scholarly journals Classification of molecular subtypes of high-grade serous ovarian cancer by MALDI-Imaging.

2021 ◽  
Vol 39 (15_suppl) ◽  
pp. e17544-e17544
Author(s):  
Wanja Nikolai Kassuhn ◽  
Oliver Klein ◽  
Silvia Darb-Esfahani ◽  
Hedwig Lammert ◽  
Sylwia Handzik ◽  
...  
Keyword(s):  
Machine Learning ◽  
Ovarian Cancer ◽  
Molecular Subtypes ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Clear Correlation ◽  
High Grade ◽  
Serous Ovarian Cancer ◽  
Tissue Samples ◽  
Maldi Ims

e17544 Background: High-grade serous ovarian cancer (HGSOC) can be separated by gene expression profiling into four molecular subtypes with clear correlation of the clinical outcome. However, these gene signatures have not been implemented in clinical practice to stratify patients for targeted therapy. This is mainly due to a lack of easy, cost-effective and reproducible methods, as well as the high heterogeneity of HGSOC. Hence, we aimed to examine the potential of unsupervised matrix assisted laser desorption/ionization imaging mass spectrometry (MALDI-IMS) to stratify patients, which might benefit from targeted therapeutic strategies. Methods: Molecular subtyping of paraffin-embedded tissue samples from 279 HGSOC patients was performed by NanoString analysis (ground truth labeling). Next, we applied MALDI-IMS, a novel technology to identify distinct mass profiles on the same paraffin-embedded tissue sections paired with machine learning algorithms to identify HGSOC subtypes by proteomic signature. Finally, we devised a novel strategy to annotate spectra of stromal origin. Results: We elucidated a MALDI-derived proteomic signature (135 peptides) able to classify HGSOC subtypes. Random forest classifiers achieved an area under the curve (AUC) of 0.983. Furthermore, we demonstrated that the exclusion of stroma associated spectra provides tangible improvements to classification quality (AUC = 0.988). False discovery rates (FDR) were reduced from 10.2% to 8.0%. Finally, novel MALDI-based stroma annotation achieved near-perfect classifications (AUC = 0.999, FDR < 1.0%). Conclusions: Here, we present a concept integrating MALDI-IMS with machine learning algorithms to classify patients according to distinct molecular subtypes of HGSOC. This has great potential to assign patients for targeted therapies.

scholarly journals Classification of Molecular Subtypes of High-Grade Serous Ovarian Cancer by MALDI-Imaging

Cancers ◽  
2021 ◽  
Vol 13 (7) ◽  
pp. 1512
Author(s):  
Wanja Kassuhn ◽  
Oliver Klein ◽  
Silvia Darb-Esfahani ◽  
Hedwig Lammert ◽  
Sylwia Handzik ◽  
...  
Keyword(s):  
Machine Learning ◽  
Ovarian Cancer ◽  
Molecular Subtypes ◽  
Learning Algorithms ◽  
Imaging Mass Spectrometry ◽  
Machine Learning Algorithms ◽  
High Grade ◽  
Serous Ovarian Cancer ◽  
Tissue Samples ◽  
Maldi Ims

Despite the correlation of clinical outcome and molecular subtypes of high-grade serous ovarian cancer (HGSOC), contemporary gene expression signatures have not been implemented in clinical practice to stratify patients for targeted therapy. Hence, we aimed to examine the potential of unsupervised matrix-assisted laser desorption/ionization imaging mass spectrometry (MALDI-IMS) to stratify patients who might benefit from targeted therapeutic strategies. Molecular subtyping of paraffin-embedded tissue samples from 279 HGSOC patients was performed by NanoString analysis (ground truth labeling). Next, we applied MALDI-IMS paired with machine-learning algorithms to identify distinct mass profiles on the same paraffin-embedded tissue sections and distinguish HGSOC subtypes by proteomic signature. Finally, we devised a novel approach to annotate spectra of stromal origin. We elucidated a MALDI-derived proteomic signature (135 peptides) able to classify HGSOC subtypes. Random forest classifiers achieved an area under the curve (AUC) of 0.983. Furthermore, we demonstrated that the exclusion of stroma-associated spectra provides tangible improvements to classification quality (AUC = 0.988). Moreover, novel MALDI-based stroma annotation achieved near-perfect classifications (AUC = 0.999). Here, we present a concept integrating MALDI-IMS with machine-learning algorithms to classify patients according to distinct molecular subtypes of HGSOC. This has great potential to assign patients for personalized treatment.

