A machine learning strategy for the identification of key in silico descriptors and prediction models for IgG monoclonal antibody developability properties
Identification of favorable biophysical properties for protein therapeutics as part of developability assessment is a crucial part of the preclinical development process. Successful prediction of such properties and bioassay results from calculated in silico features has potential to reduce the time and cost of delivering clinical-grade material to patients, but nevertheless has remained an ongoing challenge to the field. Here, we demonstrate an automated and flexible machine learning workflow designed to compare and identify the most powerful features from computationally derived physiochemical feature sets, generated from popular commercial software packages. We implement this workflow with medium-sized datasets of human and humanized IgG molecules to generate predictive regression models for two key developability endpoints, hydrophobicity and poly-specificity. The most important features discovered through the automated workflow corroborate several previous literature reports, and newly discovered features suggest directions for further research and potential model improvement.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2023 |
|---|---|
| Erschienen: |
2023 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:15 |
|---|---|
| Enthalten in: |
mAbs - 15(2023), 1 vom: 05. Jan., Seite 2248671 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Waight, Andrew B [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Antibodies, Monoclonal |
|---|
| Anmerkungen: |
Date Completed 02.11.2023 Date Revised 08.11.2023 published: Print Citation Status MEDLINE |
|---|
| doi: |
10.1080/19420862.2023.2248671 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM361085982 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM361085982 | ||
| 003 | DE-627 | ||
| 005 | 20231226084411.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231226s2023 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1080/19420862.2023.2248671 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1203.xml |
| 035 | |a (DE-627)NLM361085982 | ||
| 035 | |a (NLM)37610144 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Waight, Andrew B |e verfasserin |4 aut | |
| 245 | 1 | 2 | |a A machine learning strategy for the identification of key in silico descriptors and prediction models for IgG monoclonal antibody developability properties |
| 264 | 1 | |c 2023 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Completed 02.11.2023 | ||
| 500 | |a Date Revised 08.11.2023 | ||
| 500 | |a published: Print | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a Identification of favorable biophysical properties for protein therapeutics as part of developability assessment is a crucial part of the preclinical development process. Successful prediction of such properties and bioassay results from calculated in silico features has potential to reduce the time and cost of delivering clinical-grade material to patients, but nevertheless has remained an ongoing challenge to the field. Here, we demonstrate an automated and flexible machine learning workflow designed to compare and identify the most powerful features from computationally derived physiochemical feature sets, generated from popular commercial software packages. We implement this workflow with medium-sized datasets of human and humanized IgG molecules to generate predictive regression models for two key developability endpoints, hydrophobicity and poly-specificity. The most important features discovered through the automated workflow corroborate several previous literature reports, and newly discovered features suggest directions for further research and potential model improvement | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a Biophysical | |
| 650 | 4 | |a IgG1 | |
| 650 | 4 | |a computational | |
| 650 | 4 | |a descriptors | |
| 650 | 4 | |a developability | |
| 650 | 4 | |a machine learning | |
| 650 | 7 | |a Immunoglobulin G |2 NLM | |
| 650 | 7 | |a Antibodies, Monoclonal |2 NLM | |
| 700 | 1 | |a Prihoda, David |e verfasserin |4 aut | |
| 700 | 1 | |a Shrestha, Rojan |e verfasserin |4 aut | |
| 700 | 1 | |a Metcalf, Kevin |e verfasserin |4 aut | |
| 700 | 1 | |a Bailly, Marc |e verfasserin |4 aut | |
| 700 | 1 | |a Ancona, Marco |e verfasserin |4 aut | |
| 700 | 1 | |a Widatalla, Talal |e verfasserin |4 aut | |
| 700 | 1 | |a Rollins, Zachary |e verfasserin |4 aut | |
| 700 | 1 | |a Cheng, Alan C |e verfasserin |4 aut | |
| 700 | 1 | |a Bitton, Danny A |e verfasserin |4 aut | |
| 700 | 1 | |a Fayadat-Dilman, Laurence |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t mAbs |d 2009 |g 15(2023), 1 vom: 05. Jan., Seite 2248671 |w (DE-627)NLM194097110 |x 1942-0870 |7 nnns |
| 773 | 1 | 8 | |g volume:15 |g year:2023 |g number:1 |g day:05 |g month:01 |g pages:2248671 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1080/19420862.2023.2248671 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 15 |j 2023 |e 1 |b 05 |c 01 |h 2248671 | ||