RSC - Digital Discovery latest articles

Cluster-based virtual reaction generation with reaction site-centered buffer zone

Digital Discovery, 2026, Accepted Manuscript
DOI: 10.1039/D6DD00069J, Paper

Open Access

This article is licensed under a Creative Commons Attribution 3.0 Unported Licence.

Ha Eun Kim, Hyun Woo Kim, Won-jin Chung
AI-assisted prediction of chemical reactions has garnered significant attention and research over the past several years, particularly in the field of synthetic and medicinal chemistry. To improve the prediction accuracy,...
The content of this RSS Feed (c) The Royal Society of Chemistry

When Chemistry is Too Colourful: Gamut Clipping in 8-bit sRGB Risks Misinterpretation of Camera-Based Chemical Analysis †

Digital Discovery, 2026, Accepted Manuscript
DOI: 10.1039/D6DD00065G, Paper

Open Access

This article is licensed under a Creative Commons Attribution-NonCommercial 3.0 Unported Licence.

Calum Fyfe, Shengkai Yu, Marc Reid
Digital cameras are increasingly utilised to capture visual changes in chemical processes. Monitoring colour with computer vision tools serves as a valuable proxy for monitoring bulk chemical changes. Most consumer-grade...
The content of this RSS Feed (c) The Royal Society of Chemistry

Artificial intelligence-driven optimization of closed-loop CO2 capture and conversion

Digital Discovery, 2026, Advance Article
DOI: 10.1039/D5DD00585J, Paper

Open Access

This article is licensed under a Creative Commons Attribution-NonCommercial 3.0 Unported Licence.

Yongwook Kim, Basil M. W. de Hepcée, Mehrdad Mokhtari, Marzieh Namdari, Giuseppe V. Crescenzo, Curtis P. Berlinguette
AI-driven optimization of closed-loop reactive carbon capture. The optimized reactive carbon capture process yields a CO₂ capture efficiency of 83% and a FE_CO of 42%, highlighting a viable pathway for economical carbon capture and utilization.
To cite this article before page numbers are assigned, use the DOI form of citation above.
The content of this RSS Feed (c) The Royal Society of Chemistry

Towards “on-demand” van der Waals epitaxy with adaptive ensemble sampling atomistic workflows

Digital Discovery, 2026, Advance Article
DOI: 10.1039/D6DD00049E, Paper

Open Access

This article is licensed under a Creative Commons Attribution-NonCommercial 3.0 Unported Licence.

Soumendu Bagchi, Ankita Biswas, Prasanna V. Balachandran, Ayana Ghosh, P. Ganesh
A real-time bayesian sampling with computing-resource scalable ensemble molecular dynamics workflow uncovers crystallization pathways for on-demand target moire twisted MoS₂ bi-layers from amorphous precursors.
To cite this article before page numbers are assigned, use the DOI form of citation above.
The content of this RSS Feed (c) The Royal Society of Chemistry

BEACON: a Bayesian optimization inspired strategy for efficient novelty search

Digital Discovery, 2026, Advance Article
DOI: 10.1039/D6DD00123H, Paper

Open Access

This article is licensed under a Creative Commons Attribution 3.0 Unported Licence.

Wei-Ting Tang, Ankush Chakrabarty, Joel A. Paulson
BEACON uses multi-output probabilistic models and novelty scores to guide costly evaluations, enabling efficient discovery of diverse attainable outcomes rather than a single optimum.
To cite this article before page numbers are assigned, use the DOI form of citation above.
The content of this RSS Feed (c) The Royal Society of Chemistry

Wide-surface furnace for in situ X-ray diffraction of combinatorial samples using a high-throughput approach

Digital Discovery, 2026, Advance Article
DOI: 10.1039/D6DD00067C, Paper

Open Access

This article is licensed under a Creative Commons Attribution-NonCommercial 3.0 Unported Licence.

Giulio Cordaro, Juande Sirvent, Cristian Mocuta, Fjorelo Buzi, Thierry Martin, Federico Baiutti, Alex Morata, Albert Tarancòn, Dominique Thiaudière, Guilhem Dezanneau
High-throughput experimentation of synchrotron X-ray diffraction and fluorescence enabled the collection of the thermal expansion coefficients of an entire ternary system using a combinatorial library of LSCFM in a wide-surface furnace.
To cite this article before page numbers are assigned, use the DOI form of citation above.
The content of this RSS Feed (c) The Royal Society of Chemistry

Accelerating Quantum Materials Characterization: Hybrid Active Learning for Autonomous Spin Wave Spectroscopy

Digital Discovery, 2026, Accepted Manuscript
DOI: 10.1039/D6DD00232C, Paper

Open Access

This article is licensed under a Creative Commons Attribution 3.0 Unported Licence.

William Ratcliff
Autonomous neutron spectroscopy must solve three distinct tasks: detection (where is the signal?), inference (which Hamiltonian governs it?), and refinement (what are the parameters?). No single controller solves all three...
The content of this RSS Feed (c) The Royal Society of Chemistry

From Benchmark to Production: A Surrogate-Assisted Multi-Objective Optimization Framework for Industrial Chemical Formulation at Scale

Digital Discovery, 2026, Accepted Manuscript
DOI: 10.1039/D6DD00112B, Paper

Open Access

This article is licensed under a Creative Commons Attribution 3.0 Unported Licence.

