Gian Marco Ghiandoni
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Gian Marco Ghiandoni has a total of 67 co-authors. Here are the top co-authors by number of shared publications:
- Andrey I. Frolov
Medicinal Chemistry, Research and Early Development, Cardiovascular, Renal and Metabolism (CVRM), BioPharmaceuticals R&D, AstraZeneca, Gothenburg, Sweden
3 shared publications - Abdul Ingar
Discovery Sciences, R&D, AstraZeneca, The Discovery Centre (DISC), 1 Francis Crick Avenue, CB2 0AA Cambridge, U.K.
2 shared publications - Anaïs F. M. Noisier
Medicinal Chemistry CVRM, Discovery Sciences, BioPharmaceuticals R&D, AstraZeneca, Pepparedsleden 1, 43183 Mölndal, Sweden
2 shared publications Beining Chen
Department of Chemistry University of Sheffield Dainton Building, Brook Hill Sheffield S3 7HF UK
2 shared publicationsDimitar Hristozov
Evotec (U.K.) Ltd 114 Innovation Drive, Milton Park Abingdon OX14 4RZ UK
2 shared publications- Hannah L. Bolt
Department of Chemistry, Durham University, South Road, Durham, DH1 3LE, United Kingdom
2 shared publications
Latest Publications
- Top Cited PapersOpen Access
- 7 August 2026
- Published by Springer Nature in Nature Reviews Drug Discovery
- Vol. 25 (11) , 855-876
Artificial intelligence in drug discovery — what it is, where we stand and the path forward
- 7 August 2026
- Published by Springer Nature in Nature Reviews Drug Discovery
- Vol. 25 (11) , 855-876
Top Cited PapersOpen AccessArtificial intelligence in drug discovery — what it is, where we stand and the path forward
- Open Access
- 5 July 2026
- Published by American Chemical Society (ACS) in Journal of Chemical Information and Modeling
- Vol. 66 (14) , 7821-7839
Advancing Biochemical Molecule Registration, Representation and Search for New Drug Modalities
The pharmaceutical industry’s shift toward new drug modalities, including therapeutic peptides, modified oligonucleotides, and antibody–drug conjugates, has exposed fundamental gaps in cheminformatics infrastructure. Unlike small molecules, which benefit from mature representation standards and reliable data exchange, new modalities lack robust and interoperable systems capable of capturing their structural and chemical complexity. Drawing on our experience at AstraZeneca, we examine these challenges across peptides, oligonucleotides, and ADCs, focusing on the limitations of current approaches, particularly HELM. We show that these limitations arise from both technical constraints, as new modalities exceed the scope of purely atomistic or sequence-based representations, and organizational gaps, including unresolved standardization and governance. We argue that local solutions exacerbate fragmentation, and that vendor- and community-driven standards, open implementations, and stronger governance are required to enable standardized and interoperable chemical information systems for next-generation therapeutics.
- 5 July 2026
- Published by American Chemical Society (ACS) in Journal of Chemical Information and Modeling
- Vol. 66 (14) , 7821-7839
Open AccessAdvancing Biochemical Molecule Registration, Representation and Search for New Drug Modalities
The pharmaceutical industry’s shift toward new drug modalities, including therapeutic peptides, modified oligonucleotides, and antibody–drug conjugates, has exposed fundamental gaps in cheminformatics infrastructure. Unlike small molecules, which benefit from mature representation standards and reliable data exchange, new modalities lack robust and interoperable systems capable of capturing their structural and chemical complexity. Drawing on our experience at AstraZeneca, we examine these challenges across peptides, oligonucleotides, and ADCs, focusing on the limitations of current approaches, particularly HELM. We show that these limitations arise from both technical constraints, as new modalities exceed the scope of purely atomistic or sequence-based representations, and organizational gaps, including unresolved standardization and governance. We argue that local solutions exacerbate fragmentation, and that vendor- and community-driven standards, open implementations, and stronger governance are required to enable standardized and interoperable chemical information systems for next-generation therapeutics.