Dynamic of molecular subtypes of high‐grade serous ovarian cancer in paired primary and relapsed biopsies.

2019 ◽  
Vol 37 (15_suppl) ◽  
pp. e17091-e17091
Author(s):  
Elena Ioana Braicu ◽  
Hagen Kulbe ◽  
Felix Dreher ◽  
Eliane T Taube ◽  
Frauke Ringel ◽  
...  
Keyword(s):  
Ovarian Cancer ◽  
Clinical Outcome ◽  
Molecular Subtypes ◽  
Molecular Subtype ◽  
High Grade ◽  
Serous Ovarian Cancer ◽  
Microarray Gene Expression ◽  
Tissue Samples ◽  
Paired Samples ◽  
Nanostring Technology

e17091 Background: Previously four molecular subtypes of high grade serous ovarian cancer (HGSOC) with distinct biological features and clinical outcome have been described: C1 (mesenchymal), C2 (immunoreactive), C4 (differentiated), and C5 (proliferative). Using Nanostring technique and a minimal signature of 39 classifier genes could reproduce the subtypes identified by microarray gene expression profiling (Leong HS et al. Australian Ovarian Cancer Study. J Pathol. 2015). Methods: We characterized paraffin embedded tissue samples from 279 HGSOC patients for molecular subtypes, utilizing the 39 classifier signature and 9 control genes by Nanostring nCounter Analysis System. From 16 patients paired primary and relapsed samples were available. Only chemonaive primary HGSOC patients were included in the study. FFPEs and clinical data were provided by TOC ( www.toc-network.de ). For each sample, probability scores for the four molecular subtypes (C1, C2, C4, and C5) were calculated. The highest calculated score determined the most likely subtype of the tumor. Results: Of all analyzed primary tumor samples, 88 (31.5%) were classified as C1, 83 (29.8%), 53 (19.0%) and 55 (19.7%) as subtypes C2, C4 and C5, respectively. Our results confirmed data by the AOCS study, which described the distribution of HGSOC with 40.2% (C1), 22.5% (C2), 20.1% (C4) and 17.2% (C5), respectively. Within the paired samples, for 12 of the 16 patients dynamic changes in the molecular subtypes between primary and relapse occurred, while in the remaining 4 patients the phenotype was stable. Conclusions: Molecular subtypes of HGSOC using Nanostring technology with a small panel of classifier genes can be confirmed. Furthermore, the data showed that a change of the established molecular subtype might occur during the evolution of the disease, and therefore translate in a different clinical outcome.

scholarly journals Development of a Genomic Signatures-Based Predictor of Initial Platinum-Resistance in Advanced High-Grade Serous Ovarian Cancer Patients

2021 ◽  
Vol 10 ◽  
Author(s):  
Yuan Li ◽  
Xiaolan Zhang ◽  
Yan Gao ◽  
Chunliang Shang ◽  
Bo Yu ◽  
...  
Keyword(s):  
Ovarian Cancer ◽  
Predictive Accuracy ◽  
Predictive Performance ◽  
Platinum Resistance ◽  
High Grade ◽  
Serous Ovarian Cancer ◽  
Single Nucleotide Variants ◽  
Tissue Samples ◽  
Platinum Sensitive ◽  
Platinum Based Chemotherapy

