challenge 2020

The results of the AnDi challenge 2020 are in the paper: Muñoz-Gil et al. Objective comparison of methods to decode anomalous diffusion, arXiv:2105.06766, 2021.

Objective and tasks

The competition was aimed to assess the performance of methods in quantifying anomalous diffusion, with respect to three different tasks:

  • T1 – anomalous exponent inference
  • T2 – model classification
  • T3 – trajectory segmentation

each for 1D, 2D, and 3D trajectories. The performance was assessed with common metrics on simulated datasets with trajectory length and signal-to-noise level reproducing realistic experimental conditions. The submitted methods were also compared on the blind analysis of experimental trajectories.

Participants

team/softwaremethodtask1task2task3platformopen accesscontact
Anomalous Unicorns
HYDRAS
Ensemble of CNN and RNN1D1D-PythonGitHubBorja Requena
ICFO-The Institute of Photonic Sciences
Castelldefels (Barcelona), Spain
BITBayesian inference1D+2D+3D1D+2D+3D1D+2D+3DMatlabGitHubMichael A. Lomholt
PhyLife, Department of Physics, Chemistry and Pharmacy,
University of Southern Denmark
Odense M, Denmark
DecBayComp
Gratin
Graph neural network1D1D-PythonGitHubJean-Baptiste Masson
Institut Pasteur, Decision and Bayesian Computation lab
Paris, France
DeepSPTResNet + XGBoost1D1DPythonGitHubTaegeun Song
Center for AI and Natural Sciences, Korea Institute for Advanced Study
Seoul, Korea
eduN
RANDI
RNN + Dense NN1D+2D+3D1D+2D+3D1D+2D+3DPythonGitHubStefano Bo
Max Planck Institute for the Physics of Complex Systems (MPI-PKS)
Dresden, Germany
Erasmus MC
FEST
bi-LSTM + Dense NN1D+2D+3D1D+2D+3DPythonGitHubHélène Kabbech
Erasmus MC, Department of Cell Biology
Rotterdam, The Netherlands
FCICNN1D+2D1D+2D1D+2DPythonGitHubTom Bland
The Francis Crick Institute
London, UK
HNU
Just LSTM it
LSTM1D+2D+3DPythonGitHub

Zihan Huang
School of Physics and Electronics, Hunan University
Changsha, China
NOACNN + bi-LSTM1DPythonGitHub
Jose Alberto Conejero
Instituto Universitario de Matemática Pura y Aplicada, Universitat Politècnica de València
Valencia, Spain
QuBI
AnDi-ELM
ELM1D1DMatlabGitHubCarlo Manzo
Facultat de Ciències i Tecnologia, UVIC-UCC
Vic, Spain
TSAScaling analysis and feature engineering1D+2D+3D1DPythonGitHubErez Aghion
Max Planck Institute for the Physics of Complex Systems (MPI-PKS)
Dresden, Germany
UCL
CONDOR
Feature engineering + NN1D+2D+3D1D+2D+3DMatlabGitHubGiorgio Volpe
Department of Chemistry, University College London
London, UK
UPV-MATCNN + bi-LSTM1D+2D+3D1D+2D+3DPythonGitHub
Òscar Garibo i Orts
Instituto Universitario de Matemática Pura y Aplicada, Universitat Politècnica de València
Valencia, Spain
Wust ML A1D: RISE + forest classi er
2D: MrSEQL + logistic reg.
1D+2D+3DPythonGitHub Janusz Szwabiński
Faculty of Pure and Applied Mathematics, Wrocław University of Science
and Technology
Wrocław, Poland
Wust ML BGradient boosting regression + classifier1D+2D1D+2D+3DPythonT1: GitHub
T2: GitHub
Hanna Loch-Olszewska & Patrycja Kowalek
Faculty of Pure and Applied Mathematics, Wrocław University of Science and Technology
Wrocław, Poland

Datasets

For the final phase of the competitions, methods were evaluated over the test dataset 2020. Datasets were simulated using the andi-datasets package.