Machine learning modeling for solubility prediction of recombinant antibody fragment in four different E. coli strains
Abstract The solubility of proteins is usually a necessity for their functioning. Recently an emergence of machine learning approaches as trained alternatives to statistical models has been evidenced for empirical modeling and optimization. Here, soluble production of anti-EpCAM extracellular domain...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2022-03-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-022-09500-6 |
| _version_ | 1830440622743355392 |
|---|---|
| author | Atieh Hashemi Majid Basafa Aidin Behravan |
| author_facet | Atieh Hashemi Majid Basafa Aidin Behravan |
| author_sort | Atieh Hashemi |
| collection | DOAJ |
| description | Abstract The solubility of proteins is usually a necessity for their functioning. Recently an emergence of machine learning approaches as trained alternatives to statistical models has been evidenced for empirical modeling and optimization. Here, soluble production of anti-EpCAM extracellular domain (EpEx) single chain variable fragment (scFv) antibody was modeled and optimized as a function of four literature based numerical factors (post-induction temperature, post-induction time, cell density of induction time, and inducer concentration) and one categorical variable using artificial neural network (ANN) and response surface methodology (RSM). Models were established by the CCD experimental data derived from 232 separate experiments. The concentration of soluble scFv reached 112.4 mg/L at the optimum condition and strain (induction at cell density 0.6 with 0.4 mM IPTG for 24 h at 23 °C in Origami). The predicted value obtained by ANN for the response (106.1 mg/L) was closer to the experimental result than that obtained by RSM (97.9 mg/L), which again confirmed a higher accuracy of ANN model. To the author’s knowledge this is the first report on comparison of ANN and RSM in statistical optimization of fermentation conditions of E.coli for the soluble production of recombinant scFv. |
| first_indexed | 2024-12-21T05:08:41Z |
| format | Article |
| id | doaj.art-5be27ebd34074199ad726a1ef0ec05c9 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-12-21T05:08:41Z |
| publishDate | 2022-03-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-5be27ebd34074199ad726a1ef0ec05c92022-12-21T19:15:07ZengNature PortfolioScientific Reports2045-23222022-03-0112111110.1038/s41598-022-09500-6Machine learning modeling for solubility prediction of recombinant antibody fragment in four different E. coli strainsAtieh Hashemi0Majid Basafa1Aidin Behravan2Department of Pharmaceutical Biotechnology, School of Pharmacy, Shahid Beheshti University of Medical SciencesDepartment of Pharmaceutical Biotechnology, School of Pharmacy, Shahid Beheshti University of Medical SciencesDepartment of Pharmaceutical Biotechnology, School of Pharmacy, Shahid Beheshti University of Medical SciencesAbstract The solubility of proteins is usually a necessity for their functioning. Recently an emergence of machine learning approaches as trained alternatives to statistical models has been evidenced for empirical modeling and optimization. Here, soluble production of anti-EpCAM extracellular domain (EpEx) single chain variable fragment (scFv) antibody was modeled and optimized as a function of four literature based numerical factors (post-induction temperature, post-induction time, cell density of induction time, and inducer concentration) and one categorical variable using artificial neural network (ANN) and response surface methodology (RSM). Models were established by the CCD experimental data derived from 232 separate experiments. The concentration of soluble scFv reached 112.4 mg/L at the optimum condition and strain (induction at cell density 0.6 with 0.4 mM IPTG for 24 h at 23 °C in Origami). The predicted value obtained by ANN for the response (106.1 mg/L) was closer to the experimental result than that obtained by RSM (97.9 mg/L), which again confirmed a higher accuracy of ANN model. To the author’s knowledge this is the first report on comparison of ANN and RSM in statistical optimization of fermentation conditions of E.coli for the soluble production of recombinant scFv.https://doi.org/10.1038/s41598-022-09500-6 |
| spellingShingle | Atieh Hashemi Majid Basafa Aidin Behravan Machine learning modeling for solubility prediction of recombinant antibody fragment in four different E. coli strains Scientific Reports |
| title | Machine learning modeling for solubility prediction of recombinant antibody fragment in four different E. coli strains |
| title_full | Machine learning modeling for solubility prediction of recombinant antibody fragment in four different E. coli strains |
| title_fullStr | Machine learning modeling for solubility prediction of recombinant antibody fragment in four different E. coli strains |
| title_full_unstemmed | Machine learning modeling for solubility prediction of recombinant antibody fragment in four different E. coli strains |
| title_short | Machine learning modeling for solubility prediction of recombinant antibody fragment in four different E. coli strains |
| title_sort | machine learning modeling for solubility prediction of recombinant antibody fragment in four different e coli strains |
| url | https://doi.org/10.1038/s41598-022-09500-6 |
| work_keys_str_mv | AT atiehhashemi machinelearningmodelingforsolubilitypredictionofrecombinantantibodyfragmentinfourdifferentecolistrains AT majidbasafa machinelearningmodelingforsolubilitypredictionofrecombinantantibodyfragmentinfourdifferentecolistrains AT aidinbehravan machinelearningmodelingforsolubilitypredictionofrecombinantantibodyfragmentinfourdifferentecolistrains |