The Cheminformatics Gateway is designed to cover all computational approaches to representing and analysing chemical structures and chemical data. In particular, we are interested in uses of current computer technology in the broad field of chemical research. This includes current trending topics such as AI in drug discovery on the large,
de novo design and library enumeration, and reaction informatics.
Understanding when or why computational methods do not work, and why there might be fundamental limitations to computational approaches is as important for advancing the field as the development of new concepts and methods. Therefore, contributions reporting negative data and/or showing why computational methods fail are also encouraged. Through this approach the Cheminformatics Gateway aims to improve reproducibility, credit researchers for all their outputs, and disseminate valuable research which may struggle to find a ‘home’ via traditional publication venues.
Further details and background information are provided in the
Editorial introducing the Cheminformatics Gateway.
Joint Python and Cheminformatics Call for Papers
We are inviting article contributions to the Cheminformatics Gateway and
Python collection. We’re welcoming any submissions around Python software related to cheminformatics, big data analysis and artificial intelligence. This is a great opportunity to get credit for the software you’re producing and bring further visibility and impact to your work by having it featured as part of the Cheminformatics Gateway and the Python collection.
If you are interested in contributing or have any questions, please get in contact with any of our Gateway advisors or email
research@f1000.com.
The machine learning gateway area provides a rapid and open platform for the broad range of research relating to machine learning. This area extends to machine learning applications within chemical information science and related interdisciplinary areas.
We welcome all types of publications related to machine learning, including but not limited to: benchmarking studies, novel deep learning architectures, reinforcement learning, active machine learning, transfer learning, generative models, explainable AI, and uncertainty quantification.
The metabolomics gateway area provides a platform for rapid dissemination of the latest research relating to metabolomics and its intersection with chemical information science.
We welcome all types of publications related to metabolomics, including but not limited to: databases, mass spectrometry analysis, automated structure elucidation, biomarker discovery, spatiotemporal analysis, ecological niches, pharmacognosy, and biodiversity.