Machine Learning‐Based Prediction of Immunomodulatory Properties of Polymers: Toward a Faster and Easier Development of Anti‐Inflammatory Biomaterials
In biomaterials development, creating materials with desirable properties can be a time‐consuming and resource‐intensive process, often relying on serendipitous discoveries. A potential route to accelerate this process is to employ artificial intelligence methodologies such as machine learning (ML)....
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley-VCH
2024-03-01
|
| Series: | Advanced NanoBiomed Research |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/anbr.202300085 |
| _version_ | 1827324513990213632 |
|---|---|
| author | Aghilas Akkache Lisa Clavier Oleh Mezhenskyi Kateryna Andriienkova Thibaut Soubrié Philippe Lavalle Nihal Engin Vrana Varvara Gribova |
| author_facet | Aghilas Akkache Lisa Clavier Oleh Mezhenskyi Kateryna Andriienkova Thibaut Soubrié Philippe Lavalle Nihal Engin Vrana Varvara Gribova |
| author_sort | Aghilas Akkache |
| collection | DOAJ |
| description | In biomaterials development, creating materials with desirable properties can be a time‐consuming and resource‐intensive process, often relying on serendipitous discoveries. A potential route to accelerate this process is to employ artificial intelligence methodologies such as machine learning (ML). Herein, the possibility to predict anti‐inflammatory properties of the polymers by using a simplified model of inflammation and a restrained dataset is explored. Cellular assays with 50 different polymers are conducted using the murine macrophage cell line RAW 264.7 as a model. These experiments generate a dataset which is used to develop a ML model based on Bayesian logistic regression. After conducting a Bayesian logistic regression analysis, two ML models, K‐nearest neighbors (KNN) and Naïve Bayes, are employed to predict anti‐inflammatory polymers properties. The study finds that the probability of a polymer having anti‐inflammatory properties is multiplied by three if it is a polycation, and that nitric oxide secretion is a good indicator in determining the anti‐inflammatory properties of a polymer, which in this work are defined by tumor necrosis factor alpha expression decrease. Overall, the study suggests that with appropriate dataset design, ML techniques can provide valuable information on functional polymer properties, enabling faster and more efficient biomaterial development. |
| first_indexed | 2024-04-25T02:14:43Z |
| format | Article |
| id | doaj.art-3480122132d4476abcb4a7045ce2dd18 |
| institution | Directory Open Access Journal |
| issn | 2699-9307 |
| language | English |
| last_indexed | 2024-04-25T02:14:43Z |
| publishDate | 2024-03-01 |
| publisher | Wiley-VCH |
| record_format | Article |
| series | Advanced NanoBiomed Research |
| spelling | doaj.art-3480122132d4476abcb4a7045ce2dd182024-03-07T10:48:32ZengWiley-VCHAdvanced NanoBiomed Research2699-93072024-03-0143n/an/a10.1002/anbr.202300085Machine Learning‐Based Prediction of Immunomodulatory Properties of Polymers: Toward a Faster and Easier Development of Anti‐Inflammatory BiomaterialsAghilas Akkache0Lisa Clavier1Oleh Mezhenskyi2Kateryna Andriienkova3Thibaut Soubrié4Philippe Lavalle5Nihal Engin Vrana6Varvara Gribova7SPARTHA Medical 1 Rue Eugène Boeckel 67000 Strasbourg FranceBiomaterials and Bioengineering Laboratory INSERM UMR 1121 1 rue Eugène Boeckel 67000 Strasbourg FrancePreste 242 boulevard Voltaire 75011 Paris FrancePreste 242 boulevard Voltaire 75011 Paris FrancePreste 242 boulevard Voltaire 75011 Paris FranceSPARTHA Medical 1 Rue Eugène Boeckel 67000 Strasbourg FranceSPARTHA Medical 1 Rue Eugène Boeckel 67000 Strasbourg FranceBiomaterials and Bioengineering Laboratory INSERM UMR 1121 1 rue Eugène Boeckel 67000 Strasbourg FranceIn biomaterials development, creating materials with desirable properties can be a time‐consuming and resource‐intensive process, often relying on serendipitous discoveries. A potential route to accelerate this process is to employ artificial intelligence methodologies such