TEDDY_logistic_humann.Rmd

---
title: "TEDDY_species_pathways_binary_models"
author: "Sam Zimmerman"
date: "2023-05-24"
output: html_document
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
```

```{bash}
#run lasso binary regression 

/n/data1/joslin/icrb/kostic/szimmerman/TEDDY_analysis/models_input_files_parsed_v4_pathway_no_header.csv

/n/data1/joslin/icrb/kostic/szimmerman/TEDDY_analysis/models_input_files_parsed_v4_species_no_header.csv

split -l 50 /n/data1/joslin/icrb/kostic/szimmerman/TEDDY_analysis/models_input_files_parsed_v4_pathway_no_header.csv models_input_files_parsed_v4_pathway_no_header_before_condition_

split -l 50 /n/data1/joslin/icrb/kostic/szimmerman/TEDDY_analysis/models_input_files_parsed_v4_species_no_header.csv models_input_files_parsed_v4_species_no_header_before_condition_

sbatch -n 1 -c 1 --mem=5G -p short -t 0-01:00 scripts/run_lasso_binary_bulk.bash models_input_files_parsed_v4_pathway_no_header_before_condition_aa microbiome NA all 1 NA

for x in models_input_files_parsed_v4_pathway_no_header_before_condition_*
do
sbatch -n 1 -c 1 --mem=5G -p short -t 0-01:00 scripts/run_lasso_binary_bulk.bash ${x} microbiome NA all 1 NA
done

for x in models_input_files_parsed_v4_species_no_header_before_condition_*
do
sbatch -n 1 -c 1 --mem=5G -p short -t 0-01:00 scripts/run_lasso_binary_bulk.bash ${x} microbiome NA all 1 NA
done

```

```{bash}
split -l 10 input_files_ttest_sig_v4_pathways_species.csv input_files_ttest_sig_v4_pathways_species_

for x in input_files_ttest_sig_v4_pathways_species_*
do
sbatch -n 1 -c 1 --mem=5G -p short -t 0-01:00 scripts/run_lasso_binary_bulk.bash ${x} microbiome NA ttest_sig 1 NA
done

# random forest

sbatch -n 1 -c 1 --mem=5G -p short -t 0-04:00 scripts/run_rf_bulk.bash input_files_ttest_sig_v4_pathways_species_aa microbiome NA ttest_sig 1 NA


for x in input_files_ttest_sig_v4_pathways_species_*
do
sbatch -n 1 -c 1 --mem=5G -p short -t 0-04:00 scripts/run_rf_bulk.bash ${x} microbiome NA ttest_sig 1 NA
done

Rscript scripts/find_failed_job_folders.R /n/data1/joslin/icrb/kostic/szimmerman/TEDDY_analysis/input_files_ttest_sig_v4_pathways_species.csv _speciesoutput_random_forest_binary_NA_loss_microbiome_selection_method_ttest_sig_feature_list_microbiome.rds failed_rf_binary_species_microbiome.txt

Rscript scripts/find_failed_job_folders.R /n/data1/joslin/icrb/kostic/szimmerman/TEDDY_analysis/input_files_ttest_sig_v4_pathways_species.csv _pathwayoutput_random_forest_binary_NA_loss_microbiome_selection_method_ttest_sig_feature_list_microbiome.rds failed_rf_binary_pathway_microbiome.txt

cat failed_rf_binary_species_microbiome.txt failed_rf_binary_pathway_microbiome.txt > failed_rf_binary_species_pathway_microbiome.txt

split -l 10 failed_rf_binary_species_pathway_microbiome.txt failed_rf_binary_species_pathway_microbiome_

for x in failed_rf_binary_species_pathway_microbiome_*
do
sbatch -n 1 -c 1 --mem=5G -p short -t 0-04:00 scripts/run_rf_bulk.bash ${x} microbiome NA ttest_sig 1 NA
done

```

#Now run models but combine autoantibodies and such with microbiome genes

```{bash}
grep -v "healthy_pre-t1d" /n/data1/joslin/icrb/kostic/szimmerman/TEDDY_analysis/models_input_files_parsed_v4_species_no_header.csv > /n/data1/joslin/icrb/kostic/szimmerman/TEDDY_analysis/models_input_files_parsed_v4_species_no_header_no_healthy_pret1d.csv

grep "healthy_pre-t1d" /n/data1/joslin/icrb/kostic/szimmerman/TEDDY_analysis/models_input_files_parsed_v4_species_no_header.csv > /n/data1/joslin/icrb/kostic/szimmerman/TEDDY_analysis/models_input_files_parsed_v4_species_no_header_healthy_pret1d.csv

