A Subset of Secreted Proteins in Ascites Can Predict Platinum-Free Interval in Ovarian Cancer
The time between the last cycle of chemotherapy and recurrence, the platinum-free interval (PFI), predicts overall survival in high-grade serous ovarian cancer (HGSOC). To identify secreted proteins associated with a shorter PFI, we utilized machine learning to predict the PFI from ascites compositi...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Cancers |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-6694/14/17/4291 |
| _version_ | 1797496014379155456 |
|---|---|
| author | Molly J. Carroll Katja Kaipio Johanna Hynninen Olli Carpen Sampsa Hautaniemi David Page Pamela K. Kreeger |
| author_facet | Molly J. Carroll Katja Kaipio Johanna Hynninen Olli Carpen Sampsa Hautaniemi David Page Pamela K. Kreeger |
| author_sort | Molly J. Carroll |
| collection | DOAJ |
| description | The time between the last cycle of chemotherapy and recurrence, the platinum-free interval (PFI), predicts overall survival in high-grade serous ovarian cancer (HGSOC). To identify secreted proteins associated with a shorter PFI, we utilized machine learning to predict the PFI from ascites composition. Ascites from stage III/IV HGSOC patients treated with neoadjuvant chemotherapy (NACT) or primary debulking surgery (PDS) were screened for secreted proteins and Lasso regression models were built to predict the PFI. Through regularization techniques, the number of analytes used in each model was reduced; to minimize overfitting, we utilized an analysis of model robustness. This resulted in models with 26 analytes and a root-mean-square error (RMSE) of 19 days for the NACT cohort and 16 analytes and an RMSE of 7 days for the PDS cohort. High concentrations of MMP-2 and EMMPRIN correlated with a shorter PFI in the NACT patients, whereas high concentrations of uPA Urokinase and MMP-3 correlated with a shorter PFI in PDS patients. Our results suggest that the analysis of ascites may be useful for outcome prediction and identified factors in the tumor microenvironment that may lead to worse outcomes. Our approach to tuning for model stability, rather than only model accuracy, may be applicable to other biomarker discovery tasks. |
| first_indexed | 2024-03-10T01:57:40Z |
| format | Article |
| id | doaj.art-32e2d3fc0cb1487197ba6b38fcd96acd |
| institution | Directory Open Access Journal |
| issn | 2072-6694 |
| language | English |
| last_indexed | 2024-03-10T01:57:40Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Cancers |
| spelling | doaj.art-32e2d3fc0cb1487197ba6b38fcd96acd2023-11-23T12:53:04ZengMDPI AGCancers2072-66942022-09-011417429110.3390/cancers14174291A Subset of Secreted Proteins in Ascites Can Predict Platinum-Free Interval in Ovarian CancerMolly J. Carroll0Katja Kaipio1Johanna Hynninen2Olli Carpen3Sampsa Hautaniemi4David Page5Pamela K. Kreeger6Department of Biomedical Engineering, University of Wisconsin-Madison, Madison, WI 53706, USAResearch Center for Cancer, Infections and Immunity, Institute of Biomedicine, University of Turku, FI-20014 Turku, FinlandDepartment of Obstetrics and Gynecology, Turku University Hospital and University of Turku, FI-20014 Turku, FinlandResearch Center for Cancer, Infections and Immunity, Institute of Biomedicine, University of Turku, FI-20014 Turku, FinlandResearch Program in Systems Oncology, Research Programs Unit, Faculty of Medicine, University of Helsinki, FI-00014 Helsinki, FinlandDepartment of Biostatistics and Bioinformatics, Duke University, Durham, NC 27710, USADepartment of Biomedical Engineering, University of Wisconsin-Madison, Madison, WI 53706, USAThe time between the last cycle of chemotherapy and recurrence, the platinum-free interval (PFI), predicts overall survival in high-grade serous ovarian