Skip to content

Commit 76b534a

Browse files
niklasesniklases
committed
Refactor-7
1 parent 9ed0fa3 commit 76b534a

File tree

3 files changed

+244
-12
lines changed

3 files changed

+244
-12
lines changed

‎.gitignore‎

Lines changed: 243 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -8,7 +8,9 @@ workflow/.ipynb_checkpoints/
88
# Byte-compiled / optimized / DLL files
99
__pycache__/
1010
*.py[cod]
11-
# Created (test) output files
11+
12+
13+
# Created test/output files
1214
scripts/Encoding_low_N/apc.png
1315
scripts/Encoding_low_N/low_N_avGFP_extrapolation.png
1416
datasets/ANEH/LS.fasl
@@ -133,3 +135,243 @@ datasets/AVGFP/ml_pls_avGFP_dca_encoded_train_concat_lvls_extrapolation.png
133135
datasets/AVGFP/ml_pls_avGFP_aaidx_encoded_train_concat_lvls_extrapolation.png
134136
datasets/AVGFP/ml_pls_avGFP_onehot_encoded_train_concat_lvls_extrapolation.png
135137
scripts/Encoding_low_N/AVGFP/low_N_avGFP_extrapolation.png
138+
datasets/AVGFP/WERD780101_PLS_ML_Model_Performance.png
139+
datasets/AVGFP/VINM940103_PLS_ML_Model_Performance.png
140+
datasets/AVGFP/TS.fasl
141+
datasets/AVGFP/Recomb_Double_Split/Recomb_Double_Split7.fasta
142+
datasets/AVGFP/Recomb_Double_Split/Recomb_Double_Split6.fasta
143+
datasets/AVGFP/Recomb_Double_Split/Recomb_Double_Split5.fasta
144+
datasets/AVGFP/Recomb_Double_Split/Recomb_Double_Split4.fasta
145+
datasets/AVGFP/Recomb_Double_Split/Recomb_Double_Split3.fasta
146+
datasets/AVGFP/Recomb_Double_Split/Recomb_Double_Split2.fasta
147+
datasets/AVGFP/Recomb_Double_Split/Recomb_Double_Split1.fasta
148+
datasets/AVGFP/Recomb_Double_Split/Recomb_Double_Split0.fasta
149+
datasets/AVGFP/Predictions_Hybrid_TopavGFP_prediction_set.txt
150+
datasets/AVGFP/PLMC_DE_trajectories.png
151+
datasets/AVGFP/Pickles/WERD780101
152+
datasets/AVGFP/Pickles/VINM940103
153+
datasets/AVGFP/Pickles/PLMC
154+
datasets/AVGFP/Pickles/MLplmc
155+
datasets/AVGFP/Pickles/MLgremlin
156+
datasets/AVGFP/Pickles/LAWE840101
157+
datasets/AVGFP/Pickles/HYBRIDplmc
158+
datasets/AVGFP/Pickles/HYBRIDgremlin
159+
datasets/AVGFP/Pickles/GEIM800103
160+
datasets/AVGFP/Pickles/FASG760103
161+
datasets/AVGFP/None_DE_trajectories.png
162+
datasets/AVGFP/Model_Results.txt
163+
datasets/AVGFP/MLplmc_DE_trajectories.png
164+
datasets/AVGFP/MLgremlin_DE_trajectories.png
165+
datasets/AVGFP/ml_ridge_avGFP_dca_encoded_train_lvl_1_extrapolation.png
166+
datasets/AVGFP/ml_ridge_avGFP_dca_encoded_train_concat_lvls_extrapolation.png
167+
datasets/AVGFP/ml_ridge_avGFP_aaidx_encoded_train_lvl_1_extrapolation.png
168+
datasets/AVGFP/ml_ridge_avGFP_aaidx_encoded_train_concat_lvls_extrapolation.png
169+
datasets/AVGFP/LS.fasl
170+
datasets/AVGFP/low_N_avGFP_dca_encoded_ml_ridge.png
171+
datasets/AVGFP/low_N_avGFP_aaidx_encoded_ml_ridge.png
172+
datasets/AVGFP/LAWE840101_PLS_ML_Model_Performance.png
