Results section

13 files changed, 295 insertions, 82 deletions

diff --git a/Makefile b/Makefile
index a95eb32..d0fba04 100644
--- a/Makefile
+++ b/Makefile
@@ -8,7 +8,7 @@ PANDOC_SCHOLAR_PATH   = pandoc-scholar
 OUTFILE_PREFIX        = mutagenicity
 DEFAULT_EXTENSIONS    = pdf #latex docx html #odt epub
 #PANDOC_WRITER_OPTIONS = --filter=panpipe --filter=pandoc-placetable --filter=pandoc-citeproc -M tmpvar=test
-PANDOC_WRITER_OPTIONS = --filter=pandoc-crossref --filter=pandoc-placetable --filter=pandoc-citeproc 
+PANDOC_WRITER_OPTIONS = --filter=pandoc-placetable --filter=pandoc-crossref --filter=pandoc-citeproc
 TEMPLATE_FILE_LATEX   = pandoc-scholar.latex
 
 # Lazar
@@ -28,24 +28,25 @@ CONFUSION_MATRICES_DIR = 10-fold-crossvalidations/confusion-matrices
 R_CV_DIR = 10-fold-crossvalidations/R
 TENSORFLOW_CV_DIR = 10-fold-crossvalidations/tensorflow
 
-TABLES = tables/r-summary.csv tables/tf-summary.csv tables/lazar-summary.csv tables/R-SVM.csv tables/R-RF.csv tables/R-DL.csv tables/tensorflow-all.csv tables/tensorflow-selected.csv tables/lazar-all.csv tables/lazar-high-confidence.csv tables/lazar-padel-all.csv tables/lazar-padel-high-confidence.csv
+#TABLES = tables/r-summary.csv tables/tf-summary.csv tables/lazar-summary.csv tables/R-SVM.csv tables/R-RF.csv tables/R-DL.csv tables/tensorflow-all.csv tables/tensorflow-selected.csv tables/lazar-all.csv tables/lazar-high-confidence.csv tables/lazar-padel-all.csv tables/lazar-padel-high-confidence.csv
+TABLES = tables/R-SVM.csv tables/R-RF.csv tables/R-DL.csv tables/tensorflow-all.csv tables/tensorflow-selected.csv tables/lazar-all.csv tables/lazar-high-confidence.csv tables/lazar-padel-all.csv tables/lazar-padel-high-confidence.csv
 
 R_SUMMARIES = $(SUMMARIES_DIR)/R-SVM.json $(SUMMARIES_DIR)/R-RF.json $(SUMMARIES_DIR)/R-DL.json
 TF_SUMMARIES = $(SUMMARIES_DIR)/tensorflow-all.json $(SUMMARIES_DIR)/tensorflow-selected.json
 LAZAR_SUMMARIES = $(SUMMARIES_DIR)/lazar-all.json $(SUMMARIES_DIR)/lazar-high-confidence.json $(SUMMARIES_DIR)/lazar-padel-all.json $(SUMMARIES_DIR)/lazar-padel-high-confidence.json
 
-SUMMARIES = $(R_SUMMARIES) $(TF_SUMMARIES) $(LAZAR_SUMMARIES)
+#SUMMARIES = $(R_SUMMARIES) $(TF_SUMMARIES) $(LAZAR_SUMMARIES)
 
 CONFUSION_MATRICES = $(CONFUSION_MATRICES_DIR)/R-SVM.csv $(CONFUSION_MATRICES_DIR)/R-RF.csv $(CONFUSION_MATRICES_DIR)/R-DL.csv $(CONFUSION_MATRICES_DIR)/tensorflow-all.csv $(CONFUSION_MATRICES_DIR)/tensorflow-selected.csv $(CONFUSION_MATRICES_DIR)/lazar-all.csv $(CONFUSION_MATRICES_DIR)/lazar-high-confidence.csv $(CONFUSION_MATRICES_DIR)/lazar-padel-all.csv $(CONFUSION_MATRICES_DIR)/lazar-padel-high-confidence.csv
 