Shehan Sohil Makani
The deployment of AI-driven optimization in industrial chemistry faces a fundamental challenge that benchmark studies rarely address: how to handle the combinatorial complexity, multi-objective tension, high evaluation cost, and data...
The content of this RSS Feed (c) The Royal Society of Chemistry

Navigating the path to autonomy: real-world lessons from an air-free self-driving laboratory

Digital Discovery, 2026, Advance Article
DOI: 10.1039/D6DD00269B, Perspective

Open Access

This article is licensed under a Creative Commons Attribution-NonCommercial 3.0 Unported Licence.

Lily A. Robertson, Ilya A. Shkrob, Rafael Vescovi, Logan Ward, Ryan Lewis, Noah H. Paulson, Tobias Ginsburg, Casey Stone, Benjamin T. Diroll, Magali S. Ferrandon, Zhengcheng Zhang
While autonomous experimentation has promise to accelerate discovery in physcial sciences, the real-world integration of predictive models and experimentation is non-trivial especially for sensitive chemistries that must remain air and water free.
To cite this article before page numbers are assigned, use the DOI form of citation above.
The content of this RSS Feed (c) The Royal Society of Chemistry

Benchmarking Deep Learning Models for Raman Spectroscopy Across Open-Source Datasets

Digital Discovery, 2026, Accepted Manuscript
DOI: 10.1039/D6DD00044D, Paper

Open Access

This article is licensed under a Creative Commons Attribution 3.0 Unported Licence.

Adithya Sineesh, Akshita Ramya Kamsali
Deep learning classifiers for Raman spectroscopy are increasingly reported to outperform classical chemometric approaches. However, their evaluations are often conducted in isolation or compared against traditional machine learning methods or...
The content of this RSS Feed (c) The Royal Society of Chemistry

CrystalCV: a computer vision system for analysis of crystallization experiments

Digital Discovery, 2026, Advance Article
DOI: 10.1039/D6DD00140H, Paper

Open Access

This article is licensed under a Creative Commons Attribution-NonCommercial 3.0 Unported Licence.

Nicholas Sandor, Makhsud I. Saidaminov
CrystalCV automates complex crystallization analysis using computer vision methods to persistently monitor multiple simultaneous growth events.
To cite this article before page numbers are assigned, use the DOI form of citation above.
The content of this RSS Feed (c) The Royal Society of Chemistry

Closed-loop discovery of energy materials empowered by artificial intelligence models

Digital Discovery, 2026, Advance Article
DOI: 10.1039/D6DD00218H, Perspective

Open Access

This article is licensed under a Creative Commons Attribution 3.0 Unported Licence.

Chenyao Ma, Yuhang Wang, Di Zhang, Wei Du, Qiang Gao, Rui Su, Kan Xu, Huan Gu, Limin Li, Piao Ma, Hao Li
This Perspective outlines a 4th⁺ paradigm for energy materials discovery, integrating databases, machine learning interatomic potentials, large language models, and AI agents into closed-loop research workflows.
To cite this article before page numbers are assigned, use the DOI form of citation above.
The content of this RSS Feed (c) The Royal Society of Chemistry

A reproducible Python workflow for absorber-light-source spectral matching: overlap-calculator

Digital Discovery, 2026, Advance Article
DOI: 10.1039/D6DD00247A, Paper

Open Access

This article is licensed under a Creative Commons Attribution 3.0 Unported Licence.

Pinar Seyitdanlioglu
Overlap-calculator transforms TD-DFT and UV-vis spectra into reproducible source-dependent overlap descriptors, enabling transparent absorber-light-source matching for indoor photovoltaics and optoelectronic materials screening.
To cite this article before page numbers are assigned, use the DOI form of citation above.
The content of this RSS Feed (c) The Royal Society of Chemistry

Accelerating ligand discovery by combining Bayesian optimization with MMGBSA-based binding affinity calculations

Digital Discovery, 2026, Advance Article
DOI: 10.1039/D5DD00522A, Paper

Open Access

This article is licensed under a Creative Commons Attribution 3.0 Unported Licence.

Lucas Andersen, Max Rausch-Dupont, Alejandro Martínez León, Andrea Volkamer, Jochen S. Hub, Dietrich Klakow
Combination of MD simulations with an active learning pipeline to bring an MD-level of accuracy to the drug discovery process of identifying the most potent binders. Evaluated on 60.000 computationally derived binding affinities of the MCL1 protein.
To cite this article before page numbers are assigned, use the DOI form of citation above.
The content of this RSS Feed (c) The Royal Society of Chemistry

Scientists might be reaffirming the relevance of human oversight as AI lands in labs

Digital Discovery, 2026, Advance Article
DOI: 10.1039/D6DD00030D, Opinion

Open Access

This article is licensed under a Creative Commons Attribution 3.0 Unported Licence.

