Computers in Biology and Medicine · 2024 · 10 citations · 62 references
MedicineGeneticsOncologyPharmacogeneticsPharmacogenomicsPharmacogenomics In OncologyCancer GenomicsCancer PharmacogenomicsChemotherapy PharmacogenomicsGenetic Risk AssessmentGenetic Risk PredictionPharmacogenomics In Pediatric OncologyChemotherapy-induced OtotoxicityCisplatin OtotoxicityGenerative Adversarial NetworksGenetic Risk MarkersGenetic Risk VariantsInterpretable ModelingInterpretable Neural NetworksNeural Network Modeling
Cisplatin-induced ototoxicity remains a significant concern in pediatric cancer treatment due to its permanent impact on quality of life. Previously, genetic association analyses have been performed to detect genetic variants associated with this adverse reaction. In this study, a combination of interpretable neural networks and Generative Adversarial Networks (GANs) was employed to identify genetic markers associated with cisplatin-induced ototoxicity. The applied method, BRI-Net, incorporates biological domain knowledge to define the network structure and employs adversarial training to learn an unbiased representation of the data, which is robust to known confounders. Leveraging genomic data from a cohort of 362 cisplatin-treated pediatric cancer patients recruited by the CPNDS (Canadian Pharmacogenomics Network for Drug Safety), this model revealed two statistically significant single nucleotide polymorphisms to be associated with cisplatin-induced ototoxicity. Two markers within the CERS6 (rs13022792, p-value: 3 × 10 −4 ) and TLR4 (rs10759932, p-value: 7 × 10 −4 ) genes were associated with this cisplatin-induced adverse reaction. CERS6, a ceramide synthase, contributes to elevated ceramide levels, a known initiator of apoptotic signals in mouse models of inner ear hair cells. TLR4, a pattern-recognition protein, initiates inflammation in response to cisplatin, and reduced TLR4 expression has been shown in murine hair cells to confer protection from ototoxicity. Overall, these findings provide a foundation for understanding the genetic landscape of cisplatin-induced ototoxicity, with implications for improving patient care and treatment outcomes. • BRI-Net, a neural network model, computes feature importance and causality in genomic studies. • In children treated with cisplatin, BRI-Net revealed two significant biomarkers of ototoxicity. • CERS6 rs13022792 increases the risk of cisplatin hearing loss; TLR4 rs10759932 is protective. • CER6 rs13022792 is strongly associated with ceramide elevation, triggering apoptosis in the ear. • TLR4 rs10759932 is strongly associated with initiating inflammation in response to cisplatin.
62
Damian Szklarczyk, Annika L. Gable, David Lyon et al. · Nucleic Acids Research · 2018 · 19.2K citations · Full text
Second-generation PLINK: rising to the challenge of larger and richer datasets
Christopher Chang, Carson C. Chow, Laurent CAM Tellier et al. · GigaScience · 2015 · 14K citations · Full text
Generative adversarial networks
Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza et al. · Communications of the ACM · 2020 · 13.6K citations · Full text
dbSNP: the NCBI database of genetic variation
Stephen T. Sherry · Nucleic Acids Research · 2001 · 7.8K citations · Full text
UniProt: the Universal Protein Knowledgebase in 2023
Alex Bateman, María Martin, Sandra Orchard et al. · Nucleic Acids Research · 2022 · 7K citations · Full text