BackgroundHigh grade serous ovarian cancer (HGSOC) is the most common subtype of ovarian cancer. Although platinum-based chemotherapy has been the cornerstone for HGSOC treatment, nearly 25% of patients would have less than 6 months of interval since the last platinum chemotherapy, referred to as platinum-resistance. Currently, no precise tools to predict platinum resistance have been developed yet.MethodsNinety-nine HGSOC patients, who have finished cytoreductive surgery and platinum-based chemotherapy in Peking University Third Hospital from 2018 to 2019, were enrolled. Whole-genome sequencing (WGS) and whole-exome sequencing (WES) were performed on the collected tumor tissue samples to establish a platinum-resistance predictor in a discovery cohort of 57 patients, and further validated in another 42 HGSOC patients.ResultsA high prevalence of alterations in DNA damage repair (DDR) pathway, including BRCA1/2, was identified both in the platinum-sensitive and resistant HGSOC patients. Compared with the resistant subgroup, there was a trend of higher prevalence of homologous recombination deficiency (HRD) in the platinum-sensitive subgroup (78.95% vs. 47.37%, p=0.0646). Based on the HRD score, microhomology insertions and deletions (MHID), copy number changes load, duplication load of 1–100 kb, single nucleotide variants load, and eight other mutational signatures, a combined predictor of platinum-resistance, named as DRDscore, was established. DRDscore outperformed in predicting the platinum-sensitivity than the previously reported biomarkers with a predictive accuracy of 0.860 at a threshold of 0.7584. The predictive performance of DRDscore was validated in an independent cohort of 42 HGSOC patients with a sensitivity of 90.9%.ConclusionsA multi-genomic signature-based analysis enabled the prediction of initial platinum resistance in advanced HGSOC patients, which may serve as a novel assessment of platinum resistance, provide therapeutic guidance, and merit further validation.

A 2-Protein Signature Predicting Clinical Outcome in High-Grade Serous Ovarian Cancer

2018 ◽  
Vol 28 (1) ◽  
pp. 51-58 ◽  
Author(s):  
Chengjuan Jin ◽  
Yingfeng Xue ◽  
Yingwei Li ◽  
Hualei Bu ◽  
Hongfeng Yu ◽  
...  
Keyword(s):  
Ovarian Cancer ◽  
Molecular Subtypes ◽  
Disease Free Survival ◽  
Tissue Microarrays ◽  
Multivariate Regression Analysis ◽  
High Grade ◽  
Serous Ovarian Cancer ◽  
Free Survival ◽  
Formalin Fixed Paraffin ◽  
Formalin Fixed Paraffin Embedded

ObjectiveHigh-grade serous ovarian cancer (HGSOC) accounts for approximately 70% deaths in ovarian cancer. The overall survival (OS) of HGSOC is poor and still remains a clinical challenge. High-grade serous ovarian cancer can be divided into 4 molecular subtypes. The prognosis of different molecular subtypes is still unclear. We aimed to investigate the prognostic values of immunohistochemistry-based different molecular subtypes in patients with HGSOC.MethodsWe analyzed the protein expression of representative biomarkers (CXCL11, HMGA2, and MUC16) of 3 different molecular subtypes in 110 formalin-fixed, paraffin-embedded HGSOC by tissue microarrays.ResultsHigh CXCL11 expression predicted worse OS, not disease-free survival (DFS; P = 0.028 for OS, P = 0.191 for DFS). High HMGA2 expression predicted worse OS and DFS (P = 0.037 for OS, P = 0.021 for DFS). MUC16 expression was not associated with OS or DFS (P = 0.919 for OS, P = 0.517 for DFS). Multivariate regression analysis showed that CXCL11 combined with HMGA2 signature was an independent predictor for OS and DFS in patients with HGSOC.ConclusionsCXCL11 combined with HMGA2 signature was a clinically applicable prognostic model that could precisely predict an HGSOC patient's OS and tumor recurrence. This model could serve as an important tool for risk assessment of HGSOC prognosis.

scholarly journals Evaluation of Combined Cancer Markers With Lactate Dehydrogenase and Application of Machine Learning Algorithms for Differentiating Benign Disease From Malignant Ovarian Cancer

2021 ◽  
Vol 28 ◽  
pp. 107327482110334
Author(s):  
Seri Jeong ◽  
Dae-Soon Son ◽  
Minseob Cho ◽  
Nuri Lee ◽  
Wonkeun Song ◽  
...  
Keyword(s):  
Machine Learning ◽  
Ovarian Cancer ◽  
Lactate Dehydrogenase ◽  
Total Population ◽  
Early Stage ◽  
Learning Algorithms ◽  
Benign Disease ◽  
Machine Learning Algorithms ◽  
Cancer Markers ◽  
Early Stage Ovarian Cancer