173+
datasets/AVGFP/HYBRIDplmc_DE_trajectories.png
174+
datasets/AVGFP/GREMLIN_DE_trajectories.png
175+
datasets/AVGFP/GEIM800103_PLS_ML_Model_Performance.png
176+
datasets/AVGFP/FASG760103_PLS_ML_Model_Performance.png
177+
datasets/AVGFP/EvoTraj/Trajectories.csv
178+
datasets/AVGFP/DCA_PLS_ML_Model_Performance.png
179+
datasets/AVGFP/DCA_ML_Model_Performance.png
180+
datasets/AVGFP/DCA_Hybrid_Model_Performance.png
181+
datasets/AVGFP/CV_performance/WERD780101_PLS_CV_Results.txt
182+
datasets/AVGFP/CV_performance/WERD780101_PLS_5-fold-CV.png
183+
datasets/AVGFP/CV_performance/VINM940103_PLS_CV_Results.txt
184+
datasets/AVGFP/CV_performance/VINM940103_PLS_5-fold-CV.png
185+
datasets/AVGFP/CV_performance/LAWE840101_PLS_CV_Results.txt
186+
datasets/AVGFP/CV_performance/LAWE840101_PLS_5-fold-CV.png
187+
datasets/AVGFP/CV_performance/GEIM800103_PLS_CV_Results.txt
188+
datasets/AVGFP/CV_performance/GEIM800103_PLS_5-fold-CV.png
189+
datasets/AVGFP/CV_performance/FASG760103_PLS_CV_Results.txt
190+
datasets/AVGFP/CV_performance/FASG760103_PLS_5-fold-CV.png
191+
datasets/AVGFP/CV_performance/DCA_PLS_CV_Results.txt
192+
datasets/AVGFP/CV_performance/DCA_PLS_5-fold-CV.png
193+
datasets/AVGFP/avGFP_prediction_set.fasta
194+
datasets/ANEH/WEBA780101_RIDGE_ML_Model_Performance.png
195+
datasets/ANEH/WEBA780101_PLS_LOOCV_ML_Model_Performance.png
196+
datasets/ANEH/WEBA780101_ELASTICNET_ML_Model_Performance.png
197+
datasets/ANEH/SUEM840102_RIDGE_ML_Model_Performance.png
198+
datasets/ANEH/SUEM840102_LASSO_ML_Model_Performance.png
199+
datasets/ANEH/SUEM840102_ELASTICNET_ML_Model_Performance.png
200+
datasets/ANEH/RICJ880105_PLS_LOOCV_ML_Model_Performance.png
201+
datasets/ANEH/Recomb_Triple_Split/Predictions_MLplmc_TopRecomb_Triple_Split.txt
202+
datasets/ANEH/Recomb_Triple_Split/Predictions_MLgremlin_TopRecomb_Triple_Split.txt
203+
datasets/ANEH/Recomb_Quintuple_Split/Predictions_ONEHOT_TopRecomb_Quintuple_Split.txt
204+
datasets/ANEH/Recomb_Quintuple_Split/Predictions_MLplmc_TopRecomb_Quintuple_Split.txt
205+
datasets/ANEH/Recomb_Quintuple_Split/Predictions_MLgremlin_TopRecomb_Quintuple_Split.txt
206+
datasets/ANEH/Recomb_Quintuple_Split/Predictions_FAUJ880104_TopRecomb_Quintuple_Split.txt
207+
datasets/ANEH/Recomb_Quadruple_Split/Predictions_ONEHOT_TopRecomb_Quadruple_Split.txt
208+
datasets/ANEH/Recomb_Quadruple_Split/Predictions_MLplmc_TopRecomb_Quadruple_Split.txt
209+
datasets/ANEH/Recomb_Quadruple_Split/Predictions_MLgremlin_TopRecomb_Quadruple_Split.txt
210+
datasets/ANEH/Recomb_Quadruple_Split/Predictions_FAUJ880104_TopRecomb_Quadruple_Split.txt
211+
datasets/ANEH/Recomb_Double_Split/Predictions_Hybrid_TopRecomb_Double_Split.txt
212+
datasets/ANEH/RACS770103_RIDGE_ML_Model_Performance.png
213+
datasets/ANEH/RACS770103_ELASTICNET_ML_Model_Performance.png
214+