 DATA = data/mutagenicity.sdf data/mutagenicity.csv data/mutagenicity-fingerprints.csv
 
-all: $(DATA) $(TABLES) mutagenicity.pdf $(SUMMARIES_DIR)/results.json
+all: $(DATA) $(TABLES) mutagenicity.pdf 
 #all: $(SUMMARIES) $(DATA) $(TABLES) mutagenicity.pdf
 include $(PANDOC_SCHOLAR_PATH)/Makefile
 export: $(DATA) 
 
-mutagenicity.mustache.md: $(SUMMARIES_DIR)/results.json mutagenicity.md
+mutagenicity.mustache.md: results.yaml mutagenicity.md
 	mustache $^ > $@
 
 # tables
@@ -64,11 +65,14 @@ tables/%.csv: $(CONFUSION_MATRICES_DIR)/%.csv
 
 # summaries
 
-$(SUMMARIES_DIR)/results.json: $(SUMMARIES)
-	scripts/results.rb $^ > $@
+#$(SUMMARIES_DIR)/results.json: $(SUMMARIES)
+	#scripts/results.rb $^ > $@
 
-$(SUMMARIES_DIR)/%.json: $(CONFUSION_MATRICES_DIR)/%.csv
-	scripts/confusion-matrix-summary.rb $< > $@
+#$(SUMMARIES_DIR)/%.json: $(CONFUSION_MATRICES_DIR)/%.csv
+	#scripts/confusion-matrix-summary.rb $< > $@
+
+results.yaml: $(CONFUSION_MATRICES)
+	scripts/confusion-matrix-summary.rb $^ > $@
 
 # confusion matrices
 
diff --git a/mutagenicity.md b/mutagenicity.md
index 2f80bad..a9fa116 100644
--- a/mutagenicity.md
+++ b/mutagenicity.md
@@ -25,6 +25,7 @@ institute:
 bibliography: bibliography.bib
 keywords: mutagenicity, (Q)SAR, lazar, random forest, support vector machine, deep learning
 documentclass: scrartcl
+tblPrefix: Table
 ...
 
 Abstract
@@ -335,83 +336,60 @@ Validation
 Results
 =======
 
-{{#programs}}
-{{name}} Models
---------
-{{#algos}}
-
-### {{name}}
-
-10-fold crossvalidation of the {{abbrev}} model gave an accuracy of
-{{accuracy_perc}}%
-a sensitivity of
-{{true_positive_rate_perc}}%
-and a specificity of
-{{true_negative_rate_perc}}%
-The confusion matrix of the
-model, calculated for 8080 instances, is provided in Table 1.
-
-```{.table file="tables/R-RF.csv" caption="Confusion matrix for R Random Forest predictions"}
-```
-{{/algos}}
-{{/programs}}
-
 R Models
 --------
 
 ### Random Forest
 
-The validation showed that the RF model has an accuracy of
-{{R-RF.accuracy}}%
-`cat /home/ch/src/mutagenicity-paper/10-fold-crossvalidations/summaries/R-RF.json|jq '.accuracy * 100 | round'`{pipe="sh"}%,
-a sensitivity of
-`cat /home/ch/src/mutagenicity-paper/10-fold-crossvalidations/summaries/R-RF.json|jq '.true_positive_rate * 100 | round'`{pipe="sh"}%,
-and a specificity of
-`cat /home/ch/src/mutagenicity-paper/10-fold-crossvalidations/summaries/R-RF.json|jq '.true_negative_rate * 100 | round'`{pipe="sh"}%,
-The confusion matrix of the
-model, calculated for 8080 instances, is provided in Table 1.
-
-```{.table file="tables/R-RF.csv" caption="Confusion matrix for R Random Forest predictions"}
+10-fold crossvalidation of the R-RF model gave an accuracy of
+{{R-RF.acc_perc}}%, a sensitivity of {{R-RF.tpr_perc}}% and a specificity of
+{{R-RF.tnr_perc}}%.  The confusion matrix for {{R-RF.n}}
+predictions is provided in @tbl:R-RF.
+
+```{#tbl:R-RF .table file="tables/R-RF.csv" caption="Confusion matrix for R Random Forest predictions"}
 ```
 
 ### Support Vector Machines
 
-The validation showed that the SVM model has an accuracy of 62%, a
-sensitivity of 65% and a specificity of 60%. The confusion matrix of SVM
-model, calculated for 8080 instances, is provided in Table 2.
-
+10-fold crossvalidation of the R-SVM model gave an accuracy of
+{{R-SVM.acc_perc}}%, a sensitivity of {{R-SVM.tpr_perc}}% and a specificity of
+{{R-SVM.tnr_perc}}%.  The confusion matrix for {{R-SVM.n}}
+predictions is provided in @tbl:R-SVM.
 
-```{.table file="tables/R-SVM.csv" caption="Confusion matrix for R Support Vector Machine predictions"}
+```{#tbl:R-SVM .table file="tables/R-SVM.csv" caption="Confusion matrix for R Support Vector Machine predictions"}
 ```
 
