Transfer learning enables prediction of CYP2D6 haplotype function

Abstract

Cytochrome P450 2D6 (CYP2D6) is a highly polymorphic gene whose protein product metabolizes more than 20% of clinically used drugs. Genetic variations in CYP2D6 are responsible for interindividual heterogeneity in drug response that can lead to drug toxicity and ineffective treatment, making CYP2D6 one of the most important pharmacogenes. Prediction of CYP2D6 phenotype relies on curation of literature-derived functional studies to assign a functional status to CYP2D6 haplotypes. As the number of large-scale sequencing efforts grows, new haplotypes continue to be discovered, and assignment of function is challenging to maintain. To address this challenge, we have trained a convolutional neural network to predict functional status of CYP2D6 haplotypes, called Hubble.2D6. Hubble.2D6 predicts haplotype function from sequence data and was trained using two pre-training steps with a combination of real and simulated data. We find that Hubble.2D6 predicts CYP2D6 haplotype functional status with 88% accuracy in a held-out test set and explains 47.5% of the variance in in vitro functional data among star alleles with unknown function. Hubble.2D6 may be a useful tool for assigning function to haplotypes with uncurated function, and used for screening individuals who are at risk of being poor metabolizers.

Global spectrum of population‐specific common missense variation in cytochrome P450 pharmacogenes

“…It is also important to study relevant single variants as part of a haplotype in addition to their effects in isolation (e.g., for CYP2C9, CYP2D6, and CYP2C19 see Muroi et al, 2014; Niinuma et al, 2014; Takahashi et al, 2015) because some variants co‐exist with other genetic variation in complex haplotypes (Table 2) and may exert different effects in combination. These studies are crucial for haplotype function assignments in PharmGKB and PharmVar and may also be used to build better haplotype‐level pharmacogene prediction tools as has been done for CYP2D6 (McInnes et al, 2020).…”

Opportunities and challenges for the computational interpretation of rare variation in clinically important genes

“… 78 , 79 Several methods have been developed specifically for the evaluation of alleles in pharmacogenes, namely CYP2D6 (MIM: 124030 ). 80 , 81 These purpose-built models outperform existing methods and are capable of assessing the impact of any combination of variants observed in a haplotype rather than single variants. One major drawback of deep learning is that it requires an immense amount of data in order to estimate the large number of parameters required for good performance.…”

Genomewide Association Studies in Pharmacogenomics

“…All rights reserved machine learning which may someday increase the clinical utility of rare variants as they are detected in patients. [96][97][98]…”

“…Two examples worth mentioning about followed up from initial PGx GWAS are the used of multiple functional genomics studies to discover additional mechanism of drug action of anastrozole 93 and the utilization of massively parallel variant function assays to determine 3,000 missense variants in NUDT15 94 and more than 6,000 missense variants in CYP2C9 95 . This increase in functional data enables computational prediction of variant function using approaches, such as machine learning, which may someday increase the clinical utility of rare variants as they are detected in patients 96–98 …”