Merging dev - clean repo (#6)

* fix bug * change rule writing format Mg++ to Mg2+ * update uncertain hydrogen handling * fix * update source * update source * clean repo * clean notebook * clean notebook * start cleaning * update data AAM comparison * cleaning * clean * enhance readme * fix readme * fix readme
TieuLongPhan · Oct 2, 2024 · 497c726 · 497c726
1 parent b609e33
commit 497c726
Show file tree

Hide file tree

Showing 37 changed files with 437 additions and 562 deletions.
diff --git a/.gitignore b/.gitignore
@@ -1,16 +1,16 @@
 *.pyc
-
 *.DS_Store
 *.gml
 .pytest_cache
 __pycache__
-
-
 *.tar.gz
 *pkl.gz
 *json.gz
 *txt
-Data/DPO/*
 _test.py
 *pkl
-Backup/*
+Data/Classification/*
+Data/Report/*
+Data/Temp/Benchmark/Complete/*
+Data/Temp/Benchmark/Hier/*
+Data/Temp/Benchmark/Raw/*
diff --git a/Data/AAM/results_benchmark/aam_benchmark.json.gz b/Data/AAM/results_benchmark/aam_benchmark.json.gz
@@ -0,0 +1 @@
+[{"mapper": "rxn_mapper", "ecoli_accuracy": 72.53, "ecoli_success_rate": 100.0, "recon3d_accuracy": 48.69, "recon3d_success_rate": 100.0, "uspto_3k_accuracy": 93.53, "uspto_3k_success_rate": 100.0, "golden_accuracy": 87.43, "golden_success_rate": 100.0, "natcomm_accuracy": 87.58, "natcomm_success_rate": 100.0, "Biochemical_accuracy": 58.63, "Biochemical_success_rate": 100.0, "Chemical_accuracy": 90.93, "Chemical_success_rate": 100.0}, {"mapper": "graphormer", "ecoli_accuracy": 42.12, "ecoli_success_rate": 100.0, "recon3d_accuracy": 34.82, "recon3d_success_rate": 100.0, "uspto_3k_accuracy": 95.1, "uspto_3k_success_rate": 100.0, "golden_accuracy": 89.59, "golden_success_rate": 100.0, "natcomm_accuracy": 92.87, "natcomm_success_rate": 100.0, "Biochemical_accuracy": 37.86, "Biochemical_success_rate": 100.0, "Chemical_accuracy": 93.05, "Chemical_success_rate": 100.0}, {"mapper": "local_mapper", "ecoli_accuracy": 69.96, "ecoli_success_rate": 100.0, "recon3d_accuracy": 50.79, "recon3d_success_rate": 100.0, "uspto_3k_accuracy": 97.77, "uspto_3k_success_rate": 100.0, "golden_accuracy": 89.08, "golden_success_rate": 100.0, "natcomm_accuracy": 92.67, "natcomm_success_rate": 100.0, "Biochemical_accuracy": 58.78, "Biochemical_success_rate": 100.0, "Chemical_accuracy": 94.38, "Chemical_success_rate": 100.0}, {"mapper": "rdt", "ecoli_accuracy": 78.02, "ecoli_success_rate": 100.0, "recon3d_accuracy": 54.97, "recon3d_success_rate": 100.0, "uspto_3k_accuracy": 90.87, "uspto_3k_success_rate": 100.0, "golden_accuracy": 82.54, "golden_success_rate": 99.77, "natcomm_accuracy": 84.11, "natcomm_success_rate": 99.19, "Biochemical_accuracy": 64.58, "Biochemical_success_rate": 100.0, "Chemical_accuracy": 87.45, "Chemical_success_rate": 99.85}, {"mapper": "ensemble_1", "ecoli_accuracy": 87.96, "ecoli_success_rate": 39.56, "recon3d_accuracy": 68.29, "recon3d_success_rate": 42.93, "uspto_3k_accuracy": 100.0, "uspto_3k_success_rate": 68.8, "golden_accuracy": 98.61, "golden_success_rate": 73.72, "natcomm_accuracy": 99.47, "natcomm_success_rate": 77.19, "Biochemical_accuracy": 76.1, "Biochemical_success_rate": 41.53, "Chemical_accuracy": 99.47, "Chemical_success_rate": 71.23}, {"mapper": "ensemble_2", "ecoli_accuracy": 92.0, "ecoli_success_rate": 36.63, "recon3d_accuracy": 72.37, "recon3d_success_rate": 39.79, "uspto_3k_accuracy": 100.0, "uspto_3k_success_rate": 66.3, "golden_accuracy": 99.24, "golden_success_rate": 67.12, "natcomm_accuracy": 99.44, "natcomm_success_rate": 72.3, "Biochemical_accuracy": 80.16, "Biochemical_success_rate": 38.47, "Chemical_accuracy": 99.69, "Chemical_success_rate": 67.14}]
diff --git a/Data/AAM/results_benchmark/ecoli/ecoli_aam_reactions.json.gz b/Data/AAM/results_benchmark/ecoli/ecoli_aam_reactions.json.gz
diff --git a/Data/AAM/results_benchmark/ecoli/ecoli_reactions.json.gz b/Data/AAM/results_benchmark/ecoli/ecoli_reactions.json.gz
