Supervised Learning for Predictive Pore Size Classification of Regenerated Cellulose Membranes Based on Atomic Force Microscopy Measurements
Nanoporous dialysis membranes made of regenerated cellulose are used as molecular weight cutoff standards in bioseparations. In this study, mesoporous standards with Stokes’ radii (50 kDa/2.7 nm, 100 kDa/3.4 nm and 1000 kDa/7.3 nm) and overlapping skewed distributions were characterized using AFM, w...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Materials |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1944/14/21/6724 |
| _version_ | 1797512134776586240 |
|---|---|
| author | Alex Hadsell Huong Chau Richard Barber Unyoung Kim Maryam Mobed-Miremadi |
| author_facet | Alex Hadsell Huong Chau Richard Barber Unyoung Kim Maryam Mobed-Miremadi |
| author_sort | Alex Hadsell |
| collection | DOAJ |
| description | Nanoporous dialysis membranes made of regenerated cellulose are used as molecular weight cutoff standards in bioseparations. In this study, mesoporous standards with Stokes’ radii (50 kDa/2.7 nm, 100 kDa/3.4 nm and 1000 kDa/7.3 nm) and overlapping skewed distributions were characterized using AFM, with the specific aim of generating pore size classifiers for biomimetic membranes using supervised learning. Gamma transformation was used prior to conducting discriminant analysis in terms of the area under the receiver operating curve (AUC) and classification accuracy (Acc). Monte Carlo simulations were run to generate datasets (<i>n</i> = 10) on which logistic regression was conducted using a constant ratio of 80:20 (measurement:algorithm training), followed by algorithm validation by WEKA. The proposed algorithm can classify the 1000 kDa vs. 100 kDa (AUC > 0.8) correctly, but discrimination is weak for the 100 kDa vs. 50 kDa (AUC < 0.7), the latter being attributed to the instrument accuracy errors below 5 nm. As indicated by the results of the cross-validation study, a test size equivalent to 70% (AUC<sub>tapping</sub> = 0.8341 ± 0.0519, Acc<sub>tapping</sub> = 76.8% ± 5.9%) and 80% (AUC<sub>fluid</sub> = 0.7614 ± 0.0314, Acc<sub>tfluid</sub> = 76.2% ± 1.0%) of the training sets for the tapping and fluid modes are needed for correct classification, resulting in predicted reduction of scan times. |
| first_indexed | 2024-03-10T05:56:36Z |
| format | Article |
| id | doaj.art-30e0479694cc4a5da47a4f4f0a0f00d0 |
| institution | Directory Open Access Journal |
| issn | 1996-1944 |
| language | English |
| last_indexed | 2024-03-10T05:56:36Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Materials |
| spelling | doaj.art-30e0479694cc4a5da47a4f4f0a0f00d02023-11-22T21:16:26ZengMDPI AGMaterials1996-19442021-11-011421672410.3390/ma14216724Supervised Learning for Predictive Pore Size Classification of Regenerated Cellulose Membranes Based on Atomic Force Microscopy MeasurementsAlex Hadsell0Huong Chau1Richard Barber2Unyoung Kim3Maryam Mobed-Miremadi4Department of Bioengineering, Santa Clara University, Santa Clara, CA 95053, USADepartment of Bioengineering, Santa Clara University, Santa Clara, CA 95053, USACenter for Nanostructures, Santa Clara University, Santa Clara, CA 95053, USADepartment of Bioengineering, Santa Clara University, Santa Clara, CA 95053, USADepartment of Bioengineering, Santa Clara University, Santa Clara, CA 95053, USANanoporous dialysis membranes made of regenerated cellulose are used as molecular weight cutoff standards in bioseparations. In this study, mesoporous standards with Stokes’ radii (50 kDa/2.7 nm, 100 kDa/3.4 nm and 1000 kDa/7.3 nm) and overlapping skewed distributions were characterized using AFM, with the specific aim of generating pore size classifiers for biomimetic membranes using supervised learning. Gamma transformation was used prior to conducting discriminant analysis in terms of the area under the receiver operating curve (AUC) and classification accuracy (Acc). Monte Carlo simulations were run to generate datasets (<i>n</i> = 10) on which logistic regression was conducted using a constant ratio of 80:20 (measurement:algorithm training), followed by algorithm validation by WEKA. The proposed algorithm can classify the 1000 kDa vs. 100 kDa (AUC > 0.8) correctly, but discrimination is weak for the 100 kDa vs. 50 kDa (AUC < 0.7), the latter being attributed to the instrument accuracy errors below 5 nm. As indicated by the results of the cross-validation study, a test size equivalent to 70% (AUC<sub>tapping</sub> = 0.8341 ± 0.0519, Acc<sub>tapping</sub> = 76.8% ± 5.9%) and 80% (AUC<sub>fluid</sub> = 0.7614 ± 0.0314, Acc<sub>tfluid</sub> = 76.2% ± 1.0%) of the training sets for the tapping and fluid modes are needed for correct classification, resulting in predicted reduction of scan times.https://www.mdpi.com/1996-1944/14/21/6724supervised learningatomic force microscopyregenerated cellulose |
| spellingShingle | Alex Hadsell Huong Chau Richard Barber Unyoung Kim Maryam Mobed-Miremadi Supervised Learning for Predictive Pore Size Classification of Regenerated Cellulose Membranes Based on Atomic Force Microscopy Measurements Materials supervised learning atomic force microscopy regenerated cellulose |
| title | Supervised Learning for Predictive Pore Size Classification of Regenerated Cellulose Membranes Based on Atomic Force Microscopy Measurements |
| title_full | Supervised Learning for Predictive Pore Size Classification of Regenerated Cellulose Membranes Based on Atomic Force Microscopy Measurements |
| title_fullStr | Supervised Learning for Predictive Pore Size Classification of Regenerated Cellulose Membranes Based on Atomic Force Microscopy Measurements |
| title_full_unstemmed | Supervised Learning for Predictive Pore Size Classification of Regenerated Cellulose Membranes Based on Atomic Force Microscopy Measurements |
| title_short | Supervised Learning for Predictive Pore Size Classification of Regenerated Cellulose Membranes Based on Atomic Force Microscopy Measurements |
| title_sort | supervised learning for predictive pore size classification of regenerated cellulose membranes based on atomic force microscopy measurements |
| topic | supervised learning atomic force microscopy regenerated cellulose |
| url | https://www.mdpi.com/1996-1944/14/21/6724 |
| work_keys_str_mv | AT alexhadsell supervisedlearningforpredictiveporesizeclassificationofregeneratedcellulosemembranesbasedonatomicforcemicroscopymeasurements AT huongchau supervisedlearningforpredictiveporesizeclassificationofregeneratedcellulosemembranesbasedonatomicforcemicroscopymeasurements AT richardbarber supervisedlearningforpredictiveporesizeclassificationofregeneratedcellulosemembranesbasedonatomicforcemicroscopymeasurements AT unyoungkim supervisedlearningforpredictiveporesizeclassificationofregeneratedcellulosemembranesbasedonatomicforcemicroscopymeasurements AT maryammobedmiremadi supervisedlearningforpredictiveporesizeclassificationofregeneratedcellulosemembranesbasedonatomicforcemicroscopymeasurements |