diff options
author | Christoph Helma <helma@in-silico.ch> | 2020-10-19 23:54:19 +0200 |
---|---|---|
committer | Christoph Helma <helma@in-silico.ch> | 2020-10-19 23:54:19 +0200 |
commit | 2c3bc133700f7e1e1ea8d038d87da1f3095ed103 (patch) | |
tree | 3e6ee6cf30cfd00cf8af3103851ad464bcb9ca7e /Makefile | |
parent | 6b05cf7e4f5c0489325b496cbeeb332ec321c5a7 (diff) |
PA prediction summary
Diffstat (limited to 'Makefile')
-rw-r--r-- | Makefile | 23 |
1 files changed, 18 insertions, 5 deletions
@@ -13,6 +13,7 @@ TEMPLATE_FILE_LATEX = pandoc-scholar.latex # Experiments # crossvalidations + LAZAR_CONFUSION_MATRIX_DIR = 10-fold-crossvalidations/lazar/crossvalidation/confusion_matrices LAZAR_PADEL_CONFUSION_MATRIX_DIR = 10-fold-crossvalidations/lazar-padel/crossvalidation/confusion_matrices R_CV_DIR = 10-fold-crossvalidations/R @@ -22,8 +23,10 @@ CONFUSION_MATRICES_DIR = 10-fold-crossvalidations/confusion-matrices CONFUSION_MATRICES = $(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 $(CONFUSION_MATRICES_DIR)/R-RF.csv $(CONFUSION_MATRICES_DIR)/R-SVM.csv $(CONFUSION_MATRICES_DIR)/R-DL.csv $(CONFUSION_MATRICES_DIR)/tensorflow-rf.v3.csv $(CONFUSION_MATRICES_DIR)/tensorflow-lr.v3.csv $(CONFUSION_MATRICES_DIR)/tensorflow-lr2.v3.csv $(CONFUSION_MATRICES_DIR)/tensorflow-nn.v3.csv CV_SUMMARY = 10-fold-crossvalidations/summary.yaml +PA_SUMMARY = pyrrolizidine-alkaloids/summary.yaml # PA predictions + PA_DIR = pyrrolizidine-alkaloids PA_LAZAR_DIR = $(PA_DIR)/lazar PA_R_DIR = $(PA_DIR)/R @@ -32,13 +35,14 @@ PA_TF_DIR = $(PA_DIR)/tensorflow PA_PREDICTIONS = $(PA_LAZAR_DIR)/pa-mp2d-predictions.csv $(PA_LAZAR_DIR)/pa-padel-predictions.csv $(PA_R_DIR)/PA.RF.outcome.csv $(PA_R_DIR)/PA.SVM.outcome.csv $(PA_R_DIR)/PA.DL.outcome.csv $(PA_TF_DIR)/pred.lr.v3-ext-Padel-2D.csv $(PA_TF_DIR)/pred.lr2.v3-ext-Padel-2D.csv $(PA_TF_DIR)/pred.rf.v3-ext-Padel-2D.csv $(PA_TF_DIR)/pred.nn.v3-ext-Padel-2D.csv # manuscript + TABLES = tables/lazar-summary.csv tables/r-summary.csv tables/tensorflow-summary.csv tables/pa-tab.tex FIGURES = figures/roc.png figures/tsne-mp2d.png figures/tsne-padel.png -all: $(TABLES) $(FIGURES) mutagenicity.pdf +all: $(TABLES) $(FIGURES) $(CV_SUMMARY) mutagenicity.pdf include $(PANDOC_SCHOLAR_PATH)/Makefile -mutagenicity.mustache.md: $(CV_SUMMARY) mutagenicity.md $(TABLES) $(FIGURES) +mutagenicity.mustache.md: $(CV_SUMMARY) $(PA_SUMMARY) mutagenicity.md $(TABLES) $(FIGURES) mustache $^ > $@ # figures @@ -62,6 +66,7 @@ figures/roc.csv: $(CV_SUMMARY) scripts/summary2roc.rb $< > $@ # tables + tables/pa-tab.tex: tables/pa-table.csv scripts/pa-tex-table.rb $< > $@ @@ -77,10 +82,10 @@ tables/r-summary.csv: $(CV_SUMMARY) tables/tensorflow-summary.csv: $(CV_SUMMARY) scripts/summary2table.rb tensorflow > $@ -# crossvalidation summary +# PA summary -$(CV_SUMMARY): $(CONFUSION_MATRICES) - scripts/confusion-matrix-summary.rb $^ > $@ +$(PA_SUMMARY): tables/pa-table.csv + scripts/pa-summary.rb $< > $@ # PA predictions @@ -93,9 +98,15 @@ $(PA_LAZAR_DIR)/pa-mp2d-predictions.csv: $(PA_LAZAR_DIR)/pa-smiles.csv $(PA_LAZAR_DIR)/pa-smiles.csv: pyrrolizidine-alkaloids/180920_PA_complete_SMILES.csv cut -f1,4 -d ';' $< | sed 's/;/,/' > $@ +# crossvalidation summary + +$(CV_SUMMARY): $(CONFUSION_MATRICES) + scripts/confusion-matrix-summary.rb $^ > $@ + # confusion matrices ## lazar + $(CONFUSION_MATRICES_DIR)/lazar-all.csv: $(LAZAR_CONFUSION_MATRIX_DIR) cp $</all $@ @@ -109,6 +120,7 @@ $(CONFUSION_MATRICES_DIR)/lazar-padel-high-confidence.csv: $(LAZAR_PADEL_CONFUSI cp $</high_confidence $@ ## R + $(CONFUSION_MATRICES_DIR)/R-SVM.csv: $(R_CV_DIR)/Sgl-Observations-SVM.csv scripts/cv-r-confusion-matrix.rb $< > $@ @@ -119,6 +131,7 @@ $(CONFUSION_MATRICES_DIR)/R-DL.csv: $(R_CV_DIR)/Sgl-Observations-DL.csv scripts/cv-r-confusion-matrix.rb $< > $@ ## tensorflow + $(TENSORFLOW_CV_DIR)/pred.lr.v3.norm.sorted.csv: $(TENSORFLOW_CV_DIR)/pred.lr.v3.norm.csv sort -n $< > $@ |