A data science roadmap for open science organizations engaged in early-stage drug discovery

K Edfeldt, AM Edwards, O Engkvist, J Günther… - Nature …, 2024 - nature.com
Abstract The Structural Genomics Consortium is an international open science research
organization with a focus on accelerating early-stage drug discovery, namely hit discovery …

The Road Ahead for Metal–Organic Frameworks: Current Landscape, Challenges and Future Prospects

ML Barsoum, KM Fahy, W Morris, VP Dravid… - ACS …, 2025 - ACS Publications
This perspective highlights the transformative potential of Metal–Organic Frameworks
(MOFs) in environmental and healthcare sectors. It discusses work that has advanced …

Generation and human-expert evaluation of interesting research ideas using knowledge graphs and large language models

X Gu, M Krenn - arxiv preprint arxiv:2405.17044, 2024 - pure.mpg.de
Advanced artificial intelligence (AI) systems with access to millions of research papers could
inspire new research ideas that may not be conceived by humans alone. However, how …

Looking Back the Nonlinear Optical Crystals in a Functionalized Unit's Perspective

M Mutailipu, J Li, S Pan - Advanced Functional Materials, 2025 - Wiley Online Library
Nonlinear optics, signifying a revolutionary paradigm change within the realm of optics, has
ushered in a transformative era by employing the nonlinear optical crystals to manipulate …

Accelerating Structure Prediction of Molecular Crystals using Actively Trained Moment Tensor Potential

N Rybin, IS Novikov, AV Shapeev - Physical Chemistry Chemical …, 2024 - pubs.rsc.org
Inspired by the recent success of machine-learned interatomic potentials for crystal structure
prediction of the inorganic crystals, we present a methodology that exploits Moment Tensor …

Efficient evolutionary search over chemical space with large language models

H Wang, M Skreta, CT Ser, W Gao, L Kong… - arxiv preprint arxiv …, 2024 - arxiv.org
Molecular discovery, when formulated as an optimization problem, presents significant
computational challenges because optimization objectives can be non-differentiable …

Role of the human-in-the-loop in emerging self-driving laboratories for heterogeneous catalysis

C Scheurer, K Reuter - Nature Catalysis, 2025 - nature.com
Self-driving laboratories (SDLs) represent a cutting-edge convergence of machine learning
with laboratory automation. SDLs operate in active learning loops, in which a machine …

A Sober Look at LLMs for Material Discovery: Are They Actually Good for Bayesian Optimization Over Molecules?

A Kristiadi, F Strieth-Kalthoff, M Skreta… - arxiv preprint arxiv …, 2024 - arxiv.org
Automation is one of the cornerstones of contemporary material discovery. Bayesian
optimization (BO) is an essential part of such workflows, enabling scientists to leverage prior …

Spiers Memorial Lecture: How to do impactful research in artificial intelligence for chemistry and materials science

AH Cheng, CT Ser, M Skreta, A Guzmán-Cordero… - Faraday …, 2025 - pubs.rsc.org
Machine learning has been pervasively touching many fields of science. Chemistry and
materials science are no exception. While machine learning has been making a great …

Reaction blueprints and logical control flow for parallelized chiral synthesis in the Chemputer

M Šiaučiulis, C Knittl-Frank, SH M. Mehr… - Nature …, 2024 - nature.com
Despite recent proliferation of programmable robotic chemistry hardware, current chemical
programming ontologies lack essential structured programming constructs like variables …