Merge pull request #25 from bioinfoUQAM/dev

Dev

.gitignore

@@ -1,3 +1,136 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# Output data from example script
+output/
+
 build/
 .vscode/
 __pycache__/

README.md

@@ -1,6 +1,13 @@
 # Caribou
 Alignment-free bacterial identification and classification in metagenomics sequencing data using machine learning.
 
+## Proof of Concept
+The jupyter notebook `workflow_example.ipynb` shows the workflow and it's output using example data. In this notebook, the steps are identified for better understanding.
+
+Data used in the `workflow_example.ipynb` is located in the `example_data/` folder.
+
+This data was also used to test and debug the Caribou analysis pipeline.
+
 ## Installation
 The Caribou analysis pipeline was developped in python3 and can be easily installed through the python wheel. The repo must be cloned first and then the package can be installed using the following commands lines in the desired folder :
 ```

example_data/30_genomes.csv

@@ -0,0 +1,31 @@
+id,species,genus,family,order,class,phylum,domain
+VBOR01000009.1,WS-7 sp005893165,WS-7,SZUA-252,SZUA-252,RBG-16-71-46,Eisenbacteria,Bacteria
+PMOP01000016.1,Palsa-360 sp003161495,Palsa-360,UBA7541,UBA7541,Acidobacteriae,Acidobacteriota,Bacteria
+DHUT01000069.1,Sedimentibacter sp002409285,Sedimentibacter,Sedimentibacteraceae,Tissierellales,Clostridia,Firmicutes_A,Bacteria
+JAAZAC010000025.1,Actinotalea sp012514545,Actinotalea,Cellulomonadaceae,Actinomycetales,Actinomycetia,Actinobacteriota,Bacteria
+URUG01000300.1,Faecalimonas sp900550975,Faecalimonas,Lachnospiraceae,Lachnospirales,Clostridia,Firmicutes_A,Bacteria
+CAJCBY010000033.1,Aquirufa sp903960725,Aquirufa,Spirosomaceae,Cytophagales,Bacteroidia,Bacteroidota,Bacteria
+JABXKY010000147.1,RBG-16-57-9 sp013619005,RBG-16-57-9,TCS64,TCS64,Bathyarchaeia,Thermoproteota,Archaea
+JABBOX010000109.1,UBA4719 sp012927555,UBA4719,Dermatophilaceae,Actinomycetales,Actinomycetia,Actinobacteriota,Bacteria
+JAABRC010000419.1,JAABRC01 sp011391115,JAABRC01,Burkholderiaceae,Burkholderiales,Gammaproteobacteria,Proteobacteria,Bacteria
+CAAFRK010000216.1,Veillonella sp900765235,Veillonella,Veillonellaceae,Veillonellales,Negativicutes,Firmicutes_C,Bacteria
+URSE01000035.1,Veillonella sp900550455,Veillonella,Veillonellaceae,Veillonellales,Negativicutes,Firmicutes_C,Bacteria
+UQEY01000009.1,Eubacterium_R sp900540235,Eubacterium_R,Acutalibacteraceae,Oscillospirales,Clostridia,Firmicutes_A,Bacteria
+NZ_QEST01000278.1,Streptomyces sp003311645,Streptomyces,Streptomycetaceae,Streptomycetales,Actinomycetia,Actinobacteriota,Bacteria
+NZ_LRTR01000260.1,Streptomyces europaeiscabiei,Streptomyces,Streptomycetaceae,Streptomycetales,Actinomycetia,Actinobacteriota,Bacteria
+JACMKV010000045.1,JACMKV01 sp014379915,JACMKV01,JACMKV01,Burkholderiales,Gammaproteobacteria,Proteobacteria,Bacteria
+CACNVV010000042.1,Pelagibacter sp902624015,Pelagibacter,Pelagibacteraceae,Pelagibacterales,Alphaproteobacteria,Proteobacteria,Bacteria
+WLHF01000026.1,Planktophila sp009702835,Planktophila,Nanopelagicaceae,Nanopelagicales,Actinomycetia,Actinobacteriota,Bacteria
+DKBA01000026.1,UBA6912 sp002450985,UBA6912,UBA5794,UBA5794,Acidimicrobiia,Actinobacteriota,Bacteria
+WBXD01000017.1,UBA1315 sp008932935,UBA1315,Akkermansiaceae,Verrucomicrobiales,Verrucomicrobiae,Verrucomicrobiota,Bacteria
+PBSX01000072.1,CABZJG01 sp002726375,CABZJG01,Rhodobacteraceae,Rhodobacterales,Alphaproteobacteria,Proteobacteria,Bacteria
+JAAYQI010000217.1,JAAYQI01 sp012519385,JAAYQI01,Anaerotignaceae,Lachnospirales,Clostridia,Firmicutes_A,Bacteria
+PMSQ01000054.1,Sulfotelmatobacter sp003168355,Sulfotelmatobacter,Koribacteraceae,Acidobacteriales,Acidobacteriae,Acidobacteriota,Bacteria
+NZ_LCZE01000023.1,Pseudomonas_E fluorescens_N,Pseudomonas_E,Pseudomonadaceae,Pseudomonadales,Gammaproteobacteria,Proteobacteria,Bacteria
+DNMQ01000225.1,Pseudomonas_A sp003488145,Pseudomonas_A,Pseudomonadaceae,Pseudomonadales,Gammaproteobacteria,Proteobacteria,Bacteria
+CAIXRL010000197.1,CAIXRL01 sp903921835,CAIXRL01,RBG-16-71-46,RBG-16-71-46,RBG-16-71-46,Eisenbacteria,Bacteria
+JAAYXU010000041.1,JAAYXU01 sp012515725,JAAYXU01,UMGS416,Christensenellales,Clostridia_A,Firmicutes_A,Bacteria
+DHMB01000127.1,CAG-841 sp002405565,CAG-841,CAG-272,Oscillospirales,Clostridia,Firmicutes_A,Bacteria
+JACNFQ010000081.1,NIOZ-UU106 sp014384545,NIOZ-UU106,UBA6624,UBA6624,UBA6624,UBP7,Bacteria
+CAJCHR010000269.1,Novosphingobium sp903970225,Novosphingobium,Sphingomonadaceae,Sphingomonadales,Alphaproteobacteria,Proteobacteria,Bacteria
+QMMC01000579.1,B10-G4 sp003647065,B10-G4,SG8-38,Polyangiales,Polyangia,Myxococcota,Bacteria

example_data/cucurbita_sample_3.csv

@@ -0,0 +1,4 @@
+id,species,domain
+NW_019663258,Cucurbita,host
+NW_019657536,Cucurbita,host
+NEWN01002765,Cucurbita,host