Protein-protein interaction prediction for targeted protein degradation

Orasch, Oliver; Weber, Noah; Müller, Michael G.; Amanzadi, Amir; Gasbarri, Chiara; Trummer, Christopher

doi:10.1101/2022.02.25.481776

Cited by 4 publications

(3 citation statements)

References 57 publications

(64 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Predicting the binding affinities between two protein partners in a high throughput fashion is still an open challenge. However, protein-protein decoy generation and ranking algorithms, both physics-based and ML-based, show promise in finding the most likely complexes formed between two proteins 70,[84][85][86][87][88] . These complexes then need to be evaluated by their ability to bind and to be stabilized by small molecules.…”

Section: Concluding Discussionmentioning

confidence: 99%

“…Inspired by the MaSIF and dMaSIF protein-protein interaction prediction workflow, Orasch and coworkers 88 devised an DL model that learns the most suitable embeddings for predicting protein-protein interactions using point cloud representation of protein surfaces together with precomputed features. They trained this model using the MaSIF dataset and a more diverse orthogonal dataset and then applied it to predict protein-protein interfaces formed upon PROTAC binding.…”

Section: Computational Approaches For Identifying Weak Protein-protei...mentioning

confidence: 99%

See 1 more Smart Citation

Protein–protein interfaces in molecular glue-induced ternary complexes: classification, characterization, and prediction

et al. 2023

View full text Add to dashboard Cite

show abstract

Section: Concluding Discussionmentioning

confidence: 99%

Section: Computational Approaches For Identifying Weak Protein-protei...mentioning

confidence: 99%

Protein–protein interfaces in molecular glue-induced ternary complexes: classification, characterization, and prediction

et al. 2023

View full text Add to dashboard Cite

show abstract

“…However, experimental methods to detect PPI sites are both costly and time-intensive. In recent years, computer-aided approaches have been developed as screening tools, but these tools are primarily based on sequence information and are therefore limited in their ability to address spatial requirements and have thus far not been applied to targeted protein degradation (Orasch et al, 2022).…”

Section: Discussionmentioning

confidence: 99%

Glypican-3, Vascular Endothelial Growth Factor and Golgi Protein-73 for Differentiation between Liver Cirrhosis and Hepatocellular Carcinoma

Mamdouh

Soliman

Khorshed

et al. 2023

Asian Pac J Cancer Prev

View full text Add to dashboard Cite

Background: Hepatocellular carcinoma (HCC) accounts for more than 80% of primary liver cancers. Moreover, in the next 10 years, more than one million patients are expected to die from liver cancer as estimated by the World Health Organization. The aim of the present study is to evaluate the clinical utility of using Glypican (GPC3), Vascular endothelial growth factor (VEGF) and Golgi protein 73 (GP73) in serum by Enzyme-Linked Immunosorbent Assay (ELISA) and by Real-Time Polymerase Chain Reaction (RT-PCR), as diagnostic markers to differentiate HCC from cirrhotic liver disease. Methods: A total of 50 patients with histologically-proven HCC, 50 liver cirrhosis patients and 20 healthy volunteers as controls were enrolled in this study, blood samples were obtained from each patient. Expression of the studied biomarkers was evaluated by ELISA and Real-Time PCR. Results: Statistical analysis of RT-PCR results showed that the expression of GPC3, VEGF and GP73 in serum of patients with HCC was significant (P value < 0.001, 0.01, and < 0.001) respectively and increased when compared to the cirrhotic group. Furthermore, the serum protein levels of GPC3 and VEGF in HCC and cirrhotic patients were significant when compared to the control group. While no significance was found between HCC and cirrhotic group. The serum protein level of GP73 was significantly increased in HCC and cirrhosis groups compared to the control group (P value < 0.001). Moreover, a significant increase was evident in HCC group compared to cirrhotic group (P value < 0.001). The results of the present study showed that the combination of VEGF and GP73 could discriminate HCC from cirrhosis. Conclusion: GPC3, VEGF and GP73 are reliable biomarkers for diagnosis of HCC. The serum level of GP73 is a potential screening marker for discriminating HCC from liver cirrhosis.

show abstract

An Ensemble Classifiers for Improved Prediction of Native–Non-Native Protein–Protein Interaction

Pratiwi,

Tayara,

Chong

2024

IJMS

View full text Add to dashboard Cite

In this study, we present an innovative approach to improve the prediction of protein–protein interactions (PPIs) through the utilization of an ensemble classifier, specifically focusing on distinguishing between native and non-native interactions. Leveraging the strengths of various base models, including random forest, gradient boosting, extreme gradient boosting, and light gradient boosting, our ensemble classifier integrates these diverse predictions using a logistic regression meta-classifier. Our model was evaluated using a comprehensive dataset generated from molecular dynamics simulations. While the gains in AUC and other metrics might seem modest, they contribute to a model that is more robust, consistent, and adaptable. To assess the effectiveness of various approaches, we compared the performance of logistic regression to four baseline models. Our results indicate that logistic regression consistently underperforms across all evaluated metrics. This suggests that it may not be well-suited to capture the complex relationships within this dataset. Tree-based models, on the other hand, appear to be more effective for problems involving molecular dynamics simulations. Extreme gradient boosting (XGBoost) and light gradient boosting (LightGBM) are optimized for performance and speed, handling datasets effectively and incorporating regularizations to avoid over-fitting. Our findings indicate that the ensemble method enhances the predictive capability of PPIs, offering a promising tool for computational biology and drug discovery by accurately identifying potential interaction sites and facilitating the understanding of complex protein functions within biological systems.

show abstract

Protein-protein interaction prediction for targeted protein degradation

Cited by 4 publications

References 57 publications

Protein–protein interfaces in molecular glue-induced ternary complexes: classification, characterization, and prediction

Protein–protein interfaces in molecular glue-induced ternary complexes: classification, characterization, and prediction

Glypican-3, Vascular Endothelial Growth Factor and Golgi Protein-73 for Differentiation between Liver Cirrhosis and Hepatocellular Carcinoma

An Ensemble Classifiers for Improved Prediction of Native–Non-Native Protein–Protein Interaction

Contact Info

Product

Resources

About