Automated Assay of a Four-Protein Biomarker Panel for Improved Detection of Ovarian Cancer

Walker, Carol; Nguyen, Tuan-Minh; Jessel, Shlomit; Alvero, Ayesha B.; Silasi, Dan‐Arin; Rutherford, Thomas J.; Drăghici, Sorin; Mor, Gil

doi:10.3390/cancers13020325

Cited by 5 publications

(5 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MIF not only activates T‐lymphocytes but also impedes macrophage migration. 55 Its involvement extends across immune regulation, inflammation, tumour development and metabolic control. 56 Functioning as a pro‐inflammatory cytokine, MIF, primarily sourced from T cells, induces the production of inflammatory mediators, including TNF‐alpha, IL‐1 beta, IL‐6 and IL‐8.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Unravelling infiltrating T‐cell heterogeneity in kidney renal clear cell carcinoma: Integrative single‐cell and spatial transcriptomic profiling

Chen,

Zuo,

Huang

et al. 2024

J Cellular Molecular Medi

View full text Add to dashboard Cite

Kidney renal clear cell carcinoma (KIRC) pathogenesis intricately involves immune system dynamics, particularly the role of T cells within the tumour microenvironment. Through a multifaceted approach encompassing single‐cell RNA sequencing, spatial transcriptome analysis and bulk transcriptome profiling, we systematically explored the contribution of infiltrating T cells to KIRC heterogeneity. Employing high‐density weighted gene co‐expression network analysis (hdWGCNA), module scoring and machine learning, we identified a distinct signature of infiltrating T cell‐associated genes (ITSGs). Spatial transcriptomic data were analysed using robust cell type decomposition (RCTD) to uncover spatial interactions. Further analyses included enrichment assessments, immune infiltration evaluations and drug susceptibility predictions. Experimental validation involved PCR experiments, CCK‐8 assays, plate cloning assays, wound‐healing assays and Transwell assays. Six subpopulations of infiltrating and proliferating T cells were identified in KIRC, with notable dynamics observed in mid‐ to late‐stage disease progression. Spatial analysis revealed significant correlations between T cells and epithelial cells across varying distances within the tumour microenvironment. The ITSG‐based prognostic model demonstrated robust predictive capabilities, implicating these genes in immune modulation and metabolic pathways and offering prognostic insights into drug sensitivity for 12 KIRC treatment agents. Experimental validation underscored the functional relevance of PPIB in KIRC cell proliferation, invasion and migration. Our study comprehensively characterizes infiltrating T‐cell heterogeneity in KIRC using single‐cell RNA sequencing and spatial transcriptome data. The stable prognostic model based on ITSGs unveils infiltrating T cells' prognostic potential, shedding light on the immune microenvironment and offering avenues for personalized treatment and immunotherapy.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Among these, macrophage migration inhibitory factor (MIF) emerges as a cytokine with diverse functions. MIF not only activates T‐lymphocytes but also impedes macrophage migration 55 . Its involvement extends across immune regulation, inflammation, tumour development and metabolic control 56 .…”

Section: Discussionmentioning

confidence: 99%

Unravelling infiltrating T‐cell heterogeneity in kidney renal clear cell carcinoma: Integrative single‐cell and spatial transcriptomic profiling

Chen,

Zuo,

Huang

et al. 2024

J Cellular Molecular Medi

View full text Add to dashboard Cite

show abstract

“…Lastly, based on the modified six-protein panel we developed a five-protein signature—Proteomic Model 2017 (CA125, HE4, OPN, leptin and PRL) that revealed a c-index of 0.96 [ 36 ]. In 2021, Walker et al [ 46 ] re-evaluated the six-protein panel previously reported by their group [ 28 , 29 ]. Leptin and IGF-II, having the lowest sensitivity and specificity, were removed from the model.…”

Section: Discussionmentioning

confidence: 99%

“…CA125, MIF, OPN, and PRL were quantified using an automated multiplex platform and evaluated using four classification techniques. Their four-protein model yielded a c-index of 0.935 [ 46 ]. These results are of particular interest because the protein selection is identical with that of our Proteomic Model 2021.…”

Section: Discussionmentioning

confidence: 99%

Biomarker-Based Models for Preoperative Assessment of Adnexal Mass: A Multicenter Validation Study