datasets/ANEH/QIAN880129_PLS_LOOCV_ML_Model_Performance.png
215+
datasets/ANEH/Predictions_Hybrid_Top37_ANEH_variants_prediction_set.txt
216+
datasets/ANEH/Pickles/RICJ880105
217+
datasets/ANEH/Pickles/RACS770103
218+
datasets/ANEH/Pickles/QIAN880129
219+
datasets/ANEH/Pickles/MANP780101
220+
datasets/ANEH/Pickles/KARS160122
221+
datasets/ANEH/Pickles/KARS160113
222+
datasets/ANEH/Pickles/KARS160106
223+
datasets/ANEH/Pickles/KARS160104
224+
datasets/ANEH/Pickles/HYBRIDplmc
225+
datasets/ANEH/Pickles/HYBRIDgremlin
226+
datasets/ANEH/Pickles/HYBRID_LVL_1
227+
datasets/ANEH/Pickles/FINA770101
228+
datasets/ANEH/Pickles/FAUJ880103
229+
datasets/ANEH/Pickles/CHOP780215
230+
datasets/ANEH/Pickles/CHOP780211
231+
datasets/ANEH/Pickles/CHOC760101
232+
datasets/ANEH/Pickles/CHAM830106
233+
datasets/ANEH/Pickles/CHAM830104
234+
datasets/ANEH/ONEHOT_RIDGE_ML_Model_Performance.png
235+
datasets/ANEH/ONEHOT_PLS_LOOCV_ML_Model_Performance.png
236+
datasets/ANEH/ONEHOT_LASSO_ML_Model_Performance.png
237+
datasets/ANEH/ONEHOT_ELASTICNET_ML_Model_Performance.png
238+
datasets/ANEH/MLgremlin_DE_trajectories.png
239+
datasets/ANEH/ml_pls_37_ANEH_variants_plmc_dca_encoded_train_lvl_1_extrapolation.png
240+
datasets/ANEH/ml_pls_37_ANEH_variants_plmc_dca_encoded_train_concat_lvls_extrapolation.png
241+
datasets/ANEH/ml_pls_37_ANEH_variants_gremlin_dca_encoded_train_lvl_1_extrapolation.png
242+
datasets/ANEH/ml_pls_37_ANEH_variants_gremlin_dca_encoded_train_concat_lvls_extrapolation.png
243+
datasets/ANEH/MITS020101_PLS_LOOCV_ML_Model_Performance.png
244+
datasets/ANEH/MANP780101_RIDGE_ML_Model_Performance.png
245+
datasets/ANEH/MANP780101_ELASTICNET_ML_Model_Performance.png
246+
datasets/ANEH/low_N_37_ANEH_variants_plmc_dca_encoded_ml_pls.png
247+
datasets/ANEH/low_N_37_ANEH_variants_gremlin_dca_encoded_ml_pls.png
248+
datasets/ANEH/low_N_37_ANEH_variants_dca_encoded_hybrid_ridge.png
249+
datasets/ANEH/KARS160122_LASSO_ML_Model_Performance.png
250+
datasets/ANEH/KARS160122_ELASTICNET_ML_Model_Performance.png
251+
datasets/ANEH/KARS160113_PLS_LOOCV_ML_Model_Performance.png
252+
datasets/ANEH/KARS160113_LASSO_ML_Model_Performance.png
253+
datasets/ANEH/KARS160111_PLS_LOOCV_ML_Model_Performance.png
254+
datasets/ANEH/KARS160106_LASSO_ML_Model_Performance.png
255+
datasets/ANEH/KARS160104_LASSO_ML_Model_Performance.png
256+
datasets/ANEH/HYBRIDplmc_DE_trajectories.png
257+
datasets/ANEH/hybrid_ridge_37_ANEH_variants_dca_encoded_train_lvl_1_extrapolation.png
258+
datasets/ANEH/hybrid_ridge_37_ANEH_variants_dca_encoded_train_concat_lvls_extrapolation.png
259+
datasets/ANEH/FUKS010102_PLS_LOOCV_ML_Model_Performance.png
260+
datasets/ANEH/FINA770101_LASSO_ML_Model_Performance.png
261+
datasets/ANEH/FAUJ880110_RIDGE_ML_Model_Performance.png
262+
datasets/ANEH/FAUJ880110_ELASTICNET_ML_Model_Performance.png
