\@writefile{toc}{\contentsline {subsection}{\numberline {2.1.1}MGA content and organization}{24}{subsection.2.1.1}}
\@writefile{lof}{\contentsline {figure}{\numberline {2.1}{\ignorespaces \textbf {Content of the MGA repository by 2018} \textbf {A} Proportion of samples in the database grouped by type. \textbf {B} Proportion of samples grouped by organism. Assemblies belonging to the same organism are merged together. \textbf {C} Samples numbers stratified by type and organism. Dot areas are proportional to the total number of samples in that category. The corresponding numbers can be found in a weakly updated table posted on the MGA home page at \url {http://ccg.vital-it.ch/mga}. Figure and legend taken and adapted from \citep {dreos_mga_2018}.\relax }}{24}{figure.caption.11}}
\newlabel{lab_resources_mga_stats}{{2.1}{24}{\textbf {Content of the MGA repository by 2018} \textbf {A} Proportion of samples in the database grouped by type. \textbf {B} Proportion of samples grouped by organism. Assemblies belonging to the same organism are merged together. \textbf {C} Samples numbers stratified by type and organism. Dot areas are proportional to the total number of samples in that category. The corresponding numbers can be found in a weakly updated table posted on the MGA home page at \url {http://ccg.vital-it.ch/mga}. Figure and legend taken and adapted from \citep {dreos_mga_2018}.\relax }{figure.caption.11}{}}
\@writefile{lof}{\contentsline {figure}{\numberline {2.2}{\ignorespaces \textbf {Schematic representation of the EPDnew pipeline} \textbf {A} Download of authoritative gene catalogs and primary TSS mapping data from public databases, data repositories and consortium websites. \textbf {B} Quality control (QC) of incoming data (e.g. read mapping efficiency, contaminations, etc.). \textbf {C} Data passing QC are reformatted and incorporated into the MGA repository. \textbf {D} Selection of a subset of TSS mapping experiments for generating a new organism-specific TSS collection. \textbf {E} Input data for a new module of EPDnew. \textbf {F} Organism-specific automatic database assembly pipeline tailored to the input data, see \citep {dreos_epd_2013} for a detailed description of the human EPDnew assembly pipeline. \textbf {G} Preliminary or final TSS collection \textbf {H} Manual sanity checks of individual randomly selected promoter entries using the corresponding entry viewer. \textbf {I} Automatic quality evaluation of the TSS collections as a whole by motif enrichment tests, see Figure \ref {lab_resources_epd_motifs} for an example. \textbf {L} Feedback is collected from quality evaluation steps H and I. This may lead to the exclusion, replacement or addition of source data sets or modifications (e.g. program parameter fine-tuning) of the computational database generation pipeline. Note that the development of a final, publicly released EPDnew module typically involves several evaluation-modification cycles. Figure and legend taken and adapted from \citep {dreos_eukaryotic_2017}.\relax }}{26}{figure.caption.12}}
\newlabel{lab_resources_epd_pipeline}{{2.2}{26}{\textbf {Schematic representation of the EPDnew pipeline} \textbf {A} Download of authoritative gene catalogs and primary TSS mapping data from public databases, data repositories and consortium websites. \textbf {B} Quality control (QC) of incoming data (e.g. read mapping efficiency, contaminations, etc.). \textbf {C} Data passing QC are reformatted and incorporated into the MGA repository. \textbf {D} Selection of a subset of TSS mapping experiments for generating a new organism-specific TSS collection. \textbf {E} Input data for a new module of EPDnew. \textbf {F} Organism-specific automatic database assembly pipeline tailored to the input data, see \citep {dreos_epd_2013} for a detailed description of the human EPDnew assembly pipeline. \textbf {G} Preliminary or final TSS collection \textbf {H} Manual sanity checks of individual randomly selected promoter entries using the corresponding entry viewer. \textbf {I} Automatic quality evaluation of the TSS collections as a whole by motif enrichment tests, see Figure \ref {lab_resources_epd_motifs} for an example. \textbf {L} Feedback is collected from quality evaluation steps H and I. This may lead to the exclusion, replacement or addition of source data sets or modifications (e.g. program parameter fine-tuning) of the computational database generation pipeline. Note that the development of a final, publicly released EPDnew module typically involves several evaluation-modification cycles. Figure and legend taken and adapted from \citep {dreos_eukaryotic_2017}.\relax }{figure.caption.12}{}}
\@writefile{lot}{\contentsline {table}{\numberline {2.1}{\ignorespaces \textbf {Current contents of EPDnew} 'Promoters' indicate the number of TSS entries in EPDnew. 'Genes' indicates the number of genes having at least one TSS annotated in EPDnew. 'Genes' indicates the number of protein coding genes contained in the genome annotation (except for nc species). 'nc' stands for non-coding and indicates the long non-coding gene annotations. For 'nc' entries, 'genes' refers to the number of long non-coding genes present in the annotation. In parenthesis are indicated the percentages of genes having a at least one TSS annotated in EPDnew.\relax }}{27}{table.caption.13}}
\newlabel{lab_resources_epd_stats}{{2.1}{27}{\textbf {Current contents of EPDnew} 'Promoters' indicate the number of TSS entries in EPDnew. 'Genes' indicates the number of genes having at least one TSS annotated in EPDnew. 'Genes' indicates the number of protein coding genes contained in the genome annotation (except for nc species). 'nc' stands for non-coding and indicates the long non-coding gene annotations. For 'nc' entries, 'genes' refers to the number of long non-coding genes present in the annotation. In parenthesis are indicated the percentages of genes having a at least one TSS annotated in EPDnew.\relax }{table.caption.13}{}}
\@writefile{toc}{\contentsline {subsection}{\numberline {2.2.1}EPDnew now annotates (some of) your mushrooms and vegetables}{27}{subsection.2.2.1}}
\citation{dreos_eukaryotic_2017}
\citation{dreos_mga_2018}
\citation{ambrosini_chip-seq_2016}
\citation{ambrosini_signal_2003}
\citation{dreos_epd_2013}
\citation{dreos_eukaryotic_2017}
\citation{raney_track_2014}
\@writefile{lof}{\contentsline {figure}{\numberline {2.3}{\ignorespaces \textbf {TSS Mapping precision} Occurrence of the TATA-box \textbf {A} and initiator \textbf {B} around \textit {H.sapiens} TSSs from EPDnew releases (004 and 006) and from a list of gene starts from UCSC Gene list, which was used as input for the generation of the EPDnew collection. This figure was created using Oprof from the SSA server \citep {ambrosini_signal_2003}. Detailed instructions to recreate the figure can be found in section \ref {lab_resources_epd_methods_oprof}.\relax }}{28}{figure.caption.14}}
\newlabel{lab_resources_epd_motifs}{{2.3}{28}{\textbf {TSS Mapping precision} Occurrence of the TATA-box \textbf {A} and initiator \textbf {B} around \textit {H.sapiens} TSSs from EPDnew releases (004 and 006) and from a list of gene starts from UCSC Gene list, which was used as input for the generation of the EPDnew collection. This figure was created using Oprof from the SSA server \citep {ambrosini_signal_2003}. Detailed instructions to recreate the figure can be found in section \ref {lab_resources_epd_methods_oprof}.\relax }{figure.caption.14}{}}
\@writefile{toc}{\contentsline {subsection}{\numberline {2.2.2}Increased mapping precision in human}{28}{subsection.2.2.2}}
\@writefile{toc}{\contentsline {subsection}{\numberline {2.2.3}Integration of EPDnew with other resources}{28}{subsection.2.2.3}}