Andreas Denger
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Interests
Andreas Denger has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Adina Vultur
The Wistar Institute, Philadelphia, PA 19104, USA
6 shared publications - Carsten Kummerow
Department of Biophysics, Saarland University, Homburg, Germany
6 shared publications Christian Ickes
6 shared publications- Christine Silvia Gibhardt
Molecular Physiology, Institute of Cardiovascular Physiology, University Medical Center, Georg-August-University, Göttingen, Germany
6 shared publications Gabriela Salinas
6 shared publicationsHedwig Stanisz
6 shared publications
Latest Publications
- Open Access
Application of Protein Structure Encodings and Sequence Embeddings for Transporter Substrate Prediction
Membrane transporters play a crucial role in any cell. Identifying the substrates they translocate across membranes is important for many fields of research, such as metabolomics, pharmacology, and biotechnology. In this study, we leverage recent advances in deep learning, such as amino acid sequence embeddings with protein language models (pLMs), highly accurate 3D structure predictions with AlphaFold 2, and structure-encoding 3Di sequences from FoldSeek, for predicting substrates of membrane transporters. We test new deep learning features derived from both sequence and structure, and compare them to the previously best-performing protein encodings, which were made up of amino acid k-mer frequencies and evolutionary information from PSSMs. Furthermore, we compare the performance of these features either using a previously developed SVM model, or with a regularized feedforward neural network (FNN). When evaluating these models on sugar and amino acid carriers in A. thaliana, as well as on three types of ion channels in human, we found that both the DL-based features and the FNN model led to a better and more consistent classification performance compared to previous methods. Direct encodings of 3D structures with Foldseek, as well as structural embeddings with ProstT5, matched the performance of state-of-the-art amino acid sequence embeddings calculated with the ProtT5-XL model when used as input for the FNN classifier.
Open AccessApplication of Protein Structure Encodings and Sequence Embeddings for Transporter Substrate Prediction
Membrane transporters play a crucial role in any cell. Identifying the substrates they translocate across membranes is important for many fields of research, such as metabolomics, pharmacology, and biotechnology. In this study, we leverage recent advances in deep learning, such as amino acid sequence embeddings with protein language models (pLMs), highly accurate 3D structure predictions with AlphaFold 2, and structure-encoding 3Di sequences from FoldSeek, for predicting substrates of membrane transporters. We test new deep learning features derived from both sequence and structure, and compare them to the previously best-performing protein encodings, which were made up of amino acid k-mer frequencies and evolutionary information from PSSMs. Furthermore, we compare the performance of these features either using a previously developed SVM model, or with a regularized feedforward neural network (FNN). When evaluating these models on sugar and amino acid carriers in A. thaliana, as well as on three types of ion channels in human, we found that both the DL-based features and the FNN model led to a better and more consistent classification performance compared to previous methods. Direct encodings of 3D structures with Foldseek, as well as structural embeddings with ProstT5, matched the performance of state-of-the-art amino acid sequence embeddings calculated with the ProtT5-XL model when used as input for the FNN classifier.
- Open Access
- 19 December 2024
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 19 (12) , e0315330
Identifying optimal substrate classes of membrane transporters
Membrane transporters are responsible for moving a wide variety of molecules across biological membranes, making them integral to key biological pathways in all organisms. Identifying all membrane transporters within a (meta-)proteome, along with their specific substrates, provides important information for various research fields, including biotechnology, pharmacology, and metabolomics. Protein datasets are frequently annotated with thousands of molecular functions that form complex networks, often with partial or full redundancy and hierarchical relationships. This complexity, along with the low sample count for more specific functions, makes them unsuitable as classes for supervised learning methods, meaning that the creation of an optimal subset of annotations is required. However, selection of this subset requires extensive manual effort, along with knowledge about the biology behind the respective functions. Here, we present an automated pipeline to address this problem. Unlike previous approaches for reducing redundancy in GO datasets, we employ machine learning to identify a subset of functional annotations in a training dataset. Classes in the resulting predictive model meet four essential criteria: sufficient sample size for training predictive models, minimal redundancy, strong class separability, and relevance to substrate transport. Furthermore, we implemented a pipeline for creating training datasets of transmembrane transporters that cover a wide range of organisms, including plants, bacteria, mammals, and single-cell eukaryotes. For a dataset containing 98.1% of transporters from S. cerevisiae, the pipeline automatically reduced the number of functional annotations from 287 to 11 GO terms that could be classified with a median pairwise F1 score of 0.87±0.16. For a meta-organism dataset containing 96% of all transport proteins from S. cerevisiae, A. thaliana, E. coli and human, the number of classes was reduced from 695 to 49, with a median F1 score of 0.92±0.10 between pairs of GO terms. When lowering the percentage of covered proteins down to 67%, the pipeline found a subset of 30 GO terms with a median F1 score of 0.95±0.06.
