Machine-Learned Association of Next-Generation Sequencing-Derived Variants in Thermosensitive Ion Channels Genes with Human Thermal Pain Sensitivity Phenotypes

Abstract

Genetic association studies have shown their usefulness in assessing the role of ion channels in human thermal pain perception. We used machine learning to construct a complex phenotype from pain thresholds to thermal stimuli and associate it with the genetic information derived from the next-generation sequencing (NGS) of 15 ion channel genes which are involved in thermal perception, including ASIC1, ASIC2, ASIC3, ASIC4, TRPA1, TRPC1, TRPM2, TRPM3, TRPM4, TRPM5, TRPM8, TRPV1, TRPV2, TRPV3, and TRPV4. Phenotypic information was complete in 82 subjects and NGS genotypes were available in 67 subjects. A network of artificial neurons, implemented as emergent self-organizing maps, discovered two clusters characterized by high or low pain thresholds for heat and cold pain. A total of 1071 variants were discovered in the 15 ion channel genes. After feature selection, 80 genetic variants were retained for an association analysis based on machine learning. The measured performance of machine learning-mediated phenotype assignment based on this genetic information resulted in an area under the receiver operating characteristic curve of 77.2%, justifying a phenotype classification based on the genetic information. A further item categorization finally resulted in 38 genetic variants that contributed most to the phenotype assignment. Most of them (10) belonged to the TRPV3 gene, followed by TRPM3 (6). Therefore, the analysis successfully identified the particular importance of TRPV3 and TRPM3 for an average pain phenotype defined by the sensitivity to moderate thermal stimuli.

Interpretation of cluster structures in pain‐related phenotype data using explainable artificial intelligence (XAI)

“…Following the cluster interpretation from the contribution of the variables submitted to clustering, which was the aim of the present analyses, the clusters are open for further scientific investigations, e.g. on the role of genetic factors, which was analysed on another clustering in the same data set (Lötsch et al., 2020), or on gender differences. The latter were not statistically significant in the present cluster solution, as a χ 2 test (Pearson, 1900) showed (χ 2 = 0.33639, df = 1, p = 0.5619).…”

“…A suitable pain‐related data set was available from a recent study on patterns in parameters of quantitative sensory testing (QST) in response to harmful thermal stimuli (Lötsch et al., 2017, 2020). However, its cluster structure was initially unknown and had to be determined using a clustering method.…”

“…All test persons had given written consent to the study procedures including genotyping. The details of the study have already been reported in detail (Lötsch et al., 2017, 2020).…”