Background The differential diagnosis of ovarian cancer is important, and there has been ongoing research to identify biomarkers with higher performance. This study aimed to evaluate the diagnostic utility of combinations of cancer markers classified by machine learning algorithms in patients with early stage ovarian cancer, which has rarely been reported. Methods In total, 730 serum samples were assayed for lactate dehydrogenase (LD), neutrophil-to-lymphocyte ratio (NLR), human epididymis protein 4 (HE4), cancer antigen 125 (CA125), and risk of ovarian malignancy algorithm (ROMA). Among them, 53 were diagnosed with early stage ovarian cancer, and the remaining 677 were diagnosed with benign disease. Results The areas under the receiver operating characteristic curves (ROC-AUCs) of the ROMA, HE4, CA125, LD, and NLR for discriminating ovarian cancer from non-cancerous disease were .707, .680, .643, .657, and .624, respectively. ROC-AUC of the combination of ROMA and LD (.709) was similar to that of single ROMA in the total population. In the postmenopausal group, ROC-AUCs of HE4 and CA125 combined with LD presented the highest value (.718). When machine learning algorithms were applied to ROMA combined with LD, the ROC-AUC of random forest was higher than that of other applied algorithms in the total population (.757), showing acceptable performance. Conclusion Our data suggest that the combinations of ovarian cancer-specific markers with LD classified by random forest may be a useful tool for predicting ovarian cancer, particularly in clinical settings, due to easy accessibility and cost-effectiveness. Application of an optimal combination of cancer markers and algorithms would facilitate appropriate management of ovarian cancer patients.

Predicting 180-day mortality for women with ovarian cancer using machine learning and patient-reported outcome data.

2021 ◽  
Vol 39 (15_suppl) ◽  
pp. e13555-e13555
Author(s):  
Chris Sidey-Gibbons ◽  
Charlotte C. Sun ◽  
Cai Xu ◽  
Amy Schneider ◽  
Sheng-Chieh Lu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Ovarian Cancer ◽  
End Of Life ◽  
Learning Algorithms ◽  
The United States ◽  
Patient Reported Outcome ◽  
Machine Learning Algorithms ◽  
Electronic Health Record Data ◽  
Testing Dataset ◽  
Patient Reported

e13555 Background: Contra to national guidelines, women with ovarian cancer often receive aggressive treatment until the end-of-life. We trained machine learning algorithms to predict mortality within 180 days for women with ovarian cancer. Methods: Data were collected data from a single academic cancer institution in the United States. Women with recurrent ovarian cancer completed biopsychosocial patient-reported outcome measures (PROMs) every 90 days. We randomly partitioned our dataset into training and testing samples with a 2:1 ratio. We used synthetic minority oversampling to reduce class imbalance in the training dataset. We fitted training data to six machine learning algorithms and combined their classifications on the testing dataset into a voting ensemble. We assessed the accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUROC) for each algorithm. Results: We recruited 245 patients who completed 1319 assessments. The final voting ensemble performed well across all performance metrics (Accuracy = .79, Sensitivity = .71, Specificity = .80, AUROC = .76). The algorithm correctly identified 25 of the 35 women in the testing dataset who died within 180 days of assessment Conclusions: Machine learning algorithms trained using PROM data offer state-of-the-art performance in predicting whether a woman with ovarian cancer will reach the end-of-life within 180 days. We highlight the importance of PROM data in ML models of mortality. Our model exhibits substantial improvements in prediction sensitivity compared to other similar models trained using electronic health record data alone. This model could inform clinical decision making and improve the uptake of appropriate end-of-life care. Further research is warranted to expand on these findings in a larger, more diverse sample.

scholarly journals HDAC6 Degradation Inhibits the Growth of High-Grade Serous Ovarian Cancer Cells

Cancers ◽  
2020 ◽  
Vol 12 (12) ◽  
pp. 3734
Author(s):  
Ahlam Ali ◽  
Fengyu Zhang ◽  
Aaron Maguire ◽  
Tara Byrne ◽  
Karolina Weiner-Gorzel ◽  
...  
Keyword(s):  
Gene Expression ◽  
Ovarian Cancer ◽  
Cell Proliferation ◽  
Protein Expression ◽  
First Generation ◽  
Ovarian Cancer Cells ◽  
High Grade ◽  
Serous Ovarian Cancer ◽  
Tissue Samples ◽  
Risk Of Death

