Tox21
PulseAugur coverage of Tox21 — every cluster mentioning Tox21 across labs, papers, and developer communities, ranked by signal.
-
New framework uses LLMs to learn interpretable logic programs
Researchers have developed a new neurosymbolic framework called grasp that combines language models with functional gradient boosting to learn probabilistic logic programs. This approach addresses the difficulty of indu…
-
New 'Predictive Credit' Protocol Measures Value of AI Explanations in Science
A new research paper introduces "Predictive Credit," a protocol designed to measure the value of scientific explanations in improving experimental forecasts. The study tested this protocol across various datasets, inclu…
-
ToxLens framework enhances molecular toxicity prediction with leakage-aware learning
Researchers have developed ToxLens, a novel graph-learning framework designed to improve the accuracy and reliability of molecular toxicity predictions. This framework addresses the issue of performance overstatement in…
-
Graph tools boost small language model molecular prediction accuracy by up to 74%
A new arXiv paper introduces a Context-Augmented Prompting framework designed to enhance the molecular property prediction capabilities of small language models (SLMs). This framework enables SLMs to utilize external to…
-
Pharmacogenomic data boosts drug-drug interaction prediction with GNNs
Researchers have developed a method to enhance drug-drug interaction (DDI) prediction using Graph Neural Networks (GNNs) by incorporating pharmacogenomic data. This approach augments molecular structure information with…
-
Study finds smaller AI models outperform large ones in drug discovery predictions
A new paper challenges the assumption that larger AI models are always superior in drug discovery. Researchers found that classical machine learning models and graph neural networks often outperform larger, general-purp…