263+
datasets/ANEH/FAUJ880104_PLS_LOOCV_ML_Model_Performance.png
264+
datasets/ANEH/FAUJ880103_LASSO_ML_Model_Performance.png
265+
datasets/ANEH/FAUJ880103_ELASTICNET_ML_Model_Performance.png
266+
datasets/ANEH/Diverse_Double_Split/Predictions_MLplmc_TopDiverse_Double_Split.txt
267+
datasets/ANEH/Diverse_Double_Split/Predictions_MLgremlin_TopDiverse_Double_Split.txt
268+
datasets/ANEH/DCA_RIDGE_ML_Model_Performance.png
269+
datasets/ANEH/DCA_PLS_LOOCV_ML_Model_Performance.png
270+
datasets/ANEH/DCA_LASSO_ML_Model_Performance.png
271+
datasets/ANEH/DCA_Hybrid_Model_Performance.png
272+
datasets/ANEH/DCA_ELASTICNET_ML_Model_Performance.png
273+
datasets/ANEH/CV_performance/WEBA780101_RIDGE_CV_Results.txt
274+
datasets/ANEH/CV_performance/WEBA780101_RIDGE_5-fold-CV.png
275+
datasets/ANEH/CV_performance/WEBA780101_PLS_LOOCV_CV_Results.txt
276+
datasets/ANEH/CV_performance/WEBA780101_PLS_LOOCV_5-fold-CV.png
277+
datasets/ANEH/CV_performance/WEBA780101_ELASTICNET_CV_Results.txt
278+
datasets/ANEH/CV_performance/WEBA780101_ELASTICNET_5-fold-CV.png
279+
datasets/ANEH/CV_performance/SUEM840102_RIDGE_CV_Results.txt
280+
datasets/ANEH/CV_performance/SUEM840102_RIDGE_5-fold-CV.png
281+
datasets/ANEH/CV_performance/SUEM840102_LASSO_CV_Results.txt
282+
datasets/ANEH/CV_performance/SUEM840102_LASSO_5-fold-CV.png
283+
datasets/ANEH/CV_performance/SUEM840102_ELASTICNET_CV_Results.txt
284+
datasets/ANEH/CV_performance/SUEM840102_ELASTICNET_5-fold-CV.png
285+
datasets/ANEH/CV_performance/RICJ880105_PLS_LOOCV_CV_Results.txt
286+
datasets/ANEH/CV_performance/RICJ880105_PLS_LOOCV_5-fold-CV.png
287+
datasets/ANEH/CV_performance/RACS770103_RIDGE_CV_Results.txt
288+
datasets/ANEH/CV_performance/RACS770103_RIDGE_5-fold-CV.png
289+
datasets/ANEH/CV_performance/RACS770103_ELASTICNET_CV_Results.txt
290+
datasets/ANEH/CV_performance/RACS770103_ELASTICNET_5-fold-CV.png
291+
datasets/ANEH/CV_performance/QIAN880129_PLS_LOOCV_CV_Results.txt
292+
datasets/ANEH/CV_performance/QIAN880129_PLS_LOOCV_5-fold-CV.png
293+
datasets/ANEH/CV_performance/ONEHOT_RIDGE_CV_Results.txt
294+
datasets/ANEH/CV_performance/ONEHOT_RIDGE_5-fold-CV.png
295+
datasets/ANEH/CV_performance/ONEHOT_PLS_LOOCV_CV_Results.txt
296+
datasets/ANEH/CV_performance/ONEHOT_PLS_LOOCV_5-fold-CV.png
297+
datasets/ANEH/CV_performance/ONEHOT_LASSO_CV_Results.txt
298+
datasets/ANEH/CV_performance/ONEHOT_LASSO_5-fold-CV.png
299+
datasets/ANEH/CV_performance/ONEHOT_ELASTICNET_CV_Results.txt
300+
datasets/ANEH/CV_performance/ONEHOT_ELASTICNET_5-fold-CV.png
301+
datasets/ANEH/CV_performance/MITS020101_PLS_LOOCV_CV_Results.txt
302+
datasets/ANEH/CV_performance/MITS020101_PLS_LOOCV_5-fold-CV.png
303+
datasets/ANEH/CV_performance/MANP780101_RIDGE_CV_Results.txt
304+
datasets/ANEH/CV_performance/MANP780101_RIDGE_5-fold-CV.png
305+
