Initial mapping subsection in report

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

@@ -324,13 +324,28 @@ class LongTable(object):
 def nice_int(num, default="None"):
     if num is None:
         return default
-    return locale.format("%i", int(num), grouping=True)
+    try:
+        return locale.format("%i", int(num), grouping=True)
+    except:
+        return default
 
 
 def nice_flt(num, default="None"):
     if num is None:
         return default
-    return locale.format("%.2f", float(num), grouping=True)
+    try:
+        return locale.format("%.2f", float(num), grouping=True)
+    except:
+        return default
+
+
+def float2nice_pct(num, default="None"):
+    if num is None:
+        return default
+    try:
+        return locale.format("%.2f", float(num) * 100.0, grouping=True)
+    except:
+        return default
 
 
 # and some handy functions
@@ -363,6 +378,7 @@ def write_template(run, template_file, logo_file):
     # put in out filter functions
     env.filters["nice_int"] = nice_int
     env.filters["nice_flt"] = nice_flt
+    env.filters["float2nice_pct"] = float2nice_pct
 
     # write tex template for pdflatex
     jinja_template = env.get_template(path.basename(template_file))
@@ -384,6 +400,7 @@ class GentrapLib(object):
         self.sample = sample
         self.name = name
         self._raw = summary
+        # flexiprep settings
         self.flexiprep = summary.get("flexiprep", {})
         self.clipping = not self.flexiprep["settings"]["skip_clip"]
         self.trimming = not self.flexiprep["settings"]["skip_trim"]
@@ -400,6 +417,8 @@ class GentrapLib(object):
         if "fastqc_R2_qc" in self.flexiprep["files"]:
             self.fastqc_r2_qc_files = self.flexiprep["files"]["fastqc_R2_qc"]
             self.fastqc_r2_qc = FastQC(self.fastqc_r2_qc_files["fastqc_data"]["path"])
+        # mapping metrics settings
+        self.aln_metrics = summary.get("bammetrics", {}).get("stats", {}).get("alignment_metrics", {})
 
     def __repr__(self):
         return "{0}(sample=\"{1}\", lib=\"{2}\")".format(

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

@@ -2,3 +2,5 @@
 \label{lib:(((lib.name)))}
 
 ((* include "lib_seqeval.tex" *))
+\clearpage
+((* include "lib_mapping.tex" *))

