arXiv subjects

Chanati Jantrachotechatchawan

Publications and source records attributed to Chanati Jantrachotechatchawan.

3 recordsLinked to original sources

arXiv2022

DNA Methylation in hypoxia in Mycobacterium tuberculosis

Tuberculosis is one of the most lethal contagious diseases caused by Mycobacterium tuberculosis (MTB), in many cases, the infected did not show any symptoms, because the bacilli entered the dormant stage in granulomas. The dormant stage of MTB is also associated with higher resistance to drugs and the immune system. Among multiple epigenetic regulations critical to MTB stress responses, DNA methylation is necessary for the survival of MTB in hypoxic conditions, which is a common stress event during granuloma formation. This review gathers previous findings and demonstrates a meta-analysis by collecting hypoxia gene expression data from several articles and perform association analysis between those genes and methylation site profiles across whole genomes of representative strains pf lineage 2 and 4. While more data is required for more conclusive support, our results suggest that methylation sites in the possible promoter regions may induce differential gene regulation in hypoxia.

q-bio.GN↗

arXiv2021

Automatic Detection of Depression from Stratified Samples of Audio Data

Depression is a common mental disorder which has been affecting millions of people around the world and becoming more severe with the arrival of COVID-19. Nevertheless proper diagnosis is not accessible in many regions due to a severe shortage of psychiatrists. This scarcity is worsened in low-income countries which have a psychiatrist to population ratio 210 times lower than that of countries with better economies. This study aimed to explore applications of deep learning in diagnosing depression from voice samples. We collected data from the DAIC-WOZ database which contained 189 vocal recordings from 154 individuals. Voice samples from a patient with a PHQ-8 score equal or higher than 10 were deemed as depressed and those with a PHQ-8 score lower than 10 were considered healthy. We applied mel-spectrogram to extract relevant features from the audio. Three types of encoders were tested i.e. 1D CNN, 1D CNN-LSTM, and 1D CNN-GRU. After tuning hyperparameters systematically, we found that 1D CNN-GRU encoder with a kernel size of 5 and 15 seconds of recording data appeared to have the best performance with F1 score of 0.75, precision of 0.64, and recall of 0.92.

cs.SD↗

arXiv2021

Using Bayesian Network Analysis to Reveal Complex Natures of Relationships

Relationships are vital for mankind in many aspects. According to Maslow hierarchy of needs, it is suggested that while a healthy relationship is an essential part of a human life that fundamentally determines our goals and purposes, an unsuccessful relationship can lead to suicide and other major psychological problems. However, a complete understanding of this topic still remains a challenge and the divorce rate is rising more than ever before to almost 50 percents. The objective of this research is to explore the association between each group of behaviors by performing Bayesian network analysis on a large publically available Experiences in Close Relationships Scale, a test of attachment style survey (ECR) data from openpsychometrics database. The resulting directed acyclic graph has 2 root nodes (Q02 from avoidant and Q05 from anxious attachment) and 5 end nodes (Q16, Q34, and Q36 from anxious attachment). The network can be divided into 5 clusters, 2 avoidance and 3 anxiety clusters. Furthermore, our list of items in the clusters are consistent with the findings of previous factor analysis studies and our estimated coefficients are significantly correlated with those of one partial correlation network study.

stat.AP↗