TUCAN: A molecular identifier and descriptor applicable to the whole periodic table from hydrogen to oganesson

Brammer, Jan C.; Blanke, Gerd; Kellner, Claudia; Hoffmann, Alexander; Herres‐Pawlis, Sonja; Schatzschneider, Ulrich

doi:10.21203/rs.3.rs-1466562/v1

“…While some solutions have been proposed, they have not been widely applied yet. [33,34] In our case we took advantage of the fact that all 288 tested compounds and any compound of this class we wished to predict shared several similarities. All compounds contain ruthenium(II), have a chlorido ligand and in an approximation adopt the same pseudo-"piano stool" geometry.…”

Section: Resultsmentioning

confidence: 99%

Using Machine Learning to Predict the Antibacterial Activity of Ruthenium Complexes**

Orsi,

Shing Loh,

Weng

et al. 2024

Angew Chem Int Ed

6

0

View full text Add to dashboard Cite

Rising antimicrobial resistance (AMR) and lack of innovation in the antibiotic pipeline necessitate novel approaches to discovering new drugs. Metal complexes have proven to be promising antimicrobial compounds, but the number of studied compounds is still low compared to the millions of organic molecules investigated so far. Lately, machine learning (ML) has emerged as a valuable tool for guiding the design of small organic molecules, potentially even in low‐data scenarios. For the first time, we extend the application of ML to the discovery of metal‐based medicines. Utilising 288 modularly synthesized ruthenium arene Schiff‐base complexes and their antibacterial properties, a series of ML models were trained. The models perform well and are used to predict the activity of 54 new compounds. These displayed a 5.7x higher hit‐rate (53.7%) against methicillin‐resistant Staphylococcus aureus (MRSA) compared to the original library (9.4%), demonstrating that ML can be applied to improve the success‐rates in the search of new metalloantibiotics. This work paves the way for more ambitious applications of ML in the field of metal‐based drug discovery.

show abstract

“…Obwohl einige Lösungen vorgeschlagen wurden, wurden sie bisher nicht weit angewendet. [33,34] In diesem Projekt nutzten wir die Tatsache, dass sowohl die 288 getesteten als auch die neuen, zu vorhersagenden Komplexe, mehrere Merkmale miteinander teilen. Alle Verbindungen enthalten Ruthenium(II), verfügen über einen Chlorido-Liganden und besitzen approximiert die gleiche pseudo-"Klavierhocker"-Geometrie.…”

Section: Ergebnisse Und Diskussionunclassified

Maschinelles Lernen zur Vorhersage antibakterieller Aktivität von Ruthenium‐Komplexen**

Orsi,

Shing Loh,

Weng

et al. 2024

Angewandte Chemie

0

View full text Add to dashboard Cite

Rising antimicrobial resistance (AMR) and lack of innovation in the antibiotic pipeline necessitate novel approaches to discovering new drugs. Metal complexes have proven to be promising antimicrobial compounds, but the number of studied compounds is still low compared to the millions of organic molecules investigated so far. Lately, machine learning (ML) has emerged as a valuable tool for guiding the design of small organic molecules, potentially even in low‐data scenarios. For the first time, we extend the application of ML to the discovery of metal‐based medicines. Utilising 288 modularly synthesized ruthenium arene Schiff‐base complexes and their antibacterial properties, a series of ML models were trained. The models perform well and are used to predict the activity of 54 new compounds. These displayed a 5.7x higher hit‐rate (53.7%) against methicillin‐resistant Staphylococcus aureus (MRSA) compared to the original library (9.4%), demonstrating that ML can be applied to improve the success‐rates in the search of new metalloantibiotics. This work paves the way for more ambitious applications of ML in the field of metal‐based drug discovery.

show abstract

Graph neural networks for materials science and chemistry

Reiser

¹

,

Neubert

²

,

Eberhard

³

et al. 2022

View full text Add to dashboard Cite

Machine learning plays an increasingly important role in many areas of chemistry and materials science, being used to predict materials properties, accelerate simulations, design new structures, and predict synthesis routes of new materials. Graph neural networks (GNNs) are one of the fastest growing classes of machine learning models. They are of particular relevance for chemistry and materials science, as they directly work on a graph or structural representation of molecules and materials and therefore have full access to all relevant information required to characterize materials. In this Review, we provide an overview of the basic principles of GNNs, widely used datasets, and state-of-the-art architectures, followed by a discussion of a wide range of recent applications of GNNs in chemistry and materials science, and concluding with a road-map for the further development and application of GNNs.

show abstract

TUCAN: A molecular identifier and descriptor applicable to the whole periodic table from hydrogen to oganesson

Cited by 3 publications

References 28 publications

Using Machine Learning to Predict the Antibacterial Activity of Ruthenium Complexes**

Using Machine Learning to Predict the Antibacterial Activity of Ruthenium Complexes**

Maschinelles Lernen zur Vorhersage antibakterieller Aktivität von Ruthenium‐Komplexen**

Graph neural networks for materials science and chemistry

Contact Info

Product

Resources

About