2010
DOI: 10.1007/s11030-010-9232-y
|View full text |Cite
|
Sign up to set email alerts
|

Prediction of carcinogenicity for diverse chemicals based on substructure grouping and SVM modeling

Abstract: The Carcinogenicity Reliability Database (CRDB) was constructed by collecting experimental carcinogenicity data on about 1,500 chemicals from six sources, including IARC, and NTP databases, and then by ranking their reliabilities into six unified categories. A wide variety of 911 organic chemicals were selected from the database for QSAR modeling, and 1,504 kinds of different molecular descriptors were calculated, based on their 3D molecular structures as modeled by the Dragon software. Positive (carcinogenic)… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
8
0
1

Year Published

2011
2011
2021
2021

Publication Types

Select...
5
2
2
1

Relationship

0
10

Authors

Journals

citations
Cited by 34 publications
(9 citation statements)
references
References 50 publications
0
8
0
1
Order By: Relevance
“…While they assume that the predictors are conditionally independent, they often perform well even when this assumption does not fully hold, and compared to other algorithms may be more straightforward to interpret. Support vector machines are a newer machine learning approach which to date has been used relatively rarely in medical research (34) but more broadly in signal detection tasks (35). In essence, SVM algorithms take a set of training vectors and use one of several kernel functions to project them to a higher dimensional space, enabling identification of a separating hyperplane between classes (36).…”
Section: Methodsmentioning
confidence: 99%
“…While they assume that the predictors are conditionally independent, they often perform well even when this assumption does not fully hold, and compared to other algorithms may be more straightforward to interpret. Support vector machines are a newer machine learning approach which to date has been used relatively rarely in medical research (34) but more broadly in signal detection tasks (35). In essence, SVM algorithms take a set of training vectors and use one of several kernel functions to project them to a higher dimensional space, enabling identification of a separating hyperplane between classes (36).…”
Section: Methodsmentioning
confidence: 99%
“…Modelirati se također mogu i biološke aktivnosti kao antivirusne i antitumorske. 12 Pomoću molekulskog modeliranja mogu se uštedjeti vrijeme i sredstva za ispitivanje velikog broja spojeva kao i cijelih baza poput PubChema. Strukturna svojstva opisuju se deskriptorima.…”
Section: Uvodunclassified
“…Fjodorova et al predicted the carcinogenicity of non-congeneric chemicals with 68% accuracy using counter propagation artificial neural network (CP ANN) 8 . Tanabe et al reported accuracy of 70% for non-congeneric chemicals based on SVM and improved the accuracy to 80% by developing models on the chemical subgroups based on their structure 9 . Zhang et al presented binary classification models based on ensemble of eXtreme Gradient Boosting (XGBoost) method that predicted the carcinogenicity of chemicals with 70% accuracy 10 .…”
Section: Introductionmentioning
confidence: 99%