Dev 0.4.0

.github/workflows/build.yml

@@ -9,13 +9,12 @@ permissions:
   contents: read
 
 jobs:
-  build:
-
+  ubuntu:
+    name: ubuntu
     runs-on: [ubuntu-latest]
     strategy:
       matrix:
-        python-version: ["3.9", "3.10", "3.11", "3.12"]
-
+        python-version: ["3.10", "3.11", "3.12"]
     steps:
     - uses: actions/checkout@v4
     - name: Set up Python ${{ matrix.python-version }}
@@ -37,3 +36,32 @@ jobs:
     - name: Export Pythonpath and run PyPEF API and CLI version test with pytest
       run: |
         export PYTHONPATH="${PYTHONPATH}:${PWD}" && python -m pytest tests/
+
+  windows:
+    name: windows
+    runs-on: [windows-latest]
+    strategy:
+      matrix:
+        python-version: ["3.10", "3.11", "3.12"]
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v5
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Display Path and Python version
+      run: |
+        python -c "import sys, platform; print(sys.version, platform.system())"
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install flake8 pytest
+        pip install -r requirements.txt
+    - name: Lint with flake8
+      run: |
+        # stop the build if there are Python syntax errors or undefined names
+        flake8 .\pypef --count --select=E9,F63,F7,F82 --show-source --statistics
+    - name: Export Pythonpath and run PyPEF API and CLI version test with pytest
+      shell: pwsh
+      run: |
+        $env:PYTHONPATH = "${PWD};${env:PYTHONPATH}";python -m pytest .\tests\

.gitignore

@@ -18,19 +18,40 @@ __pycache__/
 scripts/ProteinGym_runs/DMS_msa_files/
 scripts/ProteinGym_runs/DMS_ProteinGym_substitutions/
 scripts/ProteinGym_runs/ProteinGym_AF2_structures/
-scripts/ProteinGym_runs/multi_point_dms_mut_data.json
-scripts/ProteinGym_runs/single_point_dms_mut_data.json
-scripts/ProteinGym_runs/higher_point_dms_mut_data.json
 scripts/ProteinGym_runs/_Description_DMS_substitutions_data.csv
 
