Computational tools for drug discovery: AI-based

ToolsPurposeReferences
DeepChemDrug discovery task prediction[28]
DTI-CNNDL based drug-target interaction prediction[29]
ORGANICMolecular generation tool with desired properties[30]
ChemputerChemical synthesis reporting procedure[31]
DeltaVinaRescoring protein-ligand binding affinity: scoring[32]
DeepCPIDrug–protein interaction prediction[33]
PotentialNetA CNN graph-based ligand-binding affinity prediction[34]
DeepNeuralNet-QSARPrediction of molecular activity[35]
Hit DexterPrediction of molecules responding to biochemical assays[36]
DeepToxFor toxicity prediction[37]
PPB2Polypharmacology prediction[38]
SCScoreFor evaluation of the synthesis complexity of a molecule[39]
NNScoreProtein-ligand interaction scoring study[40]
SIEVE-ScoreStructure-based virtual screening[41]
REINVENTMolecular de novo design based on RNN and RL[42]

RL: reinforcement learning; DTI-CNN: drug-target interaction-CNN; QSAR: quantitative structure-activity relationship; PPB2: polypharmacology browser 2; SCScore: synthetic complexity score; SIEVE-Score: similarity of interaction energy vector-score; DeepTox: DL for toxicity; NNScore: neutral-network receptor-ligand scoring function