Step Change Improvement in ADMET Prediction with PotentialNet Deep Featurization
The Absorption, Distribution, Metabolism, Elimination, and Toxicity (ADMET) properties of drug candidates are estimated to account for up to 50% of all clinical trial failures. Predicting ADMET properties has therefore been of great interest to the cheminformatics and medicinal chemistry communities in recent decades. Traditional cheminformatics approaches, whether the learner is a random forest or a deep neural network, leverage fixed fingerprint feature representations of molecules. In contrast, in this paper, we learn the features most relevant to each chemical task at hand by representing each molecule explicitly as a graph, where each node is an atom and each edge is a bond. By applying graph convolutions to this explicit molecular representation, we achieve, to our knowledge, unprecedented accuracy in prediction of ADMET properties. By challenging our methodology with rigorous cross-validation procedures and prospective analyses, we show that deep featurization better enables molecular predictors to not only interpolate but also extrapolate to new regions of chemical space.
Code (0)
등록된 구현이 없습니다.
Tasks
molecular representationSimilar Papers 제목 키워드 기반
HelixADMET: a robust and endpoint extensible ADMET system incorporating self-supervised knowledge transfer
Accurate ADMET (an abbreviation for "absorption, distribution, metabolism, excretion, and toxicity") predictions can efficiently screen out undesirable drug candidates in the early stage of drug discovery. In recent year…
Drug DiscoverySelf-Supervised LearningTransfer LearningChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction
Accurate prediction of ADMET (Absorption, Distribution, Metabolism, Excretion, and Toxicity) is important for drug discovery. Most predictors use undirected molecular graphs and pairwise edges. This choice misses asymmet…
Drug DiscoveryAccurate ADMET Prediction with XGBoost
The absorption, distribution, metabolism, excretion, and toxicity (ADMET) properties are important in drug discovery as they define efficacy and safety. In this work, we applied an ensemble of features, including fingerp…
Drug DiscoveryMolecular Property PredictionPredictionTDC ADMET Benchmarking Group+1Auto-ADMET: An Effective and Interpretable AutoML Method for Chemical ADMET Property Prediction
Machine learning (ML) has been playing important roles in drug discovery in the past years by providing (pre-)screening tools for prioritising chemical compounds to pass through wet lab experiments. One of the main ML ta…
AutoMLComputational chemistryDrug DiscoveryProperty PredictionPotentialNet for Molecular Property Prediction
The arc of drug discovery entails a multiparameter optimization problem spanning vast length scales. They key parameters range from solubility (angstroms) to protein-ligand binding (nanometers) to in vivo toxicity (meter…
ARCBIG-bench Machine LearningClusteringDrug Discovery+4