From 71d288d7b47bbe872263920d87f9ba27f541f437 Mon Sep 17 00:00:00 2001
From: veghp <pvegh@posteo.uk>
Date: Thu, 25 Apr 2024 17:57:57 +0100
Subject: [PATCH] Refactor to collect re-use count

---
 seqreport/SeqCollection.py             | 10 ++++++----
 seqreport/report_assets/seq_report.pug | 17 +++++++++++------
 2 files changed, 17 insertions(+), 10 deletions(-)

diff --git a/seqreport/SeqCollection.py b/seqreport/SeqCollection.py
index 54fac8b..fe86a7f 100644
--- a/seqreport/SeqCollection.py
+++ b/seqreport/SeqCollection.py
@@ -146,7 +146,7 @@ def calculate_values(self):
                 next(reader)  # ignore header
                 for row in reader:
                     all_rows += row[1:]  # first column is construct name
-            self.savings_list = []
+            self.savings_dict = {}
             self.total_savings = 0
             for record in self.sequences:
                 count_in_plan = all_rows.count(record.id)
@@ -154,7 +154,7 @@ def calculate_values(self):
                     self.total_savings += len(record.seq) * (
                         count_in_plan - 1
                     )  # ignore first synthesis
-                    self.savings_list += [record.id]
+                    self.savings_dict[record.id] = count_in_plan
                 # else we don't have any savings from the sequence.
                 if count_in_plan < 1:  # also find the ones not in the assembly plan
                     self.not_in_plan += [record.id]
@@ -165,10 +165,12 @@ def calculate_values(self):
                 self.total_cost_savings
             )  # (in)accuracy is fine for our purposes
             # For the PDF report:
-            self.savings_list_text = " ; ".join(self.savings_list)
             self.not_in_plan_text = " ; ".join(self.not_in_plan)
+            self.savings_dict_text = " ; ".join(
+                [f"{key}  (×{value})" for key, value in self.savings_dict.items()]
+            )
         else:
-            self.savings_list_text = ""
+            self.savings_dict_text = ""
             self.not_in_plan_text = ""
 
 
diff --git a/seqreport/report_assets/seq_report.pug b/seqreport/report_assets/seq_report.pug
index d889225..bbc00ec 100644
--- a/seqreport/report_assets/seq_report.pug
+++ b/seqreport/report_assets/seq_report.pug
@@ -69,9 +69,9 @@ else
 
 if seqcollection.assembly_plan
 
-  if seqcollection.savings_list_text
+  if seqcollection.savings_dict_text
     p.
-      Re-used sequences in the provided assembly plan: {{ seqcollection.savings_list_text }}.
+      Sequences used more than once in the provided assembly plan: {{ seqcollection.savings_dict_text }}.
     p.
       Total savings: <b>{{ seqcollection.total_savings }}</b> bp or <b>{{ seqcollection.currency_symbol }}{{ seqcollection.total_cost_savings }}</b>.
   else
@@ -94,10 +94,10 @@ div(style="margin-top:1cm; margin-bottom:1cm;")
 p
   strong Seq Report
 p.
-  The report was generated by <a href="https://github.com/Edinburgh-Genome-Foundry/Seq_Report/">Seq Report</a>,
-  a software published by the Edinburgh Genome Foundry (EGF).
-  Seq Report is part of the <a href="https://edinburgh-genome-foundry.github.io/">EGF Codons</a>
-  engineering biology software suite for DNA design, manufacturing and validation.
+  The sequence re-use section shows the basepair-<i>savings</i>, and also ignores
+  per-sequence cost. For example, savings for seq1 (×3) with length L is calculated as
+  2 × L × {{ seqcollection.currency_symbol }}/base.
+  
 
 p.
   Parameters:
@@ -106,6 +106,11 @@ p.
     <li>Cost per sequence = <b>{{ seqcollection.currency_symbol }}{{ seqcollection.cost_per_seq }}</b> </li>
   </ul>
 
+p.
+  The report was generated by <a href="https://github.com/Edinburgh-Genome-Foundry/Seq_Report/">Seq Report</a>,
+  a software published by the Edinburgh Genome Foundry (EGF).
+  Seq Report is part of the <a href="https://edinburgh-genome-foundry.github.io/">EGF Codons</a>
+  engineering biology software suite for DNA design, manufacturing and validation.
 
 
 style.