 ### Deep Learning
 
-The validation showed that the DL model generated in R has an accuracy
-of 59%, a sensitivity of 89% and a specificity of 30%. The confusion
-matrix of the model, normalised to 8080 instances, is provided in Table
-3.
+10-fold crossvalidation of the R-DL model gave an accuracy of
+{{R-DL.acc_perc}}%, a sensitivity of {{R-DL.tpr_perc}}% and a specificity of
+{{R-DL.tnr_perc}}%.  The confusion matrix for {{R-DL.n}}
+predictions is provided in @tbl:R-DL.
 
-```{.table file="tables/R-DL.csv" caption="Confusion matrix for R Deep Learning predictions"}
-```
-
-```{.table file="tables/r-summary.csv" caption="Summary of R model validations"}
+```{#tbl:R-DL .table file="tables/R-DL.csv" caption="Confusion matrix for R Deep Learning predictions"}
 ```
 
 TensorFlow Models
 -----------------
 
-The validation showed that the DL model generated in TensorFlow has an
-accuracy of 68%, a sensitivity of 70% and a specificity of 46%. The
-confusion matrix of the model, normalised to 8080 instances, is provided
-in Table 4.
+### Without feature selection
 
-```{.table file="tables/tensorflow-all.csv" caption="Confusion matrix for Tensorflow predictions without variable selecetion"}
-```
+10-fold crossvalidation of the TensorFlow DL model gave an accuracy of
+{{tensorflow-all.acc_perc}}%, a sensitivity of {{tensorflow-all.tpr_perc}}% and a specificity of
+{{tensorflow-all.tnr_perc}}%.  The confusion matrix for {{tensorflow-all.n}}
+predictions is provided in @tbl:tensorflow-all.
 
-```{.table file="tables/tensorflow-selected.csv" caption="Confusion matrix for Tensorflow predictions with variable selecetion"}
+```{#tbl:tensorflow-all .table file="tables/tensorflow-all.csv" caption="Confusion matrix for Tensorflow predictions without feature selecetion"}
 ```
 
-```{.table file="tables/tf-summary.csv" caption="Summary of TensorFlow model validations"}
+### With feature selection
+
+10-fold crossvalidation of the TensorFlow model with feature selection gave an accuracy of
+{{tensorflow-selected.acc_perc}}%, a sensitivity of {{tensorflow-selected.tpr_perc}}% and a specificity of
+{{tensorflow-selected.tnr_perc}}%.  The confusion matrix for {{tensorflow-selected.n}}
+predictions is provided in @tbl:tensorflow-selected.
+
+```{#tbl:tensorflow-selected .table file="tables/tensorflow-selected.csv" caption="Confusion matrix for Tensorflow predictions with feature selecetion"}
 ```
 
 `lazar` Models
@@ -419,23 +397,59 @@ in Table 4.
 
 ### MolPrint2D Descriptors
 
-```{.table file="tables/lazar-all.csv" caption="Confusion matrix for lazar predictions with MolPrint2D descriptors"}
+10-fold crossvalidation of the lazar model with MolPrint2D descriptors gave an accuracy of
+{{lazar-all.acc_perc}}%, a sensitivity of {{lazar-all.tpr_perc}}% and a specificity of
+{{lazar-all.tnr_perc}}%. 
+The confusion matrix for {{lazar-all.n}}
+predictions is provided in @tbl:lazar-all.
+
+```{#tbl:lazar-all .table file="tables/lazar-all.csv" caption="Confusion matrix for lazar predictions with MolPrint2D descriptors"}
 ```
 
