Atlas of virus specific CD8+ Tcells

<p>Code and Data accompanying the manuscript &quot; &quot;</p> <p><strong>TS logistic regression&nbsp;model:</strong></p> <ul> <li>TargetScape_Model_FCS_Input.zip&nbsp;contains the TS data in pickled format to be imported in python</li> <li>targetscape-model-paper-20221001.html contains the python code to perform data analysis, model training, testing and interpretation</li> </ul> <p><strong>TAP logistic regression model:</strong></p> <ul> <li>Generate_Pseudobulk_Markers_ADT_TAP_Cohort.R to generate candidate features by pseudo-bulking surface markers across donors.</li> <li>TAP_ParameterBenchmarking_Model_Training_Evaluation.R to perform model training and parameter benchmark.</li> <li>TAP_DiscoveryCohort_Epitopes.rds file containing a Seurat object of the TAP-Cohort.</li> <li>Cohort_Pseudobulk_ADT_Virus_markers.RDS RDS file containing the candidate markers and their fold-changes/p-values, generated by<em>&nbsp;Generate_Pseudobulk_Markers_ADT_TAP_Cohort.R</em></li> <li><a href="https://zenodo.org/api/files/e8452b8d-5749-4f08-be29-b9c0922a5727/Leave-one-epitope-out-TAP.R">Leave-one-epitope-out-TAP.R</a>: R script to train a model using one epitope as a validation set.</li> </ul> <p><strong>Figures related to Machine Learning approaches:</strong></p> <ul> <li>Model_Analysis_Figure_Table_Generation.R script to generate Figures 3 and Figure 4 of the main manuscript as well as corresponding Supplementary Figures</li> <li>TargetScapeModel_Feature_Importance.csv contains the regression coefficients of the model learned on TargetScape (TS) data.</li> <li>TargetScape_Cohort_Logicle.csv contains the actual data of the TS cohort after logicle transformation.</li> <li>TargetScape_Validation_Cohort_Logicle.csv contains the actual data of the TS validation cohort after logicle transformation</li> <li>TargetScape_Model_Predictions.csv contains predictions of the TS model made on the TS validation cohort</li> <li>Performance_Benchmarking_TAP.zip&nbsp;contains all parameter benchmarking performance files generated by the TAP model above while executing&nbsp;TAP_ParameterBenchmarking_Model_Training_Evaluation<em>.R.</em></li> <li>Performance_Selected_Model.txt contains model performance information on the selected TAP model</li> <li>TAP_Model_MultinomialElaNetLogRegModel_minCellsPerPatient_30_minCellsPerVirus_200_ResourcePaper.RDS contains the best model trained on TAP data.</li> <li>TAP-Validation.RDS contains the Seurat object of the TAP validation cohort.</li> </ul>