Table 2 FGDD feature missing rates.
From: An explainable dataset linking facial phenotypes and genes to rare genetic diseases
Category | Sub-category | Feature Description | Missing Rate (%) |
|---|---|---|---|
Demographic Features | Patient number | Numbers of patients in this patient group | 0.00 |
Gender | Biological sex | 1.65 | |
Age | Patient’s age in years | 9.67 | |
Region | Country level geographic location | 34.43 | |
Race | Ethnic classification | 28.24 | |
Facial Phenotype Features | HPO features | 437 columns HPO terms describing facial features | 0.00 |
Variation Features | Variant gene | Gene name associated with the variant | 14.12 |
Variant details | Specific mutation information in HGVS format | 1.56 | |
Variant chromosome | Associated chromosome | 1.48 | |
Variant chromosome location | Associated chromosome location | 1.56 | |
Variant exon count | Associated chromosome exon count | 0.00 | |
Disease Features | Disease id | OMIM identifier | 39.93 |
