1
|
Morales N, Valdés-Muñoz E, González J, Valenzuela-Hormazábal P, Palma JM, Galarza C, Catagua-González Á, Yáñez O, Pereira A, Bustos D. Machine Learning-Driven Classification of Urease Inhibitors Leveraging Physicochemical Properties as Effective Filter Criteria. Int J Mol Sci 2024; 25:4303. [PMID: 38673888 PMCID: PMC11049951 DOI: 10.3390/ijms25084303] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/15/2024] [Revised: 04/03/2024] [Accepted: 04/08/2024] [Indexed: 04/28/2024] Open
Abstract
Urease, a pivotal enzyme in nitrogen metabolism, plays a crucial role in various microorganisms, including the pathogenic Helicobacter pylori. Inhibiting urease activity offers a promising approach to combating infections and associated ailments, such as chronic kidney diseases and gastric cancer. However, identifying potent urease inhibitors remains challenging due to resistance issues that hinder traditional approaches. Recently, machine learning (ML)-based models have demonstrated the ability to predict the bioactivity of molecules rapidly and effectively. In this study, we present ML models designed to predict urease inhibitors by leveraging essential physicochemical properties. The methodological approach involved constructing a dataset of urease inhibitors through an extensive literature search. Subsequently, these inhibitors were characterized based on physicochemical properties calculations. An exploratory data analysis was then conducted to identify and analyze critical features. Ultimately, 252 classification models were trained, utilizing a combination of seven ML algorithms, three attribute selection methods, and six different strategies for categorizing inhibitory activity. The investigation unveiled discernible trends distinguishing urease inhibitors from non-inhibitors. This differentiation enabled the identification of essential features that are crucial for precise classification. Through a comprehensive comparison of ML algorithms, tree-based methods like random forest, decision tree, and XGBoost exhibited superior performance. Additionally, incorporating the "chemical family type" attribute significantly enhanced model accuracy. Strategies involving a gray-zone categorization demonstrated marked improvements in predictive precision. This research underscores the transformative potential of ML in predicting urease inhibitors. The meticulous methodology outlined herein offers actionable insights for developing robust predictive models within biochemical systems.
Collapse
Affiliation(s)
- Natalia Morales
- Magíster en Ciencias de la Computación, Universidad Católica del Maule, Talca 3460000, Chile; (N.M.); (J.G.)
| | - Elizabeth Valdés-Muñoz
- Doctorado en Biotecnología Traslacional, Centro de Biotecnología de los Recursos Naturales, Universidad Católica del Maule, Talca 3480094, Chile;
| | - Jaime González
- Magíster en Ciencias de la Computación, Universidad Católica del Maule, Talca 3460000, Chile; (N.M.); (J.G.)
| | - Paulina Valenzuela-Hormazábal
- Departamento de Farmacología, Facultad de Ciencias Biológicas, Universidad de Concepción, Concepción 4030000, Chile;
| | - Jonathan M. Palma
- Facultad de Ingeniería, Universidad de Talca, Curicó 3344158, Chile;
| | - Christian Galarza
- Departamento de Matemáticas, Facultad de Ciencias Naturales y Matemáticas, Escuela Superior Politécnica del Litoral, Guayaquil EC090903, Ecuador; (C.G.); (Á.C.-G.)
| | - Ángel Catagua-González
- Departamento de Matemáticas, Facultad de Ciencias Naturales y Matemáticas, Escuela Superior Politécnica del Litoral, Guayaquil EC090903, Ecuador; (C.G.); (Á.C.-G.)
