Identifying Potential Machine Learning Algorithms for the Simulation of Binding Affinities to Molecularly Imprinted Polymers
Molecularly imprinted polymers (MIPs) are synthetic receptors engineered towards the selective binding of a target molecule; however, the manner in which MIPs interact with other molecules is of great importance. Being able to rapidly analyze the binding of potential molecular interferences and dete...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-09-01
|
| Series: | Computation |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-3197/9/10/103 |
| _version_ | 1827679804060598272 |
|---|---|
| author | Joseph W. Lowdon Hikaru Ishikura Malene K. Kvernenes Manlio Caldara Thomas J. Cleij Bart van Grinsven Kasper Eersels Hanne Diliën |
| author_facet | Joseph W. Lowdon Hikaru Ishikura Malene K. Kvernenes Manlio Caldara Thomas J. Cleij Bart van Grinsven Kasper Eersels Hanne Diliën |
| author_sort | Joseph W. Lowdon |
| collection | DOAJ |
| description | Molecularly imprinted polymers (MIPs) are synthetic receptors engineered towards the selective binding of a target molecule; however, the manner in which MIPs interact with other molecules is of great importance. Being able to rapidly analyze the binding of potential molecular interferences and determine the selectivity of a MIP can be a long tedious task, being time- and resource-intensive. Identifying computational models capable of reliably predicting and reporting the binding of molecular species is therefore of immense value in both a research and commercial setting. This research therefore sets focus on comparing the use of machine learning algorithms (multitask regressor, graph convolution, weave model, DAG model, and inception) to predict the binding of various molecular species to a MIP designed towards 2-methoxphenidine. To this end, each algorithm was “trained” with an experimental dataset, teaching the algorithms the structures and binding affinities of various molecular species at varying concentrations. A validation experiment was then conducted for each algorithm, comparing experimental values to predicted values and facilitating the assessment of each approach by a direct comparison of the metrics. The research culminates in the construction of binding isotherms for each species, directly comparing experimental vs. predicted values and identifying the approach that best emulates the real-world data. |
| first_indexed | 2024-03-10T06:38:18Z |
| format | Article |
| id | doaj.art-271752ce1b6749c0b538a939773f72a1 |
| institution | Directory Open Access Journal |
| issn | 2079-3197 |
| language | English |
| last_indexed | 2024-03-10T06:38:18Z |
| publishDate | 2021-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Computation |
| spelling | doaj.art-271752ce1b6749c0b538a939773f72a12023-11-22T17:52:00ZengMDPI AGComputation2079-31972021-09-0191010310.3390/computation9100103Identifying Potential Machine Learning Algorithms for the Simulation of Binding Affinities to Molecularly Imprinted PolymersJoseph W. Lowdon0Hikaru Ishikura1Malene K. Kvernenes2Manlio Caldara3Thomas J. Cleij4Bart van Grinsven5Kasper Eersels6Hanne Diliën7Sensor Engineering Department, Faculty of Science and Engineering, Maastricht University, P.O. Box 616, 6200 MD Maastricht, The NetherlandsMaastricht Science Programme, Faculty of Science and Engineering, Maastricht University, P.O. Box 616, 6200 MD Maastricht, The NetherlandsMaastricht Science Programme, Faculty of Science and Engineering, Maastricht University, P.O. Box 616, 6200 MD Maastricht, The NetherlandsSensor Engineering Department, Faculty of Science and Engineering, Maastricht University, P.O. Box 616, 6200 MD Maastricht, The NetherlandsSensor Engineering Department, Faculty of Science and Engineering, Maastricht University, P.O. Box 616, 6200 MD Maastricht, The NetherlandsSensor Engineering Department, Faculty of Science and Engineering, Maastricht University, P.O. Box 616, 6200 MD Maastricht, The NetherlandsSensor Engineering Department, Faculty of Science and Engineering, Maastricht University, P.O. Box 616, 6200 MD Maastricht, The