Retrieve high-confidence NDD genes

1 Introduction

Retrieve high-confidence NDD genes from various databases.

2 Geisinger DBD Genes Database

library(vroom)
library(tidyverse)

work_dir <- "/home/yangrui/data"
file <- "Geisinger_DBD_Genes_Database.Full_LoF_Table_Data.csv"

setwd(work_dir)
# keep high confidence candidate genes:
# 1: genes with three or more de novo pathogenic loss-of-function variants
# AR: genes with autosomal inheiritance
df <- vroom(file) %>%
    filter(Tier %in% c("1", "AR")) %>%
    arrange(Tier) %>%
    distinct()
vroom_write(df, file = "Geisinger_DBD_Genes_Database.Full_LoF_Table_Data.high_confidence.tsv")

3 SysNDD

Go to SysNDD.

library(vroom)
library(tidyverse)

work_dir <- "/home/yangrui/data"
file <- "SysNDD.sysndd_gene_table.txt"

setwd(work_dir)
# keep high confidence candidate genes: Definitive
df <- vroom(file) %>%
    filter(entities_category %in% c("Definitive")) %>%
    arrange(entities_category) %>%
    distinct()
vroom_write(df, file = "SysNDD.sysndd_gene_table.high_confidence.tsv")

4 SFARI GENE

Go to SFARI GENE.

library(vroom)
library(tidyverse)

work_dir <- "/home/yangrui/data"
file <- "ASD.SFARI_Gene.genes_04-03-2025release_04-15-2025export.csv"

setwd(work_dir)
# keep high confidence candidate genes: 1
df <- vroom(file) %>%
    filter(`gene-score` %in% c(1)) %>%
    arrange(`gene-score`) %>%
    distinct()
vroom_write(df, file = "ASD.SFARI_Gene.genes_04-03-2025release_04-15-2025export.high_confidence.tsv")

5 Gene2Phenotype

Go to Gene2Phenotype.

library(vroom)
library(tidyverse)

work_dir <- "/home/yangrui/data"
file <- "DD.Gene2Phenotype.G2P_DD_2025-04-15.csv"

setwd(work_dir)
# keep high confidence candidate genes: definitive
df <- vroom(file) %>%
    filter(confidence %in% c("definitive")) %>%
    arrange(confidence) %>%
    distinct()
vroom_write(df, file = "DD.Gene2Phenotype.G2P_DD_2025-04-15.high_confidence.tsv")

# whether a disease is NDD is recognized by AI
high_confidence_file <- "DD.Gene2Phenotype.G2P_DD_2025-04-15.high_confidence.tsv"
ndd_label_file <- "DD.Gene2Phenotype.G2P_DD_2025-04-15.high_confidence.with_NDD_flag.tsv"

high_confidence_df <- vroom(high_confidence_file)
ndd_label_df <- vroom(ndd_label_file)
df <- inner_join(high_confidence_df, ndd_label_df, by = c("disease name" = "disease_name")) %>%
    filter(is_ndd == "Yes") %>%
    distinct()
vroom_write(df, file = "NDD.Gene2Phenotype.G2P_DD_2025-04-15.high_confidence.tsv")

6 GeneTrek

Go to GeneTrek.

library(vroom)
library(tidyverse)

work_dir <- "/home/yangrui/data"
file <- "NDD.GeneTrek.genetrek_data_2024-04-26.tsv"

setwd(work_dir)
# keep high confidence candidate genes:
# High Confidence Epilepsy Genes
# or
# High Confidence NDD genes v3
df <- vroom(file) %>%
    filter((`High Confidence Epilepsy Genes` | `High Confidence NDD genes v3`) & (`Gene type` == "protein-coding")) %>%
    distinct()
vroom_write(df, file = "NDD.GeneTrek.genetrek_data_2024-04-26.high_confidence.tsv")

7 SPARK

Go to SPARK.