datasets/ANEH/CV_performance/MANP780101_ELASTICNET_CV_Results.txt
306+
datasets/ANEH/CV_performance/MANP780101_ELASTICNET_5-fold-CV.png
307+
datasets/ANEH/CV_performance/KARS160122_LASSO_CV_Results.txt
308+
datasets/ANEH/CV_performance/KARS160122_LASSO_5-fold-CV.png
309+
datasets/ANEH/CV_performance/KARS160122_ELASTICNET_CV_Results.txt
310+
datasets/ANEH/CV_performance/KARS160122_ELASTICNET_5-fold-CV.png
311+
datasets/ANEH/CV_performance/KARS160113_PLS_LOOCV_CV_Results.txt
312+
datasets/ANEH/CV_performance/KARS160113_PLS_LOOCV_5-fold-CV.png
313+
datasets/ANEH/CV_performance/KARS160113_LASSO_CV_Results.txt
314+
datasets/ANEH/CV_performance/KARS160113_LASSO_5-fold-CV.png
315+
datasets/ANEH/CV_performance/KARS160111_PLS_LOOCV_CV_Results.txt
316+
datasets/ANEH/CV_performance/KARS160111_PLS_LOOCV_5-fold-CV.png
317+
datasets/ANEH/CV_performance/KARS160106_LASSO_CV_Results.txt
318+
datasets/ANEH/CV_performance/KARS160106_LASSO_5-fold-CV.png
319+
datasets/ANEH/CV_performance/KARS160104_LASSO_CV_Results.txt
320+
datasets/ANEH/CV_performance/KARS160104_LASSO_5-fold-CV.png
321+
datasets/ANEH/CV_performance/FUKS010102_PLS_LOOCV_CV_Results.txt
322+
datasets/ANEH/CV_performance/FUKS010102_PLS_LOOCV_5-fold-CV.png
323+
datasets/ANEH/CV_performance/FINA770101_LASSO_CV_Results.txt
324+
datasets/ANEH/CV_performance/FINA770101_LASSO_5-fold-CV.png
325+
datasets/ANEH/CV_performance/FAUJ880110_RIDGE_CV_Results.txt
326+
datasets/ANEH/CV_performance/FAUJ880110_RIDGE_5-fold-CV.png
327+
datasets/ANEH/CV_performance/FAUJ880110_ELASTICNET_CV_Results.txt
328+
datasets/ANEH/CV_performance/FAUJ880110_ELASTICNET_5-fold-CV.png
329+
datasets/ANEH/CV_performance/FAUJ880104_PLS_LOOCV_CV_Results.txt
330+
datasets/ANEH/CV_performance/FAUJ880104_PLS_LOOCV_5-fold-CV.png
331+
datasets/ANEH/CV_performance/FAUJ880103_LASSO_CV_Results.txt
332+
datasets/ANEH/CV_performance/FAUJ880103_LASSO_5-fold-CV.png
333+
datasets/ANEH/CV_performance/FAUJ880103_ELASTICNET_CV_Results.txt
334+
datasets/ANEH/CV_performance/FAUJ880103_ELASTICNET_5-fold-CV.png
335+
datasets/ANEH/CV_performance/DCA_RIDGE_CV_Results.txt
336+
datasets/ANEH/CV_performance/DCA_RIDGE_5-fold-CV.png
337+
datasets/ANEH/CV_performance/DCA_PLS_LOOCV_CV_Results.txt
338+
datasets/ANEH/CV_performance/DCA_PLS_LOOCV_5-fold-CV.png
339+
datasets/ANEH/CV_performance/DCA_LASSO_CV_Results.txt
340+
datasets/ANEH/CV_performance/DCA_LASSO_5-fold-CV.png
341+
datasets/ANEH/CV_performance/DCA_ELASTICNET_CV_Results.txt
342+
datasets/ANEH/CV_performance/DCA_ELASTICNET_5-fold-CV.png
343+
datasets/ANEH/CV_performance/CHOP780215_LASSO_CV_Results.txt
344+
datasets/ANEH/CV_performance/CHOP780215_LASSO_5-fold-CV.png
345+
datasets/ANEH/CV_performance/CHOP780211_RIDGE_CV_Results.txt
346+
datasets/ANEH/CV_performance/CHOP780211_RIDGE_5-fold-CV.png
347+
datasets/ANEH/CV_performance/CHOC760101_LASSO_CV_Results.txt
