PEDIA: prioritization of exome data by image analysis

Authors

Hsieh TC1,2,3, Mensah MA2,3, Pantel JT1,2,3, Aguilar D4, Bar O5, Bayat A6, Becerra-Solano L7, Bentzen HB8, Biskup S9, Borisov O1, Braaten O10, Ciaccio C11, Coutelier M2, Cremer K12, Danyel M2, Daschkey S13, Eden HD5, Devriendt K14, Wilson S15, Douzgou S16,17, Đukić D1, Ehmke N2, Fauth C18, Fischer-Zirnsak B2, Fleischer N5, Gabriel H19, Graul-Neumann L2, Gripp KW20, Gurovich Y5, Gusina A21, Haddad N2, Hajjir N2, Hanani Y5, Hertzberg J2, Hoertnagel K9, Howell J22, Ivanovski I23, Kaindl A24, Kamphans T25, Kamphausen S26, Karimov C27, Kathom H28, Keryan A27, Knaus A1, Köhler S29, Kornak U2, Lavrov A30, Leitheiser M2, Lyon GJ31, Mangold E32, Reina PM33, Carrascal AM34, Mitter D35, Herrador LM36, Nadav G5, Nöthen M12, Orrico A37, Ott CE2, Park K38, Peterlin B39, Pölsler L18, Raas-Rothschild A40, Randolph L27, Revencu N41, Fagerberg CR42, Robinson PN43, Rosnev S2, Rudnik S18, Rudolf G39, Schatz U18, Schossig A18, Schubach M3, Shanoon O5, Sheridan E44, Smirin-Yosef P45, Spielmann M2, Suk EK46, Sznajer Y47, Thiel CT48, Thiel G46, Verloes A49, Vrecar I39, Wahl D50, Weber I18, Winter K2, Wiśniewska M51, Wollnik B52, Yeung MW1, Zhao M2, Zhu N2, Zschocke J18, Mundlos S2, Horn D2, Krawitz PM53
  1. Institute of Genomic Statistics and Bioinformatics, University of Bonn, Bonn, Germany.
  2. Charité – Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin, and Berlin Institute of Health, Institute of Medical Genetics and Human Genetics, Berlin, Germany.
  3. Berlin Institute of Health (BIH), Berlin, Germany.
  4. Centro de Cáncer de Mama, Tecnológico de Monterrey, Monterrey, Mexico.
  5. FDNA Inc., Boston, MA, USA.
  6. Rigshospitalet, Department of Neurology, Copenhagen, Denmark.
  7. Unidad de Investigación Médica en Medicina Reproductiva, Mexico City, Mexico.
  8. Centre for Medical Ethics, Faculty of Medicine and the Norwegian Research Center for Computers and Law, Faculty of Law, University of Oslo, Oslo, Norway.
  9. CeGaT GmbH, Tübingen, Germany.
  10. Faculty of Medicine, Department of Medical Genetics, University of Oslo, Blindern, Oslo, Norway.
  11. Developmental Neurology Unit, Fondazione IRCCS Istituto Neurologico Carlo Besta, Milan, Italy.
  12. Department of Human Genetics, University Hospital of Bonn, Bonn, Germany.
  13. Medical Faculty, Heinrich Heine University Düsseldorf, Düsseldorf, Germany.
  14. Department of Human Genetics, KU Leuven, Leuven, Belgium.
  15. Department of Human Genetics, University of Hamburg, Hamburg, Germany.
  16. Manchester Centre for Genomic Medicine, St Mary’s Hospital, Central Manchester University Hospitals NHS Foundation Trust Manchester Academic Health Sciences Centre, Manchester, United Kingdom.
  17. School of Biological Sciences, Division of Evolution and Genomic Sciences, University of Manchester, Manchester, United Kingdom.
  18. Division of Human Genetics, Medical University of Innsbruck, Innsbruck, Austria.
  19. Center for Genomics and Transcriptomics, Eberhard Karls University of Tübingen, Tübingen, Germany.
  20. A. I. duPont Hospital for Children, Wilmington, DE, USA.
  21. National Research and Applied Medicine Centre ‚Mother and Child“, Minsk, Belarus.
  22. Lineagen, Salt Lake City, Utah, USA.
  23. Clinical Genetics Unit, AUSL-IRCCS Reggio Emilia, Reggio Emilia, Italy.
  24. Center for Chronically Sick Children (Sozialpädiatrisches Zentrum, SPZ), Charité – Universitätsmedizin Berlin, Berlin, Germany.
  25. GeneTalk, Bonn, Germany.
  26. University Hospital Magdeburg, Magdeburg, Germany.