Renan Gonçalves Leonel da Silva, Li Du, Gil Eyal
Artificial Intelligence (AI) is prompting scientists to reflect on the shifting role of human judgment, interpretation, and oversight in experimental practice. The Graphical Abstract image was generated by Google Gemini.
To cite this article before page numbers are assigned, use the DOI form of citation above.
The content of this RSS Feed (c) The Royal Society of Chemistry

Cost-aware Bayesian optimization of real-world nanoindentation workflows for accelerated mechanical characterization

Digital Discovery, 2026, Advance Article
DOI: 10.1039/D5DD00518C, Paper

Open Access

This article is licensed under a Creative Commons Attribution 3.0 Unported Licence.

Vivek Chawla, Stephen Puplampu, Haochen Zhu, Philip D. Rack, Dayakar Penumadu, Sergei Kalinin
Cost-aware Bayesian optimization enables adaptive nanoindentation workflows by accounting for instrument constraints, enabling order-of-magnitude gains in efficiency for adaptive mechanical mapping under real instrument constraints.
To cite this article before page numbers are assigned, use the DOI form of citation above.
The content of this RSS Feed (c) The Royal Society of Chemistry

ADEPT-PolyGraphMT: automated molecular simulation and multi-task multi-fidelity machine learning for polymer property generation and prediction

Digital Discovery, 2026, Advance Article
DOI: 10.1039/D6DD00206D, Paper

Open Access

This article is licensed under a Creative Commons Attribution-NonCommercial 3.0 Unported Licence.

Sobin Alosious, Yuhan Liu, Jiaxin Xu, Gang Liu, Renzheng Zhang, Meng Jiang, Tengfei Luo
An integrated framework combining automated molecular simulations and multi-task, multi-fidelity machine learning for scalable polymer property generation, prediction, and large-scale screening.
To cite this article before page numbers are assigned, use the DOI form of citation above.
The content of this RSS Feed (c) The Royal Society of Chemistry

Learning rates: predicting rate coefficients for hydrogen abstraction reactions

Digital Discovery, 2026, Advance Article
DOI: 10.1039/D6DD00113K, Paper

Open Access

This article is licensed under a Creative Commons Attribution 3.0 Unported Licence.

Calvin Pieters, Alon Grinberg Dana
Reaction-aware DMPNN + RAD descriptors inject local 3D abstraction geometry into 2D molecular graphs, enabling rapid prediction of Arrhenius parameters and temperature-dependent rate coefficients.
To cite this article before page numbers are assigned, use the DOI form of citation above.
The content of this RSS Feed (c) The Royal Society of Chemistry

Introduction to “Quantum computing for chemistry, material science and biotechnology”

Digital Discovery, 2026, Advance Article
DOI: 10.1039/D6DD90023B, Editorial

Open Access

This article is licensed under a Creative Commons Attribution 3.0 Unported Licence.

Matthias Degroote, Joonho Lee, Pauline Ollitrault
Matthias Degroote, Joonho Lee and Pauline Ollitrault introduce the Digital Discovery themed collection on “Quantum computing for chemistry, material science and biotechnology”.
To cite this article before page numbers are assigned, use the DOI form of citation above.
The content of this RSS Feed (c) The Royal Society of Chemistry

Bayesian active learning to accelerate high throughput phase diagram exploration

Digital Discovery, 2026, 5,2478-2490
DOI: 10.1039/D5DD00459D, Paper

Open Access

This article is licensed under a Creative Commons Attribution-NonCommercial 3.0 Unported Licence.

Mingzhou Fan, Yucheng Wang, Guillermo Vazquez, Ruida Zhou, Ibrahim Karaman, Raymundo Arróyave, Xiaoning Qian
BALPI accelerates phase diagram discovery by adaptively sampling thermodynamic space with quantified uncertainty, efficiently identifying sparse and disconnected phase stability regions.
The content of this RSS Feed (c) The Royal Society of Chemistry

Hybrid quantum algorithm for simulating real-time thermal correlation functions

Digital Discovery, 2026, 5,2759-2769
DOI: 10.1039/D5DD00381D, Paper

Open Access

This article is licensed under a Creative Commons Attribution-NonCommercial 3.0 Unported Licence.

Elliot C. Eklund, Nandini Ananth
We introduce a hybrid Path Integral Monte Carlo (hPIMC) algorithm to calculate quantum, real-time, thermal correlation functions for condensed phase systems.
The content of this RSS Feed (c) The Royal Society of Chemistry

A graph-based approach to selection of feasible compositions for compositionally graded alloy design

Digital Discovery, 2026, 5,2743-2758
DOI: 10.1039/D6DD00006A, Paper

Open Access

This article is licensed under a Creative Commons Attribution 3.0 Unported Licence.

Mikayla Obrist, James Hanagan, Marshall Allen, Bernard Gaskey, Richard Malak, Raymundo Arróyave
Graph-based subgraph analysis to identify connected regions of feasible alloy compositions, enabling selection of continuous paths that balance manufacturability, phase stability, and performance for compositionally graded alloy design.
The content of this RSS Feed (c) The Royal Society of Chemistry

Rapid prediction of single-site adsorbate probability distributions in metal–organic frameworks using graph neural networks

Digital Discovery, 2026, 5,2650-2668
DOI: 10.1039/D6DD00027D, Paper

Open Access

This article is licensed under a Creative Commons Attribution 3.0 Unported Licence.

