Artificial Intelligence (AI) for Plant Talk: Connecting Plant Cell2cell Communication to Growth
- Beschreibung
Are you curious about how plants communicate and how artificial intelligence can help us understand it?
Join this hands-on interdisciplinary project that combines plant biology, image processing, and machine learning to explore how cells connect and influence plant growth!
No prior coding experience is required — the project is designed for both beginners and advanced students.
------------------------------------------------------------------
Project Overview:
Unlike animal cells, plant cells have rigid cell walls that give them defined shapes, form tissues, and protect against stresses such as insect bites, fungal invasion, or heat.
Yet, plants still need to transmit signals between cells — a process called cell-to-cell (Cell2Cell) communication.
Over millions of years, plants have evolved microscopic channels known as plasmodesmata that pass through their cell walls, allowing neighboring cells to exchange signals and molecules directly.
In this project, we will investigate how cell-to-cell communication relates to plant growth, focusing on rosette leaf development in Arabidopsis.
We already have datasets that include:
(a) Time-lapse images of leaf growth (fitness)
(b) Callose abundance (a key cell wall component) across various Arabidopsis mutants
(c) Cell-to-cell permeability measurements
Now it’s time to turn these data into insight using AI and machine learning — to analyze, predict, and visualize how communication between cells affects growth across different genotypes.
----------------------------------------------------------------------
What You’ll Do:
Use ImageJ or other image segmentation tools to extract leaf area from time-lapse images
Organize growth and communication data into a structured dataset
Train machine learning models to classify phenotypes with defective cell-to-cell communication
Build a predictive model using biological data from additional Arabidopsis mutants
- Projektzeitraum
- Wintersemester 2025/2026 und Sommersemester 2026
- Bewerbungszeitraum
- 13. bis 27.10.2025
- Durchführung
- nach Absprache
- Details zu Projektzeitraum und Durchführung
wir sind sehr flexibel mit diesem Projekt und können uns gerne nach dem Stundenplan der Interessenten richten.
- Studienfach
- offen für alle Studienfächer
- Betreuende
- Dr. Lin Xi, Prof. Dr. Waltraud Schulze
- Institut
- Institut für Biologie (190) (Systembiologie der Pflanze 190D)
- Sprache
- englisch
- Teilnehmendenanzahl
- min. 1, max. 2
- Arbeitsaufwand
-
ca. 120 Stunden pro Teilnehmende:r
| 4
ECTS-Punkte
Arbeitsaufwand (Stunden und ggf. ECTS) sind ungefähre Angaben. Die tatsächlich vergebenen ECTS-Punkte ergeben sich aus der tatsächlich geleisteten Arbeit.
- Für dieses Projekt ist ein Motivationsschreiben des Studierenden erforderlich
- Projektart
- theoretisch/nicht experimentell
- Lernziele
-
Die Teilnehmende lernen in diesem Projekt:
- Core skills in image processing and computer vision
- Applying ML（machine learning) techniques to different types of biological data
- Understanding plant phenotype quantitative analysis
- Cross-disciplinary problem-solving in biology and data science
- Anmerkungen für Studierende
- Dokument
- Schlagworte
- Pflanzen, Methoden, Datenanalyse (deskriptive Auswertung