Update report template

public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/scripts/pdf_report.py

@@ -422,9 +422,9 @@ class GentrapLib(object):
         # insert size metrics files
         self.inserts_metrics_files = summary.get("bammetrics", {}).get("files", {}).get("insert_size_metrics", {})
         # rna metrics files and stats
+        self.rna_metrics_files = summary.get("gentrap", {}).get("files", {}).get("rna_metrics", {})
         _rmetrics = summary.get("gentrap", {}).get("stats", {}).get("rna_metrics", {})
         if _rmetrics:
-            self.rna_metrics_files = summary.get("gentrap", {}).get("files", {}).get("rna_metrics", {})
             self.rna_metrics = {k: v for k, v in _rmetrics.items() }
             pf_bases = float(_rmetrics["pf_bases"])
             exonic_bases = int(_rmetrics.get("coding_bases", 0)) + int(_rmetrics.get("utr_bases", 0))
@@ -461,10 +461,15 @@ class GentrapSample(object):
         self.libs = \
             {l: GentrapLib(self.run, self, l, summary["libraries"][l]) \
                 for l in self.lib_names}
+        self.is_paired_end = summary.get("gentrap", {}).get("stats", {}).get("pipeline", {})["all_paired"]
+        # mapping metrics settings
+        self.aln_metrics = summary.get("bammetrics", {}).get("stats", {}).get("alignment_metrics", {})
+        # insert size metrics files
+        self.inserts_metrics_files = summary.get("bammetrics", {}).get("files", {}).get("insert_size_metrics", {})
         # rna metrics files and stats
+        self.rna_metrics_files = summary.get("gentrap", {}).get("files", {}).get("rna_metrics", {})
         _rmetrics = summary.get("gentrap", {}).get("stats", {}).get("rna_metrics", {})
         if _rmetrics:
-            self.rna_metrics_files = summary.get("gentrap", {}).get("files", {}).get("rna_metrics", {})
             self.rna_metrics = {k: v for k, v in _rmetrics.items() }
             pf_bases = float(_rmetrics["pf_bases"])
             exonic_bases = int(_rmetrics.get("coding_bases", 0)) + int(_rmetrics.get("utr_bases", 0))

public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/templates/pdf/lib_mapping.tex

@@ -77,7 +77,6 @@
 =))
 ((* endif *))
 
-((* if lib.sample.libs|length > 1 *))
 \subsubsection{RNA-specific metrics}
 
 \IfFileExists{((( lib.rna_metrics_files.output_chart.path )))}
@@ -111,5 +110,3 @@
         \hline
     \end{tabular}
 \end{center}
-
-((* endif *))

public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/templates/pdf/sample.tex

 \part{Sample "((( sample.name )))" Results}
 \label{sample:(((sample.name)))}
 
+((* if sample.libs|length > 1 *))
 ((* include "sample_mapping.tex" *))
+((* endif *))
 
 ((* for lib in sample.libs.values() *))
 ((* include "lib.tex" *))

public/gentrap/src/main/resources/nl/lumc/sasc/biopet/pipelines/gentrap/templates/pdf/sample_mapping.tex