-```{.table file="tables/lazar-high-confidence.csv" caption="Confusion matrix for high confidence lazar predictions with MolPrint2D descriptors"}
+Predictions with high confidence had an accuracy of
+{{lazar-high-confidence.acc_perc}}%, a sensitivity of {{lazar-high-confidence.tpr_perc}}% and a specificity of
+{{lazar-high-confidence.tnr_perc}}%. 
+The confusion matrix for {{lazar-high-confidence.n}}
+predictions is provided in @tbl:lazar-high-confidence.
+
+
+```{#tbl:lazar-high-confidence .table file="tables/lazar-high-confidence.csv" caption="Confusion matrix for high confidence lazar predictions with MolPrint2D descriptors"}
 ```
 
 ### PaDEL Descriptors
 
-```{.table file="tables/lazar-padel-all.csv" caption="Confusion matrix for lazar predictions with PaDEL descriptors"}
-```
+10-fold crossvalidation of the lazar model with PaDEL descriptors gave an accuracy of
+{{lazar-all.acc_perc}}%, a sensitivity of {{lazar-all.tpr_perc}}% and a specificity of
+{{lazar-all.tnr_perc}}%. 
+The confusion matrix for {{lazar-all.n}}
+predictions is provided in @tbl:lazar-padel-all.
 
-```{.table file="tables/lazar-padel-high-confidence.csv" caption="Confusion matrix for high confidence lazar predictions with PaDEL descriptors"}
+```{#tbl:lazar-padel-all .table file="tables/lazar-padel-all.csv" caption="Confusion matrix for lazar predictions with PaDEL descriptors" }
 ```
 