as machine learning (ML). Herein, the possibility to predict anti‐inflammatory properties of the polymers by using a simplified model of inflammation and a restrained dataset is explored. Cellular assays with 50 different polymers are conducted using the murine macrophage cell line RAW 264.7 as a model. These experiments generate a dataset which is used to develop a ML model based on Bayesian logistic regression. After conducting a Bayesian logistic regression analysis, two ML models, K‐nearest neighbors (KNN) and Naïve Bayes, are employed to predict anti‐inflammatory polymers properties. The study finds that the probability of a polymer having anti‐inflammatory properties is multiplied by three if it is a polycation, and that nitric oxide secretion is a good indicator in determining the anti‐inflammatory properties of a polymer, which in this work are defined by tumor necrosis factor alpha expression decrease. Overall, the study suggests that with appropriate dataset design, ML techniques can provide valuable information on functional polymer properties, enabling faster and more efficient biomaterial development.https://doi.org/10.1002/anbr.202300085Bayesian logistic regressionin silicoinflammationmachine learningpolymerspredictive models |
| spellingShingle | Aghilas Akkache Lisa Clavier Oleh Mezhenskyi Kateryna Andriienkova Thibaut Soubrié Philippe Lavalle Nihal Engin Vrana Varvara Gribova Machine Learning‐Based Prediction of Immunomodulatory Properties of Polymers: Toward a Faster and Easier Development of Anti‐Inflammatory Biomaterials Advanced NanoBiomed Research Bayesian logistic regression in silico inflammation machine learning polymers predictive models |
| title | Machine Learning‐Based Prediction of Immunomodulatory Properties of Polymers: Toward a Faster and Easier Development of Anti‐Inflammatory Biomaterials |
| title_full | Machine Learning‐Based Prediction of Immunomodulatory Properties of Polymers: Toward a Faster and Easier Development of Anti‐Inflammatory Biomaterials |
| title_fullStr | Machine Learning‐Based Prediction of Immunomodulatory Properties of Polymers: Toward a Faster and Easier Development of Anti‐Inflammatory Biomaterials |
| title_full_unstemmed | Machine Learning‐Based Prediction of Immunomodulatory Properties of Polymers: Toward a Faster and Easier Development of Anti‐Inflammatory Biomaterials |
| title_short | Machine Learning‐Based Prediction of Immunomodulatory Properties of Polymers: Toward a Faster and Easier Development of Anti‐Inflammatory Biomaterials |
| title_sort | machine learning based prediction of immunomodulatory properties of polymers toward a faster and easier development of anti inflammatory biomaterials |
| topic | Bayesian logistic regression in silico inflammation machine learning polymers predictive models |
| url | https://doi.org/10.1002/anbr.202300085 |
| work_keys_str_mv | AT aghilasakkache machinelearningbasedpredictionofimmunomodulatorypropertiesofpolymerstowardafasterandeasierdevelopmentofantiinflammatorybiomaterials AT lisaclavier machinelearningbasedpredictionofimmunomodulatorypropertiesofpolymerstowardafasterandeasierdevelopmentofantiinflammatorybiomaterials AT olehmezhenskyi machinelearningbasedpredictionofimmunomodulatorypropertiesofpolymerstowardafasterandeasierdevelopmentofantiinflammatorybiomaterials AT katerynaandriienkova machinelearningbasedpredictionofimmunomodulatorypropertiesofpolymerstowardafasterandeasierdevelopmentofantiinflammatorybiomaterials AT thibautsoubrie machinelearningbasedpredictionofimmunomodulatorypropertiesofpolymerstowardafasterandeasierdevelopmentofantiinflammatorybiomaterials AT philippelavalle machinelearningbasedpredictionofimmunomodulatorypropertiesofpolymerstowardafasterandeasierdevelopmentofantiinflammatorybiomaterials AT nihalenginvrana machinelearningbasedpredictionofimmunomodulatorypropertiesofpolymerstowardafasterandeasierdevelopmentofantiinflammatorybiomaterials AT varvaragribova machinelearningbasedpredictionofimmunomodulatorypropertiesofpolymerstowardafasterandeasierdevelopmentofantiinflammatorybiomaterials |