sparse-growth-curve: a Computational Pipeline for Parsing Cellular Growth Curves with Low Temporal Resolution

Abstract

Here, we introduce a Python-based repository, sparse-growth-curve, a software package designed for parsing cellular growth curves with low temporal resolution. The repository uses cell density and time data as the input, automatically separates different growth phases, calculates the exponential growth rates, and produces multiple graphs to aid in interpretation.

FIG 1

Overview of the process within sparse-growth-curve. (A) The input for the method (red open circles connected by dashed lines) is cell density X_i versus time t_i. Here, we use an imperfect and very sparse curve to illustrate the functionality of the software. (B) The output of the method is piecewise linear regression for each phase. The exponential phase is highlighted in red. The doubling rates are labeled. (C) The subdomains of the piecewise fit in plot B are determined through decision tree regression. Here, gray open circles and squares represent the instantaneous doubling rates calculated from the input data. Red solid squares represent the noise-removed rates versus time for decision tree regression. The state prediction (dashed line) ends up as a step function, and each step corresponds to a growth phase. (D) An extended feature of the sparse-growth-curve package is that the package imports experimental growth curves of multiple strains under multiple conditions. Exponential growth rates for all of the growth curves are calculated. The conversion of doubling rate γ to specific growth rate λ is λ = ln(2)γ. The solid lines are the interpolated connection mean growth rates, and the shaded areas indicate the range between the maximum and minimum growth rates.