- 19 December 2024
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 19 (12) , e0315330
Open AccessIdentifying optimal substrate classes of membrane transporters
Membrane transporters are responsible for moving a wide variety of molecules across biological membranes, making them integral to key biological pathways in all organisms. Identifying all membrane transporters within a (meta-)proteome, along with their specific substrates, provides important information for various research fields, including biotechnology, pharmacology, and metabolomics. Protein datasets are frequently annotated with thousands of molecular functions that form complex networks, often with partial or full redundancy and hierarchical relationships. This complexity, along with the low sample count for more specific functions, makes them unsuitable as classes for supervised learning methods, meaning that the creation of an optimal subset of annotations is required. However, selection of this subset requires extensive manual effort, along with knowledge about the biology behind the respective functions. Here, we present an automated pipeline to address this problem. Unlike previous approaches for reducing redundancy in GO datasets, we employ machine learning to identify a subset of functional annotations in a training dataset. Classes in the resulting predictive model meet four essential criteria: sufficient sample size for training predictive models, minimal redundancy, strong class separability, and relevance to substrate transport. Furthermore, we implemented a pipeline for creating training datasets of transmembrane transporters that cover a wide range of organisms, including plants, bacteria, mammals, and single-cell eukaryotes. For a dataset containing 98.1% of transporters from S. cerevisiae, the pipeline automatically reduced the number of functional annotations from 287 to 11 GO terms that could be classified with a median pairwise F1 score of 0.87±0.16. For a meta-organism dataset containing 96% of all transport proteins from S. cerevisiae, A. thaliana, E. coli and human, the number of classes was reduced from 695 to 49, with a median F1 score of 0.92±0.10 between pairs of GO terms. When lowering the percentage of covered proteins down to 67%, the pipeline found a subset of 30 GO terms with a median F1 score of 0.95±0.06.
- Open Access
- 31 March 2023
- Published by American Association for Cancer Research (AACR)
Supplementary Files 1-11 from Protein Signatures of NK Cell–Mediated Melanoma Killing Predict Response to Immunotherapies
A file containing RPPA and RNAseq datasets, pathway analyses and prediction calculations presented in the main figures.
- 31 March 2023
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Files 1-11 from Protein Signatures of NK Cell–Mediated Melanoma Killing Predict Response to Immunotherapies
A file containing RPPA and RNAseq datasets, pathway analyses and prediction calculations presented in the main figures.
- Open Access
- 31 March 2023
- Published by American Association for Cancer Research (AACR)
Supplementary Figures from Protein Signatures of NK Cell–Mediated Melanoma Killing Predict Response to Immunotherapies
A file containing supplementary figures 1-8 and the supplementary table S1.
- 31 March 2023
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Figures from Protein Signatures of NK Cell–Mediated Melanoma Killing Predict Response to Immunotherapies
A file containing supplementary figures 1-8 and the supplementary table S1.
- Open Access
- 31 March 2023
- Published by American Association for Cancer Research (AACR)
Supplementary Files 1-11 from Protein Signatures of NK Cell–Mediated Melanoma Killing Predict Response to Immunotherapies
A file containing RPPA and RNAseq datasets, pathway analyses and prediction calculations presented in the main figures.
