Hello! Thanks for developing this wonderful tool. I recently came across your Molecular Systems Biology paper, and would love to try out TcellMatch on a set of TCRs from a 10x Single Cell Immune Profiling kit. We are hoping to see if we find any hits for the antigen specificity of the TCR sequences.
In particular, I was just looking at your tutorials, and trying to figure out which would be best for my use case. I saw that the paper mentions availability of a pre-trained model:
To facilitate the usage of our predictive algorithms, we built the Python package TcellMatch, which hosts a pre-trained model zoo for analysts to impute pMHC-derived antigen specificities and allows the transfer and re-training of models on new data sets.
Would you advise I follow the tutorials to train your model using the referenced IEDB or 10x data sets, and then run the trained model on my own 10x data, or is there a pre-trained option I should be using? Thanks for your help!
Hello! Thanks for developing this wonderful tool. I recently came across your Molecular Systems Biology paper, and would love to try out TcellMatch on a set of TCRs from a 10x Single Cell Immune Profiling kit. We are hoping to see if we find any hits for the antigen specificity of the TCR sequences. In particular, I was just looking at your tutorials, and trying to figure out which would be best for my use case. I saw that the paper mentions availability of a pre-trained model:
Would you advise I follow the tutorials to train your model using the referenced IEDB or 10x data sets, and then run the trained model on my own 10x data, or is there a pre-trained option I should be using? Thanks for your help!