grep -v "healthy_pre-t1d" /n/data1/joslin/icrb/kostic/szimmerman/TEDDY_analysis/models_input_files_parsed_v4_pathway_no_header.csv > /n/data1/joslin/icrb/kostic/szimmerman/TEDDY_analysis/models_input_files_parsed_v4_pathway_no_header_no_healthy_pret1d.csv

grep "healthy_pre-t1d" /n/data1/joslin/icrb/kostic/szimmerman/TEDDY_analysis/models_input_files_parsed_v4_pathway_no_header.csv > /n/data1/joslin/icrb/kostic/szimmerman/TEDDY_analysis/models_input_files_parsed_v4_pathway_no_header_healthy_pret1d.csv

split -l 50 /n/data1/joslin/icrb/kostic/szimmerman/TEDDY_analysis/models_input_files_parsed_v4_species_no_header_no_healthy_pret1d.csv models_input_files_parsed_v4_species_no_header_no_healthy_pret1d_

split -l 50 /n/data1/joslin/icrb/kostic/szimmerman/TEDDY_analysis/models_input_files_parsed_v4_species_no_header_healthy_pret1d.csv models_input_files_parsed_v4_species_no_header_healthy_pret1d_

split -l 50 /n/data1/joslin/icrb/kostic/szimmerman/TEDDY_analysis/models_input_files_parsed_v4_pathway_no_header_no_healthy_pret1d.csv models_input_files_parsed_v4_pathway_no_header_no_healthy_pret1d_

split -l 50 /n/data1/joslin/icrb/kostic/szimmerman/TEDDY_analysis/models_input_files_parsed_v4_pathway_no_header_healthy_pret1d.csv models_input_files_parsed_v4_pathway_no_header_healthy_pret1d_

#run lasso

for x in models_input_files_parsed_v4_species_no_header_no_healthy_pret1d_*
do
sbatch -n 1 -c 1 --mem=5G -p short -t 0-01:00 scripts/run_lasso_binary_bulk.bash ${x} microbiome,fdr,grs2 fdr,grs2 all 1 NA
done

for x in models_input_files_parsed_v4_species_no_header_no_healthy_pret1d_*
do
sbatch -n 1 -c 1 --mem=5G -p short -t 0-01:00 scripts/run_lasso_binary_bulk.bash ${x} microbiome,fdr,grs2,Sex fdr,grs2,Sex all 1 NA
done


for x in models_input_files_parsed_v4_species_no_header_healthy_pret1d_*
do
sbatch -n 1 -c 1 --mem=5G -p short -t 0-01:00 scripts/run_lasso_binary_bulk.bash ${x} microbiome,number_autoantibodies,fdr,grs2 number_autoantibodies,fdr,grs2 all 1 NA
done

for x in models_input_files_parsed_v4_species_no_header_healthy_pret1d_*
do
sbatch -n 1 -c 1 --mem=5G -p short -t 0-01:00 scripts/run_lasso_binary_bulk.bash ${x} microbiome,fdr,grs2 fdr,grs2 all 1 NA
done


for x in models_input_files_parsed_v4_species_no_header_healthy_pret1d_*
do
sbatch -n 1 -c 1 --mem=5G -p short -t 0-01:00 scripts/run_lasso_binary_bulk.bash ${x} microbiome,number_autoantibodies,fdr,grs2,Sex number_autoantibodies,fdr,grs2,Sex all 1 NA
done


for x in models_input_files_parsed_v4_pathway_no_header_no_healthy_pret1d_*
do
sbatch -n 1 -c 1 --mem=5G -p short -t 0-01:00 scripts/run_lasso_binary_bulk.bash ${x} microbiome,fdr,grs2 fdr,grs2 all 1 NA
done

for x in models_input_files_parsed_v4_pathway_no_header_no_healthy_pret1d_*
do
sbatch -n 1 -c 1 --mem=5G -p short -t 0-01:00 scripts/run_lasso_binary_bulk.bash ${x} microbiome,fdr,grs2,Sex fdr,grs2,Sex all 1 NA
done


for x in models_input_files_parsed_v4_pathway_no_header_healthy_pret1d_*
do
sbatch -n 1 -c 1 --mem=5G -p short -t 0-01:00 scripts/run_lasso_binary_bulk.bash ${x} microbiome,number_autoantibodies,fdr,grs2 number_autoantibodies,fdr,grs2 all 1 NA
done

for x in models_input_files_parsed_v4_pathway_no_header_healthy_pret1d_*
do
sbatch -n 1 -c 1 --mem=5G -p short -t 0-01:00 scripts/run_lasso_binary_bulk.bash ${x} microbiome,fdr,grs2 fdr,grs2 all 1 NA
done


for x in models_input_files_parsed_v4_pathway_no_header_healthy_pret1d_*
do
sbatch -n 1 -c 1 --mem=5G -p short -t 0-01:00 scripts/run_lasso_binary_bulk.bash ${x} microbiome,number_autoantibodies,fdr,grs2,Sex number_autoantibodies,fdr,grs2,Sex all 1 NA
done

```

#Now do the same thing but with ttest_sig

