Back

A computational model of CAR T-cell immunotherapy predicts leukemia patient responses at remission, resistance, and relapse

Liu, L.; Ma, C.; Zhang, Z.; Chen, W.

2021-09-23 oncology
10.1101/2021.09.21.21263913 medRxiv
Show abstract

Adaptive CD19-targeted CAR (Chimeric Antigen Receptor) T-cell transfer has become a promising treatment for leukemia. Though patient responses vary across different clinical trials, there currently lacks reliable early diagnostic methods to predict patient responses to those novel therapies. Recently, computational models achieve to in silico depict patient responses, with prediction application being limited. We herein established a computational model of CAR T-cell therapy to recapitulate key cellular mechanisms and dynamics during treatment based on a set of clinical data from different CAR T-cell trials, and revealed critical determinants related to patient responses at remission, resistance, and relapse. Furthermore, we performed a clinical trial simulation using virtual patient cohorts generated based on real clinical patient dataset. With input of early-stage CAR T-cell dynamics, our model successfully predicted late responses of various virtual patients compared to clinical observance. In conclusion, our patient-based computational immuno-oncology model may inform clinical treatment and management.

Matching journals

The top 11 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.