Histone deacetylase 6 (HDAC6) is a unique histone deacetylating enzyme that resides in the cell cytoplasm and is linked to the modulation of several key cancer related responses, including cell proliferation and migration. The promising anti-cancer response of the first-generation HDAC6 catalytic inhibitors continues to be assessed in clinical trials, although its role in high grade serous ovarian cancer is unclear. This study investigated HDAC6 tumor expression by immunohistochemistry in high-grade serous ovarian cancer (HGSOC) tissue samples and a meta-analysis of HDAC6 gene expression in ovarian cancer from publicly available data. The pharmacological activity of HDAC6 inhibition was assessed in a patient-derived model of HGSOC. HDAC6 was found to be highly expressed in HGSOC tissue samples and in the patient-derived HGSOC cell lines where higher HDAC6 protein and gene expression was associated with a decreased risk of death (hazard ratio (HR) 0.38, (95% confidence interval (CI), 0.16–0.88; p = 0.02); HR = 0.88 (95% CI, 0.78–0.99; p = 0.04)). Similarly, the multivariate analysis of HDAC6 protein expression, adjusting for stage, grade, and cytoreduction/cytoreductive surgery was associated with a decreased risk of death (HR = 0.19 (95% CI, 0.06–0.55); p = 0.002). Knock-down of HDAC6 gene expression with siRNA and protein expression with a HDAC6 targeting protein degrader decreased HGSOC cell proliferation, migration, and viability. Conversely, the selective inhibition of HDAC6 with the catalytic domain inhibitor, Ricolinostat (ACY-1215), inhibited HDAC6 deacetylation of α-tubulin, resulting in a sustained accumulation of acetylated α-tubulin up to 24 h in HGSOC cells, did not produce a robust inhibition of HDAC6 protein function. Inhibition of HGSOC cell proliferation by ACY-1215 was only achieved with significantly higher and non-selective doses of ACY-1215. In summary, we demonstrated, for the first time, that HDAC6 over-expression in HGSOC and all ovarian cancers is a favorable prognostic marker. We provide evidence to suggest that inhibition of HDAC6 catalytic activity with first generation HDAC6 inhibitors has limited efficacy as a monotherapy in HGSOC.

scholarly journals Machine Learning-Based Risk Prediction of Critical Care Unit Admission for Advanced Stage High Grade Serous Ovarian Cancer Patients Undergoing Cytoreductive Surgery: The Leeds-Natal Score

2021 ◽  
Vol 11 (1) ◽  
pp. 87
Author(s):  
Alexandros Laios ◽  
Raissa Vanessa De Oliveira Silva ◽  
Daniel Lucas Dantas De Freitas ◽  
Yong Sheung Tan ◽  
Gwendolyn Saalmink ◽  
...  
Keyword(s):  
Machine Learning ◽  
Ovarian Cancer ◽  
Critical Care ◽  
Cytoreductive Surgery ◽  
Critical Care Unit ◽  
Predictive Score ◽  
High Grade ◽  
Advanced Stage ◽  
Serous Ovarian Cancer ◽  
Estimated Blood Loss

Achieving complete surgical cytoreduction in advanced stage high grade serous ovarian cancer (HGSOC) patients warrants an availability of Critical Care Unit (CCU) beds. Machine Learning (ML) could be helpful in monitoring CCU admissions to improve standards of care. We aimed to improve the accuracy of predicting CCU admission in HGSOC patients by ML algorithms and developed an ML-based predictive score. A cohort of 291 advanced stage HGSOC patients with fully curated data was selected. Several linear and non-linear distances, and quadratic discriminant ML methods, were employed to derive prediction information for CCU admission. When all the variables were included in the model, the prediction accuracies were higher for linear discriminant (0.90) and quadratic discriminant (0.93) methods compared with conventional logistic regression (0.84). Feature selection identified pre-treatment albumin, surgical complexity score, estimated blood loss, operative time, and bowel resection with stoma as the most significant prediction features. The real-time prediction accuracy of the Graphical User Interface CCU calculator reached 95%. Limited, potentially modifiable, mostly intra-operative factors contributing to CCU admission were identified and suggest areas for targeted interventions. The accurate quantification of CCU admission patterns is critical information when counseling patients about peri-operative risks related to their cytoreductive surgery.

Sign in / Sign up

Export Citation Format

Share Document