```{bash}
grep -v "healthy_pre-t1d" /n/data1/joslin/icrb/kostic/szimmerman/TEDDY_analysis/input_files_ttest_sig_v4_pathways_species.csv > /n/data1/joslin/icrb/kostic/szimmerman/TEDDY_analysis/input_files_ttest_sig_v4_pathways_species_no_healthyT1d.csv

grep "healthy_pre-t1d" /n/data1/joslin/icrb/kostic/szimmerman/TEDDY_analysis/input_files_ttest_sig_v4_pathways_species.csv > /n/data1/joslin/icrb/kostic/szimmerman/TEDDY_analysis/input_files_ttest_sig_v4_pathways_species_healthyT1d.csv

split -l 10 input_files_ttest_sig_v4_pathways_species_no_healthyT1d.csv input_files_ttest_sig_v4_pathways_species_no_healthyT1d_

split -l 10 input_files_ttest_sig_v4_pathways_species_healthyT1d.csv input_files_ttest_sig_v4_pathways_species_healthyT1d_

for x in input_files_ttest_sig_v4_pathways_species_no_healthyT1d_*
do
sbatch -n 1 -c 1 --mem=5G -p short -t 0-01:00 scripts/run_lasso_binary_bulk.bash ${x} microbiome,fdr,grs2 fdr,grs2 ttest_sig 1 NA
done

for x in input_files_ttest_sig_v4_pathways_species_no_healthyT1d_*
do
sbatch -n 1 -c 1 --mem=5G -p short -t 0-01:00 scripts/run_lasso_binary_bulk.bash ${x} microbiome,fdr,grs2,Sex fdr,grs2,Sex ttest_sig 1 NA
done


for x in input_files_ttest_sig_v4_pathways_species_healthyT1d_*
do
sbatch -n 1 -c 1 --mem=5G -p short -t 0-01:00 scripts/run_lasso_binary_bulk.bash ${x} microbiome,number_autoantibodies,fdr,grs2 number_autoantibodies,fdr,grs2 ttest_sig 1 NA
done

for x in input_files_ttest_sig_v4_pathways_species_healthyT1d_*
do
sbatch -n 1 -c 1 --mem=5G -p short -t 0-01:00 scripts/run_lasso_binary_bulk.bash ${x} microbiome,fdr,grs2 fdr,grs2 ttest_sig 1 NA
done


for x in input_files_ttest_sig_v4_pathways_species_healthyT1d_*
do
sbatch -n 1 -c 1 --mem=5G -p short -t 0-01:00 scripts/run_lasso_binary_bulk.bash ${x} microbiome,number_autoantibodies,fdr,grs2,Sex number_autoantibodies,fdr,grs2,Sex ttest_sig 1 NA
done


for x in input_files_ttest_sig_v4_pathways_species_no_healthyT1d_*
do
sbatch -n 1 -c 1 --mem=5G -p short -t 0-04:00 scripts/run_rf_bulk.bash ${x} microbiome,fdr,grs2 fdr,grs2 ttest_sig 1 NA
done

for x in input_files_ttest_sig_v4_pathways_species_no_healthyT1d_*
do
sbatch -n 1 -c 1 --mem=5G -p short -t 0-04:00 scripts/run_rf_bulk.bash ${x} microbiome,fdr,grs2 fdr,grs2 ttest_sig 1 NA
done


for x in input_files_ttest_sig_v4_pathways_species_healthyT1d_*
do
sbatch -n 1 -c 1 --mem=5G -p short -t 0-04:00 scripts/run_rf_bulk.bash ${x} microbiome,number_autoantibodies,fdr,grs2 number_autoantibodies,fdr,grs2 ttest_sig 1 NA
done

for x in input_files_ttest_sig_v4_pathways_species_healthyT1d_*
do
sbatch -n 1 -c 1 --mem=5G -p short -t 0-04:00 scripts/run_rf_bulk.bash ${x} microbiome,fdr,grs2 fdr,grs2 ttest_sig 1 NA
done


for x in input_files_ttest_sig_v4_pathways_species_healthyT1d_*
do
sbatch -n 1 -c 1 --mem=5G -p short -t 0-04:00 scripts/run_rf_bulk.bash ${x} microbiome,number_autoantibodies,fdr,grs2,Sex number_autoantibodies,fdr,grs2,Sex ttest_sig 1 NA
done


```