RDKit
PulseAugur coverage of RDKit — every cluster mentioning RDKit across labs, papers, and developer communities, ranked by signal.
4 day(s) with sentiment data
-
GFlowNet interpretability study questions learned chemistry in drug discovery models
A new study published on arXiv investigates the interpretability of GFlowNets, a type of AI model used for drug discovery. Researchers developed a framework to analyze SynFlowNet, a GFlowNet trained on drug-likeness, an…
-
New Python library bridges molecular ML and scikit-learn
A new Python library called scikit-fingerprints has been released, designed to integrate molecular machine learning functionalities with the scikit-learn ecosystem. This library, built upon RDKit, provides a unified int…
-
Study probes explicit view routing in graph-text alignment models
Researchers have investigated the effectiveness of explicit view routing in graph-text alignment models, particularly for tasks involving molecular graphs and their textual descriptions. Their controlled study, using th…
-
New audit framework assesses molecular AI representations beyond predictive accuracy
A new research paper introduces a reliability-aware audit for molecular representations, moving beyond simple predictive accuracy. The study evaluates generic molecular encoders like MoLFormer and ChemBERTa against conv…
-
APEX protocol enables rapid virtual screening of massive drug discovery libraries
Researchers have developed APEX, a novel protocol for efficiently searching massive combinatorial synthesis libraries (CSLs) used in drug discovery. APEX employs a neural network surrogate to predict compound objectives…
-
AI Co-Scientist Workflow Targets EGFR Inhibitor Resistance
Researchers have developed an AI co-scientist workflow to discover new EGFR inhibitors, specifically targeting the C797S mutation that causes resistance to existing treatments. The process involves using ChEMBL and UniP…
-
New AI method recovers valid molecules from text prompts
Researchers have introduced AMREC, a novel approach for recovering valid molecular structures from text-guided generation by large language models. Unlike previous methods that focused solely on fixing invalid chemical …
-
New frameworks leverage LLMs and evolution for AI agent generation
Researchers have developed novel frameworks for generating and refining multi-agent systems (MAS) using evolutionary algorithms and large language models (LLMs). EvoMAS, for instance, employs evolutionary generation in …
-
AI model learns chemical properties from molecular data, controlling for sequence shortcuts
Researchers have developed a new method to evaluate molecular generative models, specifically Transformer-VAEs trained on SELFIES. Their approach addresses the issue where apparent property predictability might stem fro…
-
Bolek model grounds AI reasoning in molecular structure for drug discovery
Researchers have developed Bolek, a compact multimodal language model designed for molecular reasoning. This model integrates molecular structure embeddings into an instruction-tuned text decoder, enabling it to ground …
-
Machine learning models predict Alzheimer's drug candidates from natural compounds
Researchers have developed a machine learning approach to identify potential Alzheimer's disease treatments from natural compounds. The study utilized cheminformatics to extract molecular descriptors and trained various…