A Simple Machine Learning-Based Quantitative Structure–Activity Relationship Model for Predicting pIC<sub>50</sub> Inhibition Values of FLT3 Tyrosine Kinase
<b>Background/Objectives:</b> Acute myeloid leukemia (AML) presents significant therapeutic challenges, particularly in cases driven by mutations in the FLT3 tyrosine kinase. This study aimed to develop a robust and user-friendly machine learning-based quantitative structure–activity rel...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Pharmaceuticals |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8247/18/1/96 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832587714208202752 |
|---|---|
| author | Jackson J. Alcázar Ignacio Sánchez Cristian Merino Bruno Monasterio Gaspar Sajuria Diego Miranda Felipe Díaz Paola R. Campodónico |
| author_facet | Jackson J. Alcázar Ignacio Sánchez Cristian Merino Bruno Monasterio Gaspar Sajuria Diego Miranda Felipe Díaz Paola R. Campodónico |
| author_sort | Jackson J. Alcázar |
| collection | DOAJ |
| description | <b>Background/Objectives:</b> Acute myeloid leukemia (AML) presents significant therapeutic challenges, particularly in cases driven by mutations in the FLT3 tyrosine kinase. This study aimed to develop a robust and user-friendly machine learning-based quantitative structure–activity relationship (QSAR) model to predict the inhibitory potency (pIC<sub>50</sub> values) of FLT3 inhibitors, addressing the limitations of previous models in dataset size, diversity, and predictive accuracy. <b>Methods:</b> Using a dataset which was 14 times larger than those employed in prior studies (1350 compounds with 1269 molecular descriptors), we trained a random forest regressor, chosen due to its superior predictive performance and resistance to overfitting. Rigorous internal validation via leave-one-out and 10-fold cross-validation yielded <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi mathvariant="normal">Q</mi><mn>2</mn></msup></semantics></math></inline-formula> values of 0.926 and 0.922, respectively, while external validation on 270 independent compounds resulted in an R<sup>2</sup> value of 0.941 with a standard deviation of 0.237. <b>Results:</b> Key molecular descriptors influencing the inhibitor potency were identified, thereby improving the interpretability of structural requirements. Additionally, a user-friendly computational tool was developed to enable rapid prediction of pIC<sub>50</sub> values and facilitate ligand-based virtual screening, leading to the identification of promising FLT3 inhibitors. <b>Conclusions:</b> These results represent a significant advancement in the field of FLT3 inhibitor discovery, offering a reliable, practical, and efficient approach for early-stage drug development, potentially accelerating the creation of targeted therapies for AML. |
| format | Article |
| id | doaj-art-6dc81ab53e824c16be8f60f3b12575d6 |
| institution | Kabale University |
| issn | 1424-8247 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Pharmaceuticals |
| spelling | doaj-art-6dc81ab53e824c16be8f60f3b12575d62025-01-24T13:45:22ZengMDPI AGPharmaceuticals1424-82472025-01-011819610.3390/ph18010096A Simple Machine Learning-Based Quantitative Structure–Activity Relationship Model for Predicting pIC<sub>50</sub> Inhibition Values of FLT3 Tyrosine KinaseJackson J. Alcázar0Ignacio Sánchez1Cristian Merino2Bruno Monasterio3Gaspar Sajuria4Diego Miranda5Felipe Díaz6Paola R. Campodónico7Centro de Química Médica, Facultad de Medicina Clínica Alemana, Universidad del Desarrollo, Santiago 7780272, ChileCentro de Química Médica, Facultad de Medicina Clínica Alemana, Universidad del Desarrollo, Santiago 7780272, ChileCentro de Química Médica, Facultad de Medicina Clínica Alemana, Universidad del Desarrollo, Santiago 7780272, ChileCentro de Química Médica, Facultad de Medicina Clínica Alemana, Universidad del Desarrollo, Santiago 7780272, ChileCentro de Química Médica, Facultad de Medicina Clínica Alemana, Universidad del Desarrollo, Santiago 7780272, ChileCentro de Química Médica, Facultad de Medicina Clínica Alemana, Universidad del Desarrollo, Santiago 7780272, ChileCentro de Química Médica, Facultad de Medicina Clínica Alemana, Universidad del Desarrollo, Santiago 7780272, ChileCentro de Química Médica, Facultad de Medicina Clínica Alemana, Universidad del Desarrollo, Santiago 7780272, Chile<b>Background/Objectives:</b> Acute myeloid leukemia (AML) presents significant therapeutic challenges, particularly in cases driven by mutations in the FLT3 tyrosine kinase. This study aimed to develop a robust and user-friendly machine learning-based quantitative structure–activity relationship (QSAR) model to predict the inhibitory potency (pIC<sub>50</sub> values) of FLT3 inhibitors, addressing the limitations of previous models in dataset size, diversity, and predictive accuracy. <b>Methods:</b> Using a dataset which was 14 times larger than those employed in prior studies (1350 compounds with 1269 molecular descriptors), we trained a random forest regressor, chosen due to its superior predictive performance and resistance to overfitting. Rigorous internal validation via leave-one-out and 