCs) and diffuse-type gastric cancer (GC), gene expression was analyzed.

METHODS

Gene expression of MSCs and diffuse-type GC cells were analyzed by microarray. Genes related to stem cells, cancer and the epithelial-mesenchymal transition (EMT) were extracted from human gene lists using Gene Ontology and reference information. Gene panels were generated, and messenger RNA gene expression in MSCs and diffuse-type GC cells was analyzed. Cluster analysis was performed using the NCSS software.

RESULTS

The gene expression of regulator of G-protein signaling 1 (RGS1) was up-regulated in diffuse-type GC cells compared with MSCs. A panel of stem-cell related genes and genes involved in cancer or the EMT were examined. Stem-cell related genes, such as growth arrest-specific 6, musashi RNA-binding protein 2 and hairy and enhancer of split 1 (Drosophila), NOTCH family genes and Notch ligands, such as delta-like 1 (Drosophila) and Jagged 2, were regulated.

CONCLUSION

Expression of RGS1 is up-regulated, and genes related to stem cells and NOTCH signaling are altered in diffuse-type GC compared with MSCs.