cancer (HGSOC). To identify secreted proteins associated with a shorter PFI, we utilized machine learning to predict the PFI from ascites composition. Ascites from stage III/IV HGSOC patients treated with neoadjuvant chemotherapy (NACT) or primary debulking surgery (PDS) were screened for secreted proteins and Lasso regression models were built to predict the PFI. Through regularization techniques, the number of analytes used in each model was reduced; to minimize overfitting, we utilized an analysis of model robustness. This resulted in models with 26 analytes and a root-mean-square error (RMSE) of 19 days for the NACT cohort and 16 analytes and an RMSE of 7 days for the PDS cohort. High concentrations of MMP-2 and EMMPRIN correlated with a shorter PFI in the NACT patients, whereas high concentrations of uPA Urokinase and MMP-3 correlated with a shorter PFI in PDS patients. Our results suggest that the analysis of ascites may be useful for outcome prediction and identified factors in the tumor microenvironment that may lead to worse outcomes. Our approach to tuning for model stability, rather than only model accuracy, may be applicable to other biomarker discovery tasks.https://www.mdpi.com/2072-6694/14/17/4291ovarian cancerascitesLassoplatinum-free intervalmodel stabilityrobustness |
| spellingShingle | Molly J. Carroll Katja Kaipio Johanna Hynninen Olli Carpen Sampsa Hautaniemi David Page Pamela K. Kreeger A Subset of Secreted Proteins in Ascites Can Predict Platinum-Free Interval in Ovarian Cancer Cancers ovarian cancer ascites Lasso platinum-free interval model stability robustness |
| title | A Subset of Secreted Proteins in Ascites Can Predict Platinum-Free Interval in Ovarian Cancer |
| title_full | A Subset of Secreted Proteins in Ascites Can Predict Platinum-Free Interval in Ovarian Cancer |
| title_fullStr | A Subset of Secreted Proteins in Ascites Can Predict Platinum-Free Interval in Ovarian Cancer |
| title_full_unstemmed | A Subset of Secreted Proteins in Ascites Can Predict Platinum-Free Interval in Ovarian Cancer |
| title_short | A Subset of Secreted Proteins in Ascites Can Predict Platinum-Free Interval in Ovarian Cancer |
| title_sort | subset of secreted proteins in ascites can predict platinum free interval in ovarian cancer |
| topic | ovarian cancer ascites Lasso platinum-free interval model stability robustness |
| url | https://www.mdpi.com/2072-6694/14/17/4291 |
| work_keys_str_mv | AT mollyjcarroll asubsetofsecretedproteinsinascitescanpredictplatinumfreeintervalinovariancancer AT katjakaipio asubsetofsecretedproteinsinascitescanpredictplatinumfreeintervalinovariancancer AT johannahynninen asubsetofsecretedproteinsinascitescanpredictplatinumfreeintervalinovariancancer AT ollicarpen asubsetofsecretedproteinsinascitescanpredictplatinumfreeintervalinovariancancer AT sampsahautaniemi asubsetofsecretedproteinsinascitescanpredictplatinumfreeintervalinovariancancer AT davidpage asubsetofsecretedproteinsinascitescanpredictplatinumfreeintervalinovariancancer AT pamelakkreeger asubsetofsecretedproteinsinascitescanpredictplatinumfreeintervalinovariancancer AT mollyjcarroll subsetofsecretedproteinsinascitescanpredictplatinumfreeintervalinovariancancer AT katjakaipio subsetofsecretedproteinsinascitescanpredictplatinumfreeintervalinovariancancer AT johannahynninen subsetofsecretedproteinsinascitescanpredictplatinumfreeintervalinovariancancer AT ollicarpen subsetofsecretedproteinsinascitescanpredictplatinumfreeintervalinovariancancer AT sampsahautaniemi subsetofsecretedproteinsinascitescanpredictplatinumfreeintervalinovariancancer AT davidpage subsetofsecretedproteinsinascitescanpredictplatinumfreeintervalinovariancancer AT pamelakkreeger subsetofsecretedproteinsinascitescanpredictplatinumfreeintervalinovariancancer |