Tag: ChEMBL

Researchers used a recurrent neural network fine-tuned on 5,178 validated mTOR inhibitors to generate 200 novel molecules, four of which ...

Researchers fused machine learning, molecular docking and molecular dynamics simulations into a virtual screening pipeline that discovered HY-18,623, a nanomolar ...

Researchers have introduced a unified family of sum-connectivity descriptors that reweights classical molecular graph indices and shows systematic gains in ...

Researchers combined machine learning and deep learning with multiple molecular fingerprints to build predictive models that identified two promising topoisomerase ...

Researchers have introduced a fourteen-member family of product-connectivity molecular descriptors that mitigate the dominance of highly connected substructures in classical ...

Researchers have built a fully open-source KNIME machine-learning workflow that curates thousands of PD-L1 bioactivity records and reliably predicts inhibitor ...