Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

AlphaML : A clear, legible, explainable, transparent, and elucidative binary classification platform for tabular data

Nasimian, Ahmad LU ; Younus, Saleena LU ; Tatli, Özge LU ; Hammarlund, Emma U. LU ; Pienta, Kenneth J. ; Rönnstrand, Lars LU orcid and Kazi, Julhash U. LU orcid (2024) In Patterns 5(1).
Abstract

Leveraging the potential of machine learning and recognizing the broad applications of binary classification, it becomes essential to develop platforms that are not only powerful but also transparent, interpretable, and user friendly. We introduce alphaML, a user-friendly platform that provides clear, legible, explainable, transparent, and elucidative (CLETE) binary classification models with comprehensive customization options. AlphaML offers feature selection, hyperparameter search, sampling, and normalization methods, along with 15 machine learning algorithms with global and local interpretation. We have integrated a custom metric for hyperparameter search that considers both training and validation scores, safeguarding against... (More)

Leveraging the potential of machine learning and recognizing the broad applications of binary classification, it becomes essential to develop platforms that are not only powerful but also transparent, interpretable, and user friendly. We introduce alphaML, a user-friendly platform that provides clear, legible, explainable, transparent, and elucidative (CLETE) binary classification models with comprehensive customization options. AlphaML offers feature selection, hyperparameter search, sampling, and normalization methods, along with 15 machine learning algorithms with global and local interpretation. We have integrated a custom metric for hyperparameter search that considers both training and validation scores, safeguarding against under- or overfitting. Additionally, we employ the NegLog2RMSL scoring method, which uses both training and test scores for a thorough model evaluation. The platform has been tested using datasets from multiple domains and offers a graphical interface, removing the need for programming expertise. Consequently, alphaML exhibits versatility, demonstrating promising applicability across a broad spectrum of tabular data configurations.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
deep tabular learning, drug sensitivity prediction, DSML 3: Development/Pre-production: Data science output has been rolled out/validated across multiple domains/problems, ensemble learning, explainable AI, feature selection, hyperparameter optimization, machine learning, precision medicine, TabNet, XGBoost
in
Patterns
volume
5
issue
1
article number
100897
publisher
Cell Press
external identifiers
  • pmid:38264719
  • scopus:85182023114
ISSN
2666-3899
DOI
10.1016/j.patter.2023.100897
language
English
LU publication?
yes
id
dc2c2fcf-4a4a-4e45-a325-6d54fda9193f
date added to LUP
2024-02-26 13:02:48
date last changed
2024-06-21 02:10:36
@article{dc2c2fcf-4a4a-4e45-a325-6d54fda9193f,
  abstract     = {{<p>Leveraging the potential of machine learning and recognizing the broad applications of binary classification, it becomes essential to develop platforms that are not only powerful but also transparent, interpretable, and user friendly. We introduce alphaML, a user-friendly platform that provides clear, legible, explainable, transparent, and elucidative (CLETE) binary classification models with comprehensive customization options. AlphaML offers feature selection, hyperparameter search, sampling, and normalization methods, along with 15 machine learning algorithms with global and local interpretation. We have integrated a custom metric for hyperparameter search that considers both training and validation scores, safeguarding against under- or overfitting. Additionally, we employ the NegLog2RMSL scoring method, which uses both training and test scores for a thorough model evaluation. The platform has been tested using datasets from multiple domains and offers a graphical interface, removing the need for programming expertise. Consequently, alphaML exhibits versatility, demonstrating promising applicability across a broad spectrum of tabular data configurations.</p>}},
  author       = {{Nasimian, Ahmad and Younus, Saleena and Tatli, Özge and Hammarlund, Emma U. and Pienta, Kenneth J. and Rönnstrand, Lars and Kazi, Julhash U.}},
  issn         = {{2666-3899}},
  keywords     = {{deep tabular learning; drug sensitivity prediction; DSML 3: Development/Pre-production: Data science output has been rolled out/validated across multiple domains/problems; ensemble learning; explainable AI; feature selection; hyperparameter optimization; machine learning; precision medicine; TabNet; XGBoost}},
  language     = {{eng}},
  number       = {{1}},
  publisher    = {{Cell Press}},
  series       = {{Patterns}},
  title        = {{AlphaML : A clear, legible, explainable, transparent, and elucidative binary classification platform for tabular data}},
  url          = {{http://dx.doi.org/10.1016/j.patter.2023.100897}},
  doi          = {{10.1016/j.patter.2023.100897}},
  volume       = {{5}},
  year         = {{2024}},
}