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

+\subsection{Mapping}
+\label{sec:map}
+
+\subsubsection{Mapping statistics}
+
+Table~\ref{tab:bamstat-((( lib.sample.name )))-((( lib.name ))))} shows the overview statistics of the
+generated alignment file.
+
+\indent
+
+% number + percentage of reads mapped to genome
+% number + percentage of properly paired reads
+\begin{center}
+    \captionof{table}{Mapping Overview}
+    \label{tab:bamstat-((( lib.sample.name )))-((( lib.name ))))}
+    \setlength{\tabcolsep}{11pt}
+    ((* if lib.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 & ((( lib.aln_metrics.PAIR.total_reads|nice_int ))) & ((( lib.aln_metrics.FIRST_OF_PAIR.total_reads|nice_int ))) & ((( lib.aln_metrics.SECOND_OF_PAIR.total_reads|nice_int ))) \\
+        Mean read length & ((( lib.aln_metrics.PAIR.mean_read_length|nice_flt ))) & ((( lib.aln_metrics.FIRST_OF_PAIR.mean_read_length|nice_flt ))) & ((( lib.aln_metrics.SECOND_OF_PAIR.mean_read_length|nice_flt ))) \\
+        Strand balance & ((( lib.aln_metrics.PAIR.strand_balance|nice_flt ))) & ((( lib.aln_metrics.FIRST_OF_PAIR.strand_balance|nice_flt ))) & ((( lib.aln_metrics.SECOND_OF_PAIR.strand_balance|nice_flt ))) \\
+        \% Mapped to reference & ((( lib.aln_metrics.PAIR.pct_pf_reads_aligned|float2nice_pct )))\% & ((( lib.aln_metrics.FIRST_OF_PAIR.pct_pf_reads_aligned|float2nice_pct )))\% & ((( lib.aln_metrics.SECOND_OF_PAIR.pct_pf_reads_aligned|float2nice_pct )))\% \\
+        \% Mapped to reference (MAPQ >= 20) & ((( lib.aln_metrics.PAIR.pct_pf_reads_aligned|float2nice_pct )))\% & ((( lib.aln_metrics.FIRST_OF_PAIR.pct_pf_reads_aligned|float2nice_pct )))\% & ((( lib.aln_metrics.SECOND_OF_PAIR.pct_pf_reads_aligned|float2nice_pct )))\% \\
+        Mismatch rate & ((( lib.aln_metrics.PAIR.pf_mismatch_rate|float2nice_pct )))\% & ((( lib.aln_metrics.FIRST_OF_PAIR.pf_mismatch_rate|float2nice_pct )))\% & ((( lib.aln_metrics.SECOND_OF_PAIR.pf_mismatch_rate|float2nice_pct )))\% \\
+        Indel rate & ((( lib.aln_metrics.PAIR.pf_indel_rate|float2nice_pct )))\% & ((( lib.aln_metrics.FIRST_OF_PAIR.pf_indel_rate|float2nice_pct )))\% & ((( lib.aln_metrics.SECOND_OF_PAIR.pf_indel_rate|float2nice_pct )))\% \\
+        Chimeras & ((( lib.aln_metrics.PAIR.pct_chimeras|float2nice_pct )))\% & ((( lib.aln_metrics.FIRST_OF_PAIR.pct_chimeras|float2nice_pct )))\% & ((( lib.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 & ((( lib.aln_metrics.UNPAIRED.total_reads|nice_int ))) \\
+        Mean read length & ((( lib.aln_metrics.UNPAIRED.mean_read_length|nice_flt ))) \\
+        Strand balance & ((( lib.aln_metrics.UNPAIRED.strand_balance|nice_flt ))) \\
+        \% Mapped to reference & ((( lib.aln_metrics.UNPAIRED.pct_pf_reads_aligned|float2nice_pct )))\% \\
+        \% Mapped to reference (MAPQ >= 20) & ((( lib.aln_metrics.UNPAIRED.pct_pf_reads_aligned|float2nice_pct )))\% \\
+        Mismatch rate & ((( lib.aln_metrics.UNPAIRED.pf_mismatch_rate|float2nice_pct )))\% \\
+        Indel rate & ((( lib.aln_metrics.UNPAIRED.pf_indel_rate|float2nice_pct )))\% \\
+        \hline
+    ((* endif *))
+    \end{tabular}
+\end{center}
+
+((=
+%((* if run.is_paired_end *))
+%% inferred insert size distribution
+%\subsection{Insert size distribution}
+%
+%This section contains a quick overview of the insert size distribution
+%of the mapped reads.
+%
+%\indent
+%
+%There are three possible types of inserts the graph may denote:
+%\begin{description}
+%    \item[\textit{inward}] \hfill \\
+%        Each read pair maps to opposite strands and point towards each other.
+%    \item[\textit{outward}] \hfill \\
+%        Each read pair maps to opposite strands and point away from each other.
+%    \item[\textit{same directions}] \hfill \\
+%        Both read pair map to the same strand.
+%\end{description}
+%
+%\IfFileExists{((( vars['OUT_DIR'] )))/((( vars['SAMPLE'] ))).insertsizes.png}
+%{
+%    \begin{figure}[h!]
+%        \centering
+%        \includegraphics[width=0.7\textwidth]{((( vars['OUT_DIR'] )))/((( vars['SAMPLE'] ))).insertsizes.png}
+%        \caption{Distribution of insert size length of paired-end reads mapped to opposite strands.}
+%    \end{figure}
+%}
+%{
+%    \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 *))
+=))