2025-03-122025-03-122022-02CARDOSO, Eduardo Gil Serrão. Analyzing the impact of dimensionality reduction over human intestinal absorption prediction through machine learning. Orientador: Claudomiro de Souza de Sales Júnior. 2022. 173 f. Trabalho de Conclusão de Curso (Bacharelado em Ciência da Computação) – Faculdade de Computação, Instituto de Ciências Exatas e Naturais, Universidade Federal do Pará, Belém, 2022. Disponível em: https://bdm.ufpa.br/jspui/handle/prefix/7851. Acesso em:.https://bdm.ufpa.br/jspui/handle/prefix/7851A desirable property in drug development is oral delivery. Virtual screening of chemical compounds according to their oral bioavailability with computational intelligence could accelerate the prediction of their human intestinal absorption (HIA). Despite the existence of several studies aimed at predicting the intestinal permeability of chemical compounds, none attempted to evaluate the impact of using physicochemical and structural properties related to oral bioavailability with both dimensionality reduction (DR) and machine learning (ML) techniques. This case study presents an analysis on the impact of applying DR techniques such as Principal Component Analysis (PCA), Kernel PCA (KPCA), Ivis, Truncated Singular Vector Decomposition (TSVD) and Uniform Manifold Approximation and Projection (UMAP) along with ML predictors such as K-Nearest Neighbors (KNN), Multi-Layer Perceptron (MLP), Support Vector Machine (SVM) and Random Forest (RF) in predicting HIA of small molecules, shedding light in the models behavior as dimensionality changes. Results demonstrate that, despite reducing the dimensionality by more than 90%, lower-dimensional models for KNN, SVM and RF still delivered competitive results, demonstrating the viability and potential of projection-based DR as a pre-processing step.Acesso AbertoRedução de dimensionalidade baseada em projeçãoAprendizado profundoDescoberta de drogasAbsorção intestinal humanaAprendizado de máquinaProjection-based dimensionality reductionDeep learningDrug discoveryHuman intestinal absorptionMachine learningCNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAOTrabalho de Curso - Graduação - Monografia