/trove/index-card/dfba33be-5a92-45c0-a8e0-ac15684b0cc1

trove:Indexcarddcat:CatalogRecord
https://share.osf.io/trove/index-card/dfba33be-5a92-45c0-a8e0-ac15684b0cc1
more details...
dcterms:modified
trove:focusIdentifier
https://osf.io/vh3rw
https://doi.org/10.31219/osf.io/vh3rw
dcterms:issued
foaf:primaryTopic
primary topic
trove:resourceMetadata

://osf.io/vh3rw

osf:Preprint
Machine Learning Models to Classify Molecules as Cancer Kinase Inhibitors or Non-Inhibitors
more details...
dcterms:created
2022-02-12
dcterms:dateCopyrighted
2022
dcterms:description
Cancer is known to be a leading cause of death worldwide, accounting for nearly 10 million deaths in 2020 alone. Cancer cells reproduce uncontrollably and function aberrantly, sometimes forming malignant or benign tumors that metastasize to other areas of the body. While decades-old cytotoxic chemotherapy that aims to kill tumor cells has had variable success rates, recently, scientists have produced remarkable results with targeted therapies such as cytostatic chemotherapy, which uses anti-cancer drugs to prevent cancer cell proliferation. This project aims to use machine learning models, including 3 dimensional convolutional neural networks to classify checkpoint inhibitors, a type of cytostatic chemotherapy drug, from large pools of molecules. Notably, with reshaped data, the convolutional neural network tested here achieved an AUC of 0.8851, beating out more sophisticated methods.
dcterms:identifier
https://osf.io/vh3rw
https://doi.org/10.31219/osf.io/vh3rw
dcterms:modified
2022-02-13
dcterms:title
Machine Learning Models to Classify Molecules as Cancer Kinase Inhibitors or Non-Inhibitors
osf:keyword
neural networks
chemotherapy
AI
fully connected neural network
targeted therapy
cytostatic
algorithms
cancer
3-D convolutional neural network
machine learning
dcterms:creator
dcterms:publisher
dcterms:rights
dcterms:subject

://api.osf.io/v2/subjects/584240d954be81056ceca8f6

skos:Concept
Numerical Analysis and Scientific Computing
more details...
skos:prefLabel
Numerical Analysis and Scientific Computing
skos:broader

://api.osf.io/v2/subjects/584240da54be81056cecabbb

skos:Concept
Computer Sciences
more details...
skos:prefLabel
Computer Sciences
skos:broader
skos:inScheme
skos:inScheme

://api.osf.io/v2/subjects/584240d954be81056ceca84c

skos:Concept
Cell and Developmental Biology
more details...
skos:prefLabel
Cell and Developmental Biology
skos:broader
skos:inScheme

://api.osf.io/v2/subjects/584240da54be81056cecabbb

skos:Concept
Computer Sciences
more details...
skos:prefLabel
Computer Sciences
skos:broader
skos:inScheme

://api.osf.io/v2/subjects/584240db54be81056cecaccc

skos:Concept
Cancer Biology
more details...
skos:prefLabel
Cancer Biology
skos:broader

://api.osf.io/v2/subjects/584240d954be81056ceca84c

skos:Concept
Cell and Developmental Biology
more details...
skos:prefLabel
Cell and Developmental Biology
skos:broader
skos:inScheme
skos:inScheme

://api.osf.io/v2/subjects/584240da54be81056cecaca8

skos:Concept
Artificial Intelligence and Robotics
more details...
skos:prefLabel
Artificial Intelligence and Robotics
skos:broader

://api.osf.io/v2/subjects/584240da54be81056cecabbb

skos:Concept
Computer Sciences
more details...
skos:prefLabel
Computer Sciences
skos:broader
skos:inScheme
skos:inScheme
dcterms:type
owl:sameAs
sameAs
dcat:accessService
osf:hasDataResource
osf:hostingInstitution
osf:isSupplementedBy

://osf.io/auvd7

osf:Project
Supplemental materials for preprint: Machine Learning Models to Classify Molecules as Cancer Kinase Inhibitors or Non-Inhibitors
more details...
dcterms:created
2022-02-13
dcterms:identifier
https://osf.io/auvd7
dcterms:title
Supplemental materials for preprint: Machine Learning Models to Classify Molecules as Cancer Kinase Inhibitors or Non-Inhibitors
dcterms:creator
dcterms:publisher
osf:statedConflictOfInterest
foaf:isPrimaryTopicOf
is primary topic of
prov:qualifiedAttribution
qualifiedAttribution
dcat:hadRole
prov:agent
agent
osf:omits
dcterms:description
This project uses an 2nd version "Cancer Inhibitors" dataset from Kaggle that is licensed under Attribution-NonCommercial-ShareAlike 4.0 International. Data was taken from PubChem’s chemistry database of molecules and their properties, specifically their physical and chemical properties, identifiers, and chemical structures.
osf:omittedMetadataProperty