File size: 4,140 Bytes
baf3373 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 |
############################ Training Classifier ############################
HOME_LOC="x"
SCRIPT_LOC=$HOME_LOC/Classifier_Weight/training_classifiers
DATA_LOC=$HOME_LOC/Classifier_Weight/training_data_cleaned
OBJECTIVE='hemolysis' # nf/solubility/hemolysis
WT='smiles' # wt/smiles
DATA_FILE="hemo_${WT}_with_embeddings"
LOG_LOC=$SCRIPT_LOC/src/logs
DATE=$(date +%m_%d)
MODEL_TYPE='svm_gpu' # xgb/enet_gpu/svm_gpu
SPECIAL_PREFIX="${MODEL_TYPE}-${OBJECTIVE}-${WT}_new"
cd $SCRIPT_LOC
python -u train_ml.py \
--dataset_path "${DATA_LOC}/${OBJECTIVE}/${DATA_FILE}" \
--out_dir "${SCRIPT_LOC}/${OBJECTIVE}/${MODEL_TYPE}_${WT}_new" \
--model "${MODEL_TYPE}" \
--n_trials 20 > "${LOG_LOC}/${DATE}_${SPECIAL_PREFIX}.log" 2>&1
echo "Script completed at $(date)"
############################ Training Classifier (NN) ############################
HOME_LOC="x"
SCRIPT_LOC=$HOME_LOC/Classifier_Weight/training_classifiers
DATA_LOC=$HOME_LOC/Classifier_Weight/training_data_cleaned
OBJECTIVE='hemolysis' # nf/solubility/hemolysis
WT='smiles' #wt/smiles
DATA_FILE="nf_${WT}_with_embeddings_unpooled"
LOG_LOC=$SCRIPT_LOC/src/logs
DATE=$(date +%m_%d)
MODEL_TYPE='cnn' #mlp/cnn/transformer
SPECIAL_PREFIX="${MODEL_TYPE}-${OBJECTIVE}-${WT}"
# Create log directory if it doesn't exist
mkdir -p $LOG_LOC
cd $SCRIPT_LOC
python -u train_nn.py \
--dataset_path "${DATA_LOC}/${OBJECTIVE}/${DATA_FILE}" \
--out_dir "${SCRIPT_LOC}/${OBJECTIVE}/${MODEL_TYPE}_${WT}_20" \
--model "${MODEL_TYPE}" \
--n_trials 20 > "${LOG_LOC}/${DATE}_${SPECIAL_PREFIX}_20.log" 2>&1
echo "Script completed at $(date)"
############################ Training Regressor ############################
HOME_LOC="x"
SCRIPT_LOC=$HOME_LOC/Classifier_Weight/training_classifiers
DATA_LOC=$HOME_LOC/Classifier_Weight/training_data_cleaned
OBJECTIVE='permeability_pampa' # permeability_pampa/permeability_caco2
WT='smiles' # wt/smiles
DATA_FILE="pampa_${WT}_with_embeddings"
LOG_LOC=$SCRIPT_LOC/src/logs
DATE=$(date +%m_%d)
MODEL_TYPE='svr' # xgb_reg/enet_gpu/svr
SPECIAL_PREFIX="${MODEL_TYPE}-${OBJECTIVE}-${WT}"
# Create log directory if it doesn't exist
mkdir -p $LOG_LOC
cd $SCRIPT_LOC
python -u train_ml_regression.py \
--dataset_path "${DATA_LOC}/${OBJECTIVE}/${DATA_FILE}" \
--out_dir "${SCRIPT_LOC}/${OBJECTIVE}/${MODEL_TYPE}_${WT}10" \
--model "${MODEL_TYPE}" \
--n_trials 10 > "${LOG_LOC}/${DATE}_${SPECIAL_PREFIX}10.log" 2>&1
echo "Script completed at $(date)"
############################ Training Regressor (NN) ############################
HOME_LOC="x"
SCRIPT_LOC=$HOME_LOC/Classifier_Weight/training_classifiers
DATA_LOC=$HOME_LOC/Classifier_Weight/training_data_cleaned
OBJECTIVE='permeability_caco2' # permeability_pampa/permeability_caco2
WT='smiles' # wt/smiles
DATA_FILE="caco2_${WT}_with_embeddings_unpooled"
LOG_LOC=$SCRIPT_LOC/src/logs
DATE=$(date +%m_%d)
MODEL_TYPE='mlp' #mlp/cnn/transformer
SPECIAL_PREFIX="${MODEL_TYPE}-${OBJECTIVE}-${WT}"
# Create log directory if it doesn't exist
mkdir -p $LOG_LOC
cd $SCRIPT_LOC
python -u train_nn_regression.py \
--dataset_path "${DATA_LOC}/${OBJECTIVE}/${DATA_FILE}" \
--out_dir "${SCRIPT_LOC}/${OBJECTIVE}/${MODEL_TYPE}_${WT}" \
--model "${MODEL_TYPE}" \
--n_trials 200 > "${LOG_LOC}/${DATE}_${SPECIAL_PREFIX}.log" 2>&1
echo "Script completed at $(date)"
############################ Training Binding Affinity Predictor ############################
HOME_LOC="x"
SCRIPT_LOC=$HOME_LOC/Classifier_Weight/training_classifiers
DATA_LOC=$HOME_LOC/Classifier_Weight/training_data_cleaned
OBJECTIVE='binding_affinity'
WT='smiles' #wt/smiles
STATUS='pooled' #pooled/unpooled
DATA_FILE="pair_wt_${WT}_${STATUS}"
LOG_LOC=$SCRIPT_LOC/src/logs
DATE=$(date +%m_%d)
SPECIAL_PREFIX="${OBJECTIVE}-${WT}-${STATUS}"
# Create log directory if it doesn't exist
mkdir -p $LOG_LOC
cd $SCRIPT_LOC
python -u binding_training.py \
--dataset_path "${DATA_LOC}/${OBJECTIVE}/${DATA_FILE}" \
--mode "${STATUS}" \
--out_dir "${SCRIPT_LOC}/${OBJECTIVE}/wt_${WT}_${STATUS}" \
--n_trials 200 > "${LOG_LOC}/${DATE}_${SPECIAL_PREFIX}.log" 2>&1
echo "Script completed at $(date)" |