-
Notifications
You must be signed in to change notification settings - Fork 17
/
STAARpipelineSummary_Gene_Centric_Coding.r
71 lines (64 loc) · 2.84 KB
/
STAARpipelineSummary_Gene_Centric_Coding.r
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
##########################################################
# Summarization and visualization of gene-centric
# coding analysis results using STAARpipelineSummary
# Xihao Li, Zilin Li
# Initiate date: 11/04/2021
# Current date: 03/10/2022
##########################################################
rm(list=ls())
gc()
## load required packages
library(gdsfmt)
library(SeqArray)
library(SeqVarTools)
library(STAAR)
library(STAARpipeline)
library(STAARpipelineSummary)
###########################################################
# User Input
###########################################################
## aGDS directory
agds_dir <- get(load("/path_to_the_file/agds_dir.Rdata"))
## Known loci
known_loci <- get(load("/path_to_the_file/TOPMed_F5_LDL_known_loci_individual_analysis_genome_LD_pruning.Rdata"))
## Null model
obj_nullmodel <- get(load("/path_to_the_file/obj_nullmodel.Rdata"))
## results path
input_path <- "/path_to_the_results_file/"
output_path <- input_path
## number of jobs
gene_centric_coding_jobs_num <- 381
## results name
gene_centric_results_name <- "TOPMed_F5_LDL_Coding"
## QC_label
QC_label <- "annotation/filter"
## geno_missing_imputation
geno_missing_imputation <- "mean"
## variant_type
variant_type <- "SNV"
## method_cond
method_cond <- "optimal"
## alpha level
alpha <- 5E-07
## Annotation_dir
Annotation_dir <- "annotation/info/FunctionalAnnotation"
## Annotation channel
Annotation_name_catalog <- get(load("/path_to_the_file/Annotation_name_catalog.Rdata"))
# Or equivalently
# Annotation_name_catalog <- read.csv("/path_to_the_file/Annotation_name_catalog.csv")
## Use_annotation_weights
Use_annotation_weights <- TRUE
## Annotation name
Annotation_name <- c("CADD","LINSIGHT","FATHMM.XF","aPC.EpigeneticActive","aPC.EpigeneticRepressed","aPC.EpigeneticTranscription",
"aPC.Conservation","aPC.LocalDiversity","aPC.Mappability","aPC.TF","aPC.Protein")
###########################################################
# Main Function
###########################################################
Gene_Centric_Coding_Results_Summary(agds_dir=agds_dir,gene_centric_coding_jobs_num=gene_centric_coding_jobs_num,
input_path=input_path,output_path=output_path,gene_centric_results_name=gene_centric_results_name,
obj_nullmodel=obj_nullmodel,known_loci=known_loci,
method_cond=method_cond,
QC_label=QC_label,geno_missing_imputation=geno_missing_imputation,variant_type=variant_type,
Annotation_dir=Annotation_dir,Annotation_name_catalog=Annotation_name_catalog,
Use_annotation_weights=Use_annotation_weights,Annotation_name=Annotation_name,
alpha=alpha,manhattan_plot=TRUE,QQ_plot=TRUE)