From 150ca0354054610beafb5de6cb609229b5159ace Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bertrand=20N=C3=A9ron?= <bneron@pasteur.fr>
Date: Mon, 1 Sep 2014 01:11:27 +0200
Subject: [PATCH] add exercises with solutions
---
source/Control_Flow_Statements.rst | 14 +++-
source/Creating_and_Calling_Funtions.rst | 49 +++++++++++++
source/Input_output.rst | 89 ++++++++++++++++++++++++
source/_static/code/fasta_iterator.py | 33 +++++++++
source/_static/code/fasta_reader.py | 21 ++++++
source/_static/code/parse_blast.py | 23 ++++++
source/index.rst | 5 +-
7 files changed, 232 insertions(+), 2 deletions(-)
create mode 100644 source/_static/code/fasta_iterator.py
create mode 100644 source/_static/code/fasta_reader.py
create mode 100644 source/_static/code/parse_blast.py
diff --git a/source/Control_Flow_Statements.rst b/source/Control_Flow_Statements.rst
index aad5bbc..eaa6f36 100644
--- a/source/Control_Flow_Statements.rst
+++ b/source/Control_Flow_Statements.rst
@@ -38,9 +38,21 @@ The fibonacci suite can be defined as following:
a = b
b = new_number
-We will see another way more elegant to implement the fibonacci suite in next chapter.
+We will see another way more elegant to implement the fibonacci suite in :ref:`Advance Programming Techniques` section.
+Exercise
+--------
+
+display the largest element in list (containing float or integer only)?::
+ l = [1,2,3,4,58,9]
+ for i in l:
+ highest = l[0]
+ if i > highest:
+ highest = i
+ print i
+
+
Exercise
--------
diff --git a/source/Creating_and_Calling_Funtions.rst b/source/Creating_and_Calling_Funtions.rst
index 49f841c..ec5bafd 100644
--- a/source/Creating_and_Calling_Funtions.rst
+++ b/source/Creating_and_Calling_Funtions.rst
@@ -3,3 +3,52 @@
******************************
Creating and Calling Functions
******************************
+
+Exercises
+=========
+
+
+Exercice
+--------
+
+Use the code of the exetrcise 4.5.7 on the kmer. Make a function which compute all kmer of a given lenght
+in a sequence.
+
+Exercise
+--------
+
+Write a function translate taht have a nucleic sequence as parameter, and return the translate sequence.
+We give you a genetic code : ::
+
+ code = { 'ttt': 'F', 'tct': 'S', 'tat': 'Y', 'tgt': 'C',
+ 'ttc': 'F', 'tcc': 'S', 'tac': 'Y', 'tgc': 'C',
+ 'tta': 'L', 'tca': 'S', 'taa': '*', 'tga': '*',
+ 'ttg': 'L', 'tcg': 'S', 'tag': '*', 'tgg': 'W',
+ 'ctt': 'L', 'cct': 'P', 'cat': 'H', 'cgt': 'R',
+ 'ctc': 'L', 'ccc': 'P', 'cac': 'H', 'cgc': 'R',
+ 'cta': 'L', 'cca': 'P', 'caa': 'Q', 'cga': 'R',
+ 'ctg': 'L', 'ccg': 'P', 'cag': 'Q', 'cgg': 'R',
+ 'att': 'I', 'act': 'T', 'aat': 'N', 'agt': 'S',
+ 'atc': 'I', 'acc': 'T', 'aac': 'N', 'agc': 'S',
+ 'ata': 'I', 'aca': 'T', 'aaa': 'K', 'aga': 'R',
+ 'atg': 'M', 'acg': 'T', 'aag': 'K', 'agg': 'R',
+ 'gtt': 'V', 'gct': 'A', 'gat': 'D', 'ggt': 'G',
+ 'gtc': 'V', 'gcc': 'A', 'gac': 'D', 'ggc': 'G',
+ 'gta': 'V', 'gca': 'A', 'gaa': 'E', 'gga': 'G',
+ 'gtg': 'V', 'gcg': 'A', 'gag': 'E', 'ggg': 'G'
+ }
+
+bonus
+"""""
+
+This function have to take the phase as parameter
+
+bonus
+"""""
+
+This function can take genetique code as default parameter
+
+
+
+
+
diff --git a/source/Input_output.rst b/source/Input_output.rst
index aa4364e..df61015 100644
--- a/source/Input_output.rst
+++ b/source/Input_output.rst
@@ -3,3 +3,92 @@
************************************
Variables, Expression and statements
************************************
+
+Exercises
+=========
+
+Exercise
+--------
+
+Write a function which take the path of file as parameter
+and display it's content on the screen.
+
+We wait same behavior as the shell *cat* command. ::
+
+ import sys
+ import os
+
+ def cat(path):
+ if not os.path.exists(path):
+ sys.exit("no such file: {0}".format(path)
+ with open(path, 'r') as infile:
+ for line in infile:
+ print line
+
+Exercise
+--------
+
+Write a function which take the path of a file in rebase format
+and return in a dictionnary the collection of the enzyme contains in the file.
+The sequence of the binding site must be cleaned up.
+
+:download:`rebase_light.txt <_static/data/rebase_light.txt>` .
+
+Exercise
+--------
+
+write a function which take the path of a fasta file
+and return a data structure of your choice that allow to stock
+the id of the sequence and the sequence itself.
+
+:download:`seq.fasta <_static/data/seq.fasta>` .
