From c79d9fdcc6fbf769cdf352f336c9916376ae4fed Mon Sep 17 00:00:00 2001
From: Eva Holtkamp <eva.holtkamp@gmx.de>
Date: Tue, 10 Oct 2023 16:32:39 +0200
Subject: [PATCH] update config

---
 deeprvat/seed_gene_discovery/config.yaml | 62 +++++++++++++++---------
 1 file changed, 38 insertions(+), 24 deletions(-)

diff --git a/deeprvat/seed_gene_discovery/config.yaml b/deeprvat/seed_gene_discovery/config.yaml
index 444d0635..41bcafed 100644
--- a/deeprvat/seed_gene_discovery/config.yaml
+++ b/deeprvat/seed_gene_discovery/config.yaml
@@ -1,26 +1,39 @@
 phenotypes:
   - Apolipoprotein_A
-#   - Apolipoprotein_B
-#   - Calcium
-#   - Cholesterol
-#   - HDL_cholesterol
-#   - IGF_1
-#   - LDL_direct
-#   - SHBG
-#   - Total_bilirubin
-#   - Triglycerides
-#   - Urate
-#   - Standing_height
-#   - Lymphocyte_percentage
-#   - Mean_platelet_thrombocyte_volume
-#   - Mean_corpuscular_volume
-#   - Mean_reticulocyte_volume
-#   - Neutrophill_count
-#   - Platelet_count
-#   - Platelet_crit
-#   - Platelet_distribution_width
-#   - Red_blood_cell_erythrocyte_count
-
+  - Apolipoprotein_B
+  - Calcium
+  - Cholesterol
+  - HDL_cholesterol
+  - IGF_1
+  - LDL_direct
+  - SHBG
+  - Total_bilirubin
+  - Triglycerides
+  - Urate
+  - Standing_height
+  - Lymphocyte_percentage
+  - Mean_platelet_thrombocyte_volume
+  - Mean_corpuscular_volume
+  - Mean_reticulocyte_volume
+  - Neutrophill_count
+  - Platelet_count
+  - Platelet_crit
+  - Platelet_distribution_width
+  - Red_blood_cell_erythrocyte_count
+  - Body_mass_index_BMI
+  - Glucose
+  - Vitamin_D
+  - Albumin
+  - Total_protein
+  - Cystatin_C
+  - Gamma_glutamyltransferase
+  - Alkaline_phosphatase
+  - Creatinine
+  - Whole_body_fat_free_mass 
+  - Forced_expiratory_volume_in_1_second_FEV1
+  - Glycated_haemoglobin_HbA1c
+  - WHR_Body_mass_index_BMI_corrected
+  
 variant_types:
     - missense
     - plof
@@ -42,7 +55,7 @@ test_config:
     neglect_homozygous: False
     collapse_method: sum #collapsing method for burde
     var_weight_function: beta_maf 
-
+    min_mac: 10
 variant_file: variants.parquet
 
 data:
@@ -82,7 +95,7 @@ data:
             - MAF
             - is_plof
             - Consequence_missense_variant
-        gene_file: protein_coding_genes.parquet
+        gene_file: genes.parquet
         use_common_variants: False
         use_rare_variants: True
         rare_embedding:
@@ -92,10 +105,11 @@ data:
                     - MAF
                     - is_plof
                     - Consequence_missense_variant
-                gene_file: protein_coding_genes.parquet
+                gene_file: genes.parquet
                 verbose: True
         verbose: True
     dataloader_config:
         num_workers: 10
         #batch_size: 20
 
+