Advances in Digital Chemical Discovery is proposed as an open-access collection topic for the journal Discover Chemistry, dedicated to publishing high-quality theoretical research at the convergence of chemistry, materials science, and biotechnology, with a strong emphasis on data-driven methodologies. The collection aims to highlight how machine learning, artificial intelligence, automation, and advanced computational approaches are transforming the way chemical knowledge is generated, validated, and translated into applications. By placing data at the center of discovery, the collection promotes transparency, reproducibility, and accelerated scientific progress, serving a broad community that includes chemists, biologists, engineers, physicists, environmental scientists, and professionals in food, cosmetic, and pharmaceutical sciences.

The scope of Advances in Digital Chemical Discovery encompasses computational contributions that advance the acceleration of discovery processes, broadly defined but firmly anchored in chemistry. Submissions may address high-throughput and low-throughput paradigms alike, including the development of intelligent screening strategies, autonomous and robotics, chemical and materials databases, and sophisticated data analytics pipelines. Particular emphasis is placed on artificial intelligence and other high-throughput computational methodologies for molecular, materials, and formulation design; advanced and interoperable data workflows; and novel automation platforms that integrate seamlessly with computational models. In addition, the collection welcomes interdisciplinary studies at the interface of chemistry with the life sciences, materials science, physics, and engineering, as well as research that accelerates traditionally low-throughput structural or mechanistic investigations. This includes, but is not limited to explainable artificial intelligence and machine learning techniques such as feature attribution and sensitivity analysis, Shapley additive explanations, local interpretable model-agnostic explanations, Anchor explanations, attention-based neural architectures, saliency mapping, counterfactual explanations, symbolic regression, sparse and linearized surrogate models, interpretable graph neural networks, rule-based and decision-tree ensembles, Bayesian inference and probabilistic graphical models, uncertainty quantification and calibration methods, causal inference frameworks, active learning with uncertainty-aware acquisition functions, physics-informed and hybrid mechanistic–machine learning models, and latent space disentanglement approaches, as well as large language model and natural language processing techniques including semantic literature mining, transformer-based text embeddings, domain-adapted and chemically grounded language models, retrieval-augmented generation, knowledge graph construction from text, automated hypothesis generation, document clustering and topic modeling, scientific text summarization, named entity recognition for chemical and biological entities, and question-answering systems for research, and agentic artificial intelligence techniques such as autonomous research agents, multi-agent systems, tool-using and planning-enabled AI, closed-loop decision-making frameworks, and self-reflective or self-improving agents for experimental design, data analysis, and knowledge discovery. By bringing together contributions across chemical, food, cosmetic, pharmacological, toxicological, environmental, materials, biochemical, biomedical, and biophysical sciences, Advances in Digital Chemical Discovery seeks to reflect the breadth and depth of digital innovation in modern chemistry.

Driven by the ongoing digital transformation of the chemical industry, academy and related sectors, this Collection aspires to become a premier venue for disseminating foundational methods, applied technologies, and integrative case studies that redefine discovery in the twenty-first century. Through rigorous peer review and open access dissemination, Advances in Digital Chemical Discovery will foster cross-disciplinary dialogue, encourage the adoption of reproducible digital practices, and accelerate the translation of data-centric research into scientific and societal impact.

Keywords: Artificial intelligence, Machine Learning, Molecular design, Deep Learning, Quantum mechanics, Statistical mechanics, Molecular modeling, Cheminformatics, Bioinformatics, Digital transformation, Autonomous discovery.

This Collection supports and amplifies research related to SDG 9.