Sequencing data from enrichment against vWF-A1 domain and peptide targets

Sequence files from enrichments against Von Willebrand factor domain A1 (wild type and mutant 2B) and two 30 mer peptide regions across the mutable region on the domain. There are 3 sequence files - Training, Holdout and Raw Sequences. Training sequences were used to train a sequence model and the holdout sequences were used to validate the model. The Raw sequences are the training and holdout sequences combined. A label map is included. The pre-trained sequence model is also included which can be used to create the UMAP representations as shown in the study. The pre-trained model can also be used to fine-tune classifiers, then these fine-tuned classifiers can be tested with holdout sequences as a validation.