We think there are important implications for anyone using ML to guide #polymer design or build a #SelfDrivingLab.

Good in-distribution performance is the easy part. The harder question is when and why models fail on new polymers and formulations, and the answer isn't as simple as "more data."

Can ML predict how conjugated polymers behave in solution, and will those models hold up on molecular structures they've never seen? We built a dataset and put them to the test. The results are more nuanced than we expected.

Robust learning from literature data: Model generalizability and uncertainty for predicting conjugated polymer solution conformation Predicting solution conformation and aggregation of conjugated polymers remains a bottleneck for translating solution processing into controlled film microstruc

Officially official! The group's first-ever publication is online 🥳

#ChemSky #MatSky

doi.org/10.1063/5.03...

This AI has chemical expertise — and helps synthesize 35 new compounds An open-source program helps researchers bypass a major bottleneck in the process chemical synthesis.

In my @nature.com story, I explain how chemists at Yale have created a chemistry AI tool by fine-turning the LLAMA LLM to create 2,498 expert models. Their system can judge which of the different experts to refer a query about reaction conditions to. Impressive! 🧪

www.nature.com/articles/d41...

We explore how model performance can be assessed in this scenario, and use conjugated polymer conformation as a test case.

Conventional or #selfdrivinglab experiments can be informed by prior data gathered from the literature. Important scientific challenges often require the development of previously unknown materials: materials discovery.

However, #machinelearning models are not designed for this scenario...

Robust Learning from Literature Data: Model Generalizability and Uncertainty for Predicting Conjugated Polymer Solution Conformation

🚨🚨 The group's first preprint is up on @chemrxiv.org! 🥳🥳

Robust Learning from Literature Data: Model Generalizability and Uncertainty for Predicting Conjugated Polymer Solution Conformation

📝 doi.org/10.26434/chemrxiv-2025-mdtsm

#chemsky #matsky

Do you know of any papers that have datasets of organic materials (polymers, molecules) with experimental parameters–not material properties, but stuff like concentration, temperature, whatever?

#chemsky #matsky

@uw-cei.bsky.social @imod-stc.bsky.social @coschoolofmines.bsky.social @utahchemistry.bsky.social @whitmancollege.bsky.social @ddomlab.org

Gyros PurePep chorus recently installed in the Data-Driven Organic Materials Lab @ NC State

Another instrument is up and running! We set up our
Gyros PurePep Chorus last Friday. Keep an eye out for exciting developments on this front 👀

#chemsky #matsky

#chemsky #matsky

We just completed the installation of Big Purchase #1 ™️: a quadruple (!) detector SEC from Tosoh. This bad boy has RI, UV, MALS, & viscometry 💪 We're really excited to start getting some absolute molecular weights!

Beyond molecular structure: critically assessing machine learning for designing organic photovoltaic materials and devices Our study explores the current state of machine learning (ML) as applied to predicting and designing organic photovoltaic (OPV) devices. We outline key considerations for selecting the method of encod...

Our exploration of #ML to predict #OPV device performance from molecular structure of the materials *and* processing data is now officially published in J Mater Chem A as part of their 2024 Emerging Investigators series!

doi.org/10.1039/D4TA...

The 25th Opentrons Flex

The semester's big achievement was installing our new
Opentrons Flex. Only the 25th unit installed!

A robot retrieve books from the library stacks

First semester at NC State MSE is in the books! Not only is NC State Engineering building the future of #SelfDrivingLabs, but there's an awesome self-driving library

#MatSky #Chemsky