+
+solution 1
+""""""""""
+.. literalinclude:: _static/code/fasta_reader.py
+ :linenos:
+ :language: python
+
+:download:`fasta_reader.py <_static/code/fasta_reader.py>` .
+
+solution 2
+""""""""""
+
+.. literalinclude:: _static/code/fasta_iterator.py
+ :linenos:
+ :language: python
+
+:download:`fasta_iterator.py <_static/code/fasta_iterator.py>` .
+
+
+The second version is an iterator. Thus it retrun sequence by sequence the advantage of this version.
+If the file contains lot of sequences you have not to load all the file in memory.
+You can call this function and put in in a loop or call next. work with the sequence and pass to the next sequence on so on.
+for instance : ::
+
+ for seq in fasta_iter('my_fast_file.fasta'):
+ print seq
+
+Exercise
+--------
+
+we ran a blast with the folowing command *blastall -p blastp -d uniprot_sprot -i query_seq.fasta -e 1e-05 -m 8 -o blast2.txt*
+
+-m 8 is the tabular output. So each fields is separate to the following by a '\t'
+
+The fields are: query id, database sequence (subject) id, percent identity, alignment length, number of mismatches, number of gap openings,
+query start, query end, subject start, subject end, Expect value, HSP bit score.
+
+:download:`blast2.txt <_static/data/blast2.txt>` .
+
+| parse the file
+| sort the hits by their *percent identity* in the descending order.
+| write the results in a new file.
+
+(adapted from *managing your biological data with python* p138) ::
+
+.. literalinclude:: _static/code/parse_blast_output.py
+ :linenos:
+ :language: python
+
+:download:`parse_blast_output.py <_static/code/parse_blast_output.txt>` .
\ No newline at end of file
diff --git a/source/_static/code/fasta_iterator.py b/source/_static/code/fasta_iterator.py
new file mode 100644
index 0000000..65b2a40
--- /dev/null
+++ b/source/_static/code/fasta_iterator.py
@@ -0,0 +1,33 @@
+from collections import namedtuple
+from itertools import groupby
+
+Sequence = namedtuple("Sequence", "id comment sequence")
+
+def fasta_iter(fasta_path):
+ """
+ :param fasta_file: the file containing all input sequences in fasta format.
+ :type fasta_file: file object
+ :author: http://biostar.stackexchange.com/users/36/brentp
+ :return: for a given fasta file, it returns an iterator which yields tuples
+ (string id, string comment, int sequence length)
+ :rtype: iterator
+ """
+ with open(fasta_path) as fasta_file:
+ # ditch the boolean (x[0]) and just keep the header or sequence since
+ # we know they alternate.
+ group = (x[1] for x in groupby(fasta_file , lambda line: line[0] == ">"))
+ for header in group:
+ # drop the ">"
+ header = header.next()[1:].strip()
+ header = header.split()
+ _id = header[0]
+ comment = ' '.join(header[1:])
+ seq = ''.join(s.strip() for s in group.next())
+ yield Sequence(_id, comment, seq)
+
+#using exanple:
+#f = fasta_iter('seq.fasta')
+#f.next()
+#or
+# for seq in fasta_iter('seq.fasta'):
+# do something with seq
\ No newline at end of file
diff --git a/source/_static/code/fasta_reader.py b/source/_static/code/fasta_reader.py
new file mode 100644
index 0000000..a6595c3
--- /dev/null
+++ b/source/_static/code/fasta_reader.py
@@ -0,0 +1,21 @@
+from collections import namedtuple
+
+Sequence = namedtuple("Sequence", "id comment sequence")
+
+def fasta_reader(fasta_path):
+ with open(fasta_path, 'r') as fasta_infile:
+ id = ''
+ comment = ''
+ sequence = ''
+ in_sequence = False
+ for line in fasta_infile:
+ if line.startswith('>'):
+ header = line.split()
+ id = header[0]
+ comment = ' '.join(header[1:])
+ in_sequence = True
+ elif in_sequence:
+ sequence += line.strip()
+ else:
+ continue
+ return Sequence(id , comment, sequence)
\ No newline at end of file
diff --git a/source/_static/code/parse_blast.py b/source/_static/code/parse_blast.py
new file mode 100644
index 0000000..19d0c7b
--- /dev/null
+++ b/source/_static/code/parse_blast.py
@@ -0,0 +1,23 @@
+from operator import itemgetter
+
+def parse_blast_output(input_file, output_file):
+ with open(input_file, 'r') as infile:
+ table = []
+ for line in infile:
+ print i
+ col = line.split('\t')
+ try:
+ col[2] = float(col[2])
+ except ValueError as err:
+ raise RuntimeError("error in parsing {} : {}".format(input_file, err))
+ col[-1] = col[-1][:-1]
+ table.append(col)
+ #from this point the input_file is closed
+ table_sorted = sorted(table, key = itemgetter(2), reverse = True)
+ # alternative
+ # table_sorted = sorted(table, key = lambda x : x[2], reversed = True)
+ with open(output_file, 'w') as output:
+ for row in table_sorted:
+ row = [str(x) for x in row]
+ output.write("\t".join(row) + "\n")
+
diff --git a/source/index.rst b/source/index.rst
index 1fc790f..d585d83 100644
--- a/source/index.rst
+++ b/source/index.rst
@@ -10,10 +10,13 @@ Contents:
.. toctree::
:maxdepth: 2
-
+ :numbered:
+
+ Introduction
Variables
Data_Types
Collection_Data_Types
+ Logical_Operations
Control_Flow_Statements
Creating_and_Calling_Functions
Modules_and_Packages
--
GitLab