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

Ahmad Nasimian; Saleena Younus; Özge Tatli; Emma U Hammarlund; Kenneth J Pienta; Lars Rönnstrand; Julhash U Kazi

doi:10.1016/j.patter.2023.100897

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

Patterns (N Y). 2023 Dec 13;5(1):100897. doi: 10.1016/j.patter.2023.100897. eCollection 2024 Jan 12.

Authors

Ahmad Nasimian^{1

2

3}, Saleena Younus^{1

2

3}, Özge Tatli^{1

2

3}, Emma U Hammarlund^{2

3

4}, Kenneth J Pienta⁵, Lars Rönnstrand^{1

2

3

6}, Julhash U Kazi^{1

2

3}

Affiliations

¹ Division of Translational Cancer Research, Department of Laboratory Medicine, Lund University, Lund, Sweden.
² Lund Stem Cell Center, Lund University, Lund, Sweden.
³ Lund University Cancer Centre (LUCC), Lund University, Lund, Sweden.
⁴ Tissue Development and Evolution (TiDE), Department of Experimental Medical Sciences, Lund University, Lund, Sweden.
⁵ The Cancer Ecology Center, Brady Urological Institute, Johns Hopkins School of Medicine, Baltimore, MD, USA.
⁶ Department of Hematology, Oncology and Radiation Physics, Skåne University Hospital, Lund, Sweden.

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 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.

Keywords: TabNet; XGBoost; deep tabular learning; drug sensitivity prediction; ensemble learning; explainable AI; feature selection; hyperparameter optimization; machine learning; precision medicine.