Chad Risko's Avatar

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.

584 Followers  |  444 Following  |  9 Posts  |  Joined: 21.09.2023  |  1.3438

Latest posts by cmrisko.bsky.social on Bluesky

We hope that you enjoy digging into the tool. Let us know what you think!

27.02.2025 01:49 β€” πŸ‘ 2    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

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.

27.02.2025 01:49 β€” πŸ‘ 2    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0
Preview
MolGen-Transformer: A molecule language model for the generation and latent space exploration of pi-conjugated molecules The application of generative artificial intelligence (AI) to molecular discovery has unlocked vast potential for the automated design of new chemical systems. Molecular language models (LM), however,...

Introducing MolGen-Transformer, the result of a longstanding collaboration with Baskar Ganapathysubramanian that has been led by Bella Yang and Rebekah Duke-Crockett with additional contributions from Moses Ogbaje and Parker Sornberger.

lnkd.in/eSTnFXXb

27.02.2025 01:49 β€” πŸ‘ 2    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0
Preview
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...

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...

30.01.2025 14:22 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

Using over 350 million molecule pairs with electronic structure, redox, and optical properties, we evaluate correlations between molecular fingerprints, distance functions, and properties.

30.01.2025 14:22 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0

The approach builds on the concept of neighborhood behavior and incorporates KDE analysis to quantify how well similarity measures capture property relationships.

30.01.2025 14:22 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0
Preview
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...

How do you choose your approach to identify molecular similarity? In this latest collaborative work led by Rebekah Duke, we introduce a framework to evaluate the correlation between molecular similarity and properties.

chemrxiv.org/engage/chemr...

30.01.2025 14:22 β€” πŸ‘ 3    πŸ” 1    πŸ’¬ 1    πŸ“Œ 0

Thanks! We'll have to take a look.

14.12.2024 03:09 β€” πŸ‘ 2    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

Welcome to the club!

29.11.2024 15:09 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0

@cmrisko is following 20 prominent accounts