- Open Access
- 15 April 2026
- Published by American Chemical Society (ACS) in ChemRxiv
Non-natural amino acid nomenclature for HELM monomer registration
The growing interest in studying modified and cyclic peptides is constrained by limitations in how their chemical information is encoded, represented, and analysed. Traditional sequence formats such as FASTA only allow working with linear and natural peptides. HELM and BILN formats provide more versatile and extendible notation systems for the representation of peptides with non-natural monomers or cyclic arrangements. HELM is a notation that uses a database as a source of monomers where these are defined on their structure, identifier, and attachment points. While structural representations are canonicalized using established methods, there is currently no widely accepted convention for naming peptide monomers. In this manuscript, we develop on top of the guidelines proposed by Pistoia Alliance for the naming of non-natural amino acids for their representation using HELM. Our nomenclature extends on modifications of side chains and backbone, naming of homo amino acids and peptoids, and resolves ambiguous cases using a combination of systematic and pragmatic rules.
- 15 April 2026
- Published by American Chemical Society (ACS) in ChemRxiv
Open AccessNon-natural amino acid nomenclature for HELM monomer registration
The growing interest in studying modified and cyclic peptides is constrained by limitations in how their chemical information is encoded, represented, and analysed. Traditional sequence formats such as FASTA only allow working with linear and natural peptides. HELM and BILN formats provide more versatile and extendible notation systems for the representation of peptides with non-natural monomers or cyclic arrangements. HELM is a notation that uses a database as a source of monomers where these are defined on their structure, identifier, and attachment points. While structural representations are canonicalized using established methods, there is currently no widely accepted convention for naming peptide monomers. In this manuscript, we develop on top of the guidelines proposed by Pistoia Alliance for the naming of non-natural amino acids for their representation using HELM. Our nomenclature extends on modifications of side chains and backbone, naming of homo amino acids and peptoids, and resolves ambiguous cases using a combination of systematic and pragmatic rules.
- Top Cited PapersOpen Access
- 16 January 2026
- Published by Elsevier in Drug Discovery Today
- Vol. 31 (2) , 104605
Democratising real-world drug discovery through agentic AI
- 16 January 2026
- Published by Elsevier in Drug Discovery Today
- Vol. 31 (2) , 104605
Top Cited PapersOpen AccessDemocratising real-world drug discovery through agentic AI
- 30 December 2025
- Published by American Chemical Society (ACS) in Journal of Chemical Information and Modeling
- Vol. 66 (1) , 16-27
Peptide-Tools–Web Server for Calculating Physicochemical Properties of Peptides
Peptides play an increasingly important role in medicine and materials science. Accurate estimation of peptide physicochemical parameters is essential for their design, purification, and analysis. In this manuscript, we present Peptide-Tools, a freely accessible web server with an intuitive user interface for calculating isoelectric points and evaluating common chemical stability liabilities in both natural and modified peptides. Peptide-Tools accommodates a variety of input formats and can account for the ionization states of noncanonical amino acids and other molecular fragments. The platform also computes peptide extinction coefficients at three wavelengths (205, 214, and 280 nm), with this functionality currently available only for canonical amino acids. The server relies on a command-line tool that can be installed locally. We anticipate that Peptide-Tools will streamline peptide optimization and support routine tasks in chemical and analytical laboratories.
- 30 December 2025
- Published by American Chemical Society (ACS) in Journal of Chemical Information and Modeling
- Vol. 66 (1) , 16-27
Peptide-Tools–Web Server for Calculating Physicochemical Properties of Peptides
Peptides play an increasingly important role in medicine and materials science. Accurate estimation of peptide physicochemical parameters is essential for their design, purification, and analysis. In this manuscript, we present Peptide-Tools, a freely accessible web server with an intuitive user interface for calculating isoelectric points and evaluating common chemical stability liabilities in both natural and modified peptides. Peptide-Tools accommodates a variety of input formats and can account for the ionization states of noncanonical amino acids and other molecular fragments. The platform also computes peptide extinction coefficients at three wavelengths (205, 214, and 280 nm), with this functionality currently available only for canonical amino acids. The server relies on a command-line tool that can be installed locally. We anticipate that Peptide-Tools will streamline peptide optimization and support routine tasks in chemical and analytical laboratories.