Jake Burner, Olivier Marchand, Rosa Cicciarella, Marco Gibaldi, Tom K. Woo
Adsorbate probability distributions (APDs) of MOFs can be rapidly generated by machine learning, bypassing expensive atomistic simulations. Adsorption binding sites can be reliably extracted from the APDs.
The content of this RSS Feed (c) The Royal Society of Chemistry

Novelty-aware evolutionary Bayesian optimisation for multi-objective discovery science

Digital Discovery, 2026, 5,2684-2700
DOI: 10.1039/D6DD00134C, Paper

Open Access

This article is licensed under a Creative Commons Attribution 3.0 Unported Licence.

Maytham Aqeeli, Thatchathon Leelawat, David Shorthouse
We combine evolutionary algorithms with Bayesian optimisation, and introduce a novelty-aware selection strategy to efficiently explore complex experimental design spaces.
The content of this RSS Feed (c) The Royal Society of Chemistry

Achieving a scalable machine learning workflow for crystal structure discovery with experimental validation

Digital Discovery, 2026, 5,2414-2437
DOI: 10.1039/D6DD00132G, Review Article

Open Access

This article is licensed under a Creative Commons Attribution-NonCommercial 3.0 Unported Licence.

Danila Shiryaev, Emil I. Jaffal, Sangjoon Lee, Balaranjan Selvaratnam, Anton O. Oliynyk
Interpretable and explainable machine learning models extract physical knowledge to enable the workflow to translate predictions into laboratory experimental discoveries.
The content of this RSS Feed (c) The Royal Society of Chemistry

A critical examination of active learning workflows in materials science

Digital Discovery, 2026, 5,2366-2382
DOI: 10.1039/D6DD00081A, Perspective

Open Access

This article is licensed under a Creative Commons Attribution 3.0 Unported Licence.

Akhil S. Nair, Lucas Foppa
Data-centric materials science requires carefully designed active learning workflows, but existing practices remain limited by weak design frameworks and generic implementations.
The content of this RSS Feed (c) The Royal Society of Chemistry

RobInHood: a robotic chemist in a fume hood

Digital Discovery, 2026, 5,2438-2447
DOI: 10.1039/D6DD00007J, Paper

Open Access

This article is licensed under a Creative Commons Attribution-NonCommercial 3.0 Unported Licence.

Louis Longley, Francisco Munguia-Galeano, Yushu Han, Rob Clowes, Sriram Vijayakrishnan, Adam Edwards, Gabriella Pizzuto, Hatem Fakhruldeen, Andrew Cooper
Robot-In-a-Fume-Hood (RobInHood), a robotic arm in a fume hood capable of liquid/solid dispensing, capping, heating, filtration and visual analysis. The platform performs synthesis of a cage molecule, a phthalimide, and a dye-based porosity screen.
The content of this RSS Feed (c) The Royal Society of Chemistry

PRISM: protocol refinement through intelligent simulation modeling

Digital Discovery, 2026, 5,2613-2628
DOI: 10.1039/D6DD00004E, Paper

Open Access

This article is licensed under a Creative Commons Attribution-NonCommercial 3.0 Unported Licence.

Brian Hsu, Priyanka V. Setty, Rory M. Butler, Ryan Lewis, Casey Stone, Rebecca Weinberg, Thomas Brettin, Rick Stevens, Ian Foster, Arvind Ramanathan
Digital-twin simulation catches physical errors in AI-generated lab protocols that model self-critique cannot detect. End-to-end autonomous execution produces results comparable to manual runs.
The content of this RSS Feed (c) The Royal Society of Chemistry

Gradient-enhanced neural networks for model parameter estimation applied to flow chemistry automated platforms

Digital Discovery, 2026, 5,2728-2742
DOI: 10.1039/D5DD00526D, Paper

Open Access

This article is licensed under a Creative Commons Attribution-NonCommercial 3.0 Unported Licence.

Francisco Bolaños-García, Jean-Marc Commenge, Laurent Falk
The acceleration of chemical process development through flow chemistry depends on obtaining reliable kinetic models.
The content of this RSS Feed (c) The Royal Society of Chemistry

A user-tunable machine learning framework for step-wise synthesis planning

Digital Discovery, 2026, 5,2669-2683
DOI: 10.1039/D5DD00562K, Paper

Open Access

This article is licensed under a Creative Commons Attribution 3.0 Unported Licence.

Shivesh Prakash, Nandan Patel, Hans-Arno Jacobsen, Viki Kumar Prasad
A mordern Hopfield network-based retrosynthetic tool for computer-aided synthesis planning that associates target molecules with reaction templates and uses tunable scoring of cost, temperature, and solvent toxicity to prioritize synthetic routes.
The content of this RSS Feed (c) The Royal Society of Chemistry

ConforFormer: representation for molecules through understanding of conformers

Digital Discovery, 2026, 5,2639-2649
DOI: 10.1039/D6DD00096G, Paper

Open Access

This article is licensed under a Creative Commons Attribution 3.0 Unported Licence.

