ACTION on Cancer

Lead Research Organisation: Goldsmiths University of London
Department Name: Computing Department

Abstract

Abstracts are not currently available in GtR for all funded research. This is normally because the abstract was not required at the time of proposal submission, but may be because it included sensitive information such as personal details.
 
Description we are developing new ML tools for improving cancer-relevant predictions
Exploitation Route Cancer patients could be prescribed more effective chemotherapy drug combinations
Sectors Healthcare
 
Description - SkyLab Bio company is using machine learning software developed within this project. - University of London is using our Robot Scientist as a case study in their AI module on online MSc data science programme (~500 students), and online BSc Computer Science programme (~5,000 students)
First Year Of Impact 2022
Sector Chemicals,Education
Impact Types Societal

Economic
 
Title Supplementary Information showing a list of all the ligand features considered from A simple spatial extension to the extended connectivity interaction features for binding affinity prediction 
Description The representation of the protein-ligand complexes used in building machine learning models play an important role in the accuracy of binding affinity prediction. The Extended Connectivity Interaction Features (ECIF) is one such representation. We report that (i) including the discretized distances between protein-ligand atom pairs in the ECIF scheme improves predictive accuracy, and (ii) in an evaluation using gradient boosted trees, we found that the resampling method used in selecting the best hyperparameters has a strong effect on predictive performance, especially for benchmarking purposes. 
Type Of Material Database/Collection of data 
Year Produced 2022 
Provided To Others? Yes  
URL https://rs.figshare.com/articles/dataset/Supplementary_Information_showing_a_list_of_all_the_ligand_...
 
Title Supplementary Information showing a list of all the ligand features considered from A simple spatial extension to the extended connectivity interaction features for binding affinity prediction 
Description The representation of the protein-ligand complexes used in building machine learning models play an important role in the accuracy of binding affinity prediction. The Extended Connectivity Interaction Features (ECIF) is one such representation. We report that (i) including the discretized distances between protein-ligand atom pairs in the ECIF scheme improves predictive accuracy, and (ii) in an evaluation using gradient boosted trees, we found that the resampling method used in selecting the best hyperparameters has a strong effect on predictive performance, especially for benchmarking purposes. 
Type Of Material Database/Collection of data 
Year Produced 2022 
Provided To Others? Yes  
URL https://rs.figshare.com/articles/dataset/Supplementary_Information_showing_a_list_of_all_the_ligand_...
 
Title Supplementary table showing the selected important features from A simple spatial extension to the extended connectivity interaction features for binding affinity prediction 
Description The representation of the protein-ligand complexes used in building machine learning models play an important role in the accuracy of binding affinity prediction. The Extended Connectivity Interaction Features (ECIF) is one such representation. We report that (i) including the discretized distances between protein-ligand atom pairs in the ECIF scheme improves predictive accuracy, and (ii) in an evaluation using gradient boosted trees, we found that the resampling method used in selecting the best hyperparameters has a strong effect on predictive performance, especially for benchmarking purposes. 
Type Of Material Database/Collection of data 
Year Produced 2022 
Provided To Others? Yes  
URL https://rs.figshare.com/articles/dataset/Supplementary_table_showing_the_selected_important_features...
 
Title Supplementary table showing the selected important features from A simple spatial extension to the extended connectivity interaction features for binding affinity prediction 
Description The representation of the protein-ligand complexes used in building machine learning models play an important role in the accuracy of binding affinity prediction. The Extended Connectivity Interaction Features (ECIF) is one such representation. We report that (i) including the discretized distances between protein-ligand atom pairs in the ECIF scheme improves predictive accuracy, and (ii) in an evaluation using gradient boosted trees, we found that the resampling method used in selecting the best hyperparameters has a strong effect on predictive performance, especially for benchmarking purposes. 
Type Of Material Database/Collection of data 
Year Produced 2022 
Provided To Others? Yes  
URL https://rs.figshare.com/articles/dataset/Supplementary_table_showing_the_selected_important_features...
 
Description Arctoris Ltd 
Organisation Arctoris
Country United Kingdom 
Sector Private 
PI Contribution Our research team provides description of experiments and research hypotheses. This is a test case for Arctoris to develop an interactive system with external researchers.
Collaborator Contribution Arctoris (https://www.arctoris.com/) is contributing to the project by running experiments in their lab.
Impact experimental data
Start Year 2020
 
Description Imagen 
Organisation Imagen Therapeutics
Country United Kingdom 
Sector Private 
PI Contribution expert advise on the analysis of data
Collaborator Contribution provided unique datasets
Impact datasets
Start Year 2021