- 31 March 2023
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Files 1-11 from Protein Signatures of NK Cell–Mediated Melanoma Killing Predict Response to Immunotherapies
A file containing RPPA and RNAseq datasets, pathway analyses and prediction calculations presented in the main figures.
- Open Access
- 31 March 2023
- Published by American Association for Cancer Research (AACR)
Supplementary Figures from Protein Signatures of NK Cell–Mediated Melanoma Killing Predict Response to Immunotherapies
A file containing supplementary figures 1-8 and the supplementary table S1.
- 31 March 2023
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Figures from Protein Signatures of NK Cell–Mediated Melanoma Killing Predict Response to Immunotherapies
A file containing supplementary figures 1-8 and the supplementary table S1.
- Open Access
- 31 March 2023
- Published by American Association for Cancer Research (AACR)
Data from Protein Signatures of NK Cell–Mediated Melanoma Killing Predict Response to Immunotherapies
Despite impressive advances in melanoma-directed immunotherapies, resistance is common and many patients still succumb to metastatic disease. In this context, harnessing natural killer (NK) cells, which have thus far been sidelined in the development of melanoma immunotherapy, could provide therapeutic benefits for cancer treatment. To identify molecular determinants of NK cell–mediated melanoma killing (NKmK), we quantified NK-cell cytotoxicity against a panel of genetically diverse melanoma cell lines and observed highly heterogeneous susceptibility. Melanoma protein microarrays revealed a correlation between NKmK and the abundance and activity of a subset of proteins, including several metabolic factors. Oxidative phoshorylation, measured by oxygen consumption rate, negatively correlated with melanoma cell sensitivity toward NKmK, and proteins involved in mitochondrial metabolism and epithelial–mesenchymal transition were confirmed to regulate NKmK. Two- and three-dimensional killing assays and melanoma xenografts established that the PI3K/AKT/mTOR signaling axis controls NKmK via regulation of NK cell–relevant surface proteins. A “protein-killing-signature” based on the protein analysis predicted NKmK of additional melanoma cell lines and the response of patients with melanoma to anti-PD-1 checkpoint therapy. Collectively, these findings identify novel NK cell–related prognostic biomarkers and may contribute to improved and personalized melanoma-directed immunotherapies.Significance:NK-cell cytotoxicity assays and protein microarrays reveal novel biomarkers of NK cell–mediated melanoma killing and enable development of signatures to predict melanoma patient responsiveness to immunotherapies.
- 31 March 2023
- Published by American Association for Cancer Research (AACR)
Open AccessData from Protein Signatures of NK Cell–Mediated Melanoma Killing Predict Response to Immunotherapies
Despite impressive advances in melanoma-directed immunotherapies, resistance is common and many patients still succumb to metastatic disease. In this context, harnessing natural killer (NK) cells, which have thus far been sidelined in the development of melanoma immunotherapy, could provide therapeutic benefits for cancer treatment. To identify molecular determinants of NK cell–mediated melanoma killing (NKmK), we quantified NK-cell cytotoxicity against a panel of genetically diverse melanoma cell lines and observed highly heterogeneous susceptibility. Melanoma protein microarrays revealed a correlation between NKmK and the abundance and activity of a subset of proteins, including several metabolic factors. Oxidative phoshorylation, measured by oxygen consumption rate, negatively correlated with melanoma cell sensitivity toward NKmK, and proteins involved in mitochondrial metabolism and epithelial–mesenchymal transition were confirmed to regulate NKmK. Two- and three-dimensional killing assays and melanoma xenografts established that the PI3K/AKT/mTOR signaling axis controls NKmK via regulation of NK cell–relevant surface proteins. A “protein-killing-signature” based on the protein analysis predicted NKmK of additional melanoma cell lines and the response of patients with melanoma to anti-PD-1 checkpoint therapy. Collectively, these findings identify novel NK cell–related prognostic biomarkers and may contribute to improved and personalized melanoma-directed immunotherapies.Significance:NK-cell cytotoxicity assays and protein microarrays reveal novel biomarkers of NK cell–mediated melanoma killing and enable development of signatures to predict melanoma patient responsiveness to immunotherapies.