| | - Osvaldo Yáñez
- Núcleo de Investigación en Data Science, Facultad de Ingeniería y Negocios, Universidad de las Américas, Santiago 7500000, Chile;
| | - Alfredo Pereira
- Facultad de Ingeniería, Arquitectura y Diseño, Universidad San Sebastián, Bellavista 7, Santiago 8420524, Chile
| | - Daniel Bustos
- Laboratorio de Bioinformática y Química Computacional, Departamento de Medicina Traslacional, Facultad de Medicina, Universidad Católica del Maule, Talca 3480094, Chile
| |
Collapse
|
2
|
Liu C, Cheng L, Ji L, Li F, Zhan Y, Wu B, Ke Y, Chen P, Hua F, Yuan L, Min Z, Sun L, Chen H, Cheng Y. Intestinal microbiota dysbiosis play a role in pathogenesis of patients with primary immune thrombocytopenia. Thromb Res 2020; 190:11-19. [PMID: 32272276 DOI: 10.1016/j.thromres.2020.03.012] [Citation(s) in RCA: 16] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/13/2020] [Revised: 03/02/2020] [Accepted: 03/17/2020] [Indexed: 01/04/2023]
Abstract
BACKGROUND The intestinal microbiota is essential for the maintenance of the physiology of immune homeostasis. Dysbiosis has been described in some autoimmune diseases, however its role is still elusive in primary immune thrombocytopenia (ITP), which is one kind of autoimmune diseases. This study aimed to characterize the phylogenetic diversity of the fecal microbiota and its relationship with the platelet activation status in patients with ITP. METHODS The platelet activation status was assessed by 2 platelet markers, PAC-1 (antibody that recognizes the activated GPIIb/IIIa complex) and CD62p (Platelet surface P-selectin) by flow cytometry. Total DNA was extracted from fecal samples of ITP patients and healthy controls (HC). Sequencing the V4 hypervariable region of bacterial 16S rRNA genes was used to identify the changes in phylogenetic diversity and composition of the intestinal flora. The obtained sequencing reads were assigned to operational taxonomic units (OTUs, 97% sequence identity) and taxonomically classified to assess composition and diversity. RESULTS The percentage of PAC-1+ platelets in ITP patients was higher than that in control group (p < 0.001), The percentage of CD62p+ and PAC-1+CD62p+ platelets in ITP patients both higher than those in control group (p < 0.001). At the phylum level, eight different phyla were identified in ITP individuals, with a majority of Bacteroidetes (45.96%) and Firmicutes (38.59%), followed by Proteobacteria (11.43%), Fusobacteria(1.29%), and Actinobacteria (1.22%). While in the Healthy volunteers, ten phyla were detected, with a predominance of Firmicutes (50.92%) and Bacteroidetes (34.26%), came before Proteobacteria (13.60%), and Actinobacteria (0.90%). The gut microbiota was skewed in ITP, with an increased proportion of Proteobacteria, Bacteroidetes and Bacteroidetes/Firmicutes ratio, a decreased proportion of Firmicutes compared with HC. Disease specific alterations in diversity was also identified, especially the potential markers (Anaerorhabdus, sutterella, Peptostreptococcaceae, Clostridium_XI and carnobacteriaceae, p < 0.05) for ITP. CONCLUSIONS The results suggested that the distinct microbiota dysbiosis in ITP characterized by alterations in biodiversity and composition, which could provide insights for diet therapy and fecal microbiota transplantation treatment to cure ITP. There might be somehow compensatory enhancement of platelet activation in ITP patients. And there is associate between platelet activation and intestinal microbiota in patients with ITP.
Collapse
Affiliation(s)
- Chanjuan Liu
- Department of Hematology, Zhongshan Hospital Fudan University, Shanghai 200032, China.
| | - Luya Cheng
- Department of Hematology, Zhongshan Hospital Fudan University, Shanghai 200032, China.
| | - Lili Ji
- Department of Hematology, Zhongshan Hospital Fudan University, Shanghai 200032, China.
| | - Feng Li
- Department of Hematology, Zhongshan Hospital Fudan University, Shanghai 200032, China; Department of Hematology, Zhongshan Hospital Qingpu Branch, Fudan University, Shanghai 201700, China.
| | - Yanxia Zhan
- Department of Hematology, Zhongshan Hospital Fudan University, Shanghai 200032, China.
| | - Boting Wu
- Department of Transfusion Medicine, Zhongshan Hospital Fudan University, Shanghai 200032, China.
| | - Yang Ke
- Department of Hematology, Zhongshan Hospital Fudan University, Shanghai 200032, China.
| | - Pu Chen
- Department of Clinical Laboratory, Zhongshan Hospital Fudan University, Shanghai 200032, China.
| | - Fanli Hua
- Department of Hematology, Zhongshan Hospital Qingpu Branch, Fudan University, Shanghai 201700, China.
| | - Ling Yuan
- Department of Hematology, Zhongshan Hospital Fudan University, Shanghai 200032, China.
| | - Zhihui Min
- Institute of Clinical Science, Zhongshan Hospital Fudan University, Shanghai 200032, China; Center for Tumor Diagnosis & Therapy, Jinshan Hospital, Fudan University, Shanghai 201508, China.
| | - Lihua Sun
- Department of Hematology, Zhongshan Hospital Qingpu Branch, Fudan University, Shanghai 201700, China
| | - Hao Chen
- Department of Thoracic Surgery, Zhongshan Hospital Xuhui Branch, Fudan University, Shanghai 200031, China.
| | - Yunfeng Cheng
- Department of Hematology, Zhongshan Hospital Fudan University, Shanghai 200032, China; Department of Hematology, Zhongshan Hospital Qingpu Branch, Fudan University, Shanghai 201700, China; Institute of Clinical Science, Zhongshan Hospital Fudan University, Shanghai 200032, China; Center for Tumor Diagnosis & Therapy, Jinshan Hospital, Fudan University, Shanghai 201508, China.
| |
Collapse
|