Mas Pieter Klein, Irina Rudenko, Evgeny A. Pidko, Ivan Bushmarinov
ConforFormer learns to align conformers while separating isomers, producing compact 3D molecular embeddings transferable across property prediction and similarity search tasks.
The content of this RSS Feed (c) The Royal Society of Chemistry

Navigating the landscape of modular reconfigurable laboratory automation in chemistry

Digital Discovery, 2026, 5,2383-2399
DOI: 10.1039/D5DD00330J, Review Article

Open Access

This article is licensed under a Creative Commons Attribution 3.0 Unported Licence.

Rodrigo Moreno, Jonas Jensen, Andres Faina, Kasper Stoy
Platforms, where modules encapsulate operations, material transfer, and software, can be reconfigured quickly and sometimes automatically to perform different experiments.
The content of this RSS Feed (c) The Royal Society of Chemistry

Lightweight privacy-preserving human activity recognition from CSI data using a CNN-temporal attention network

Digital Discovery, 2026, 5,2701-2715
DOI: 10.1039/D6DD00077K, Paper

Open Access

This article is licensed under a Creative Commons Attribution 3.0 Unported Licence.

Khondakar Ashik Shahriar, Maruf Ahmed, Hafiz Imtiaz
We propose an end-to-end privacy-preserving CSI-based HAR framework integrating a CNN with temporal attention, which outperforms existing studies on multiple benchmark datasets with distance, height and environmental variations.
The content of this RSS Feed (c) The Royal Society of Chemistry

Spectroscopy-assisted Bayesian optimization for efficient refolding of inclusion body proteins

Digital Discovery, 2026, 5,2716-2727
DOI: 10.1039/D6DD00035E, Paper

Open Access

This article is licensed under a Creative Commons Attribution-NonCommercial 3.0 Unported Licence.

Florian Gisperg, Robert Klausser, Matthias Kierein, Eva Prada Brichtova, Mohamed Elshazly, Julian Kopp, Oliver Spadiut
Combining Bayesian optimization with intrinsic tryptophan fluorescence spectroscopy enables efficient inclusion body refolding process development with decreased experimental effort.
The content of this RSS Feed (c) The Royal Society of Chemistry

optimade-maker: automated generation of interoperable materials APIs from static datasets

Digital Discovery, 2026, 5,2469-2477
DOI: 10.1039/D6DD00125D, Paper

Open Access

This article is licensed under a Creative Commons Attribution 3.0 Unported Licence.

Kristjan Eimre, Matthew L. Evans, Bud Macaulay, Xing Wang, Jusong Yu, Nicola Marzari, Gian-Marco Rignanese, Giovanni Pizzi
optimade-maker converts atomistic structure datasets into OPTIMADE APIs, enabling interoperable access and analysis within the OPTIMADE ecosystem.
The content of this RSS Feed (c) The Royal Society of Chemistry

Benchmarking explainable AI methods for toxicophore detection and toxicity prediction

Digital Discovery, 2026, 5,2547-2559
DOI: 10.1039/D5DD00576K, Paper

Open Access

This article is licensed under a Creative Commons Attribution 3.0 Unported Licence.

Dina Khasanova, Igor V. Tetko
High-accuracy models yield stable and chemically meaningful XAI explanations, with multiple methods consistently identifying functional groups and toxicophores across prediction tasks.
The content of this RSS Feed (c) The Royal Society of Chemistry

Constraint-aware labware layout generation from natural language for heterogeneous laboratory robots

Digital Discovery, 2026, 5,2507-2519
DOI: 10.1039/D6DD00026F, Paper

Open Access

This article is licensed under a Creative Commons Attribution 3.0 Unported Licence.

Yuya Tahara-Arai, Takashi Inagaki, Akari Kato, Koji Ochiai, Kazuya Azumi, Koichi Takahashi, Genki N. Kanda, Haruka Ozaki
The Labware-Layout Planner takes a natural language experimental description, an available labware list, and constraints as input to generate a comprehensive labware placement map and a set of natural language instructions.
The content of this RSS Feed (c) The Royal Society of Chemistry

Molecular arms race classifier for decrypting venom peptide and ion channel interactions

Digital Discovery, 2026, 5,2575-2590
DOI: 10.1039/D5DD00498E, Paper

Open Access

This article is licensed under a Creative Commons Attribution-NonCommercial 3.0 Unported Licence.

Favour Achimba, Arezoo Bybordi, Mariam Gelashvili, Jessy Ramirez, Anita Raja, Weigang Qiu, Mandë Holford
MARC is a machine learning based framework designed to predict the ion channel targets of animal venom peptides, a critical step in deorphanizing their functional activity and therapeutic potential.
The content of this RSS Feed (c) The Royal Society of Chemistry

Assessing the extrapolation capability of template-free retrosynthesis models

Digital Discovery, 2026, 5,2591-2599
DOI: 10.1039/D6DD00072J, Paper

Open Access

This article is licensed under a Creative Commons Attribution-NonCommercial 3.0 Unported Licence.

