Gene‐Specific Variant Classifier (DPYD‐Varifier) to Identify Deleterious Alleles of Dihydropyrimidine Dehydrogenase

Deleterious variants in dihydropyrimidine dehydrogenase (DPD, DPYD gene) can be highly predictive of clinical toxicity to the widely prescribed chemotherapeutic 5‐fluorouracil (5‐FU). However, there are very limited data pertaining to the functional consequences of the >450 reported no‐synonymous DPYD variants. We developed a DPYD‐specific variant classifier (DPYD‐Varifier) using machine learning and in vitro functional data for 156 missense DPYD variants. The developed model showed 85% accuracy and outperformed other in silico prediction tools. An examination of feature importance within the model provided additional insight into functional aspects of the DPD protein relevant to 5‐FU toxicity. In the absence of clinical data for unstudied variants, prediction tools like DPYD‐Varifier have great potential to individualize medicine and improve the clinical decision‐making process.

[1]  Russ B. Altman,et al.  Improving the prediction of disease-related variants using protein three-dimensional structure , 2011, BMC Bioinformatics.

[2]  J. Novotný,et al.  Influence of dihydropyrimidine dehydrogenase gene (DPYD) coding sequence variants on the development of fluoropyrimidine-related toxicity in patients with high-grade toxicity and patients with excellent tolerance of fluoropyrimidine-based chemotherapy. , 2009, Neoplasma.

[3]  R. Diasio,et al.  Novel Deleterious Dihydropyrimidine Dehydrogenase Variants May Contribute to 5‐Fluorouracil Sensitivity in an East African Population , 2017, Clinical pharmacology and therapeutics.

[4]  Jérôme Lane,et al.  IMGT®, the international ImMunoGeneTics information system® , 2004, Nucleic Acids Res..

[5]  Gabriel L. Butterfield,et al.  Comparative functional analysis of DPYD variants of potential clinical relevance to dihydropyrimidine dehydrogenase activity. , 2014, Cancer research.

[6]  A. V. van Kuilenburg,et al.  Intragenic deletions and a deep intronic mutation affecting pre-mRNA splicing in the dihydropyrimidine dehydrogenase gene as novel mechanisms causing 5-fluorouracil toxicity , 2010, Human Genetics.

[7]  Itay Mayrose,et al.  ConSurf 2016: an improved methodology to estimate and visualize evolutionary conservation in macromolecules , 2016, Nucleic Acids Res..

[8]  Daniel G. MacArthur,et al.  The ExAC browser: displaying reference data information from over 60 000 exomes , 2016, bioRxiv.

[9]  R. Diasio,et al.  A DPYD variant (Y186C) in individuals of African ancestry associated with reduced DPD enzyme activity , 2013, Clinical pharmacology and therapeutics.

[10]  Martin R. Johnson,et al.  Importance of dihydropyrimidine dehydrogenase (DPD) deficiency in patients exhibiting toxicity following treatment with 5-fluorouracil. , 2001, Advances in enzyme regulation.

[11]  C. Sander,et al.  Predicting the functional impact of protein mutations: application to cancer genomics , 2011, Nucleic acids research.

[12]  P. Vreken,et al.  Clinical implications of dihydropyrimidine dehydrogenase (DPD) deficiency in patients with severe 5-fluorouracil-associated toxicity: identification of new mutations in the DPD gene. , 2000, Clinical cancer research : an official journal of the American Association for Cancer Research.

[13]  Matthew S. Lebo,et al.  Development and validation of a computational method for assessment of missense variants in hypertrophic cardiomyopathy. , 2011, American journal of human genetics.

[14]  J. Sludden,et al.  Dihydropyrimidine dehydrogenase pharmacogenetics in patients with colorectal cancer. , 1998, British Journal of Cancer.

[15]  G. Schneider,et al.  Crystal Structure of the Productive Ternary Complex of Dihydropyrimidine Dehydrogenase with NADPH and 5-Iodouracil , 2002, The Journal of Biological Chemistry.

[16]  Martin R. Johnson,et al.  Profound dihydropyrimidine dehydrogenase deficiency resulting from a novel compound heterozygote genotype. , 2002, Clinical cancer research : an official journal of the American Association for Cancer Research.

[17]  J. Sanderson,et al.  Clinical relevance of DPYD variants c.1679T>G, c.1236G>A/HapB3, and c.1601G>A as predictors of severe fluoropyrimidine-associated toxicity: a systematic review and meta-analysis of individual patient data. , 2015, The Lancet. Oncology.

