More f prints

.gitignore

@@ -113,6 +113,8 @@ datasets/ANEH/ML_Model_Performance_WEBA780101_ELASTICNET.png
 datasets/ANEH/ML_Model_Performance_WEBA780101_PLS_LOOCV.png
 datasets/ANEH/ML_Model_Performance_WEBA780101_PLS.png
 datasets/ANEH/ML_Model_Performance_WEBA780101_RIDGE.png
+datasets/ANEH/ML_Model_Performance_CHAM830104_PLS_LOOCV.png
+datasets/ANEH/ML_Model_Performance_OOBM850104_PLS_LOOCV.png
 datasets/ANEH/ml_pls_37_ANEH_variants_aaidx_encoded_train_concat_lvls_extrapolation.png
 datasets/ANEH/ml_pls_37_ANEH_variants_aaidx_encoded_train_lvl_1_extrapolation.png
 datasets/ANEH/ml_pls_37_ANEH_variants_gremlin_dca_encoded_train_concat_lvls_extrapolation.png
@@ -250,6 +252,11 @@ datasets/ANEH/CV_performance/WEBA780101_PLS_LOOCV_5-fold-CV.png
 datasets/ANEH/CV_performance/WEBA780101_PLS_LOOCV_CV_Results.txt
 datasets/ANEH/CV_performance/WEBA780101_RIDGE_5-fold-CV.png
 datasets/ANEH/CV_performance/WEBA780101_RIDGE_CV_Results.txt
+datasets/ANEH/CV_performance/CHAM830104_PLS_LOOCV_5-fold-CV.png
+datasets/ANEH/CV_performance/CHAM830104_PLS_LOOCV_CV_Results.txt
+datasets/ANEH/CV_performance/OOBM850104_PLS_LOOCV_5-fold-CV.png
+datasets/ANEH/CV_performance/OOBM850104_PLS_LOOCV_CV_Results.txt
+datasets/ANEH/Pickles/OOBM850104
 datasets/ANEH/Diverse_Double_Split/Diverse_Double_Split1.fasta
 datasets/ANEH/Diverse_Double_Split/Predictions_FAUJ880104_TopDiverse_Double_Split.txt
 datasets/ANEH/Diverse_Double_Split/Predictions_MLgremlin_TopDiverse_Double_Split.txt

pypef/dca/gremlin_inference.py

@@ -746,6 +746,7 @@ def plot_predicted_ssm(gremlin: GREMLIN):
     wt_score = gremlin.get_wt_score()[0]
     aas = "".join(sorted(gremlin.char_alphabet.replace("-", "")))
     variantss, variant_sequencess, variant_scoress = [], [], []
+    logger.info("Predicting all SSM effects using the unsupervised GREMLIN model...")
     for i, aa_wt in enumerate(tqdm(wt_sequence)):
         variants, variant_sequences, variant_scores = [], [], []
         for aa_sub in aas:

pypef/ml/regression.py

@@ -649,11 +649,11 @@ def formatted_output(
     for (idx, val, val2, val3, val4, val5, r_m, pam) in performance_list:
         if val >= minimum_r2:
             index.append(get_basename(idx))
-            value.append('{:f}'.format(val))
-            value2.append('{:f}'.format(val2))
-            value3.append('{:f}'.format(val3))
-            value4.append('{:f}'.format(val4))
-            value5.append('{:f}'.format(val5))
+            value.append(f'{val:.6f}')
+            value2.append(f'{val2:.6f}')
+            value3.append(f'{val3:.6f}')
+            value4.append(f'{val4:.6f}')
+            value5.append(f'{val5:.6f}')
             regression_model.append(r_m.upper())
             params.append(pam)
 
@@ -853,10 +853,9 @@ def crossval_on_all(x_train, x_test, y_train, y_test, regressor: str, parameter,
         get_performances(y_test_total, y_predicted_total)
 
     with open(cv_filename, 'a') as f:
-        f.write('Regression type: {}; Parameter: {}; Encoding index: {}\n'.format(
-            regressor.upper(), parameter, name))
-        f.write('R2 = {:.5f}; RMSE = {:.5f}; NRMSE = {:.5f}; Pearson\'s r = {:.5f};'
-                ' Spearman\'s rho = {:.5f}\n\n'.format(r_squared, rmse, nrmse, pearson_r, spearman_rho))
+        f.write(f'Regression type: {regressor.upper()}; Parameter: {parameter}; Encoding index: {name}\n')
+        f.write(f'R2 = {r_squared:.6f}; RMSE = {rmse:.6f}; NRMSE = {nrmse:.6f}; Pearson\'s r = {pearson_r:.6f}; '
+                f'Spearman\'s rho = {spearman_rho:.6f}\n\n')
 
     figure, ax = plt.subplots()
     legend = r'$R^2$' + f' = {r_squared:.3f}' + f'\nRMSE = {rmse:.3f}' + f'\nNRMSE = {nrmse:.3f}' + \