-```{.table file="tables/lazar-summary.csv" caption="Summary of lazar model validations"}
+Predictions with high confidence had an accuracy of
+{{lazar-high-confidence.acc_perc}}%, a sensitivity of {{lazar-high-confidence.tpr_perc}}% and a specificity of
+{{lazar-high-confidence.tnr_perc}}%. 
+The confusion matrix for {{lazar-high-confidence.n}}
+predictions is provided in @tbl:lazar-padel-high-confidence.
+
+```{#tbl:lazar-padel-high-confidence .table file="tables/lazar-padel-high-confidence.csv" caption="Confusion matrix for high confidence lazar predictions with PaDEL descriptors"}
 ```
 
+The results of all crossvalidation experiments are summarized in @tbl:summary.
+
+| |R-RF | R-SVM | R-DL | TF | TF-FS | L | L-HC | L-P | L-P-HC|
+|-|-----|-------|------|----|-------|---|------|------|--------|
+|Accuracy|{{R-RF.acc}}|{{R-SVM.acc}}|{{R-DL.acc}}|{{tensorflow-all.acc}}|{{tensorflow-selected.acc}}|{{lazar-all.acc}}|{{lazar-high-confidence.acc}}|{{lazar-padel-all.acc}}|{{lazar-padel-high-confidence.acc}}|
+|Sensitivity|{{R-RF.tpr}}|{{R-SVM.tpr}}|{{R-DL.tpr}}|{{tensorflow-all.tpr}}|{{tensorflow-selected.tpr}}|{{lazar-all.tpr}}|{{lazar-high-confidence.tpr}}|{{lazar-padel-all.tpr}}|{{lazar-padel-high-confidence.tpr}}|
+|Specificity|{{R-RF.tnr}}|{{R-SVM.tnr}}|{{R-DL.tnr}}|{{tensorflow-all.tnr}}|{{tensorflow-selected.tnr}}|{{lazar-all.tnr}}|{{lazar-high-confidence.tnr}}|{{lazar-padel-all.tnr}}|{{lazar-padel-high-confidence.tnr}}|
+|PPV|{{R-RF.ppv}}|{{R-SVM.ppv}}|{{R-DL.ppv}}|{{tensorflow-all.ppv}}|{{tensorflow-selected.ppv}}|{{lazar-all.ppv}}|{{lazar-high-confidence.ppv}}|{{lazar-padel-all.ppv}}|{{lazar-padel-high-confidence.ppv}}|
+|NPV|{{R-RF.npv}}|{{R-SVM.npv}}|{{R-DL.npv}}|{{tensorflow-all.npv}}|{{tensorflow-selected.npv}}|{{lazar-all.npv}}|{{lazar-high-confidence.npv}}|{{lazar-padel-all.npv}}|{{lazar-padel-high-confidence.npv}}|
+|Nr. predictions|{{R-RF.n}}|{{R-SVM.n}}|{{R-DL.n}}|{{tensorflow-all.n}}|{{tensorflow-selected.n}}|{{lazar-all.n}}|{{lazar-high-confidence.n}}|{{lazar-padel-all.n}}|{{lazar-padel-high-confidence.n}}|
+
+: Summary of crossvalidation results. *R-RF*: R Random Forests, *R-SVM*: R Support Vector Machines, *R-DL*: R Deep Learning, *TF*: TensorFlow without feature selection, *TF-FS*: TensorFlow with feature selection, *L*: lazar, *L-HC*: lazar high confidence predictions, *L-P*: lazar with PaDEL descriptors, *L-P-HC*: lazar PaADEL high confidence predictions, *PPV*: Positive predictive value (Precision), *NPV*: Negative predictive value {#tbl:summary}
+
+
 Discussion
 ==========
 
diff --git a/results.yaml b/results.yaml
new file mode 100644
index 0000000..489c1dd
--- /dev/null
+++ b/results.yaml
@@ -0,0 +1,145 @@
+---
+R-SVM:
+  :tp: 2243
+  :fp: 1353
+  :tn: 2717
+  :fn: 1757
+  :n: 8070
+  :acc: 0.61
+  :tpr: 0.56
+  :tnr: 0.67
+  :ppv: 0.62
+  :npv: 0.61
+  :acc_perc: 61
+  :tpr_perc: 56
+  :tnr_perc: 67
+  :ppv_perc: 62
+  :npv_perc: 61