  27. Children’s Hospital of Los Angeles, Los Angeles, CA, USA.
  28. Department of Pediatrics, Medical University of Sofia, Sofia, Bulgaria.
  29. Charité – Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin, and Berlin Institute of Health, NeuroCure Clinical Research Center, Berlin, Germany.
  30. Research Institute of Medical Genetics of Russian Academy of Medical Sciences, Moscow, Russian Federation.
  31. Stanley Institute for Cognitive Genomics, Cold Spring Harbor Laboratory, Woodbury, New York, USA.
  32. Institute of Human Genetics, University of Bonn, Bonn, Germany.
  33. Hospital General Universitario De Valencia, Valencia, Spain.
  34. Hospital General De Requena, Servicio Pediatría, Spain.
  35. University Hospital Leipzig, Leipzig, Germany.
  36. Hospital Universitario Miguel Servet, Zaragoza, Spain.
  37. Azienda Ospedaliera Universitaria Senese, Siena, Italy.
  38. Department of Pediatrics and Neurology, University of Colorado School of Medicine, Colorado, Aurora, USA.
  39. Clinical Institute of Medical Genetics, University Medical Centre Ljubljana, Ljubljana, Slovenia.
  40. The Danek Gertner Institute of Human Genetics, Sheba Medical Center, Tel-Hashomer, Israel.
  41. Center for Human Genetics, University Hospital, Université Catholique de Louvain, Brussels, Belgium.
  42. Odense University Hospital, Odense, Denmark.
  43. The Jackson Laboratory for Genomic Medicine, Farmington, CT, USA.
  44. School of Medicine, University of Leeds, Leeds, United Kingdom.
  45. Genomic Bioinformatics Laboratory, Department of Molecular Biology, Ariel University, Ariel, Israel.
  46. Center for Prenatal Diagnosis and Human Genetics, Berlin, Germany.
  47. Cliniques universitaires Saint Luc UCL, Bruxelles, Belgium.
  48. Institute of Human Genetics, Friedrich-Alexander-Universität Erlangen-Nürnberg FAU, Erlangen, Erlangen, Germany.
  49. Hopital Robert Debré, Paris, France.
  50. Center for Human Genetics and Laboratory Diagnostics Dr. Klein, Dr. Rost and Colleagues, Martinsried, Germany.
  51. Poznañ University of Medical Sciences, Poznañ, Poland.
  52. University Medical Center Göttingen, Göttingen, Germany.
  53. Institute of Genomic Statistics and Bioinformatics, University of Bonn, Bonn, Germany. pkrawitz@uni-bonn.de.

Abstract

PURPOSE:

Phenotype information is crucial for the interpretation of genomic variants. So far it has only been accessible for bioinformatics workflows after encoding into clinical terms by expert dysmorphologists.

METHODS:

Here, we introduce an approach driven by artificial intelligence that uses portrait photographs for the interpretation of clinical exome data. We measured the value added by computer-assisted image analysis to the diagnostic yield on a cohort consisting of 679 individuals with 105 different monogenic disorders. For each case in the cohort we compiled frontal photos, clinical features, and the disease-causing variants, and simulated multiple exomes of different ethnic backgrounds.

RESULTS:

The additional use of similarity scores from computer-assisted analysis of frontal photos improved the top 1 accuracy rate by more than 20-89% and the top 10 accuracy rate by more than 5-99% for the disease-causing gene.

CONCLUSION:

Image analysis by deep-learning algorithms can be used to quantify the phenotypic similarity (PP4 criterion of the American College of Medical Genetics and Genomics guidelines) and to advance the performance of bioinformatics pipelines for exome analysis.

KEYWORDS:

computer vision; deep learning; dysmorphology; exome diagnostics; variant prioritization

References