Iuri Barbosa Pereira
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Iuri Barbosa Pereira has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Alessandro de Carvalho Cruz
Universidade Federal de Goiás
1 shared publication - Carla Maria de Sousa Silva
Universidade Federal de Goiás
1 shared publication Eloisa Dutra Caldas
1 shared publication- Jerônimo Raimundo de Oliveira Neto
Núcleo de Estudos e Pesquisas Tóxico-Farmacológicas, Faculty of Pharmacy, Federal University of Goiás
1 shared publication - Luiz Carlos da Cunha
Federal University of Goiás
1 shared publication - Ramias Vieira Calixto Freire
Universidade Federal de Goiás
1 shared publication
Latest Publications
- Open Access
- 3 April 2026
- Published by Elsevier in SSRN Electronic Journal
A comprehensive study to compare different compound representations for predicting carcinogenicity in vivo
Carcinogenicity evaluation is a critical component of chemical risk assessment, yet traditional in vivo testing remains time-consuming, costly, and ethically challenging. Computational approaches based on machine learning offer promising alternatives, but the relative contribution of different molecular representation strategies for predicting in vivo carcinogenicity remains insufficiently explored. This study aimed to systematically evaluate the impact of molecular embeddings, classical descriptors, and toxicophore structural alerts on the performance of machine learning models for in vivo carcinogenicity prediction. A curated dataset of 2,090 distinct compounds tested exclusively in vivo was assembled by integrating five major toxicological databases. Compounds were represented using classical molecular descriptors, descriptor sets enriched with structural alerts, SMILES-derived molecular embeddings, and hybrid combinations of these representations. Twenty-four machine learning classifiers were benchmarked under a 10-fold stratified cross-validation protocol. Model performance was assessed using accuracy, precision, recall, F1-score, and AUC-ROC, with statistical significance evaluated using Friedman and Nemenyi tests. Results indicated that representations combining molecular descriptors with structural alerts tend to yield the most consistent predictive performance across models. Embeddings contribute as complementary features but do not replace classical representations. These findings reinforce the central role of chemically interpretable, expert-driven descriptors, particularly those incorporating genotoxic structural alerts, in regulatory-relevant carcinogenicity modeling.
- 3 April 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessA comprehensive study to compare different compound representations for predicting carcinogenicity in vivo
Carcinogenicity evaluation is a critical component of chemical risk assessment, yet traditional in vivo testing remains time-consuming, costly, and ethically challenging. Computational approaches based on machine learning offer promising alternatives, but the relative contribution of different molecular representation strategies for predicting in vivo carcinogenicity remains insufficiently explored. This study aimed to systematically evaluate the impact of molecular embeddings, classical descriptors, and toxicophore structural alerts on the performance of machine learning models for in vivo carcinogenicity prediction. A curated dataset of 2,090 distinct compounds tested exclusively in vivo was assembled by integrating five major toxicological databases. Compounds were represented using classical molecular descriptors, descriptor sets enriched with structural alerts, SMILES-derived molecular embeddings, and hybrid combinations of these representations. Twenty-four machine learning classifiers were benchmarked under a 10-fold stratified cross-validation protocol. Model performance was assessed using accuracy, precision, recall, F1-score, and AUC-ROC, with statistical significance evaluated using Friedman and Nemenyi tests. Results indicated that representations combining molecular descriptors with structural alerts tend to yield the most consistent predictive performance across models. Embeddings contribute as complementary features but do not replace classical representations. These findings reinforce the central role of chemically interpretable, expert-driven descriptors, particularly those incorporating genotoxic structural alerts, in regulatory-relevant carcinogenicity modeling.
- Open Access
- 21 August 2021
- Published by Research, Society and Development in Research, Society and Development
- Vol. 10 (11)
Carbamazepine and carbamazepine-10, 11-epoxide therapeutic drug monitoring and biochemical and hematological evaluation in bipolar disorder outpatients
The objective of this study was to validate an analytical technique with HPLC-PDA for plasma measurement of carbamazepine (CBZ) and its metabolite carbamazepine-10, 11-epoxide (CBZ-E) for therapeutic monitoring (TM) of patients diagnosed with bipolar disorder (BD), as well as evaluating hematological and biochemical parameters of patients using CBZ. Sixteen patients registered with the Public Service of Psychiatry were selected. CBZ and CBZ-E measurements were performed with HPLC-PDA shimadzu LC-20 AT Prominence, under concentration gradient. Validation criteria: selectivity, linearity, precision, accuracy, recovery, stability. Hematological and biochemical tests were performed using conventional methods. As a result, it was obtained: accuracy >85% and precision <15%, good selectivity, robustness and stability, LOQ = 250 ng.mL-1 and HQL = 60,000 ng.mL-1. Among patients, 25% and 6.25% had CBZ and CBZ-E levels within the therapeutic range, respectively. There were hematological and biochemical changes related to the drug. The validated method is reliable for its intended purpose. TM proved to be extremely useful for detecting therapeutic failure.
- 21 August 2021
- Published by Research, Society and Development in Research, Society and Development
- Vol. 10 (11)
Open AccessCarbamazepine and carbamazepine-10, 11-epoxide therapeutic drug monitoring and biochemical and hematological evaluation in bipolar disorder outpatients
The objective of this study was to validate an analytical technique with HPLC-PDA for plasma measurement of carbamazepine (CBZ) and its metabolite carbamazepine-10, 11-epoxide (CBZ-E) for therapeutic monitoring (TM) of patients diagnosed with bipolar disorder (BD), as well as evaluating hematological and biochemical parameters of patients using CBZ. Sixteen patients registered with the Public Service of Psychiatry were selected. CBZ and CBZ-E measurements were performed with HPLC-PDA shimadzu LC-20 AT Prominence, under concentration gradient. Validation criteria: selectivity, linearity, precision, accuracy, recovery, stability. Hematological and biochemical tests were performed using conventional methods. As a result, it was obtained: accuracy >85% and precision <15%, good selectivity, robustness and stability, LOQ = 250 ng.mL-1 and HQL = 60,000 ng.mL-1. Among patients, 25% and 6.25% had CBZ and CBZ-E levels within the therapeutic range, respectively. There were hematological and biochemical changes related to the drug. The validated method is reliable for its intended purpose. TM proved to be extremely useful for detecting therapeutic failure.