AI Model for Predicting Anti-PD1 Response in Melanoma Using Multi-Omics Biomarkers
Related Experiment Video
Updated: May 6, 2026
Predictive Immune Modeling of Solid Tumors
Published on: February 25, 2020
Axel Gschwind1,2, Stephan Ossowski1,2
1Institute of Medical Genetics and Applied Genomics, University of Tübingen, 72076 Tübingen, Germany.
Background:
Immune checkpoint inhibitors (ICIs) have demonstrated significantly improved clinical efficacy in a minority of patients with advanced melanoma, whereas non-responders potentially suffer from severe side effects and delays in other treatment options. Predicting the response to anti-PD1 treatment in melanoma remains a challenge because the current FDA-approved gold standard, the nonsynonymous tumor mutation burden (nsTMB), offers limited accuracy.
Methods:
In this study, we developed a multi-omics-based machine learning model that integrates genomic and transcriptomic biomarkers to predict the response to anti-PD1 treatment in patients with advanced melanoma. We employed least absolute shrinkage and selection operator (LASSO) regression with 49 biomarkers extracted from tumor-normal whole-exome and RNA sequencing as input features. The performance of the multi-omics AI model was thoroughly compared to that of nsTMB alone and to models that use only genomic or transcriptomic biomarkers.
Results:
We used publicly available DNA and RNA-seq datasets of melanoma patients for the training and validation of our model, forming a meta-cohort of 449 patients for which the outcome was recorded as a RECIST score. The model substantially improved the prediction of anti-PD1 outcomes compared to nsTMB alone, with an ROC AUC of 0.7 in the training set and an ROC AUC of 0.64 in the test set. Using SHAP values, we demonstrated the explainability of the model's predictions on a per-sample basis.
Conclusions:
We demonstrated that models using only RNA-seq or multi-omics biomarkers outperformed nsTMB in predicting the response of melanoma patients to ICI. Furthermore, our machine learning approach improves clinical usability by providing explanations of its predictions on a per-patient basis. Our findings underscore the utility of multi-omics data for selecting patients for treatment with anti-PD1 drugs. However, to train clinical-grade AI models for routine applications, prospective studies collecting larger melanoma cohorts with consistent application of exome and RNA sequencing are required.
Insights
A new multi-omics AI model accurately predicts anti-PD1 treatment response in advanced melanoma patients. This approach outperforms current methods, offering better patient selection for immune checkpoint inhibitors (ICIs).
Area of Science:
- Oncology
- Genomics
- Bioinformatics
Background:
- Immune checkpoint inhibitors (ICIs) show variable efficacy in advanced melanoma.
- Predicting response to anti-PD1 therapy is challenging, with current methods like nonsynonymous tumor mutation burden (nsTMB) having limited accuracy.
- Non-responders face potential side effects and treatment delays.
Purpose of the Study:
- To develop and validate a multi-omics machine learning model for predicting anti-PD1 treatment response in advanced melanoma.
- To compare the predictive performance of the multi-omics model against nsTMB and models using only genomic or transcriptomic data.
Main Methods:
- A machine learning model was developed integrating genomic and transcriptomic biomarkers.
- Least absolute shrinkage and selection operator (LASSO) regression was used with 49 biomarkers from whole-exome and RNA sequencing data.
- Model performance was evaluated against nsTMB using ROC AUC on a meta-cohort of 449 melanoma patients.
Main Results:
- The multi-omics AI model demonstrated improved prediction of anti-PD1 outcomes compared to nsTMB alone.
- The model achieved an ROC AUC of 0.7 in the training set and 0.64 in the test set.
- Explainability of predictions was achieved using SHAP values on a per-sample basis.
Conclusions:
- Multi-omics and RNA-seq-based models outperform nsTMB in predicting melanoma response to ICIs.
- The machine learning approach enhances clinical usability through per-patient prediction explanations.
- Further prospective studies with larger cohorts are needed for clinical-grade AI model development.
