MLP-Based Regression Prediction Model For Compound Bioactivity
The development of breast cancer is closely linked to the estrogen receptor ERα, which is also considered to be an important target for the treatment of breast cancer. Therefore, compounds that can antagonize ERα activity may be drug candidates for the treatment of breast cancer. In drug development...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-07-01
|
| Series: | Frontiers in Bioengineering and Biotechnology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fbioe.2022.946329/full |
| _version_ | 1828265529342689280 |
|---|---|
| author | Yongfei Qin Chao Li Xia Shi Weigang Wang Weigang Wang |
| author_facet | Yongfei Qin Chao Li Xia Shi Weigang Wang Weigang Wang |
| author_sort | Yongfei Qin |
| collection | DOAJ |
| description | The development of breast cancer is closely linked to the estrogen receptor ERα, which is also considered to be an important target for the treatment of breast cancer. Therefore, compounds that can antagonize ERα activity may be drug candidates for the treatment of breast cancer. In drug development, to save manpower and resources, potential active compounds are often screened by establishing compound activity prediction model. For the 1974 compounds collected, the top 20 molecular descriptors that significantly affected the biological activity were screened using LASSO regression models combined with 10-fold cross-validation method. Further, a regression prediction model based on the MLP fully connected neural network was constructed to predict the bioactivity values of 50 new compounds. To measure the validity of the model, the model loss term was specified as the mean squared error (MSE). The results showed that the MLP-based regression prediction model had a loss value of 0.0146 on the validation set. This model is therefore well trained and the prediction strategy used is valid. The methods developed by this paper may provide a reference for the development of anti-breast cancer drugs. |
| first_indexed | 2024-04-13T04:41:46Z |
| format | Article |
| id | doaj.art-9f9bbf1fc8174b4b86d16e6483d82d61 |
| institution | Directory Open Access Journal |
| issn | 2296-4185 |
| language | English |
| last_indexed | 2024-04-13T04:41:46Z |
| publishDate | 2022-07-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Bioengineering and Biotechnology |
| spelling | doaj.art-9f9bbf1fc8174b4b86d16e6483d82d612022-12-22T03:01:59ZengFrontiers Media S.A.Frontiers in Bioengineering and Biotechnology2296-41852022-07-011010.3389/fbioe.2022.946329946329MLP-Based Regression Prediction Model For Compound BioactivityYongfei Qin0Chao Li1Xia Shi2Weigang Wang3Weigang Wang4School of Statistics and Mathematics, Zhejiang Gongshang University, Hangzhou, ChinaSchool of Statistics and Mathematics, Zhejiang Gongshang University, Hangzhou, ChinaSchool of Statistics and Mathematics, Zhejiang Gongshang University, Hangzhou, ChinaSchool of Statistics and Mathematics, Zhejiang Gongshang University, Hangzhou, ChinaCollaborative Innovation Center of Statistical Data Engineering, Technology and Application, Zhejiang Gongshang University, Hangzhou, ChinaThe development of breast cancer is closely linked to the estrogen receptor ERα, which is also considered to be an important target for the treatment of breast cancer. Therefore, compounds that can antagonize ERα activity may be drug candidates for the treatment of breast cancer. In drug development, to save manpower and resources, potential active compounds are often screened by establishing compound activity prediction model. For the 1974 compounds collected, the top 20 molecular descriptors that significantly affected the biological activity were screened using LASSO regression models combined with 10-fold cross-validation method. Further, a regression prediction model based on the MLP fully connected neural network was constructed to predict the bioactivity values of 50 new compounds. To measure the validity of the model, the model loss term was specified as the mean squared error (MSE). The results showed that the MLP-based regression prediction model had a loss value of 0.0146 on the validation set. This model is therefore well trained and the prediction strategy used is valid. The methods developed by this paper may provide a reference for the development of anti-breast cancer drugs.https://www.frontiersin.org/articles/10.3389/fbioe.2022.946329/fullbreast cancer drug candidatesbiological activityLASSO regressionMLPneural |
| spellingShingle | Yongfei Qin Chao Li Xia Shi Weigang Wang Weigang Wang MLP-Based Regression Prediction Model For Compound Bioactivity Frontiers in Bioengineering and Biotechnology breast cancer drug candidates biological activity LASSO regression MLP neural |
| title | MLP-Based Regression Prediction Model For Compound Bioactivity |
| title_full | MLP-Based Regression Prediction Model For Compound Bioactivity |
| title_fullStr | MLP-Based Regression Prediction Model For Compound Bioactivity |
| title_full_unstemmed | MLP-Based Regression Prediction Model For Compound Bioactivity |
| title_short | MLP-Based Regression Prediction Model For Compound Bioactivity |
| title_sort | mlp based regression prediction model for compound bioactivity |
| topic | breast cancer drug candidates biological activity LASSO regression MLP neural |
| url | https://www.frontiersin.org/articles/10.3389/fbioe.2022.946329/full |
| work_keys_str_mv | AT yongfeiqin mlpbasedregressionpredictionmodelforcompoundbioactivity AT chaoli mlpbasedregressionpredictionmodelforcompoundbioactivity AT xiashi mlpbasedregressionpredictionmodelforcompoundbioactivity AT weigangwang mlpbasedregressionpredictionmodelforcompoundbioactivity AT weigangwang mlpbasedregressionpredictionmodelforcompoundbioactivity |