diff --git a/.github/workflows/ubuntu.yml b/.github/workflows/ubuntu.yml
new file mode 100644
index 00000000..4e316eec
--- /dev/null
+++ b/.github/workflows/ubuntu.yml
@@ -0,0 +1,53 @@
+# dingo : a python library for metabolic networks sampling and analysis
+# dingo is part of GeomScale project
+
+# Copyright (c) 2021 Vissarion Fisikopoulos
+
+# Licensed under GNU LGPL.3, see LICENCE file
+
+name: dingo-ubuntu
+
+on: [push]
+
+jobs:
+  build:
+
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        #python-version: [2.7, 3.5, 3.6, 3.7, 3.8]
+        python-version: [3.8]
+
+    steps:
+    - uses: actions/checkout@v2
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v2
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Load submodules
+      run: |
+        git submodule update --init;
+    - name: Download and unzip the boost library
+      run: |
+        wget -O boost_1_76_0.tar.bz2 https://boostorg.jfrog.io/artifactory/main/release/1.76.0/source/boost_1_76_0.tar.bz2;
+        tar xjf boost_1_76_0.tar.bz2;
+        rm boost_1_76_0.tar.bz2;
+    - name: Install dependencies
+      run: |
+        sudo apt-get install libsuitesparse-dev;
+        curl -sSL https://raw.githubusercontent.com/python-poetry/poetry/master/get-poetry.py | python -;
+        source $HOME/.poetry/env;
+        export POETRY_VIRTUALENVS_PATH=/home/runner/.cache/pypoetry/virtualenvs
+        poetry config virtualenvs.create false --local
+        #source $(dirname $(poetry run which python))/activate
+        poetry install;	
+        #pip3 install numpy scipy;
+    - name: Run tests 
+      run: |
+        #python3 tests/fba.py;
+        #python3 tests/full_dimensional.py;
+        python3 tests/max_ball.py;
+        #python3 tests/scaling.py;
+        #run all tests
+        #python -m unittest discover test
+        #TODO: use pytest
diff --git a/README.md b/README.md
index 189f4250..1e22ea6f 100644
--- a/README.md
+++ b/README.md
@@ -1,10 +1,18 @@
 # dingo
 
-dingo is a python package that analyzes metabolic networks. It relies on high dimensional sampling with Markov Chain Monte Carlo (MCMC) methods and fast optimization methods to analyze the possible states of a metabolic network. To perform MCMC sampling, dingo relies on the C++ package [volesti](https://github.com/GeomScale/volume_approximation), which provides several algorithms for sampling convex polytopes. dingo is part of [GeomScale](https://geomscale.github.io/) project.   
-
-dingo also performs two standard methods to analyze the flux space of a metabolic network, namely Flux Balance Analysis and Flux Variability Analysis.
-
-
+`dingo` is a python package that analyzes metabolic networks.
+It relies on high dimensional sampling with Markov Chain Monte Carlo (MCMC)
+methods and fast optimization methods to analyze the possible states of a
+metabolic network. To perform MCMC sampling, `dingo` relies on the `C++` package
+[volesti](https://github.com/GeomScale/volume_approximation), which provides
+several algorithms for sampling convex polytopes.
+`dingo` also performs two standard methods to analyze the flux space of a
+metabolic network, namely Flux Balance Analysis and Flux Variability Analysis.
+
+`dingo` is part of [GeomScale](https://geomscale.github.io/) project.
+
+[![unit-tests](https://github.com/GeomScale/dingo/workflows/dingo-ubuntu/badge.svg)](https://github.com/GeomScale/dingo/actions?query=workflow%3Adingo-ubuntu)
+[![Chat](https://badges.gitter.im/boostorg/geometry.png)](https://gitter.im/GeomScale/community?utm_source=share-link&utm_medium=link&utm_campaign=share-link)
 
