Tool for PFASs BAF
BAFs prediction
BATCH prediction
Specific model development and prediction
Step 1. PFASs congener
1.1. Pls input the target chemical name
1.2. Pls input the SMILES of target chemical
1.3. Pls input the logKow values of target chemical
Step 2. Species information
2.1. Please select the speceies
Actiniidae
Alpheidae
Ambassidae
Ampullariidae
Anguillidae
Araceae
Arcidae
Astacidae
Bagridae
Belonidae
Bithyniidae
Carangidae
Centrarchidae
Chelydridae
Cichlidae
Clariidae
Clupeidae
Cobitidae
Congers
Corbiculidae
Cottidae
Crangonidae
Cynoglossidae
Cyperaceae
Cyprinidae
Diogenidae
Dorippidae
Dreissenidae
Eleotridae
Elopidae
Engraulidae
Esocidae
Euryplacidae
Flatfishes
Gammaridae
Gobiidae
Gramineae
Hairtails
Hexagrammidae
Holothuriidae
Hydrocharitaceae
Hymenosomatidae
Ictaluridae
Laminariaceae
Lateolabracidae
Littorinidae
Loliginidae
Lophiidae
Lumbriculidae
Mactridae
Mastacembelidae
Moronidae
Mugilidae
Muricidae
Mysidae
Mytilidae
Nassariidae
Naticidae
Octopodidae
Ocypodidae
Ophiocephalidae
Oplegnathidae
Oryziatidae
Osmeridae
Ostreidae
Paguridae
Palaemonidae
Palinuridae
Pangasiidae
Paralichthyidae
Penaeidae
Percichthyidae
Percidae
Pinnotheridae
Platycephalidae
Pontederiaceae
Portunidae
Potamididae
Potamogetonaceae
Ranidae
Salangidae
Salmonidae
Sciaenidae
Scophthalmidae
Scorpaenidae
Sebastidae
Serranidae
Siluridae
Solecurtidae
Sparidae
Sphyraenidae
Squillidae
Terapontidae
Tetraodontidae
Triglidae
Trionychidae
Typhaceae
Urechidae
Varunidae
Veneridae
Viviparidae
Zoarcidae
species_list
2.2. Pls input the protein content of target speceies(%)
2.3. Pls select the target tissue
Whole body
Liver
Muscle
Step 3. Aquatic system
3.1. Pls select the water type
Freshwater
Seawater
3.2. Pls input the target PFASs concentration in water (ng/L)
Step 4. Prediction
4.1. Click to predict
The predicted BAFs
4.2. Results download
Step 1. File upload
1.1.Choose xlsx file for batch prediction, pls donot change the column name
Browse...
Data template
Step 2. Prediction results
2.1. Click to predict
2.2. Results download
Step 1. Data upload
1.1.Choose xlsx file for model development
Browse...
Data template
1.2.choose xlsx file for model prediction (optional)
Browse...
Data template
Step 2. Data treatment
2.1.Set the threshold to choose chemical descriptors
2.2.Please select the dependent variable
Y
2.3.Pls assign factor variables among independent variables
2.4.Pls assign metric variables among independent variables
Step 3. Model setting
3.1.Whether use the stacking algorithm
No
Yes
3.2.algorithm
Random forest
Bayes glm
SVM
xgboost
GLM
Non-negative least squares
3.2.1.ntree
3.2.2.mtry
3.2.1.booster
gblinear
gbtree
3.2.2.nrounds
3.2.1.base algorithm
Random forest
Bayesian generalized linear regression
Kernlab's SVM
xgboost
generalized linear models
generalized additive models
Multivariate Adaptive Regression Splines
Feed-Forward Neural Networks and Multinomial Log-Linear Models
Non-negative least squares
3.2.2.meta algorithm
Random forest
Bayesian generalized linear regression
Kernlab's SVM
xgboost
generalized linear models
generalized additive models
Multivariate Adaptive Regression Splines
Feed-Forward Neural Networks and Multinomial Log-Linear Models
Non-negative least squares
Step 4. Model development
4.1.Set the fraction of data used for training
4.2.Model development data treatment
4.3.Model prediction data treatment (optional)
4.4.Model development (and prediction)
4.5.Results download