10-fold cross-validation yielded <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi mathvariant="normal">Q</mi><mn>2</mn></msup></semantics></math></inline-formula> values of 0.926 and 0.922, respectively, while external validation on 270 independent compounds resulted in an R<sup>2</sup> value of 0.941 with a standard deviation of 0.237. <b>Results:</b> Key molecular descriptors influencing the inhibitor potency were identified, thereby improving the interpretability of structural requirements. Additionally, a user-friendly computational tool was developed to enable rapid prediction of pIC<sub>50</sub> values and facilitate ligand-based virtual screening, leading to the identification of promising FLT3 inhibitors. <b>Conclusions:</b> These results represent a significant advancement in the field of FLT3 inhibitor discovery, offering a reliable, practical, and efficient approach for early-stage drug development, potentially accelerating the creation of targeted therapies for AML.https://www.mdpi.com/1424-8247/18/1/96FLT3 inhibitorsligand-based drug designcomputer-aided drug designQSAR modelingAML treatment |
| spellingShingle | Jackson J. Alcázar Ignacio Sánchez Cristian Merino Bruno Monasterio Gaspar Sajuria Diego Miranda Felipe Díaz Paola R. Campodónico A Simple Machine Learning-Based Quantitative Structure–Activity Relationship Model for Predicting pIC<sub>50</sub> Inhibition Values of FLT3 Tyrosine Kinase Pharmaceuticals FLT3 inhibitors ligand-based drug design computer-aided drug design QSAR modeling AML treatment |
| title | A Simple Machine Learning-Based Quantitative Structure–Activity Relationship Model for Predicting pIC<sub>50</sub> Inhibition Values of FLT3 Tyrosine Kinase |
| title_full | A Simple Machine Learning-Based Quantitative Structure–Activity Relationship Model for Predicting pIC<sub>50</sub> Inhibition Values of FLT3 Tyrosine Kinase |
| title_fullStr | A Simple Machine Learning-Based Quantitative Structure–Activity Relationship Model for Predicting pIC<sub>50</sub> Inhibition Values of FLT3 Tyrosine Kinase |
| title_full_unstemmed | A Simple Machine Learning-Based Quantitative Structure–Activity Relationship Model for Predicting pIC<sub>50</sub> Inhibition Values of FLT3 Tyrosine Kinase |
| title_short | A Simple Machine Learning-Based Quantitative Structure–Activity Relationship Model for Predicting pIC<sub>50</sub> Inhibition Values of FLT3 Tyrosine Kinase |
| title_sort | simple machine learning based quantitative structure activity relationship model for predicting pic sub 50 sub inhibition values of flt3 tyrosine kinase |
| topic | FLT3 inhibitors ligand-based drug design computer-aided drug design QSAR modeling AML treatment |
| url | https://www.mdpi.com/1424-8247/18/1/96 |
| work_keys_str_mv | AT jacksonjalcazar asimplemachinelearningbasedquantitativestructureactivityrelationshipmodelforpredictingpicsub50subinhibitionvaluesofflt3tyrosinekinase AT ignaciosanchez asimplemachinelearningbasedquantitativestructureactivityrelationshipmodelforpredictingpicsub50subinhibitionvaluesofflt3tyrosinekinase AT cristianmerino asimplemachinelearningbasedquantitativestructureactivityrelationshipmodelforpredictingpicsub50subinhibitionvaluesofflt3tyrosinekinase AT brunomonasterio asimplemachinelearningbasedquantitativestructureactivityrelationshipmodelforpredictingpicsub50subinhibitionvaluesofflt3tyrosinekinase AT gasparsajuria asimplemachinelearningbasedquantitativestructureactivityrelationshipmodelforpredictingpicsub50subinhibitionvaluesofflt3tyrosinekinase AT diegomiranda asimplemachinelearningbasedquantitativestructureactivityrelationshipmodelforpredictingpicsub50subinhibitionvaluesofflt3tyrosinekinase AT felipediaz asimplemachinelearningbasedquantitativestructureactivityrelationshipmodelforpredictingpicsub50subinhibitionvaluesofflt3tyrosinekinase AT paolarcampodonico asimplemachinelearningbasedquantitativestructureactivityrelationshipmodelforpredictingpicsub50subinhibitionvaluesofflt3tyrosinekinase AT jacksonjalcazar simplemachinelearningbasedquantitativestructureactivityrelationshipmodelforpredictingpicsub50subinhibitionvaluesofflt3tyrosinekinase AT ignaciosanchez simplemachinelearningbasedquantitativestructureactivityrelationshipmodelforpredictingpicsub50subinhibitionvaluesofflt3tyrosinekinase AT cristianmerino simplemachinelearningbasedquantitativestructureactivityrelationshipmodelforpredictingpicsub50subinhibitionvaluesofflt3tyrosinekinase AT brunomonasterio simplemachinelearningbasedquantitativestructureactivityrelationshipmodelforpredictingpicsub50subinhibitionvaluesofflt3tyrosinekinase AT gasparsajuria simplemachinelearningbasedquantitativestructureactivityrelationshipmodelforpredictingpicsub50subinhibitionvaluesofflt3tyrosinekinase AT diegomiranda simplemachinelearningbasedquantitativestructureactivityrelationshipmodelforpredictingpicsub50subinhibitionvaluesofflt3tyrosinekinase AT felipediaz simplemachinelearningbasedquantitativestructureactivityrelationshipmodelforpredictingpicsub50subinhibitionvaluesofflt3tyrosinekinase AT paolarcampodonico simplemachinelearningbasedquantitativestructureactivityrelationshipmodelforpredictingpicsub50subinhibitionvaluesofflt3tyrosinekinase |