 ## Installation
 
diff --git a/tests/fba.py b/tests/fba.py
new file mode 100644
index 00000000..ab0981eb
--- /dev/null
+++ b/tests/fba.py
@@ -0,0 +1,32 @@
+# dingo : a python library for metabolic networks sampling and analysis
+# dingo is part of GeomScale project
+
+# Copyright (c) 2021 Apostolos Chalkis
+
+# Licensed under GNU LGPL.3, see LICENCE file
+
+import unittest
+import os
+import scipy
+import numpy as np
+from dingo import MetabolicNetwork, PolytopeSampler
+from dingo.inner_ball import slow_inner_ball
+from dingo.scaling import gmscale
+
+
+class TestFba(unittest.TestCase):
+    
+    def test_ecoli(self):
+
+        current_directory = os.getcwd()
+        input_file_json = current_directory + "/ext_data/e_coli_core.json"
+
+        model = MetabolicNetwork.from_json(input_file_json)
+        model.set_slow_mode()
+
+        res = model.fba()
+
+        self.assertTrue(abs(res[1] - 0.8739215067486387) < 1e-03)
+
+if __name__ == "__main__":
+    unittest.main()
diff --git a/tests/full_dimensional.py b/tests/full_dimensional.py
new file mode 100644
index 00000000..17ca4e1c
--- /dev/null
+++ b/tests/full_dimensional.py
@@ -0,0 +1,34 @@
+# dingo : a python library for metabolic networks sampling and analysis
+# dingo is part of GeomScale project
+
+# Copyright (c) 2021 Apostolos Chalkis
+# Copyright (c) 2021 Vissarion Fisikopoulos
+
+# Licensed under GNU LGPL.3, see LICENCE file
+
+import unittest
+import os
+import scipy
+import numpy as np
+from dingo import MetabolicNetwork, PolytopeSampler
+from dingo.inner_ball import slow_inner_ball
+from dingo.scaling import gmscale
+
+
+class TestFullDim(unittest.TestCase):
+    
+    def test_ecoli(self):
+
+        current_directory = os.getcwd()
+        input_file_json = current_directory + "/ext_data/e_coli_core.json"
+
+        model = MetabolicNetwork.from_json(input_file_json)
+        sampler = PolytopeSampler(model)
+        sampler.set_slow_mode()
+        sampler.get_polytope()
+
+        self.assertEqual(sampler.A.shape[0], 175)
+        self.assertEqual(sampler.A.shape[1], 24)
+
+if __name__ == "__main__":
+    unittest.main()
diff --git a/tests/max_ball.py b/tests/max_ball.py
new file mode 100644
index 00000000..cd403e2f
--- /dev/null
+++ b/tests/max_ball.py
@@ -0,0 +1,33 @@
+# dingo : a python library for metabolic networks sampling and analysis
+# dingo is part of GeomScale project
+
+# Copyright (c) 2021 Apostolos Chalkis
+# Copyright (c) 2021 Vissarion Fisikopoulos
+
+# Licensed under GNU LGPL.3, see LICENCE file
+
+import unittest
+import os
+import scipy
+import numpy as np
+from dingo import MetabolicNetwork, PolytopeSampler
+from dingo.inner_ball import slow_inner_ball
+from dingo.scaling import gmscale
+
+
+class TestMaxBall(unittest.TestCase):
+    
+    def test_simple(self):
+        m = 2
+        n = 5
+        A = np.zeros((2 * n, n), dtype="float")
+        A[0:n] = np.eye(n)
+        A[n:] -= np.eye(n, n, dtype="float")
+        b = np.ones(2 * n, dtype="float")
+
+        max_ball = slow_inner_ball(A, b)
+
+        self.assertTrue(abs(max_ball[1] - 1) < 1e-04)
+
+if __name__ == "__main__":
+    unittest.main()
diff --git a/tests/scaling.py b/tests/scaling.py
new file mode 100644
index 00000000..4d85e74e
--- /dev/null
+++ b/tests/scaling.py
@@ -0,0 +1,33 @@
+# dingo : a python library for metabolic networks sampling and analysis
+# dingo is part of GeomScale project
+
+# Copyright (c) 2021 Apostolos Chalkis
+# Copyright (c) 2021 Vissarion Fisikopoulos
+
+# Licensed under GNU LGPL.3, see LICENCE file
+
+import unittest
+import os
+import scipy
+import numpy as np
+from dingo import MetabolicNetwork, PolytopeSampler
+from dingo.inner_ball import slow_inner_ball
+from dingo.scaling import gmscale
+
+
+class TestScaling(unittest.TestCase):
+    
+    def test_ecoli(self):
+
+        current_directory = os.getcwd()
+        input_file_json = current_directory + "/ext_data/e_coli_core.json"
+
+        model = MetabolicNetwork.from_json(input_file_json)
+
+        res = gmscale(model.S, 0.99)
+
+        self.assertTrue(abs(scipy.linalg.norm(res[0]) - 15.285577732002883) < 1e-03)
+        self.assertTrue(abs(scipy.linalg.norm(res[1]) - 23.138373030721855) < 1e-03)
+
+if __name__ == "__main__":
+    unittest.main()