+R-RF:
+  :tp: 2259
+  :fp: 1173
+  :tn: 2897
+  :fn: 1741
+  :n: 8070
+  :acc: 0.64
+  :tpr: 0.56
+  :tnr: 0.71
+  :ppv: 0.66
+  :npv: 0.62
+  :acc_perc: 64
+  :tpr_perc: 56
+  :tnr_perc: 71
+  :ppv_perc: 66
+  :npv_perc: 62
+R-DL:
+  :tp: 3517
+  :fp: 3099
+  :tn: 971
+  :fn: 483
+  :n: 8070
+  :acc: 0.56
+  :tpr: 0.88
+  :tnr: 0.24
+  :ppv: 0.53
+  :npv: 0.67
+  :acc_perc: 56
+  :tpr_perc: 88
+  :tnr_perc: 24
+  :ppv_perc: 53
+  :npv_perc: 67
+tensorflow-all:
+  :tp: 2507
+  :fp: 1528
+  :tn: 2550
+  :fn: 1495
+  :n: 8080
+  :acc: 0.63
+  :tpr: 0.63
+  :tnr: 0.63
+  :ppv: 0.62
+  :npv: 0.63
+  :acc_perc: 63
+  :tpr_perc: 63
+  :tnr_perc: 63
+  :ppv_perc: 62
+  :npv_perc: 63
+tensorflow-selected:
+  :tp: 2453
+  :fp: 1454
+  :tn: 2624
+  :fn: 1549
+  :n: 8080
+  :acc: 0.63
+  :tpr: 0.61
+  :tnr: 0.64
+  :ppv: 0.63
+  :npv: 0.63
+  :acc_perc: 63
+  :tpr_perc: 61
+  :tnr_perc: 64
+  :ppv_perc: 63
+  :npv_perc: 63
+lazar-all:
+  :tp: 3326
+  :fp: 833
+  :tn: 3039
+  :fn: 583
+  :n: 7781
+  :acc: 0.82
+  :tpr: 0.85
+  :tnr: 0.78
+  :ppv: 0.8
+  :npv: 0.84
+  :acc_perc: 82
+  :tpr_perc: 85
+  :tnr_perc: 78
+  :ppv_perc: 80
+  :npv_perc: 84
+lazar-high-confidence:
+  :tp: 2816
+  :fp: 571
+  :tn: 2138
+  :fn: 365
+  :n: 5890
+  :acc: 0.84
+  :tpr: 0.89
+  :tnr: 0.79
+  :ppv: 0.83
+  :npv: 0.85
+  :acc_perc: 84
+  :tpr_perc: 89
+  :tnr_perc: 79
+  :ppv_perc: 83
+  :npv_perc: 85
+lazar-padel-all:
+  :tp: 593
+  :fp: 466
+  :tn: 1777
+  :fn: 1253
+  :n: 4089
+  :acc: 0.58
+  :tpr: 0.32
+  :tnr: 0.79
+  :ppv: 0.56
+  :npv: 0.59
+  :acc_perc: 58
+  :tpr_perc: 32
+  :tnr_perc: 79
+  :ppv_perc: 56
+  :npv_perc: 59
+lazar-padel-high-confidence:
+  :tp: 593
+  :fp: 466
+  :tn: 1771
+  :fn: 1251
+  :n: 4081
+  :acc: 0.58
+  :tpr: 0.32
+  :tnr: 0.79
+  :ppv: 0.56
+  :npv: 0.59
+  :acc_perc: 58
+  :tpr_perc: 32
+  :tnr_perc: 79
+  :ppv_perc: 56
+  :npv_perc: 59
diff --git a/scripts/confusion-matrix-summary.rb b/scripts/confusion-matrix-summary.rb
index a9742f7..e0adf4e 100755
--- a/scripts/confusion-matrix-summary.rb
+++ b/scripts/confusion-matrix-summary.rb
@@ -1,19 +1,33 @@
 #!/usr/bin/env ruby
 require 'csv'
-require 'json'
+require 'yaml'
 
-csv = CSV.read(ARGV[0],headers: false,:col_sep => ",")
-tp = csv[0][0].to_f
-fp = csv[0][1].to_f
-fn = csv[1][0].to_f
-tn = csv[1][1].to_f
+results = {}
+ARGV.each do |f|
+  csv = CSV.read(f,headers: false,:col_sep => ",")
+  tp = csv[0][0].to_f
+  fp = csv[0][1].to_f
+  fn = csv[1][0].to_f
+  tn = csv[1][1].to_f
 
-result = {
-  :accuracy => (tp+tn)/(tp+fp+tn+fn),
-  :true_positive_rate => tp/(tp+fn),
-  :true_negative_rate => tn/(tn+fp),
-  :positive_predictive_value => tp/(tp+fp),
-  :negative_predictive_value => tn/(tn+fn),
-}
+  result = {
+    :tp => tp.to_i,
+    :fp => fp.to_i,
+    :tn => tn.to_i,
+    :fn => fn.to_i,
+    :n => (tp+fp+tn+fn).to_i,
+    :acc => ((tp+tn)/(tp+fp+tn+fn)).round(2),
+    :tpr => (tp/(tp+fn)).round(2),
