From 9f1c9259c14341bcdb81764677301372592681fe Mon Sep 17 00:00:00 2001
From: ksahlin <krsahlin@gmail.com>
Date: Thu, 12 Nov 2015 17:46:08 -0500
Subject: [PATCH] removed some prints to stdout and added documentation

---
 BESST/libmetrics.py | 8 ++++----
 README.md           | 8 ++++++++
 docs/MANUAL.md      | 8 ++++++++
 3 files changed, 20 insertions(+), 4 deletions(-)

diff --git a/BESST/libmetrics.py b/BESST/libmetrics.py
index 0c3b194..1051c4a 100644
--- a/BESST/libmetrics.py
+++ b/BESST/libmetrics.py
@@ -130,7 +130,7 @@ def sum_chunks(l, n):
     for i in xrange(0, len(l), n):
         yield sum(l[i:i+n])
 
-def getdistr(ins_size_reads, cont_lengths_list, param):
+def getdistr(ins_size_reads, cont_lengths_list, param, Information):
     largest_contigs = map(lambda x: int(x),sorted(nlargest(1000, cont_lengths_list)))
     #print largest_contigs
     #sorted_lengths = sorted(cont_lengths_list)
@@ -199,7 +199,7 @@ def getdistr(ins_size_reads, cont_lengths_list, param):
         adj_distr_chunked = list(sum_chunks(adjusted_distribution, chunk_size))
         mode_adj = (argmax(adj_distr_chunked) + 0.5)*chunk_size
         mode_for_different_windows.append(int(mode_adj))
-        print "mode for chunk size ", chunk_size, " : ", mode_adj
+        print >> Information, "mode for chunk size ", chunk_size, " : ", mode_adj
     mode_adj = sorted(mode_for_different_windows)[int(len(mode_for_different_windows)/2)]
     print "Choosing mode:", mode_adj
 
@@ -211,7 +211,7 @@ def getdistr(ins_size_reads, cont_lengths_list, param):
     # m_3 = sum(map(lambda x: (x - mean_isize) ** 3, ins_size_reads))/n
     skew_adj = m_3 / sigma_adj**3
 
-    print mu_adj, sigma_adj, skew_adj
+    print 'mu_adjusted:{0}, sigma_adjusted:{1}, skewness_adjusted:{2}'.format(mu_adj, sigma_adj, skew_adj)
     return adjusted_distribution, mu_adj, sigma_adj, skew_adj, median_adj, mode_adj
 #with pysam.Samfile(param.bamfile, 'rb') as bam_file:
 
@@ -334,7 +334,7 @@ def get_metrics(bam_file, param, Information):
         print >> Information, 'Skewness of distribution: ', param.skewness
 
         # weight each observation with how likely it is to see it
-        adj_distr, mu_adj, sigma_adj, skew_adj, median_adj, mode_adj = getdistr(ins_size_reads, cont_lengths_list, param)
+        adj_distr, mu_adj, sigma_adj, skew_adj, median_adj, mode_adj = getdistr(ins_size_reads, cont_lengths_list, param, Information)
         param.skew_adj = skew_adj
         print >> Information, 'Mean of getdistr adjusted distribution: ', mu_adj
         print >> Information, 'Sigma of getdistr adjusted distribution: ', sigma_adj
diff --git a/README.md b/README.md
index a50f948..b8b5420 100644
--- a/README.md
+++ b/README.md
@@ -18,6 +18,14 @@ See docs/INSTALL.md.
 Q&A
 ------------------
 
+####  What parameters should I call BESST with?
+BESST is designed to infer as much as possible from data. If this is your first time running BESST, it is highly reccomended to only run BESST as
+
+```sh
+runBESST -c /path/to/contigfile.fa -f /path/to/file1.bam /path/to/file2.bam ... -o /path/to/output --orientation {fr/rf}
+```
+For more details, see section "INPUT" further down. BESST will then infer ar much as possible from data and print everything to "/path/to/output/BESST_output/Statistics.txt". This file is useful for debugging.
+
 ####  What aligner should I use?
 BESST requires only a sorted and indexed BAM file -- your favourite aligner can be used. However, we have had the best experience with BWA-mem using default parameters on most data used in our evaluations.
 
diff --git a/docs/MANUAL.md b/docs/MANUAL.md
index 88ffa49..46c7e06 100644
--- a/docs/MANUAL.md
+++ b/docs/MANUAL.md
@@ -8,6 +8,14 @@ See docs/INSTALL.md.
 Q&A
 ------------------
 
+####  What parameters should I call BESST with?
+BESST is designed to infer as much as possible from data. If this is your first time running BESST, it is highly reccomended to only run BESST as
+
+```sh
+runBESST -c /path/to/contigfile.fa -f /path/to/file1.bam /path/to/file2.bam ... -o /path/to/output --orientation {fr/rf}
+```
+For more details, see section "INPUT" further down. BESST will then infer ar much as possible from data and print everything to "/path/to/output/BESST_output/Statistics.txt". This file is useful for debugging.
+
 ####  What aligner should I use?
 BESST requires only a sorted and indexed bamfile -- your favourite aligner can be used. However, we have had the best experience with BWA-mem using default parameters on most data used in our evaluations.