A multi-channel deep convolutional neural network for multi-classifying thyroid diseases

Comprehensive transcriptome and scRNA-seq analyses uncover the expression and underlying mechanism of SYNJ2 in papillary thyroid carcinoma

Synaptojanin 2 (SYNJ2) has crucial role in various tumors, but its role in papillary thyroid carcinoma (PTC) remains unexplored. This study first detected SYNJ2 protein expression in PTC using immunohistochemistry method and further assessed SYNJ2 mRNA expression through mRNA chip and RNA sequencing data and its association with clinical characteristics. Additionally, KEGG, GSVA, and GSEA analyses were conducted to investigate potential biological functions, while single-cell RNA sequencing data were used to explore SYNJ2's underlying mechanisms in PTC. Meanwhile, immune infiltration status in different SYNJ2 expression groups were analyzed. Besides, we investigated the immune checkpoint gene expression and implemented drug sensitivity analysis. Results indicated that SYNJ2 is highly expressed in PTC (SMD = 0.66 [95% CI: 0.17-1.15]) and could distinguish between PTC and non-PTC tissues (AUC = 0.74 [0.70-0.78]). Furthermore, the study identified 134 intersecting genes of DEGs and CEGs, mainly enriched in the angiogenesis and epithelial-mesenchymal transition (EMT) pathways. Subsequent analysis showed the above pathways were activated in PTC epithelial cells. PTC patients with high SYNJ2 expression showed higher sensitivity to the six common drugs. Summarily, SYNJ2 may promote PTC progression through angiogenesis and EMT pathways. High SYNJ2 expression is associated with better response to immunotherapy and chemotherapy.

A Review of Machine Learning Algorithms for Biomedical Applications

As the amount and complexity of biomedical data continue to increase, machine learning methods are becoming a popular tool in creating prediction models for the underlying biomedical processes. Although all machine learning methods aim to fit models to data, the methodologies used can vary greatly and may seem daunting at first. A comprehensive review of various machine learning algorithms per biomedical applications is presented. The key concepts of machine learning are supervised and unsupervised learning, feature selection, and evaluation metrics. Technical insights on the major machine learning methods such as decision trees, random forests, support vector machines, and k-nearest neighbors are analyzed. Next, the dimensionality reduction methods like principal component analysis and t-distributed stochastic neighbor embedding methods, and their applications in biomedical data analysis were reviewed. Moreover, in biomedical applications predominantly feedforward neural networks, convolutional neural networks, and recurrent neural networks are utilized. In addition, the identification of emerging directions in machine learning methodology will serve as a useful reference for individuals involved in biomedical research, clinical practice, and related professions who are interested in understanding and applying machine learning algorithms in their research or practice.