Watrowski

Obermayr

Wallisch

et al. 2022

Cancers

View full text Add to dashboard Cite

Ovarian cancer (OC) is the most lethal genital malignancy in women. We aimed to develop and validate new proteomic-based models for non-invasive diagnosis of OC. We also compared them to the modified Risk of Ovarian Malignancy Algorithm (ROMA-50), the Copenhagen Index (CPH-I) and our earlier Proteomic Model 2017. Biomarkers were assessed using bead-based multiplex technology (Luminex®) in 356 women (250 with malignant and 106 with benign ovarian tumors) from five European centers. The training cohort included 279 women from three centers, and the validation cohort 77 women from two other centers. Of six previously studied serum proteins (CA125, HE4, osteopontin [OPN], prolactin, leptin, and macrophage migration inhibitory factor [MIF]), four contributed significantly to the Proteomic Model 2021 (CA125, OPN, prolactin, MIF), while leptin and HE4 were omitted by the algorithm. The Proteomic Model 2021 revealed a c-index of 0.98 (95% CI 0.96, 0.99) in the training cohort; however, in the validation cohort it only achieved a c-index of 0.82 (95% CI 0.72, 0.91). Adding patient age to the Proteomic Model 2021 constituted the Combined Model 2021, with a c-index of 0.99 (95% CI 0.97, 1) in the training cohort and a c-index of 0.86 (95% CI 0.78, 0.95) in the validation cohort. The Full Combined Model 2021 (all six proteins with age) yielded a c-index of 0.98 (95% CI 0.97, 0.99) in the training cohort and a c-index of 0.89 (95% CI 0.81, 0.97) in the validation cohort. The validation of our previous Proteomic Model 2017, as well as the ROMA-50 and CPH-I revealed a c-index of 0.9 (95% CI 0.82, 0.97), 0.54 (95% CI 0.38, 0.69) and 0.92 (95% CI 0.85, 0.98), respectively. In postmenopausal women, the three newly developed models all achieved a specificity of 1.00, a positive predictive value (PPV) of 1.00, and a sensitivity of >0.9. Performance in women under 50 years of age (c-index below 0.6) or with normal CA125 (c-index close to 0.5) was poor. CA125 and OPN had the best discriminating power as single markers. In summary, the CPH-I, the two combined 2021 Models, and the Proteomic Model 2017 showed satisfactory diagnostic accuracies, with no clear superiority of either model. Notably, although combining values of only four proteins with age, the Combined Model 2021 performed comparably to the Full Combined Model 2021. The models confirmed their exceptional diagnostic performance in women aged ≥50. All models outperformed the ROMA-50.

show abstract

“…Supporting or comparative runs can be performed with Random Forest Regression. For example, in the study of Walker et al [14], as a result of comparative training with K-Nearest Neighbor, Logistic Regression, and Random Forest algorithms, it was generally concluded that 'random forest and four concluded that 'using the whole protein gives the best results in most cases'. Gholamnezhad et al [15] studied that random forest regression can be used with new methods based on inverse modeling with different algorithms such as Bayesian Linear Regression.…”

Section: ) Random Forest Regressormentioning

confidence: 99%

Predicting binding affinity of drug molecules with Machine Learning: Acetylcholinesterase Enzyme Study

2023

Proceeding Book of 2nd International Conference on Frontiers in Academic Research ICFAR 2023

View full text Add to dashboard Cite

This study examines the machine learning studies on the acetylcholinesterase (AChE) enzyme and summarizes the results. The AChE enzyme is an enzyme that plays an important role in the nervous system and is responsible for the breakdown of a neurotransmitter called acetylcholine. Identifying potential drug candidates targeting the AChE enzyme is of great importance in the drug discovery process. In this study, the detection and evaluation of molecules interacting with the AChE enzyme were performed using machine learning techniques such as Support Vector Regressor, Random Forest Regressor, and Extreme Gradient Boosting. The results show that machine learning is an important tool for identifying and designing compounds that interact with the AChE enzyme. This work makes a valuable contribution to research focusing on the AChE enzyme in drug discovery and has the potential to develop more effective drugs in the future.

show abstract

Automated Assay of a Four-Protein Biomarker Panel for Improved Detection of Ovarian Cancer

Cited by 5 publications

References 43 publications

Unravelling infiltrating T‐cell heterogeneity in kidney renal clear cell carcinoma: Integrative single‐cell and spatial transcriptomic profiling

Unravelling infiltrating T‐cell heterogeneity in kidney renal clear cell carcinoma: Integrative single‐cell and spatial transcriptomic profiling

Biomarker-Based Models for Preoperative Assessment of Adnexal Mass: A Multicenter Validation Study

Predicting binding affinity of drug molecules with Machine Learning: Acetylcholinesterase Enzyme Study

Contact Info

Product

Resources

About