Effects of Class Imbalance and Data Scarcity on the Performance of Binary Classification Machine Learning Models Developed Based on ToxCast/Tox21 Assay Data by Changhun Kim (682542)

“…An assay matrix based on CI and DS was prepared for 335 assays with biologically intended target information, and 28 CI assays and 3 DS assays were selected. Thirty models established by combining five molecular fingerprints (i.e., Morgan, MACCS, RDKit, Pattern, and Layered) and six algorithms [i.e., gradient boosting tree, random forest (RF), multi-layered perceptron, <i>k</i>-nearest neighbor, logistic regression, and naive Bayes] were trained using the selected assay data set. …”

RMSE on the test data when fitting (logistic) quadratic models to binary data across increasing measurement error values . by Jakub Stoklosa (3315042)

Fig 1 - by Jakub Stoklosa (3315042)

Supplementary Material 8 by Nishitha R Kumar (19750617)

“…</p><p dir="ltr">When applied to AMR prediction, SMOTE enhances the ability of classification models to accurately identify resistant <i>Escherichia coli</i> strains by balancing the dataset, ensuring that machine learning algorithms do not overlook rare resistance patterns. …”

Machine Learning-Ready Dataset for Cytotoxicity Prediction of Metal Oxide Nanoparticles by Soham Savarkar (21811825)

“…</p><p dir="ltr"><b>Applications and Model Compatibility:</b></p><p dir="ltr">The dataset is optimized for use in supervised learning workflows and has been tested with algorithms such as:</p><p dir="ltr">Gradient Boosting Machines (GBM),</p><p dir="ltr">Support Vector Machines (SVM-RBF),</p><p dir="ltr">Random Forests, and</p><p dir="ltr">Principal Component Analysis (PCA) for feature reduction.…”