Jonghwi Choe, Shuan Chen, Yousung Jung
Out-of-distribution evaluation shows template-free retrosynthesis models achieve only around 1% accuracy on unseen reaction types, with novel predictions frequently showing invalid chemical transformations.
The content of this RSS Feed (c) The Royal Society of Chemistry

Identification of drug candidates against glioblastoma with machine learning and high-throughput screening of heterogeneous cellular models

Digital Discovery, 2026, 5,2560-2574
DOI: 10.1039/D5DD00190K, Paper

Open Access

This article is licensed under a Creative Commons Attribution 3.0 Unported Licence.

Vanessa Smer-Barreto, Richard J. R. Elliott, John C. Dawson, Álvaro Lorente-Macías, Muhammad Furqan, Asier Unciti-Broceta, Diego A. Oyarzún, Neil O. Carragher
Glioblastoma multiforme (GBM) is an aggressive primary brain tumour that presents significant treatment challenges due to its complex pathology and heterogeneity.
The content of this RSS Feed (c) The Royal Society of Chemistry

CREOLab: a procedure captioning dataset for understanding creative tool use in object-rich laboratory videos

Digital Discovery, 2026, 5,2600-2612
DOI: 10.1039/D5DD00542F, Paper

Open Access

This article is licensed under a Creative Commons Attribution-NonCommercial 3.0 Unported Licence.

Shigeaki Goto, Tatsuki Hasebe
CREOLab is a laboratory video dataset for procedural captioning of human manual operations, designed to quantitatively evaluate object-knowledge biases in video captioning systems that may produce descriptions that differ from the actual procedures.
The content of this RSS Feed (c) The Royal Society of Chemistry

AI-designed and AI-implemented control systems for bespoke scientific instrumentation: application to scanning microscopy

Digital Discovery, 2026, 5,2448-2457
DOI: 10.1039/D6DD00177G, Paper

Open Access

This article is licensed under a Creative Commons Attribution 3.0 Unported Licence.

Ke Wang, David J. Ward, Matthew Ord, Boyao Liu, Andrew P. Jardine
AI-assisted development route with cross-validation and sandbox verification.
The content of this RSS Feed (c) The Royal Society of Chemistry

Reaction center prediction by analyzing attention of a chemical language model

Digital Discovery, 2026, 5,2458-2468
DOI: 10.1039/D6DD00055J, Paper

Open Access

This article is licensed under a Creative Commons Attribution 3.0 Unported Licence.

Xiaoliang Xiong, Ruizhen Jia, Yang Tian, Jingke Chen, Boxue Tian
This study proposes PABA and SPABA to predict reaction centers by interpreting attention matrices of CLMs. The 7_7 attention head is optimal; SPABA_7_7 reaches an MCC of 0.73, outperforming existing supervised methods with strong generalizability.
The content of this RSS Feed (c) The Royal Society of Chemistry

How digital is chemical research? insights from the second NFDI4Chem community survey on research data and FAIR workflows

Digital Discovery, 2026, 5,2629-2638
DOI: 10.1039/D5DD00584A, Paper

Open Access

This article is licensed under a Creative Commons Attribution 3.0 Unported Licence.

Jochen Ortmeyer, Vitali Sidorin, Daniela Adele Hausen, Ann-Christin Andres, John Jolliffe, Theo Bender, Giacomo Lanza, Steffen Neumann, Oliver Koepler, Nicole Jung, Christoph Steinbeck, Johannes Liermann, Sonja Herres-Pawlis
Chemical research data may be handled analogously or digitally in its life cycle, posing digitalisation challenges. The 2nd NFDI4Chem survey (>800 voices) gives updates on the community perspective which is evaluated in comparison to earlier surveys.
The content of this RSS Feed (c) The Royal Society of Chemistry

Identification of multi-transcriptomic prognostic biomarkers to explore natural therapeutics for lung cancer integrating machine learning

Digital Discovery, 2026, 5,2520-2546
DOI: 10.1039/D6DD00045B, Paper

Open Access

This article is licensed under a Creative Commons Attribution 3.0 Unported Licence.

Md Ahad Ali, Hriddhi Sarker, Marguba Kamrun, Humaira Sheikh, Bilkis Akter Shifa, Siam Ahmed, Tarikul Islam, Sujoy Banik, Neeraj Kumar
Transcriptomics and machine learning approaches spotlight natural compounds as CDK1 blockers.
The content of this RSS Feed (c) The Royal Society of Chemistry

AI-driven natural product-based antiviral drug development: a technical overview

Digital Discovery, 2026, 5,2400-2413
DOI: 10.1039/D5DD00504C, Review Article

Open Access

This article is licensed under a Creative Commons Attribution 3.0 Unported Licence.

