Machine learning-based microarray analyses indicate low-expression genes might collectively influence PAH disease

Abstract

Accurately predicting and testing the types of Pulmonary arterial hypertension (PAH) of each patient using cost-effective microarray-based expression data and machine learning algorithms could greatly help either identifying the most targeting medicine or adopting other therapeutic measures that could correct/restore defective genetic signaling at the early stage. Furthermore, the prediction model construction processes can also help identifying highly informative genes controlling PAH, leading to enhanced understanding of the disease etiology and molecular pathways. In this study, we used several different gene filtering methods based on microarray expression data obtained from a high-quality patient PAH dataset. Following that, we proposed a novel feature selection and refinement algorithm in conjunction with well-known machine learning methods to identify a small set of highly informative genes. Results indicated that clusters of small-expression genes could be extremely informative at predicting and differentiating different forms of PAH. Additionally, our proposed novel feature refinement algorithm could lead to significant enhancement in model performance. To summarize, integrated with state-of-the-art machine learning and novel feature refining algorithms, the most accurate models could provide near-perfect classification accuracies using very few (close to ten) low-expression genes.

Computational augmentation of neoplastic endometrial glands in digital pathology displays

“…Pre‐analytic noise reduction is commonly applied in a wide range of computational data. For example, in microarray data it is common to pre‐select genes based on signal noise and strength [20,21], and, in image analysis, neural networks accuracy can be improved by compressing input images, including in histopathology applications [22,23]. We hypothesized that small glands do not contain enough information to distinguish neoplastic‐EIN and background‐NL classes and that they were thus adding noise to the classification process.…”

A genetic algorithm approach for predicting ribonucleic acid sequencing data classification using KNN and decision tree

“…scPred RNA-seq datasets showed high accuracy [12]. RNA-DNA machine learning analysis was proposed to indicate small genome expression to influence PAH ailment, feature selection algorithm was proposed to classify relevant genes with an outcome that reveals unique PAH [13].…”

Predicting RNA-seq data using genetic algorithm and ensemble classification algorithms

“…A supervised classification RNA-Seq data model was presented using a simplified procedure with an infinite accurate classification of single cells, merging independent feature selection dimensional reduced model and machine learning procedure. Sc-Pred RNA-seq dataset from pancreatic muscle, mixing dendritic cells, colorectal tumour material elimination, and mononuclear cells were applied and presented a high-performance accuracy [12]. RNA-DNA machine learning investigation showing low genome expressions influencing PAH ailment was proposed, using an advanced feature selection and enhanced machine learning procedure for classifying irrelevant but very beneficial genes, the results displayed clusters of unrelated expression genes that reveal predicting and distinctive transformed PAH [13].…”