Forward Synthesis Planner

ASKCOS Forward Synthesis Planner

Condition recommendation
Synthesis prediction
Impurity prediction
Regio-selectivity prediction
Site selectivity prediction

Predict reagents, catalysts, solvents and temperature for a desired transformation using a neural network model. (ACS Cent. Sci., 2018, 4, 1465-1476)

New in 2021.01: Quantitative condition predictions now available using neural network v2 model. Select in settings menu.

Graph models require atom-mapped reactions. If atom-mapping is not available, please try the fingerprint models instead.

Predict most likely outcomes of a chemical reaction using a template-free WLN model for predicting likely bond changes. (Chem. Sci., 2019, 10, 370-377)

Predict likely impurities for a chemical reaction. Considers minor products, over-reaction, dimerization, solvent adducts, and subsets of reactants.

Predict selectivity of regio-selective reactions. The QM-GNN model combines a WLN graph encoding with predicted quantum descriptors as input to a multitask neural network. (ChemRxiv 2020)

Predict site selectivity of aromatic C-H functionalization reactions with a multitask neural network that uses a WLN graph encoding. (React. Chem. Eng., 2020, 5, 896-902)

Reaction score: %% reactionScore.toFixed(3) %%
# Rank Reactants (Amount) Reagents (Amount) Temperature Predict with conditions
# Rank Reagents Catalyst Solvents Solvent Score Temperature Predict with conditions
Rank Product Probability Max. Score Molecular Weight Predict impurities Predict regio-selectivities
Rank Product Probability
Progress: %% impurityProgress.message %%
No. Predicted impurities Possible mechanisms Inspector score Similarity score
Reactant Sites