- Needleman-Wunsch algorithm: global alignment
- Smith-Waterman algorithm: local alignment
- Levenshtein distance: minimum number of operations (insertion, deletion, modification) to transform one sequence to an other sequence
phmm.py : Pair Hidden Markov Model implementation
blast.py : heuristics to find local alignments in very long chains
main.py : examples of presented algorithms
data_retrieval.py : word retrieval thanks to nltk
- Install nltk with # apt-get install nltk
- Download Swadesh corpus with
>>> import nltk
>>> nltk.download()
utils.py : some useful functions which are unclassified
TODO: learning to align pairs of sequences with a Pair Hidden Markov Model.