Chapter 7
A Review of Feature Reduction Methods
for QSAR-Based Toxicity Prediction
Gabriel Idakwo, Joseph Luttrell IV, Minjun Chen, Huixiao Hong,
Ping Gong and Chaoyang Zhang
Abstract Thousands of molecular descriptors (1D to 4D) can be generated and used
as features to model quantitative structure–activity or toxicity relationship (QSAR or
QSTR) for chemical toxicity prediction. This often results in models that suffer from
the “curse of dimensionality”, a problem that can occur in machine learning practice
when too many features are employed to train a model. Here we discuss different
methods of eliminating redundant and irrelevant features to enhance prediction performance, increase interpretability, and reduce computational complexity. Several
feature selection and extraction methods are summarized along with their strengths
and shortcomings. We also highlight some commonly overlooked challenges such
as algorithm instability and selection bias while offering possible solutions.
Keywords Molecular descriptors · Feature selection · Feature extraction ·
Toxicity prediction · Machine learning · Quantitative Structure–Activity or toxicity
relationship (QSAR or QSTR) · Prediction accuracy
G. Idakwo · J. Luttrell IV · C. Zhang (B)
School of Computing Sciences and Computer Engineering,
University of Southern Mississippi, Hattiesburg, MS, USA
e-mail: Chaoyang.Zhang@usm.edu
G. Idakwo
e-mail: Gabriel.Idakwo@usm.edu
J. Luttrell IV
e-mail: Joseph.Luttrell@usm.edu
M. Chen · H. Hong
Division of Bioinformatics and Biostatistics, National Center for Toxicological Research,
US Food and Drug Administration, Jefferson, AR, USA
e-mail: Minjun.Chen@fda.hhs.gov
H. Hong
e-mail: Huixiao.Hong@fda.hhs.gov
P. Gong
Environmental Laboratory, US Army Engineer Research and Development Center,
Vicksburg, MS, USA
e-mail: Ping.Gong@usace.army.mil
© Springer Nature Switzerland AG 2019
H. Hong (ed.), Advances in Computational Toxicology, Challenges and Advances
in Computational Chemistry and Physics 30,
https://doi.org/10.1007/978-3-030-16443-0_7
119
A Review of Feature Reduction Methods
for QSAR-Based Toxicity Prediction
Gabriel Idakwo, Joseph Luttrell IV, Minjun Chen, Huixiao Hong,
Ping Gong and Chaoyang Zhang
Abstract Thousands of molecular descriptors (1D to 4D) can be generated and used
as features to model quantitative structure–activity or toxicity relationship (QSAR or
QSTR) for chemical toxicity prediction. This often results in models that suffer from
the “curse of dimensionality”, a problem that can occur in machine learning practice
when too many features are employed to train a model. Here we discuss different
methods of eliminating redundant and irrelevant features to enhance prediction performance, increase interpretability, and reduce computational complexity. Several
feature selection and extraction methods are summarized along with their strengths
and shortcomings. We also highlight some commonly overlooked challenges such
as algorithm instability and selection bias while offering possible solutions.
Keywords Molecular descriptors · Feature selection · Feature extraction ·
Toxicity prediction · Machine learning · Quantitative Structure–Activity or toxicity
relationship (QSAR or QSTR) · Prediction accuracy
G. Idakwo · J. Luttrell IV · C. Zhang (B)
School of Computing Sciences and Computer Engineering,
University of Southern Mississippi, Hattiesburg, MS, USA
e-mail: Chaoyang.Zhang@usm.edu
G. Idakwo
e-mail: Gabriel.Idakwo@usm.edu
J. Luttrell IV
e-mail: Joseph.Luttrell@usm.edu
M. Chen · H. Hong
Division of Bioinformatics and Biostatistics, National Center for Toxicological Research,
US Food and Drug Administration, Jefferson, AR, USA
e-mail: Minjun.Chen@fda.hhs.gov
H. Hong
e-mail: Huixiao.Hong@fda.hhs.gov
P. Gong
Environmental Laboratory, US Army Engineer Research and Development Center,
Vicksburg, MS, USA
e-mail: Ping.Gong@usace.army.mil
© Springer Nature Switzerland AG 2019
H. Hong (ed.), Advances in Computational Toxicology, Challenges and Advances
in Computational Chemistry and Physics 30,
https://doi.org/10.1007/978-3-030-16443-0_7
119