About Machine Learning in Drug Discovery and Development
Machine Learning in Drug Discovery and Development
About this Collection
This collection is now closed to submissions.
Drug discovery and development can be a very lengthy and expensive process. This is partly due to the fact that the cost of drug discovery must compensate for failures. One way to work towards alleviating this problem is by making the process more open, including publishing negative and early results. While the use of machine learning in drug discovery and development holds the promise to greatly improve the timeliness of the process, much attention is still needed to develop datasets that will lead to generalizable models to make novel discoveries.
This collection aims to provide a useful resource for the drug discovery and development communities and researchers working in related interdisciplinary fields. We welcome a wide range of papers, including models and methods for making predictions of binding activity, off-target binding, target fishing, identification of disease phenotypes and clinical relevance.
Using the F1000Research publishing model we are looking to create an open forum for discussion and dissemination of research around these main areas:
The collection will also seek to address various interdisciplinary challenges and ensure improved knowledge sharing across disparate communities, such as: biology, chemistry, cheminformatics, computational biophysics, bioinformatics, structural biology, computational science, applied mathematics, and clinical research.
Keywords: drug binding datasets, drug binding predictions, QSAR, drug features, protein features, model trustworthiness, adverse drug reaction, target fishing
Any questions about this collection? Please get in contact directly with Krishna Sharma (krishna.sharma@tandf.co.uk)
This collection is part of the Gateway on Artificial Intelligence & Machine Learning, which aims to provide stakeholders across academia, industry and policy with a space to disseminate work related to all areas of machine learning and AI research.
Drug discovery and development can be a very lengthy and expensive process. This is partly due to the fact that the cost of drug discovery must compensate for failures. One way to work towards alleviating this problem is by making the process more open, including publishing negative and early results. While the use of machine learning in drug discovery and development holds the promise to greatly improve the timeliness of the process, much attention is still needed to develop datasets that will lead to generalizable models to make novel discoveries.
This collection aims to provide a useful resource for the drug discovery and development communities and researchers working in related interdisciplinary fields. We welcome a wide range of papers, including models and methods for making predictions of binding activity, off-target binding, target fishing, identification of disease phenotypes and clinical relevance.
Using the F1000Research publishing model we are looking to create an open forum for discussion and dissemination of research around these main areas:
- Models and methods for drug binding predictions
- Side-effect predictions
- Drug target fishing
- Identification of disease causality
- Quantitative structure-activity relationship (QSAR)
- Datasets and dataset evaluation metrics for bias and generalizability
- Dataset featurization
The collection will also seek to address various interdisciplinary challenges and ensure improved knowledge sharing across disparate communities, such as: biology, chemistry, cheminformatics, computational biophysics, bioinformatics, structural biology, computational science, applied mathematics, and clinical research.
Keywords: drug binding datasets, drug binding predictions, QSAR, drug features, protein features, model trustworthiness, adverse drug reaction, target fishing
Any questions about this collection? Please get in contact directly with Krishna Sharma (krishna.sharma@tandf.co.uk)
This collection is part of the Gateway on Artificial Intelligence & Machine Learning, which aims to provide stakeholders across academia, industry and policy with a space to disseminate work related to all areas of machine learning and AI research.
Collection Advisor
-
Sally Ellingson