NetherlandsSensor Engineering Department, Faculty of Science and Engineering, Maastricht University, P.O. Box 616, 6200 MD Maastricht, The NetherlandsMolecularly imprinted polymers (MIPs) are synthetic receptors engineered towards the selective binding of a target molecule; however, the manner in which MIPs interact with other molecules is of great importance. Being able to rapidly analyze the binding of potential molecular interferences and determine the selectivity of a MIP can be a long tedious task, being time- and resource-intensive. Identifying computational models capable of reliably predicting and reporting the binding of molecular species is therefore of immense value in both a research and commercial setting. This research therefore sets focus on comparing the use of machine learning algorithms (multitask regressor, graph convolution, weave model, DAG model, and inception) to predict the binding of various molecular species to a MIP designed towards 2-methoxphenidine. To this end, each algorithm was “trained” with an experimental dataset, teaching the algorithms the structures and binding affinities of various molecular species at varying concentrations. A validation experiment was then conducted for each algorithm, comparing experimental values to predicted values and facilitating the assessment of each approach by a direct comparison of the metrics. The research culminates in the construction of binding isotherms for each species, directly comparing experimental vs. predicted values and identifying the approach that best emulates the real-world data.https://www.mdpi.com/2079-3197/9/10/103molecularly imprinted polymersartificial intelligenceneural networkingsimulation |
| spellingShingle | Joseph W. Lowdon Hikaru Ishikura Malene K. Kvernenes Manlio Caldara Thomas J. Cleij Bart van Grinsven Kasper Eersels Hanne Diliën Identifying Potential Machine Learning Algorithms for the Simulation of Binding Affinities to Molecularly Imprinted Polymers Computation molecularly imprinted polymers artificial intelligence neural networking simulation |
| title | Identifying Potential Machine Learning Algorithms for the Simulation of Binding Affinities to Molecularly Imprinted Polymers |
| title_full | Identifying Potential Machine Learning Algorithms for the Simulation of Binding Affinities to Molecularly Imprinted Polymers |
| title_fullStr | Identifying Potential Machine Learning Algorithms for the Simulation of Binding Affinities to Molecularly Imprinted Polymers |
| title_full_unstemmed | Identifying Potential Machine Learning Algorithms for the Simulation of Binding Affinities to Molecularly Imprinted Polymers |
| title_short | Identifying Potential Machine Learning Algorithms for the Simulation of Binding Affinities to Molecularly Imprinted Polymers |
| title_sort | identifying potential machine learning algorithms for the simulation of binding affinities to molecularly imprinted polymers |
| topic | molecularly imprinted polymers artificial intelligence neural networking simulation |
| url | https://www.mdpi.com/2079-3197/9/10/103 |
| work_keys_str_mv | AT josephwlowdon identifyingpotentialmachinelearningalgorithmsforthesimulationofbindingaffinitiestomolecularlyimprintedpolymers AT hikaruishikura identifyingpotentialmachinelearningalgorithmsforthesimulationofbindingaffinitiestomolecularlyimprintedpolymers AT malenekkvernenes identifyingpotentialmachinelearningalgorithmsforthesimulationofbindingaffinitiestomolecularlyimprintedpolymers AT manliocaldara identifyingpotentialmachinelearningalgorithmsforthesimulationofbindingaffinitiestomolecularlyimprintedpolymers AT thomasjcleij identifyingpotentialmachinelearningalgorithmsforthesimulationofbindingaffinitiestomolecularlyimprintedpolymers AT bartvangrinsven identifyingpotentialmachinelearningalgorithmsforthesimulationofbindingaffinitiestomolecularlyimprintedpolymers AT kaspereersels identifyingpotentialmachinelearningalgorithmsforthesimulationofbindingaffinitiestomolecularlyimprintedpolymers AT hannedilien identifyingpotentialmachinelearningalgorithmsforthesimulationofbindingaffinitiestomolecularlyimprintedpolymers |