diff --git a/Data/AAM/results_benchmark/golden/golden_aam_reactions.json.gz b/Data/AAM/results_benchmark/golden/golden_aam_reactions.json.gz
diff --git a/Data/AAM/results_benchmark/golden/golden_reactions.json.gz b/Data/AAM/results_benchmark/golden/golden_reactions.json.gz
diff --git a/Data/AAM/results_benchmark/natcomm/natcomm_aam_reactions.json.gz b/Data/AAM/results_benchmark/natcomm/natcomm_aam_reactions.json.gz
diff --git a/Data/AAM/results_benchmark/natcomm/natcomm_reactions.json.gz b/Data/AAM/results_benchmark/natcomm/natcomm_reactions.json.gz
diff --git a/Data/AAM/results_benchmark/recon3d/recon3d_aam_reactions.json.gz b/Data/AAM/results_benchmark/recon3d/recon3d_aam_reactions.json.gz
diff --git a/Data/AAM/results_benchmark/recon3d/recon3d_reactions.json.gz b/Data/AAM/results_benchmark/recon3d/recon3d_reactions.json.gz
diff --git a/Data/AAM/results_benchmark/uspto_3k/uspto_3k_aam_reactions.json.gz b/Data/AAM/results_benchmark/uspto_3k/uspto_3k_aam_reactions.json.gz
diff --git a/Data/AAM/results_benchmark/uspto_3k/uspto_3k_reactions.json.gz b/Data/AAM/results_benchmark/uspto_3k/uspto_3k_reactions.json.gz
diff --git a/Data/Temp/Backup/raw_results.json b/Data/Temp/Backup/raw_results.json
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1 @@
		[{"mapper": "rxn_mapper", "ecoli_accuracy": 72.53, "ecoli_success_rate": 100.0, "recon3d_accuracy": 48.69, "recon3d_success_rate": 100.0, "uspto_3k_accuracy": 93.53, "uspto_3k_success_rate": 100.0, "golden_accuracy": 87.43, "golden_success_rate": 100.0, "natcomm_accuracy": 87.58, "natcomm_success_rate": 100.0, "Biochemical_accuracy": 58.63, "Biochemical_success_rate": 100.0, "Chemical_accuracy": 90.93, "Chemical_success_rate": 100.0}, {"mapper": "graphormer", "ecoli_accuracy": 42.12, "ecoli_success_rate": 100.0, "recon3d_accuracy": 34.82, "recon3d_success_rate": 100.0, "uspto_3k_accuracy": 95.1, "uspto_3k_success_rate": 100.0, "golden_accuracy": 89.59, "golden_success_rate": 100.0, "natcomm_accuracy": 92.87, "natcomm_success_rate": 100.0, "Biochemical_accuracy": 37.86, "Biochemical_success_rate": 100.0, "Chemical_accuracy": 93.05, "Chemical_success_rate": 100.0}, {"mapper": "local_mapper", "ecoli_accuracy": 69.96, "ecoli_success_rate": 100.0, "recon3d_accuracy": 50.79, "recon3d_success_rate": 100.0, "uspto_3k_accuracy": 97.77, "uspto_3k_success_rate": 100.0, "golden_accuracy": 89.08, "golden_success_rate": 100.0, "natcomm_accuracy": 92.67, "natcomm_success_rate": 100.0, "Biochemical_accuracy": 58.78, "Biochemical_success_rate": 100.0, "Chemical_accuracy": 94.38, "Chemical_success_rate": 100.0}, {"mapper": "rdt", "ecoli_accuracy": 78.02, "ecoli_success_rate": 100.0, "recon3d_accuracy": 54.97, "recon3d_success_rate": 100.0, "uspto_3k_accuracy": 90.87, "uspto_3k_success_rate": 100.0, "golden_accuracy": 82.54, "golden_success_rate": 99.77, "natcomm_accuracy": 84.11, "natcomm_success_rate": 99.19, "Biochemical_accuracy": 64.58, "Biochemical_success_rate": 100.0, "Chemical_accuracy": 87.45, "Chemical_success_rate": 99.85}, {"mapper": "ensemble_1", "ecoli_accuracy": 87.96, "ecoli_success_rate": 39.56, "recon3d_accuracy": 68.29, "recon3d_success_rate": 42.93, "uspto_3k_accuracy": 100.0, "uspto_3k_success_rate": 68.8, "golden_accuracy": 98.61, "golden_success_rate": 73.72, "natcomm_accuracy": 99.47, "natcomm_success_rate": 77.19, "Biochemical_accuracy": 76.1, "Biochemical_success_rate": 41.53, "Chemical_accuracy": 99.47, "Chemical_success_rate": 71.23}, {"mapper": "ensemble_2", "ecoli_accuracy": 92.0, "ecoli_success_rate": 36.63, "recon3d_accuracy": 72.37, "recon3d_success_rate": 39.79, "uspto_3k_accuracy": 100.0, "uspto_3k_success_rate": 66.3, "golden_accuracy": 99.24, "golden_success_rate": 67.12, "natcomm_accuracy": 99.44, "natcomm_success_rate": 72.3, "Biochemical_accuracy": 80.16, "Biochemical_success_rate": 38.47, "Chemical_accuracy": 99.69, "Chemical_success_rate": 67.14}]