@@ -5,6 +5,78 @@
 
 \indent
 
+% number + percentage of reads mapped to genome
+% number + percentage of properly paired reads
+\begin{center}
+    \captionof{table}{Mapping Overview}
+    \label{tab:bamstat-((( sample.name )))}
+    \setlength{\tabcolsep}{11pt}
+    ((* if sample.is_paired_end *))
+    \begin{tabular}{ l r r r }
+        \hline
+        \multirow{2}{*}{Parameter} & \multicolumn{1}{c}{All Pairs} & \multicolumn{1}{c}{First in Pairs} & \multicolumn{1}{c}{Second in Pairs} \\
+         & Value & Value & Value \\
+        \hline \hline
+        Total reads & ((( sample.aln_metrics.PAIR.total_reads|nice_int ))) & ((( sample.aln_metrics.FIRST_OF_PAIR.total_reads|nice_int ))) & ((( sample.aln_metrics.SECOND_OF_PAIR.total_reads|nice_int ))) \\
+        Mean read length & ((( sample.aln_metrics.PAIR.mean_read_length|nice_flt ))) & ((( sample.aln_metrics.FIRST_OF_PAIR.mean_read_length|nice_flt ))) & ((( sample.aln_metrics.SECOND_OF_PAIR.mean_read_length|nice_flt ))) \\
+        Strand balance & ((( sample.aln_metrics.PAIR.strand_balance|nice_flt ))) & ((( sample.aln_metrics.FIRST_OF_PAIR.strand_balance|nice_flt ))) & ((( sample.aln_metrics.SECOND_OF_PAIR.strand_balance|nice_flt ))) \\
+        \% Mapped to reference & ((( sample.aln_metrics.PAIR.pct_pf_reads_aligned|float2nice_pct )))\% & ((( sample.aln_metrics.FIRST_OF_PAIR.pct_pf_reads_aligned|float2nice_pct )))\% & ((( sample.aln_metrics.SECOND_OF_PAIR.pct_pf_reads_aligned|float2nice_pct )))\% \\
+        \% Mapped to reference (MAPQ >= 20) & ((( sample.aln_metrics.PAIR.pct_pf_reads_aligned|float2nice_pct )))\% & ((( sample.aln_metrics.FIRST_OF_PAIR.pct_pf_reads_aligned|float2nice_pct )))\% & ((( sample.aln_metrics.SECOND_OF_PAIR.pct_pf_reads_aligned|float2nice_pct )))\% \\
+        Mismatch rate & ((( sample.aln_metrics.PAIR.pf_mismatch_rate|float2nice_pct )))\% & ((( sample.aln_metrics.FIRST_OF_PAIR.pf_mismatch_rate|float2nice_pct )))\% & ((( sample.aln_metrics.SECOND_OF_PAIR.pf_mismatch_rate|float2nice_pct )))\% \\
+        Indel rate & ((( sample.aln_metrics.PAIR.pf_indel_rate|float2nice_pct )))\% & ((( sample.aln_metrics.FIRST_OF_PAIR.pf_indel_rate|float2nice_pct )))\% & ((( sample.aln_metrics.SECOND_OF_PAIR.pf_indel_rate|float2nice_pct )))\% \\
+        Chimeras & ((( sample.aln_metrics.PAIR.pct_chimeras|float2nice_pct )))\% & ((( sample.aln_metrics.FIRST_OF_PAIR.pct_chimeras|float2nice_pct )))\% & ((( sample.aln_metrics.SECOND_OF_PAIR.pct_chimeras|float2nice_pct )))\% \\
+        \hline
+    ((* else *))
+    \begin{tabular}{ l r }
+        \hline
+        \multirow{1}{*}{Parameter} & \multicolumn{1}{c}{Value} \\
+        \hline \hline
+        Total reads & ((( sample.aln_metrics.UNPAIRED.total_reads|nice_int ))) \\
+        Mean read length & ((( sample.aln_metrics.UNPAIRED.mean_read_length|nice_flt ))) \\
+        Strand balance & ((( sample.aln_metrics.UNPAIRED.strand_balance|nice_flt ))) \\
+        \% Mapped to reference & ((( sample.aln_metrics.UNPAIRED.pct_pf_reads_aligned|float2nice_pct )))\% \\
+        \% Mapped to reference (MAPQ >= 20) & ((( sample.aln_metrics.UNPAIRED.pct_pf_reads_aligned|float2nice_pct )))\% \\
+        Mismatch rate & ((( sample.aln_metrics.UNPAIRED.pf_mismatch_rate|float2nice_pct )))\% \\
+        Indel rate & ((( sample.aln_metrics.UNPAIRED.pf_indel_rate|float2nice_pct )))\% \\
+        \hline
+    ((* endif *))
+    \end{tabular}
+\end{center}
+
+((* if sample.is_paired_end *))
+% inferred insert size distribution
+\subsubsection{Insert size distribution}
+
+\IfFileExists{((( sample.inserts_metrics_files.output_histogram.path )))}
+{
+    \begin{figure}[h!]
+        \centering
+        \includegraphics[width=0.7\textwidth]{((( sample.inserts_metrics_files.output_histogram.path )))}
+        \caption{Distribution of insert size length of paired-end reads mapped to opposite strands.}
+    \end{figure}
+}
+((= TODO: strand-specific stats
+%{
+%    \IfFileExists{((( vars['OUT_DIR'] )))/((( vars['SAMPLE'] ))).f.insertsizes.png}
+%    {
+%        \begin{figure}[h!]
+%            \centering
+%            \includegraphics[width=0.7\textwidth]{((( vars['OUT_DIR'] )))/((( vars['SAMPLE'] ))).f.insertsizes.png}
+%            \caption{Distribution of insert size length of paired-end reads whose first read maps to the minus strand.}
+%        \end{figure}
+%    }{}
+%    \IfFileExists{((( vars['OUT_DIR'] )))/((( vars['SAMPLE'] ))).r.insertsizes.png}
+%    {
+%        \begin{figure}[h!]
+%            \centering
+%            \includegraphics[width=0.7\textwidth]{((( vars['OUT_DIR'] )))/((( vars['SAMPLE'] ))).r.insertsizes.png}
+%            \caption{Distribution of insert size length of paired-end reads whose first read maps to the plus strand.}
+%        \end{figure}
+%    }{}
+%}
+=))
+((* endif *))
+
 
 \subsection{RNA-specific metrics}