Junxi Song, Kunhuan Yang, Yingcai Xiong, Keyu Tao, Liangyu Cai, Peng Cao, Jianjian Ji
This review highlights AI-driven innovations in natural product-based antiviral drug development, covering resource mining, target ID, screening, and preclinical/clinical applications, with opportunities and limitations.
The content of this RSS Feed (c) The Royal Society of Chemistry

Physics-informed machine learning for predicting temperature-dependent chemical properties

Digital Discovery, 2026, 5,2491-2506
DOI: 10.1039/D5DD00489F, Paper

Open Access

This article is licensed under a Creative Commons Attribution 3.0 Unported Licence.

Mahyar Rajabi-Kochi, Hanie Rezaei, Sartaaj Takrim Khan, Bhanu Mamillapalli, Maryam Ebrahimiazar, Haoming Ye, Rose Moosavian, Mohammad Zargartalebi, David Sinton, Seyed Mohamad Moosavi
Physics-informed machine learning model decouples chemistry from thermodynamic state, including temperature, to accurately predict fluid properties across thermodynamic conditions. It enables reliable design of new cooling fluids.
The content of this RSS Feed (c) The Royal Society of Chemistry

GEOMIND: a hybrid generative artificial intelligence model for geopolymer design and optimization

Digital Discovery, 2026, Advance Article
DOI: 10.1039/D5DD00383K, Paper

Open Access

This article is licensed under a Creative Commons Attribution-NonCommercial 3.0 Unported Licence.

Sébastien Rousseau, Assil Bouzid, Sylvie Rossignol, Ameni Gharzouni
GEOMIND is a hybrid machine learning model trained on an in-house database to recommend optimal geopolymer formulations for user-defined target properties.
To cite this article before page numbers are assigned, use the DOI form of citation above.
The content of this RSS Feed (c) The Royal Society of Chemistry

Protein language visualizer: a repository for homology exploration with language model embeddings

Digital Discovery, 2026, Advance Article
DOI: 10.1039/D5DD00472A, Paper

Open Access

This article is licensed under a Creative Commons Attribution 3.0 Unported Licence.

Javier Espinoza-Herrera, María F. Manríquez-García, Sofía Medina-Bermejo, Ailyn López-Jasso, Juan P. Ruiz-Alcocer, Adriana Siordia, Sarah M. Veskimägi, Nate Roethler, Adrian Jinich
The PLVis repository turns protein language model embeddings into maps of proteomic relationships, enabling accessible comparative and functional proteomic analysis.
To cite this article before page numbers are assigned, use the DOI form of citation above.
The content of this RSS Feed (c) The Royal Society of Chemistry

Good enough is better: feasibility vs. Pareto-optimality in alloy design

Digital Discovery, 2026, Advance Article
DOI: 10.1039/D5DD00517E, Paper

Open Access

This article is licensed under a Creative Commons Attribution 3.0 Unported Licence.

Cayden Maguire, Christofer Hardcastle, Trevor Hastings, Raymundo Arróyave, Brent Vela
In this work, we treat alloy design as a probabilistic constraint satisfaction problem and demonstrate the advantages of this framework over traditional optimization-based approaches.
To cite this article before page numbers are assigned, use the DOI form of citation above.
The content of this RSS Feed (c) The Royal Society of Chemistry

Automatic generation of input files with optimised k-point meshes for Quantum ESPRESSO self-consistent field single-point total energy calculations

Digital Discovery, 2026, Advance Article
DOI: 10.1039/D5DD00565E, Paper

Open Access

This article is licensed under a Creative Commons Attribution 3.0 Unported Licence.

Elena Patyukova, Junwen Yin, Susmita Basak, Samuel Pinilla, Alin M. Elena, Gilberto Teobaldi
Performing density functional theory (DFT) calculations requires a careful choice of computational parameters to ensure convergence and obtain meaningful results.
To cite this article before page numbers are assigned, use the DOI form of citation above.
The content of this RSS Feed (c) The Royal Society of Chemistry

Back to the future of lead optimization: benchmarking compound prioritization strategies

Digital Discovery, 2026, Advance Article
DOI: 10.1039/D5DD00387C, Paper

Open Access

This article is licensed under a Creative Commons Attribution-NonCommercial 3.0 Unported Licence.

Pablo Mas, Bruno Filoche-Rommé, Marc Bianciotto, Rodolphe Vuilleumier
We introduce a framework based on the Design–Make–Test–Analyze (DMTA) paradigm for simulating the outcome of prioritization strategies during lead optimization and assessing their performance in exploring and exploiting the chemical space.
To cite this article before page numbers are assigned, use the DOI form of citation above.
The content of this RSS Feed (c) The Royal Society of Chemistry

Developing a machine-learning interatomic potential for non-covalent interactions in proteins

Digital Discovery, 2026, Advance Article
DOI: 10.1039/D6DD00056H, Paper

Open Access

This article is licensed under a Creative Commons Attribution-NonCommercial 3.0 Unported Licence.