+    :tnr => (tn/(tn+fp)).round(2),
+    :ppv => (tp/(tp+fp)).round(2),
+    :npv => (tn/(tn+fn)).round(2),
+    :acc_perc => (100*(tp+tn)/(tp+fp+tn+fn)).round(0),
+    :tpr_perc => (100*tp/(tp+fn)).round(0),
+    :tnr_perc => (100*tn/(tn+fp)).round(0),
+    :ppv_perc => (100*tp/(tp+fp)).round(0),
+    :npv_perc => (100*tn/(tn+fn)).round(0),
+  }
+  results[File.basename(f,".csv")] = result
+end
 
-puts result.to_json
+puts results.to_yaml
diff --git a/tables/R-DL.csv b/tables/R-DL.csv
new file mode 100644
index 0000000..d622e0e
--- /dev/null
+++ b/tables/R-DL.csv
@@ -0,0 +1,4 @@
+,,Predictions,
+,,mutagenic,non-mutagenic
+Measurements,mutagenic,3517,3099
+,non-mutagenic,483,971
diff --git a/tables/R-RF.csv b/tables/R-RF.csv
new file mode 100644
index 0000000..d81cff6
--- /dev/null
+++ b/tables/R-RF.csv
@@ -0,0 +1,4 @@
+,,Predictions,
+,,mutagenic,non-mutagenic
+Measurements,mutagenic,2259,1173
+,non-mutagenic,1741,2897
diff --git a/tables/R-SVM.csv b/tables/R-SVM.csv
new file mode 100644
index 0000000..9aaf85f
--- /dev/null
+++ b/tables/R-SVM.csv
@@ -0,0 +1,4 @@
+,,Predictions,
+,,mutagenic,non-mutagenic
+Measurements,mutagenic,2243,1353
+,non-mutagenic,1757,2717
diff --git a/tables/lazar-all.csv b/tables/lazar-all.csv
new file mode 100644
index 0000000..c4db6a1
--- /dev/null
+++ b/tables/lazar-all.csv
@@ -0,0 +1,4 @@
+,,Predictions,
+,,mutagenic,non-mutagenic
+Measurements,mutagenic,3326,833
+,non-mutagenic,583,3039
diff --git a/tables/lazar-high-confidence.csv b/tables/lazar-high-confidence.csv
new file mode 100644
index 0000000..049c73b
--- /dev/null
+++ b/tables/lazar-high-confidence.csv
@@ -0,0 +1,4 @@
+,,Predictions,
+,,mutagenic,non-mutagenic
+Measurements,mutagenic,2816,571
+,non-mutagenic,365,2138
diff --git a/tables/lazar-padel-all.csv b/tables/lazar-padel-all.csv
new file mode 100644
index 0000000..e2436f7
--- /dev/null
+++ b/tables/lazar-padel-all.csv
@@ -0,0 +1,4 @@
+,,Predictions,
+,,mutagenic,non-mutagenic
+Measurements,mutagenic,593,466
+,non-mutagenic,1253,1777
diff --git a/tables/lazar-padel-high-confidence.csv b/tables/lazar-padel-high-confidence.csv
new file mode 100644
index 0000000..1b551d9
--- /dev/null
+++ b/tables/lazar-padel-high-confidence.csv
@@ -0,0 +1,4 @@
+,,Predictions,
+,,mutagenic,non-mutagenic
+Measurements,mutagenic,593,466
+,non-mutagenic,1251,1771
diff --git a/tables/tensorflow-all.csv b/tables/tensorflow-all.csv
new file mode 100644
index 0000000..afd74c5
--- /dev/null
+++ b/tables/tensorflow-all.csv
@@ -0,0 +1,4 @@
+,,Predictions,
+,,mutagenic,non-mutagenic
+Measurements,mutagenic,2507,1528
+,non-mutagenic,1495,2550
diff --git a/tables/tensorflow-selected.csv b/tables/tensorflow-selected.csv
new file mode 100644
index 0000000..6c0f6e5
--- /dev/null
+++ b/tables/tensorflow-selected.csv
@@ -0,0 +1,4 @@
+,,Predictions,
+,,mutagenic,non-mutagenic
+Measurements,mutagenic,2453,1454
+,non-mutagenic,1549,2624