- Open Access
- 5 November 2025
- Published by American Chemical Society (ACS) in ACS Omega
- Vol. 10 (45) , 54148-54159
Prediction of Permeability and Efflux Using Multitask Learning
In silico prediction of cell membrane permeability is crucial in drug discovery, since a compound’s permeation through membranes influences parameters such as its in vivo efficacy, bioavailability, and pharmacokinetics. This study investigates the use of multitask graph neural networks to predict a selection of permeability-related endpoints. The study utilized a harmonized, single-laboratory internal data set of over 10K compounds measured in human colorectal adenocarcinoma (Caco-2) and Madin–Darby canine kidney (MDCK) cell lines, routinely employed in experimental assays for drug permeability and efflux. This data set is an order of magnitude larger than comparable public collections, thus providing greater statistical power and a consistent error profile for model development. A series of multitask learning (MTL) models trained on such data were benchmarked against single-task approaches and evaluated on an external public data set to investigate the model’s applicability domain. The comparison between the performance of single- and multitask models suggests that MTL can achieve higher accuracy by leveraging shared information across endpoints. MTL is also shown to perform better when augmented with molecular features. In particular, the inclusion of pKa and LogD, is shown to improve the accuracy of both permeability and efflux endpoints. This work presents benchmarking results of models utilizing different data splitting strategies, accompanied by guidelines for optimal validation in the context of MTL.
- 5 November 2025
- Published by American Chemical Society (ACS) in ACS Omega
- Vol. 10 (45) , 54148-54159
Open AccessPrediction of Permeability and Efflux Using Multitask Learning
In silico prediction of cell membrane permeability is crucial in drug discovery, since a compound’s permeation through membranes influences parameters such as its in vivo efficacy, bioavailability, and pharmacokinetics. This study investigates the use of multitask graph neural networks to predict a selection of permeability-related endpoints. The study utilized a harmonized, single-laboratory internal data set of over 10K compounds measured in human colorectal adenocarcinoma (Caco-2) and Madin–Darby canine kidney (MDCK) cell lines, routinely employed in experimental assays for drug permeability and efflux. This data set is an order of magnitude larger than comparable public collections, thus providing greater statistical power and a consistent error profile for model development. A series of multitask learning (MTL) models trained on such data were benchmarked against single-task approaches and evaluated on an external public data set to investigate the model’s applicability domain. The comparison between the performance of single- and multitask models suggests that MTL can achieve higher accuracy by leveraging shared information across endpoints. MTL is also shown to perform better when augmented with molecular features. In particular, the inclusion of pKa and LogD, is shown to improve the accuracy of both permeability and efflux endpoints. This work presents benchmarking results of models utilizing different data splitting strategies, accompanied by guidelines for optimal validation in the context of MTL.
- Open Access
- 8 March 2024
- Published by Elsevier in Drug Discovery Today
- Vol. 29 (4) , 103945
Augmenting DMTA using predictive AI modelling at AstraZeneca
- 8 March 2024
- Published by Elsevier in Drug Discovery Today
- Vol. 29 (4) , 103945
Open AccessAugmenting DMTA using predictive AI modelling at AstraZeneca
- Open Access
- 6 February 2024
- Published by Wiley in Molecular Informatics
- Vol. 43 (4)
Synthetically accessible de novo design using reaction vectors: Application to PARP1 inhibitors**
De novo design has been a hotly pursued topic for many years. Most recent developments have involved the use of deep learning methods for generative molecular design. Despite increasing levels of algorithmic sophistication, the design of molecules that are synthetically accessible remains a major challenge. Reaction‐based de novo design takes a conceptually simpler approach and aims to address synthesisability directly by mimicking synthetic chemistry and driving structural transformations by known reactions that are applied in a stepwise manner. However, the use of a small number of hand‐coded transformations restricts the chemical space that can be accessed and there are few examples in the literature where molecules and their synthetic routes have been designed and executed successfully. Here we describe the application of reaction‐based de novo design to the design of synthetically accessible and biologically active compounds as proof‐of‐concept of our reaction vector‐based software. Reaction vectors are derived automatically from known reactions and allow access to a wide region of synthetically accessible chemical space. The design was aimed at producing molecules that are active against PARP1 and which have improved brain penetration properties compared to existing PARP1 inhibitors. We synthesised a selection of the designed molecules according to the provided synthetic routes and tested them experimentally. The results demonstrate that reaction vectors can be applied to the design of novel molecules of biological relevance that are also synthetically accessible.
