Merge pull request #44 from superphy/kl-apr-25

merge: pre-revisions
superphy · Jun 15, 2018 · 4f9200a · 4f9200a
2 parents d200d4d + ba29f65
commit 4f9200a
Show file tree

Hide file tree

Showing 40 changed files with 10,977 additions and 445 deletions.
diff --git a/.gitignore b/.gitignore
@@ -1,3 +1,7 @@
+doc/~$*.docx*
+
+*.pyc
+
 .idea/
 
 ## Core latex/pdflatex auxiliary files:

diff --git a/doc/_system_appendPDF_proof_hi (1).pdf b/doc/_system_appendPDF_proof_hi (1).pdf
diff --git a/doc/_system_appendPDF_proof_hi (2).pdf b/doc/_system_appendPDF_proof_hi (2).pdf
diff --git a/doc/_system_appendPDF_proof_hi.pdf b/doc/_system_appendPDF_proof_hi.pdf
diff --git a/doc/captions.docx b/doc/captions.docx
diff --git a/doc/comparison.docx b/doc/comparison.docx
diff --git a/doc/figure1.eps b/doc/figure1.eps
diff --git a/doc/figure1.png b/doc/figure1.png
diff --git a/doc/figure2.eps b/doc/figure2.eps
diff --git a/doc/figure2.png b/doc/figure2.png
diff --git a/doc/figure3.eps b/doc/figure3.eps
diff --git a/doc/figure3.png b/doc/figure3.png
diff --git a/doc/figure4.eps b/doc/figure4.eps
diff --git a/doc/figure4.png b/doc/figure4.png
diff --git a/doc/figure5.eps b/doc/figure5.eps
diff --git a/doc/figure5.png b/doc/figure5.png
diff --git a/doc/figure6.eps b/doc/figure6.eps
diff --git a/doc/figure6.psd b/doc/figure6.psd
diff --git a/doc/figure7.eps b/doc/figure7.eps
diff --git a/doc/figure7.png b/doc/figure7.png
diff --git a/doc/fishers_genomes.png b/doc/fishers_genomes.png
diff --git a/doc/fishers_overall.png b/doc/fishers_overall.png
diff --git a/doc/fishers_targets.png b/doc/fishers_targets.png
diff --git a/doc/manuscript_le-k_et-al.docx b/doc/manuscript_le-k_et-al.docx
diff --git a/doc/manuscript_le-k_et-al_nofigs.docx b/doc/manuscript_le-k_et-al_nofigs.docx
diff --git a/paper-webserver.bib b/paper-webserver.bib
diff --git a/paper-webserver.pdf b/paper-webserver.pdf
diff --git a/paper-webserver.tex b/paper-webserver.tex
@@ -22,7 +22,7 @@
 
 \title{Spfy: an integrated graph database for real-time prediction of bacterial phenotypes and downstream comparative analyses}
 
-\author[1]{Kevin K Le\thanks{kevin.le@canada.ca}}
+\author[1]{Kevin K Le\thanks{kle009@uottawa.ca}}
 \author[1]{Matthew D Whiteside}
 \author[1]{James E Hopkins}
 \author[1]{Victor PJ Gannon}
@@ -192,7 +192,7 @@ \subsection{Data Storage}
 
 Spfy primarily uses Blazegraph \url{https://github.com/blazegraph/database} for storage along with MongoDB to cache a hash table for duplicate checking.
 The cache allows Spfy to more efficiently check for duplicate files in Blazegraph than would be possible through a search of the graph structure.
-MongoDB is also used to support the 
+MongoDB is also used to support the synchronized user sessions feature of the website.
 
 \subsection{Web design}
 % para
@@ -343,7 +343,7 @@ \subsection{Comparison with other bioinformatics pipeline technologies}
 Note, however, that the two platforms are not directly comparable, due to the differences in analysis tasks involved.
 In similar tasks such as AMR determination, the ResFinder program included in BAP took an average of 3-4 minutes \cite{thomsen2016bacterial} and is similar to the RGI program included in Spfy, which took an average of 1 minute 30 seconds.
 
-However, unlike these workflow managers, Spfy is designed to help solve the re-computation of analyses by storing results in a graph database for downstream comparative studies \ref{db_comparison}. This allows Spfy to, for example, perform population-wide analyses on varied data from multiple diverse individual software.
+However, unlike these workflow managers, Spfy is designed to help solve the re-computation of analyses by storing results in a graph database for downstream comparative studies (Table \ref{db_comparison}). This allows Spfy to, for example, perform population-wide analyses on varied data from multiple diverse individual software.
 
 \small \input{tables/comparison}
 
@@ -355,28 +355,9 @@ \section{CONCLUSIONS}
 
 \textit{Conflict of interest}. None declared.
 
-\section{ACKNOWLEDGEMENTS}
-
 \newpage
 
 \bibliographystyle{unsrt}
 \bibliography{paper-webserver}
 
-\newpage
-
-\section{APPENDIX}
-
-\section{SUPPLEMENTARY INFORMATION}
-
-% Again, label panes as a) and b), then reference in the caption
-\begin{figure}[!htb]
-\minipage{0.5\textwidth}
-  \includegraphics[width=\linewidth]{images/spfy_indivs.png}
-\endminipage\hfill
-\minipage{0.5\textwidth}%
-  \includegraphics[width=\linewidth]{images/spfy_batches.png}
-\endminipage
-\caption{Runtimes of Spfy's analysis modules. A: 100 genomes were run individually, with each coloured dot representing the runtime of a separate analysis module. The blue line indicates the average actual runtime per file after accounting for parallelization. B: Average runtime when multiple genomes are enqueued together. As indicated by the line, the average runtime per genome in consistent when running more than one file.}\label{fig:supp_spfy_performance}
-\end{figure}
-
 \end{document}
diff --git a/scripts/.ipynb_checkpoints/disk_comparisons-checkpoint.ipynb b/scripts/.ipynb_checkpoints/disk_comparisons-checkpoint.ipynb
diff --git a/scripts/api-2018-05-03-10-22-35-670254_list.p b/scripts/api-2018-05-03-10-22-35-670254_list.p