Biology subjects

Schumacher, T.

Publications and source records attributed to Schumacher, T..

5 recordsLinked to original sources

bioRxiv2025

A functionally validated TCR-pMHC database for TCR specificity model development

Accurate prediction of TCR specificity forms a holy grail in immunology and large language models and computational structure predictions provide a path to achieve this. Importantly, current TCR-pMHC prediction models have been trained and evaluated using historical data of unknown quality. Here, we develop and utilize a high-throughput synthetic platform for TCR assembly and evaluation to assess a large fraction of VDJdb-deposited TCR-pMHC entries using a standardized readout of TCR function. Strikingly, this analysis demonstrates that claimed TCR reactivity is only confirmed for 50% of evaluated entries. Intriguingly, the use of TCRbridge to analyze AlphaFold3 confidence metrics reveals a substantial performance in distinguishing functionally validating and non-validating TCRs even though AlphaFold3 was not trained on this task, demonstrating the utility of the validated VDJdb (TCRvdb) database that we generated. We provide TCRvdb as a resource to the community to support training and evaluation of improved predictive TCR specificity models.

immunology↗

bioRxiv2025

Temporal and spatial composition of the tumor microenvironment predicts response to immune checkpoint inhibition

Immune checkpoint inhibition (ICI) has fundamentally changed cancer treatment. However, only a minority of patients with metastatic triple negative breast cancer (TNBC) benefit from ICI, and the determinants of response remain largely unknown. To better understand the factors influencing patient outcome, we assembled a longitudinal cohort with tissue from multiple timepoints, including primary tumor, pre-treatment metastatic tumor, and on-treatment metastatic tumor from 117 patients treated with ICI (nivolumab) in the phase II TONIC trial. We used highly multiplexed imaging to quantify the subcellular localization of 37 proteins in each tumor. To extract meaningful information from the imaging data, we developed SpaceCat, a computational pipeline that quantifies features from imaging data such as cell density, cell diversity, spatial structure, and functional marker expression. We applied SpaceCat to 678 images from 294 tumors, generating more than 800 distinct features per tumor. Spatial features were more predictive of patient outcome, including features like the degree of mixing between cancer and immune cells, the diversity of the neighboring immune cells surrounding cancer cells, and the degree of T cell infiltration at the tumor border. Non-spatial features, including the ratio between T cell subsets and cancer cells and PD-L1 levels on myeloid cells, were also associated with patient outcome. Surprisingly, we did not identify robust predictors of response in the primary tumors. In contrast, the metastatic tumors had numerous features which predicted response. Some of these features, such as the cellular diversity at the tumor border, were shared across timepoints, but many of the features, such as T cell infiltration at the tumor border, were predictive of response at only a single timepoint. We trained multivariate models on all of the features in the dataset, finding that we could accurately predict patient outcome from the pre-treatment metastatic tumors, with improved performance using the on-treatment tumors. We validated our findings in matched bulk RNA-seq data, finding the most informative features from the on-treatment samples. Our study highlights the importance of profiling sequential tumor biopsies to understand the evolution of the tumor microenvironment, elucidating the temporal and spatial dynamics underlying patient responses and underscoring the need for further research on the prognostic role of metastatic tissue and its utility in stratifying patients for ICI.

cancer biology↗

bioRxiv2023

Gene and protein sequence features augment HLA class I ligand predictions

The sensitivity of malignant tissues to T cell-based cancer immunotherapies is dependent on the presence of targetable HLA class I ligands on the tumor cell surface. Peptide intrinsic factors, such as HLA class I affinity, likelihood of proteasomal processing, and transport into the ER lumen have all been established as determinants of HLA ligand presentation. However, the role of sequence features at the gene and protein level as determinants of epitope presentation has not been systematically evaluated. To address this, we performed HLA ligandome mass spectrometry on patient-derived melanoma lines and used this data-set to evaluate the contribution of 7,124 gene and protein sequence features to HLA sampling. This analysis reveals that a number of predicted modifiers of mRNA and protein abundance and turn-over, including predicted mRNA methylation and protein ubiquitination sites, inform on the presence of HLA ligands. Importantly, integration of gene and protein sequence features into a machine learning approach augments HLA ligand predictions to a comparable degree as predictive models that include experimental measures of gene expression. Our study highlights the value of gene and protein features to HLA ligand predictions.

immunology↗

bioRxiv2023

Lack of detectable neoantigen depletion in treatment-naive cancers

While neoantigen depletion, a form of immunoediting due to Darwinian pressure exerted by the T cell based immune system during tumor evolution, has been clearly described in murine models, its prevalence in treatment-naive, developing human tumors remains controversial. We developed two novel methodologies to test for depletion of predicted neoantigens in patient cohorts, which both compare patients in terms of their expected number of neoantigens per mutational event. Application of these strategies to TCGA patient cohorts showed that neither basic nor more extensive versions of the methodologies, controlling for confounding factors such as genomic loss of the HLA locus, provided statistically significant evidence for neoantigen depletion. In the subset of analyses that did show a trend towards neoantigen depletion, statistical significance was not reached and depletion was not consistently observed across HLA alleles. Our results challenge the notion that neoantigen depletion is detectable in cohorts of unmatched patient samples using HLA binding prediction-based methodology.

cancer biology↗

bioRxiv2023

STAPLER: Efficient learning of TCR-peptide specificity prediction from full-length TCR-peptide data

The prediction of peptide-MHC (pMHC) recognition by {beta} T-cell receptors (TCRs) remains a major biomedical challenge. Here, we develop STAPLER (Shared TCR And Peptide Language bidirectional Encoder Representations from transformers), a transformer language model that uses a joint TCR{beta}- peptide input to allow the learning of patterns within and between TCR{beta} and peptide sequences that encode recognition. First, we demonstrate how data leakage during negative data generation can confound performance estimates of neural network-based models in predicting TCR - pMHC specificity. We then demonstrate that, because of its pre-training and fine-tuning masked language modeling tasks, STAPLER outperforms both neural network-based and distance-based ML models in predicting the recognition of known antigens in an independent dataset, in particular for antigens for which little related data is available. Based on this ability to efficiently learn from limited labeled TCR- peptide data, STAPLER is well-suited to utilize growing TCR - pMHC datasets to achieve accurate prediction of TCR - pMHC specificity.

bioinformatics↗