Regression plane concept for analysing continuous cellular processes with machine learning.
Abel SzkalisityFilippo PiccininiAttila BeleonTamas BalassaIstvan Gergely VargaEde MighCsaba MolnarLassi PaavolainenSanna TimonenIndranil BanerjeeElina IkonenYohei YamauchiIstvan AndoJaakko PeltonenVilja PietiäinenViktor HontiPeter HorvathPublished in: Nature communications (2021)
Biological processes are inherently continuous, and the chance of phenotypic discovery is significantly restricted by discretising them. Using multi-parametric active regression we introduce the Regression Plane (RP), a user-friendly discovery tool enabling class-free phenotypic supervised machine learning, to describe and explore biological data in a continuous manner. First, we compare traditional classification with regression in a simulated experimental setup. Second, we use our framework to identify genes involved in regulating triglyceride levels in human cells. Subsequently, we analyse a time-lapse dataset on mitosis to demonstrate that the proposed methodology is capable of modelling complex processes at infinite resolution. Finally, we show that hemocyte differentiation in Drosophila melanogaster has continuous characteristics.