Minor changes before publication in JOSS

docs/source/conf.py

@@ -15,7 +15,7 @@
 project = 'tracksegnet'
 copyright = '2024, H. Kabbech'
 author = 'H. Kabbech'
-release = '1.0.0'
+release = '1.3.0'
 
 # -- General configuration ---------------------------------------------------
 # https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration

docs/source/installation.md

@@ -1,13 +1,20 @@
-# Installation and requirements
+# Installation
 
-## Clone the repository
+## Installation with pip
 
-```bash
+```
+[sudo] pip install tracksegnet
+```
+
+## Installation from the GitHub repository and requirements
+
+- Clone the repository
+```
 git clone https://github.com/hkabbech/TrackSegNet.git
 cd TrackSegNet
 ```
 
-## Either create and run a docker container
+- Either create and run a docker container
 
 ```bash
 # Build a docker image (Rebuild the image after changing the parameters):
@@ -16,18 +23,17 @@ docker compose build
 docker compose run tracksegnet-env
 ```
 
-## Or create a virtual environment and install the packages
+- Or create a virtual environment and install the packages
 
-Requirement: python3.8 or equivalent and the virtualenv library
+Requirement: python={3.8, 3.9, 3.10} and the virtualenv library
 
 ```bash
 # Create the environment:
-python -m venv tracksegnet-env
-# virtualenv -p /usr/bin/python3 tracksegnet-env
+python -m venv tracksegnet-env # or virtualenv -p /usr/bin/python3 tracksegnet-env
 # Activate the environment:
-source ./tracksegnet-env/bin/activate # for Windows PowerShell: .\tracksegnet-env\Scripts\Activate.ps1 (run as administrator)
+ source ./tracksegnet-env/bin/activate # Or source ./tracksegnet-env/Scripts/activate for Windows. For PowerShell: .\tracksegnet-env\Scripts\Activate.ps1 (run as administrator)
 # Install the required python libraries:
-python -m pip install -r requirements.txt
+pip install -e . # or python -m pip install -r requirements.txt
 ```
 
 Note for later, to deactivate the virtual environment, type `deactivate`.

paper/paper.bib

@@ -37,15 +37,6 @@ @article{metzler2014
   publisher={Royal Society of Chemistry}
 }
 
-
-@misc{chollet2015,
-  title={Keras},
-  author={Chollet, F. and others},
-  year={2015},
-  howpublished={\url{https://keras.io}},
-}
-
-
 @article{lundahl1986,
   title={Fractional Brownian motion: A maximum likelihood estimator and its application to image texture},
   author={Lundahl, T. and Ohley, W. J. and Kay, S. M. and Siffert, R.},

paper/paper.md

@@ -1,22 +1,18 @@
 ---
 title: 'TrackSegNet: a tool for trajectory segmentation into diffusive states using supervised deep learning'
 tags:
-  - Python
   - single-particle tracking
   - trajectory segmentation
   - supervised deep learning
   - mean squared displacement
 authors:
   - name: Hélène Kabbech
     orcid: 0000-0002-9200-2112
-    affiliation: "1"
   - name: Ihor Smal
-    orcid: 0000-0001-7576-7028 
-    affiliation: "1"
+    orcid: 0000-0001-7576-7028
 affiliations:
  - name: Department of Cell Biology, Erasmus University Medical Center, Rotterdam, the Netherlands
-   index: 1
-date: 14 March 2023
+date: June 2024
 bibliography: paper.bib
 ---
 
@@ -40,7 +36,7 @@ This software is based on the method of @arts2019 with major improvements, makin
 
 Tracking particles from 2-dimensional images results in a set $\mathcal{S}$ of trajectories $r_i \in \mathcal{S}$, $i = \left\{1, \dots, P \right\}$,  where $P$ is the total number of trajectories, and $r_i(t) = (x_i(t), y_i(t))$ are the 2D coordinates of the particle $i$ at time $t$.
 
-The network is built using functions from the Keras library [@chollet2015], and is composed of a bidirectional long short-term memory (LSTM) layer (having 200 hidden units), followed by a fully connected time-distributed layer with a `SoftMax` activation function. The inputs of the network are of six trajectory features previously computed, while the outputs are probabilities for each trajectory point of belonging to one of the $N$ diffusive states, the predicted state is defined by the highest probability.
+The network is built using functions from the Keras library, and is composed of a bidirectional long short-term memory (LSTM) layer (having 200 hidden units), followed by a fully connected time-distributed layer with a `SoftMax` activation function. The inputs of the network are of six trajectory features previously computed, while the outputs are probabilities for each trajectory point of belonging to one of the $N$ diffusive states, the predicted state is defined by the highest probability.
 
 The computed features along a given trajectory are: the displacements $\Delta x_{\delta=1}$ and $\Delta y_{\delta=1}$ at the first discrete time interval $\delta=1$ (with $\Delta r_\delta (t) = r(t) - r(t+\delta)$), the distances $d_{\delta=1}$ (with $d_\delta (t) = \sqrt{\Delta x_\delta (t)^2 + \Delta y_\delta (t)^2}$), the mean of displacements $\overline{d_{\delta=1,p=1}}$ and $\overline{d_{\delta=2,p=1}}$ (with $\overline{d_{\delta,p}}(t) = \frac{1}{2p+1}\sum_{k=t-p}^{t+p} d_{\delta}(k)$ with $p\geq 1$) and the angles $\theta_{\delta=1}$ between consecutive displacements. The last feature is an addition to the initial method, used for a better distinction of the trajectory confinement. The first and last trajectory points of each trajectory vector are discarded due to missing computed feature(s).
 

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "tracksegnet"
-version = "1.2.5"
+version = "1.3.0"
 dynamic = ["dependencies"]
 authors = [
   { name="Hélène Kabbech", email="[email protected]" },

requirements.txt

@@ -13,7 +13,7 @@ google-auth-oauthlib==0.4.6
 google-pasta==0.2.0
 grpcio>=1.53.0
 h5py==3.8.0
-idna==3.4
+idna>=3.7
 importlib-metadata==6.0.0
 keras==2.11.0
 kiwisolver==1.4.4
@@ -47,7 +47,7 @@ tensorflow==2.11.1
 tensorflow-estimator==2.11.0
 tensorflow-io-gcs-filesystem==0.30.0
 termcolor==2.2.0
-tqdm==4.64.1
+tqdm>=4.66.3
 typing-extensions==4.4.0
 urllib3>=1.26.18
 werkzeug>=2.3.8
@@ -57,4 +57,4 @@ myst_parser>=2.0.0
 sphinx>=7.0.0
 sphinx_rtd_theme>=2.0.0
 readthedocs-sphinx-search>=0.1.1
-tracksegnet==1.2.5
+tracksegnet==1.3.0