-scripts/ProteinGym_runs/single_point_mut_performance.png
-scripts/ProteinGym_runs/multi_point_mut_performance.png
-
 # Created test/output files
+model_saves/*
+avGFP_shortened_dca_encoded.csv
+avGFP_dca_encoded.csv
+
 scripts/Setup/windows/Miniconda3-latest-Windows-x86_64.exe
 scripts/Setup/windows/Miniconda3/*
+
 scripts/Encoding_low_N/apc.png
 scripts/Encoding_low_N/low_N_avGFP_extrapolation.png
+
+scripts/Runtime_tests/runtimes.png
+
+scripts/ProteinGym_runs/multi_point_dms_mut_data.json
+scripts/ProteinGym_runs/single_point_dms_mut_data.json
+scripts/ProteinGym_runs/higher_point_dms_mut_data.json
+scripts/ProteinGym_runs/single_point_mut_performance_violin.png
+scripts/ProteinGym_runs/multi_point_mut_performance_violin.png
+scripts/ProteinGym_runs/single_point_mut_performance.png
+scripts/ProteinGym_runs/multi_point_mut_performance.png
+
+scripts/ESM_finetuning/DMS_msa_files/
+scripts/ESM_finetuning/DMS_ProteinGym_substitutions/
+scripts/ESM_finetuning/ProteinGym_AF2_structures/
+scripts/ESM_finetuning/higher_point_dms_mut_data.json
+scripts/ESM_finetuning/single_point_dms_mut_data.json
+scripts/ESM_finetuning/results/dca_esm_and_hybrid_opt_results_clean.csv
+scripts/ESM_finetuning/results/dca_esm_and_hybrid_opt_results.csv
+scripts/ESM_finetuning/mut_performance.png
+scripts/ESM_finetuning/_Description_DMS_substitutions_data.csv
+scripts/ESM_finetuning/mut_performance_violin.png
+
 datasets/ANEH/37_ANEH_variants_aaidx_encoded.csv
 datasets/ANEH/37_ANEH_variants_dca_encoded.csv
 datasets/ANEH/37_ANEH_variants_gremlin_dca_encoded.csv
@@ -317,6 +338,29 @@ datasets/ANEH/Recomb_Triple_Split/Predictions_MLgremlin_TopRecomb_Triple_Split.t
 datasets/ANEH/Recomb_Triple_Split/Predictions_MLplmc_TopRecomb_Triple_Split.txt
 datasets/ANEH/Recomb_Triple_Split/Predictions_ONEHOT_TopRecomb_Triple_Split.txt
 datasets/ANEH/Recomb_Triple_Split/Recomb_Triple_Split0.fasta
+datasets/ANEH/ML_Model_Performance_CHAM830106_PLS_LOOCV.png
+datasets/ANEH/ML_Model_Performance_CHOP780206_PLS_LOOCV.png
+datasets/ANEH/ML_Model_Performance_ZHOH040102_PLS.png
+datasets/ANEH/CV_performance/CHAM830106_PLS_LOOCV_5-fold-CV.png
+datasets/ANEH/CV_performance/CHAM830106_PLS_LOOCV_CV_Results.txt
+datasets/ANEH/CV_performance/CHOP780206_PLS_LOOCV_5-fold-CV.png
+datasets/ANEH/CV_performance/CHOP780206_PLS_LOOCV_CV_Results.txt
+datasets/ANEH/CV_performance/ZHOH040102_PLS_5-fold-CV.png
+datasets/ANEH/CV_performance/ZHOH040102_PLS_CV_Results.txt
+datasets/ANEH/Pickles/CHOP780206
+datasets/ANEH/Pickles/ZHOH040102
+datasets/ANEH/DCA_Hybrid_Model_Performance_ESM1v_no_ML.png
+datasets/ANEH/DCA_Hybrid_Model_Performance_GREMLIN_.png
+datasets/ANEH/DCA_Hybrid_Model_Performance_GREMLIN_ESM.png
+datasets/ANEH/DCA_Hybrid_Model_Performance_GREMLIN_no_ML_ESM.png
+datasets/ANEH/DCA_Hybrid_Model_Performance_Hybrid_ESM1v_ESM.png
+datasets/ANEH/DCA_Hybrid_Model_Performance_PLMC_.png
+datasets/ANEH/HYBRIDGREMLINESM1V_DE_trajectories.png
+datasets/ANEH/Predictions_Hybrid_ESM1v_Top37_ANEH_variants_prediction_set.txt
+datasets/ANEH/Pickles/HYBRIDGREMLINESM1V
+datasets/ANEH/SSM_landscape.png
+datasets/ANEH/SSM_landscape.csv
+
 datasets/AVGFP/apc.png
 datasets/AVGFP/avGFP_aaidx_encoded.csv
 datasets/AVGFP/avGFP_dca_encoded.csv
@@ -395,10 +439,19 @@ datasets/AVGFP/Recomb_Double_Split/Recomb_Double_Split4.fasta
 datasets/AVGFP/Recomb_Double_Split/Recomb_Double_Split5.fasta
 datasets/AVGFP/Recomb_Double_Split/Recomb_Double_Split6.fasta
 datasets/AVGFP/Recomb_Double_Split/Recomb_Double_Split7.fasta
-avGFP_shortened_dca_encoded.csv
-datasets/AVGFP/avGFP_shortened.csv
-avGFP_dca_encoded.csv
-scripts/Runtime_tests/runtimes.png
 datasets/AVGFP/Recomb_Double_Split/Predictions_Hybrid_TopRecomb_Double_Split.txt
-scripts/ProteinGym_runs/single_point_mut_performance_violin.png
-scripts/ProteinGym_runs/multi_point_mut_performance_violin.png
+datasets/AVGFP/model_saves/*
+datasets/AVGFP/Pickles/*
+datasets/AVGFP/DCA_Hybrid_Model_Performance_ESM1v_no_ML.png
+datasets/AVGFP/DCA_Hybrid_Model_Performance_ProSST_no_ML.png
+datasets/AVGFP/HYBRIDgremlinesm_DE_trajectories.png
+datasets/AVGFP/HYBRIDgremlinprosst_DE_trajectories.png
+datasets/AVGFP/DCA_Hybrid_Model_Performance_GREMLIN_.png
+datasets/AVGFP/SSM_landscape.csv
+datasets/AVGFP/SSM_landscape.png
+datasets/AVGFP/DCA_Hybrid_Model_Performance_GREMLIN_PROSST.png
+datasets/AVGFP/DCA_Hybrid_Model_Performance_Hybrid_ProSST_PROSST.png
+datasets/AVGFP/HYBRIDGREMLINESM1V_DE_trajectories.png
+datasets/AVGFP/Recomb_Double_Split/Predictions_Hybrid_ESM1v_TopRecomb_Double_Split.txt
+datasets/AVGFP/Recomb_Double_Split/Predictions_Hybrid_ProSST_TopRecomb_Double_Split.txt
+datasets/AVGFP/avGFP_shortened.csv