- 1 December 2022
- Published by American Chemical Society (ACS) in Journal of Chemical Information and Modeling
- Vol. 62 (23) , 6242-6257
Optimized Data Set and Feature Construction for Substrate Prediction of Membrane Transporters
- 1 December 2022
- Published by American Chemical Society (ACS) in Journal of Chemical Information and Modeling
- Vol. 62 (23) , 6242-6257
Optimized Data Set and Feature Construction for Substrate Prediction of Membrane Transporters
- Open Access
- 13 September 2021
- Published by American Association for Cancer Research (AACR) in Cancer Research
- Vol. 81 (21) , 5540-5554
Protein Signatures of NK Cell–Mediated Melanoma Killing Predict Response to Immunotherapies
Despite impressive advances in melanoma-directed immunotherapies, resistance is common and many patients still succumb to metastatic disease. In this context, harnessing natural killer (NK) cells, which have thus far been sidelined in the development of melanoma immunotherapy, could provide therapeutic benefits for cancer treatment. To identify molecular determinants of NK cell–mediated melanoma killing (NKmK), we quantified NK-cell cytotoxicity against a panel of genetically diverse melanoma cell lines and observed highly heterogeneous susceptibility. Melanoma protein microarrays revealed a correlation between NKmK and the abundance and activity of a subset of proteins, including several metabolic factors. Oxidative phoshorylation, measured by oxygen consumption rate, negatively correlated with melanoma cell sensitivity toward NKmK, and proteins involved in mitochondrial metabolism and epithelial–mesenchymal transition were confirmed to regulate NKmK. Two- and three-dimensional killing assays and melanoma xenografts established that the PI3K/AKT/mTOR signaling axis controls NKmK via regulation of NK cell–relevant surface proteins. A “protein-killing-signature” based on the protein analysis predicted NKmK of additional melanoma cell lines and the response of patients with melanoma to anti-PD-1 checkpoint therapy. Collectively, these findings identify novel NK cell–related prognostic biomarkers and may contribute to improved and personalized melanoma-directed immunotherapies. Significance: NK-cell cytotoxicity assays and protein microarrays reveal novel biomarkers of NK cell–mediated melanoma killing and enable development of signatures to predict melanoma patient responsiveness to immunotherapies.
- 13 September 2021
- Published by American Association for Cancer Research (AACR) in Cancer Research
- Vol. 81 (21) , 5540-5554
Open AccessProtein Signatures of NK Cell–Mediated Melanoma Killing Predict Response to Immunotherapies
Despite impressive advances in melanoma-directed immunotherapies, resistance is common and many patients still succumb to metastatic disease. In this context, harnessing natural killer (NK) cells, which have thus far been sidelined in the development of melanoma immunotherapy, could provide therapeutic benefits for cancer treatment. To identify molecular determinants of NK cell–mediated melanoma killing (NKmK), we quantified NK-cell cytotoxicity against a panel of genetically diverse melanoma cell lines and observed highly heterogeneous susceptibility. Melanoma protein microarrays revealed a correlation between NKmK and the abundance and activity of a subset of proteins, including several metabolic factors. Oxidative phoshorylation, measured by oxygen consumption rate, negatively correlated with melanoma cell sensitivity toward NKmK, and proteins involved in mitochondrial metabolism and epithelial–mesenchymal transition were confirmed to regulate NKmK. Two- and three-dimensional killing assays and melanoma xenografts established that the PI3K/AKT/mTOR signaling axis controls NKmK via regulation of NK cell–relevant surface proteins. A “protein-killing-signature” based on the protein analysis predicted NKmK of additional melanoma cell lines and the response of patients with melanoma to anti-PD-1 checkpoint therapy. Collectively, these findings identify novel NK cell–related prognostic biomarkers and may contribute to improved and personalized melanoma-directed immunotherapies. Significance: NK-cell cytotoxicity assays and protein microarrays reveal novel biomarkers of NK cell–mediated melanoma killing and enable development of signatures to predict melanoma patient responsiveness to immunotherapies.