From a53fce5455b4c718d8175ae05c443547037ffd77 Mon Sep 17 00:00:00 2001
From: Tanushree Tunstall <tanu@tunstall.in>
Date: Sat, 18 Jun 2022 14:45:48 +0100
Subject: [PATCH] added notes for running ml scripts

---
 scripts/ml/running_ml_scripts.txt | 97 +++++++++++++++++++++++++++++++
 1 file changed, 97 insertions(+)
 create mode 100644 scripts/ml/running_ml_scripts.txt

diff --git a/scripts/ml/running_ml_scripts.txt b/scripts/ml/running_ml_scripts.txt
new file mode 100644
index 0000000..ae8736f
--- /dev/null
+++ b/scripts/ml/running_ml_scripts.txt
@@ -0,0 +1,97 @@
+==================================
+# BTS data: UQ
+# Features NOT including AA index
+# Date: 30/05/2022, but reran with active_site indication column that was added lateron
+# TODO: put in folder called v1, and UQ in folder called UQ_v0 (will need to rename!)
+=================================
+./pnca_config.py
+./embb_config.py 
+./gid_config.py
+./katg_config.py
+./rpob_config.py
+
+## ./alr_config.py = NA
+# ^^^^^^^^ FIXME!
+########################################################################
+
+==================================
+# BTS data: imputed values
+# All features including AA index
+# Date: 16/05/2022
+=================================
+
+./pnca_config.py
+./embb_config.py 
+./gid_config.py
+./katg_config.py
+./rpob_config.py
+
+##./alr_config.py = NA
+########################################################################
+
+=================================
+# Split: 70/30
+# All features including AA index
+# Date: 17/05/2022 and 18/05/2022
+# captures error: 2>$1
+=================================
+
+./pnca_7030.py
+./embb_7030.py 
+# ./gid_7030.py: problems, CT values are non existing except for rouC
+./gid_7030.py 2>&1 | tee log_gid_7030.txt
+./katg_7030.py
+./rpob_7030.py
+
+##./alr_7030.py = NA
+########################################################################
+
+=================================
+# Split: 80/20
+# All features including AA index
+# Date: 17/05/2022, 18:48
+# captures error: 2>$1
+=================================
+./pnca_8020.py 2>&1 | tee log_pnca_8020.txt
+./embb_8020.py 2>&1 | tee log_embb_8020.txt
+./gid_8020.py 2>&1 | tee log_gid_8020.txt
+./katg_8020.py 2>&1 | tee log_katg_8020.txt
+./rpob_8020.py 2>&1 | tee log_rpob_8020.txt
+./alr_8020.py 2>&1 | tee log_alr_8020.txt
+
+########################################################################
+
+=================================
+# Split: scaling law
+# All features including AA index
+# Date: 17/05/2022, 18:48
+# captures error: 2>$1
+=================================
+./pnca_sl.py 2>&1 | tee log_pnca_sl.txt
+./embb_sl.py 2>&1 | tee log_embb_sl.txt
+./gid_sl.py 2>&1 | tee log_gid_sl.txt
+./katg_sl.py 2>&1 | tee log_katg_sl.txt
+./rpob_sl.py 2>&1 | tee log_rpob_sl.txt
+./alr_sl.py 2>&1 | tee log_alr_sl.txt
+
+########################################################################
+=================================
+# Split: Reverse training
+# imputed values: training set
+# actual values: blind set
+# All features including AA index
+# Date: 18/05/2022
+# captures error: 2>$1
+=================================
+./pnca_rt.py 2>&1 | tee log_pnca_rt.txt
+./embb_rt.py 2>&1 | tee log_embb_rt.txt
+./gid_rt.py 2>&1 | tee log_gid_rt.txt
+./katg_rt.py 2>&1 | tee log_katg_rt.txt
+./rpob_rt.py 2>&1 | tee log_rpob_rt.txt
+./alr_rt.py 2>&1 | tee log_alr_rt.txt
+
+
+
+
+
+