- 6 February 2024
- Published by Wiley in Molecular Informatics
- Vol. 43 (4)
Open AccessSynthetically accessible de novo design using reaction vectors: Application to PARP1 inhibitors**
De novo design has been a hotly pursued topic for many years. Most recent developments have involved the use of deep learning methods for generative molecular design. Despite increasing levels of algorithmic sophistication, the design of molecules that are synthetically accessible remains a major challenge. Reaction‐based de novo design takes a conceptually simpler approach and aims to address synthesisability directly by mimicking synthetic chemistry and driving structural transformations by known reactions that are applied in a stepwise manner. However, the use of a small number of hand‐coded transformations restricts the chemical space that can be accessed and there are few examples in the literature where molecules and their synthetic routes have been designed and executed successfully. Here we describe the application of reaction‐based de novo design to the design of synthetically accessible and biologically active compounds as proof‐of‐concept of our reaction vector‐based software. Reaction vectors are derived automatically from known reactions and allow access to a wide region of synthetically accessible chemical space. The design was aimed at producing molecules that are active against PARP1 and which have improved brain penetration properties compared to existing PARP1 inhibitors. We synthesised a selection of the designed molecules according to the provided synthetic routes and tested them experimentally. The results demonstrate that reaction vectors can be applied to the design of novel molecules of biological relevance that are also synthetically accessible.
- Open Access
- 13 March 2023
- Published by Springer Nature in Scientific Reports
- Vol. 13 (1) , 1-11
Fast calculation of hydrogen-bond strengths and free energy of hydration of small molecules
Hydrogen bonding is an interaction of great importance in drug discovery and development as it may significantly affect chemical and biological processes including the interaction of small molecules with other molecules, proteins, and membranes. In particular, hydrogen bonding can impact drug-like properties such as target affinity and oral availability which are critical to developing effective pharmaceuticals, and therefore, numerous methods for the calculation of properties such as hydrogen-bond strengths, free energy of hydration, or water solubility have been proposed over time. However, the accessibility to efficient methods for the predictions of such properties is still limited. Here, we present the development of Jazzy, an open-source tool for the prediction of hydrogen-bond strengths and free energies of hydration of small molecules. Jazzy also allows the visualisation of hydrogen-bond strengths with atomistic resolution to support the design of compounds with desired properties and the interpretation of existing data. The tool is described in its implementation, parameter fitting, and validation against two data sets of experimental hydration free energies. Jazzy is also applied against two chemical series of bioactive compounds to show that hydrogen-bond strengths can be used to understand their structure–activity relationships. Results from the validations highlight the strengths and limitations of Jazzy, and suggest its suitability for interactive design, screening, and machine-learning featurisation.
- 13 March 2023
- Published by Springer Nature in Scientific Reports
- Vol. 13 (1) , 1-11
Open AccessFast calculation of hydrogen-bond strengths and free energy of hydration of small molecules
Hydrogen bonding is an interaction of great importance in drug discovery and development as it may significantly affect chemical and biological processes including the interaction of small molecules with other molecules, proteins, and membranes. In particular, hydrogen bonding can impact drug-like properties such as target affinity and oral availability which are critical to developing effective pharmaceuticals, and therefore, numerous methods for the calculation of properties such as hydrogen-bond strengths, free energy of hydration, or water solubility have been proposed over time. However, the accessibility to efficient methods for the predictions of such properties is still limited. Here, we present the development of Jazzy, an open-source tool for the prediction of hydrogen-bond strengths and free energies of hydration of small molecules. Jazzy also allows the visualisation of hydrogen-bond strengths with atomistic resolution to support the design of compounds with desired properties and the interpretation of existing data. The tool is described in its implementation, parameter fitting, and validation against two data sets of experimental hydration free energies. Jazzy is also applied against two chemical series of bioactive compounds to show that hydrogen-bond strengths can be used to understand their structure–activity relationships. Results from the validations highlight the strengths and limitations of Jazzy, and suggest its suitability for interactive design, screening, and machine-learning featurisation.
- Open Access
- 27 December 2022
- Published by American Chemical Society (ACS) in Journal of Chemical Information and Modeling
- Vol. 63 (1) , 187-196
pIChemiSt ─ Free Tool for the Calculation of Isoelectric Points of Modified Peptides
- 27 December 2022
- Published by American Chemical Society (ACS) in Journal of Chemical Information and Modeling
- Vol. 63 (1) , 187-196
Open AccesspIChemiSt ─ Free Tool for the Calculation of Isoelectric Points of Modified Peptides