PyEvoCell: An LLM- Augmented Single Cell Trajectory Analysis Dashboard

Abstract

MotivationSeveral methods have been developed for trajectory inference in single cell studies. However, identifying relevant lineages among several celltypes is a challenging task and requires deep understanding of various celltype transitions and progression patterns. Therefore, there is a need for methods that can aid researchers in the analysis and interpretation of such trajectories. ResultsWe developed PyEvoCell, a dashboard for trajectory interpretation and analysis that is augmented by large language model (LLM) capabilities. PyEvoCell applies the LLM to the outputs of trajectory inference methods such as Monocle3, to suggest biologically relevant lineages. Once a lineage is defined, users can conduct differential expression and functional analyses which are also interpreted by the LLM. Finally, any hypothesis or claim derived from the analysis can be validated using the veracity filter, a feature enabled by the LLM, to confirm or reject claims by providing relevant PubMed citations. Software Availability and ImplementationThe software is available at https://github.com/Sanofi-Public/PyEvoCell. It contains installation instructions, user manual, demo datasets, as well as license conditions (including limitation to non-commercial uses only). Supplementary informationSupplementary information is attached.