Artificial Intelligence for Retrosynthetic Planning Needs Both Data and Expert Knowledge

F Strieth-Kalthoff, S Szymkuc, K Molga… - Journal of the …, 2024 - ACS Publications
Rapid advancements in artificial intelligence (AI) have enabled breakthroughs across many
scientific disciplines. In organic chemistry, the challenge of planning complex multistep …

Hybrid machine learning approach to predict the site selectivity of iridium-catalyzed arene borylation

E Caldeweyher, M Elkin, G Gheibi… - Journal of the …, 2023 - ACS Publications
The borylation of aryl and heteroaryl C–H bonds is valuable for the site-selective
functionalization of C–H bonds in complex molecules. Iridium catalysts ligated by bipyridine …

Predictive Minisci late stage functionalization with transfer learning

E King-Smith, FA Faber, U Reilly, AV Sinitskiy… - Nature …, 2024 - nature.com
Structural diversification of lead molecules is a key component of drug discovery to explore
chemical space. Late-stage functionalizations (LSFs) are versatile methodologies capable of …

Fine-tuning GPT-3 for machine learning electronic and functional properties of organic molecules

Z **e, X Evangelopoulos, ÖH Omar, A Troisi… - Chemical …, 2024 - pubs.rsc.org
We evaluate the effectiveness of fine-tuning GPT-3 for the prediction of electronic and
functional properties of organic molecules. Our findings show that fine-tuned GPT-3 can …

Mechanistic Inference from Statistical Models at Different Data-Size Regimes

DM Lustosa, A Milo - ACS Catalysis, 2022 - ACS Publications
The chemical sciences are witnessing an influx of statistics into the catalysis literature.
These developments are propelled by modern technological advancements that are leading …

Automated quantum chemistry for estimating nucleophilicity and electrophilicity with applications to retrosynthesis and covalent inhibitors

N Ree, AH Göller, JH Jensen - Digital Discovery, 2024 - pubs.rsc.org
Reactivity scales such as nucleophilicity and electrophilicity are valuable tools for
determining chemical reactivity and selectivity. However, prior attempts to predict or …

Active Learning Guided Computational Discovery of Plant-Based Redoxmers for Organic Nonaqueous Redox Flow Batteries

A Jain, IA Shkrob, HA Doan, K Adams… - … Applied Materials & …, 2023 - ACS Publications
Organic nonaqueous redox flow batteries (O-NRFBs) are promising energy storage devices
due to their scalability and reliance on sourceable materials. However, finding suitable …

Every atom counts: predicting sites of reaction based on chemistry within two bonds

CC Lam, JM Goodman - Digital Discovery, 2024 - pubs.rsc.org
How much chemistry can be described by looking only at each atom, its neighbours and its
next-nearest neighbours? We present a method for predicting reaction sites based only on a …

Holistic chemical evaluation reveals pitfalls in reaction prediction models

VS Gil, AM Bran, M Franke, R Schlama… - arxiv preprint arxiv …, 2023 - arxiv.org
The prediction of chemical reactions has gained significant interest within the machine
learning community in recent years, owing to its complexity and crucial applications in …

A hybrid machine-learning approach to predict the iridium-catalyzed borylation of C–H bonds

E Caldeweyher, M Elkin, G Gheibi, M Johansson… - 2022 - chemrxiv.org
The borylation of aryl and heteroaryl C–H bonds is valuable for the site-selective
functionalization of C–H bonds in complex molecules. Iridium catalysts ligated by bipyridine …