Lejia Zeng, Xintong Zhang, Yuchan Pei, Lifeng Zhao, Lan Hua, Jincai Yang, Niu Huang
A PAirwise Non-covalent Interaction Potential (PANIP) with accuracy comparable to the ωB97X-D3BJ/def2-TZVPP level for non-covalent interactions in proteins.
To cite this article before page numbers are assigned, use the DOI form of citation above.
The content of this RSS Feed (c) The Royal Society of Chemistry

Journal research data policies in materials science

Digital Discovery, 2026, Advance Article
DOI: 10.1039/D6DD00111D, Perspective

Open Access

This article is licensed under a Creative Commons Attribution 3.0 Unported Licence.

Lukas Hörmann, Hemanadhan Myneni, Rwayda Kh. S. Al-Hamd, Katarina Batalović, Silvia Bonfanti, Federico Grasselli, Saulius Gražulis, Bahattin Koç, Konstantinos Konstantinou, Ivor Lončarić, Nataliya Lopanitsyna, José Manuel Oliveira, Paolo Pegolo, Patrícia Ramos, Kevin Rossi, Sebastian P. Schwaminger, Edith Simmen, Milica Todorović, Markus Stricker, Jonathan Schmidt
Open and reproducible research in materials science relies on the availability of data, code, and established metadata standards.
To cite this article before page numbers are assigned, use the DOI form of citation above.
The content of this RSS Feed (c) The Royal Society of Chemistry

A modular approach to studying polymer processing using a self-driving lab

Digital Discovery, 2026, Advance Article
DOI: 10.1039/D6DD00146G, Paper

Open Access

This article is licensed under a Creative Commons Attribution 3.0 Unported Licence.

Adedire D. Adesiji, Dylan J. Balter, Zhaoji Yang, Kelsey L. Snapp, Joseph M. Palomba, Keith A. Brown
We report an autonomous experimentation system designed to study processing-dependent properties of polymers in a modular fashion. We test this by spray coating polymer films and discovering conditions under which they are highly iridescent.
To cite this article before page numbers are assigned, use the DOI form of citation above.
The content of this RSS Feed (c) The Royal Society of Chemistry

A property–agnostic framework for scalable molecular inverse design via quantum annealing

Digital Discovery, 2026, Advance Article
DOI: 10.1039/D6DD00012F, Paper

Open Access

This article is licensed under a Creative Commons Attribution 3.0 Unported Licence.

Yuki Deguchi, Masato Taki
Technologies for designing molecules with desired properties have the potential to drive innovation across a wide range of fields.
To cite this article before page numbers are assigned, use the DOI form of citation above.
The content of this RSS Feed (c) The Royal Society of Chemistry

Text-to-flowsheet: an LLM-assisted pipeline for expert-level digitization and automated simulation of chemical processes

Digital Discovery, 2026, Advance Article
DOI: 10.1039/D6DD00060F, Paper

Open Access

This article is licensed under a Creative Commons Attribution-NonCommercial 3.0 Unported Licence.

Jan-Frederic Laub, Luca Bosetti, André Bardow
Using a unique dataset of expert-drawn flowsheets, we develop and validate an LLM-assisted pipeline that digitizes chemical processes from natural language descriptions and automates their simulation.
To cite this article before page numbers are assigned, use the DOI form of citation above.
The content of this RSS Feed (c) The Royal Society of Chemistry

Leveraging active site information for deep learning prediction of enzyme–substrate Michaelis constants

Digital Discovery, 2026, Advance Article
DOI: 10.1039/D6DD00094K, Paper

Open Access

This article is licensed under a Creative Commons Attribution 3.0 Unported Licence.

Daniil Lepikhov, Laura Sandner, Ariane Nunes-Alves
The Michaelis constant (K_M) is a key parameter in enzymology. Active site for K_M (AS4Km) is a deep learning model that leverages explicit active site information to predict K_M values for enzyme–substrate complexes.
To cite this article before page numbers are assigned, use the DOI form of citation above.
The content of this RSS Feed (c) The Royal Society of Chemistry

A soft sensor based on pH for real-time monitoring of mRNA medicine production

Digital Discovery, 2026, Advance Article
DOI: 10.1039/D5DD00417A, Paper

Open Access

This article is licensed under a Creative Commons Attribution-NonCommercial 3.0 Unported Licence.

Mahdi Ahmed, Shady Hamed, Ricardo Cardoso, Charley Kenyon, Manoj Pohare, Mabrouka Maamra, Mark Dickman, Joan Cordiner, Zoltán Kis
A simple pH signal unlocks real-time, extensive monitoring of mRNA production via mechanistic and semi-empirical models. This aids continuous quantification of RNA yield, NTP depletion and ∼40 IVT components for monitoring and advanced control.
To cite this article before page numbers are assigned, use the DOI form of citation above.
The content of this RSS Feed (c) The Royal Society of Chemistry

Taming T-REX: a canonical language for geometry-aware generative design of transition-metal complexes

Digital Discovery, 2026, Advance Article
DOI: 10.1039/D6DD00129G, Paper

Open Access

This article is licensed under a Creative Commons Attribution 3.0 Unported Licence.

Ilia Kevlishvili, Devmin Dorabawila
T-REX strings enable coordination isomer discovery, novel structure generation and robust ML representation.
To cite this article before page numbers are assigned, use the DOI form of citation above.
The content of this RSS Feed (c) The Royal Society of Chemistry