[18]  Piero Fariselli,et al.  ConSeq: the identification of functionally and structurally important residues in protein sequences , 2004, Bioinform..

[19]  G. Schneider,et al.  Crystal structure of dihydropyrimidine dehydrogenase, a major determinant of the pharmacokinetics of the anti‐cancer drug 5‐fluorouracil , 2001, The EMBO journal.

[20]  Christophe Béroud,et al.  UMD‐Predictor: A High‐Throughput Sequencing Compliant System for Pathogenicity Prediction of any Human cDNA Substitution , 2016, Human mutation.

[21]  Tal Pupko,et al.  ConSurf 2010: calculating evolutionary conservation in sequence and structure of proteins and nucleic acids , 2010, Nucleic Acids Res..

[22]  P. Stenson,et al.  Human Gene Mutation Database (HGMD®): 2003 update , 2003, Human mutation.

[23]  A. V. van Kuilenburg.  Dihydropyrimidine dehydrogenase and the efficacy and toxicity of 5-fluorouracil. , 2004, European journal of cancer.

[24]  Sabri Boughorbel,et al.  Optimal classifier for imbalanced data using Matthews Correlation Coefficient metric , 2017, PloS one.

[25]  angesichts der Corona-Pandemie,et al.  UPDATE , 1973, The Lancet.

[26]  D. Sargent,et al.  DPYD variants as predictors of 5-fluorouracil toxicity in adjuvant colon cancer treatment (NCCTG N0147). , 2014, Journal of the National Cancer Institute.

[27]  D. Sargent,et al.  Association between DPYD c.1129-5923 C>G/hapB3 and severe toxicity to 5-fluorouracil-based chemotherapy in stage III colon cancer patients: NCCTG N0147 (Alliance). , 2016, Pharmacogenetics and genomics.

[28]  Ricardo Villamarín-Salomón,et al.  ClinVar: public archive of interpretations of clinically relevant variants , 2015, Nucleic Acids Res..

[29]  Conrad C. Huang,et al.  UCSF Chimera—A visualization system for exploratory research and analysis , 2004, J. Comput. Chem..

[30]  Influence of DPYD Genetic Polymorphisms on 5-Fluorouracil Toxicities in Patients with Colorectal Cancer: A Meta-Analysis , 2014, Gastroenterology research and practice.

[31]  Kangsheng Wang,et al.  Phenotypic profiling of DPYD variations relevant to 5-fluorouracil sensitivity using real-time cellular analysis and in vitro measurement of enzyme activity. , 2013, Cancer research.

[32]  Tom R. Gaunt,et al.  Predicting the Functional, Molecular, and Phenotypic Consequences of Amino Acid Substitutions using Hidden Markov Models , 2012, Human mutation.

[33]  R. Diasio,et al.  Quantitative Contribution of rs75017182 to Dihydropyrimidine Dehydrogenase mRNA Splicing and Enzyme Activity , 2017, Clinical pharmacology and therapeutics.

[34]  Cathy H. Wu,et al.  UniProt: the Universal Protein knowledgebase , 2004, Nucleic Acids Res..

[35]  Pierre Baldi,et al.  Assessing the accuracy of prediction algorithms for classification: an overview , 2000, Bioinform..

[36]  U. Amstutz,et al.  Dihydropyrimidine dehydrogenase gene variation and severe 5-fluorouracil toxicity: a haplotype assessment. , 2009, Pharmacogenomics.

[37]  R. Greil,et al.  DPYD Genotyping to Predict Adverse Events Following Treatment With Fluorouracil-Based Adjuvant Chemotherapy in Patients With Stage III Colon Cancer: A Secondary Analysis of the PETACC-8 Randomized Clinical Trial. , 2016, JAMA oncology.

[38]  Yongwook Choi,et al.  PROVEAN web server: a tool to predict the functional effect of amino acid substitutions and indels , 2015, Bioinform..

[39]  I. Adzhubei,et al.  Predicting Functional Effect of Human Missense Mutations Using PolyPhen‐2 , 2013, Current protocols in human genetics.

[40]  Joyce A. Mitchell,et al.  Utility of gene-specific algorithms for predicting pathogenicity of uncertain gene variants , 2012, J. Am. Medical Informatics Assoc..

[41]  M. Vihinen,et al.  Performance of mutation pathogenicity prediction methods on missense variants , 2011, Human mutation.