Chad Risko
@cmrisko.bsky.social
Father. Husband. John C. Hubbard Professor of Chemistry at U. Kentucky. Nerd. Sports Enthusiast. Views expressed are my own. he/him #EndNF.
We hope that you enjoy digging into the tool. Let us know what you think!
February 27, 2025 at 1:49 AM
We hope that you enjoy digging into the tool. Let us know what you think!
MolGen-Transformer is a generative AI model designed to address challenges of molecular language models (LM) that impact their effectiveness, and is trained on a large and diverse dataset of approximately 198 million organic molecules.
February 27, 2025 at 1:49 AM
MolGen-Transformer is a generative AI model designed to address challenges of molecular language models (LM) that impact their effectiveness, and is trained on a large and diverse dataset of approximately 198 million organic molecules.
Notably, the analysis reveals that one of the most popular similarity measures (mfpReg, Tanimoto) can rank among the worst-performing measures depending on the property being evaluated.
chemrxiv.org/engage/chemr...
chemrxiv.org/engage/chemr...
Evaluating molecular similarity measures: Do similarity measures reflect electronic structure properties?
The rapid adoption of big data, machine learning (ML), and generative artificial intelligence (AI) in chemical discovery has heightened the importance of quantifying molecular similarity. Molecular si...
chemrxiv.org
January 30, 2025 at 2:22 PM
Notably, the analysis reveals that one of the most popular similarity measures (mfpReg, Tanimoto) can rank among the worst-performing measures depending on the property being evaluated.
chemrxiv.org/engage/chemr...
chemrxiv.org/engage/chemr...
Using over 350 million molecule pairs with electronic structure, redox, and optical properties, we evaluate correlations between molecular fingerprints, distance functions, and properties.
January 30, 2025 at 2:22 PM
Using over 350 million molecule pairs with electronic structure, redox, and optical properties, we evaluate correlations between molecular fingerprints, distance functions, and properties.
The approach builds on the concept of neighborhood behavior and incorporates KDE analysis to quantify how well similarity measures capture property relationships.
January 30, 2025 at 2:22 PM
The approach builds on the concept of neighborhood behavior and incorporates KDE analysis to quantify how well similarity measures capture property relationships.
Thanks! We'll have to take a look.
December 14, 2024 at 3:09 AM
Thanks! We'll have to take a look.
Welcome to the club!
November 29, 2024 at 3:09 PM
Welcome to the club!