348+
datasets/ANEH/CV_performance/CHOC760101_LASSO_5-fold-CV.png
349+
datasets/ANEH/CV_performance/CHAM830106_RIDGE_CV_Results.txt
350+
datasets/ANEH/CV_performance/CHAM830106_RIDGE_5-fold-CV.png
351+
datasets/ANEH/CV_performance/CHAM830106_LASSO_CV_Results.txt
352+
datasets/ANEH/CV_performance/CHAM830106_LASSO_5-fold-CV.png
353+
datasets/ANEH/CV_performance/CHAM830106_ELASTICNET_CV_Results.txt
354+
datasets/ANEH/CV_performance/CHAM830106_ELASTICNET_5-fold-CV.png
355+
datasets/ANEH/CV_performance/CHAM830105_RIDGE_CV_Results.txt
356+
datasets/ANEH/CV_performance/CHAM830105_RIDGE_5-fold-CV.png
357+
datasets/ANEH/CV_performance/CHAM830105_PLS_LOOCV_CV_Results.txt
358+
datasets/ANEH/CV_performance/CHAM830105_PLS_LOOCV_5-fold-CV.png
359+
datasets/ANEH/CV_performance/CHAM830105_ELASTICNET_CV_Results.txt
360+
datasets/ANEH/CV_performance/CHAM830105_ELASTICNET_5-fold-CV.png
361+
datasets/ANEH/CV_performance/CHAM830104_RIDGE_CV_Results.txt
362+
datasets/ANEH/CV_performance/CHAM830104_RIDGE_5-fold-CV.png
363+
datasets/ANEH/CV_performance/CHAM830104_PLS_LOOCV_CV_Results.txt
364+
datasets/ANEH/CV_performance/CHAM830104_PLS_LOOCV_5-fold-CV.png
365+
datasets/ANEH/CHOP780215_LASSO_ML_Model_Performance.png
366+
datasets/ANEH/CHOP780211_RIDGE_ML_Model_Performance.png
367+
datasets/ANEH/CHOC760101_LASSO_ML_Model_Performance.png
368+
datasets/ANEH/CHAM830106_RIDGE_ML_Model_Performance.png
369+
datasets/ANEH/CHAM830106_LASSO_ML_Model_Performance.png
370+
datasets/ANEH/CHAM830106_ELASTICNET_ML_Model_Performance.png
371+
datasets/ANEH/CHAM830105_RIDGE_ML_Model_Performance.png
372+
datasets/ANEH/CHAM830105_PLS_LOOCV_ML_Model_Performance.png
373+
datasets/ANEH/CHAM830105_ELASTICNET_ML_Model_Performance.png
374+
datasets/ANEH/CHAM830104_RIDGE_ML_Model_Performance.png
375+
datasets/ANEH/CHAM830104_PLS_LOOCV_ML_Model_Performance.png
376+
datasets/ANEH/37_ANEH_variants_plmc_dca_encoded.csv
377+
datasets/ANEH/37_ANEH_variants_gremlin_dca_encoded.csv

‎scripts/CLI/Workflow_PyPEF.ipynb‎

Lines changed: 0 additions & 9 deletions
Original file line numberDiff line numberDiff line change
@@ -994,15 +994,6 @@
994994
"metadata": {
995995
"collapsed": false
996996
}
997-
},
998-
{
999-
"cell_type": "code",
1000-
"execution_count": null,
1001-
"outputs": [],
1002-
"source": [],
1003-
"metadata": {
1004-
"collapsed": false
1005-
}
1006997
}
1007998
],
1008999
"metadata": {

‎scripts/CLI/run_cli_tests_linux.sh‎

Lines changed: 1 addition & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -41,9 +41,8 @@ threads=12
4141
### Pure ML (and some hybrid model) tests on ANEH dataset
4242
cd "$path/datasets/ANEH"
4343
#######################################################################
44-
echo $PWD
4544
echo
46-
exit
45+
4746
$pypef --version
4847
echo
4948
$pypef -h

0 commit comments

Comments
 (0)