Skip to content
Browse files

improved and clean dataset construction (clustering requires cd-hit)

  • Loading branch information...
1 parent 7292535 commit eb8eade3f13189db76c806e734c8d6ea0d51d843 @waldispuhl waldispuhl committed Oct 5, 2012
View
31 Recomb/main_RECOMB.aux
@@ -0,0 +1,31 @@
+\relax
+\citation{Waldispuhl2008}
+\citation{Lari1990}
+\citation{Turner2010}
+\citation{Stombaugh2009}
+\citation{Stombaugh2009}
+\citation{Turner2010}
+\citation{Stombaugh2009}
+\@writefile{toc}{\contentsline {section}{\numberline {1}Introduction}{2}}
+\newlabel{sec:introduction}{{1}{2}}
+\@writefile{toc}{\contentsline {section}{\numberline {2}Methods}{2}}
+\newlabel{sec:methods}{{2}{2}}
+\@writefile{toc}{\contentsline {subsection}{\numberline {2.1}Definitions}{2}}
+\@writefile{toc}{\contentsline {subsection}{\numberline {2.2}Energy Model}{2}}
+\@writefile{toc}{\contentsline {subsection}{\numberline {2.3}Inside}{3}}
+\newlabel{eq:Z_in}{{1}{3}}
+\newlabel{eq:Z_rec}{{2}{3}}
+\@writefile{toc}{\contentsline {subsection}{\numberline {2.4}Outside}{4}}
+\newlabel{eq:Y_in}{{3}{4}}
+\newlabel{eq:Y_rec}{{4}{4}}
+\@writefile{toc}{\contentsline {section}{\numberline {3}Inside-Outside}{5}}
+\citation{mpmath}
+\@writefile{toc}{\contentsline {section}{\numberline {4}Results}{6}}
+\newlabel{sec:results}{{4}{6}}
+\@writefile{toc}{\contentsline {subsection}{\numberline {4.1}Implementation}{6}}
+\@writefile{toc}{\contentsline {section}{\numberline {5}Discussion}{6}}
+\newlabel{sec:conclusion}{{5}{6}}
+\@writefile{toc}{\contentsline {section}{\numberline {6}Acknowledgments}{6}}
+\newlabel{sec:acknowledgments}{{6}{6}}
+\bibstyle{plainnat}
+\bibdata{RNApyro}
View
431 Recomb/main_RECOMB.log
@@ -0,0 +1,431 @@
+This is pdfTeX, Version 3.1415926-2.4-1.40.13 (TeX Live 2012/MacPorts 2012_1) (format=pdflatex 2012.8.9) 5 OCT 2012 03:40
+entering extended mode
+ \write18 enabled.
+ file:line:error style messages enabled.
+ %&-line parsing enabled.
+**main_RECOMB.tex
+(./main_RECOMB.tex
+LaTeX2e <2011/06/27>
+Babel <v3.8m> and hyphenation patterns for english, dumylang, nohyphenation, uk
+english, usenglishmax, basque, french, loaded.
+(/opt/local/share/texmf-texlive-dist/tex/latex/base/article.cls
+Document Class: article 2007/10/19 v1.4h Standard LaTeX document class
+(/opt/local/share/texmf-texlive-dist/tex/latex/base/size11.clo
+File: size11.clo 2007/10/19 v1.4h Standard LaTeX file (size option)
+)
+\c@part=\count79
+\c@section=\count80
+\c@subsection=\count81
+\c@subsubsection=\count82
+\c@paragraph=\count83
+\c@subparagraph=\count84
+\c@figure=\count85
+\c@table=\count86
+\abovecaptionskip=\skip41
+\belowcaptionskip=\skip42
+\bibindent=\dimen102
+)
+(/opt/local/share/texmf-texlive-dist/tex/latex/geometry/geometry.sty
+Package: geometry 2010/09/12 v5.6 Page Geometry
+
+(/opt/local/share/texmf-texlive-dist/tex/latex/graphics/keyval.sty
+Package: keyval 1999/03/16 v1.13 key=value parser (DPC)
+\KV@toks@=\toks14
+)
+(/opt/local/share/texmf-texlive-dist/tex/generic/oberdiek/ifpdf.sty
+Package: ifpdf 2011/01/30 v2.3 Provides the ifpdf switch (HO)
+Package ifpdf Info: pdfTeX in PDF mode is detected.
+)
+(/opt/local/share/texmf-texlive-dist/tex/generic/oberdiek/ifvtex.sty
+Package: ifvtex 2010/03/01 v1.5 Detect VTeX and its facilities (HO)
+Package ifvtex Info: VTeX not detected.
+)
+(/opt/local/share/texmf-texlive-dist/tex/generic/ifxetex/ifxetex.sty
+Package: ifxetex 2010/09/12 v0.6 Provides ifxetex conditional
+)
+\Gm@cnth=\count87
+\Gm@cntv=\count88
+\c@Gm@tempcnt=\count89
+\Gm@bindingoffset=\dimen103
+\Gm@wd@mp=\dimen104
+\Gm@odd@mp=\dimen105
+\Gm@even@mp=\dimen106
+\Gm@layoutwidth=\dimen107
+\Gm@layoutheight=\dimen108
+\Gm@layouthoffset=\dimen109
+\Gm@layoutvoffset=\dimen110
+\Gm@dimlist=\toks15
+)
+(/opt/local/share/texmf-texlive-dist/tex/latex/graphics/graphicx.sty
+Package: graphicx 1999/02/16 v1.0f Enhanced LaTeX Graphics (DPC,SPQR)
+
+(/opt/local/share/texmf-texlive-dist/tex/latex/graphics/graphics.sty
+Package: graphics 2009/02/05 v1.0o Standard LaTeX Graphics (DPC,SPQR)
+
+(/opt/local/share/texmf-texlive-dist/tex/latex/graphics/trig.sty
+Package: trig 1999/03/16 v1.09 sin cos tan (DPC)
+)
+(/opt/local/share/texmf-texlive-dist/tex/latex/latexconfig/graphics.cfg
+File: graphics.cfg 2010/04/23 v1.9 graphics configuration of TeX Live
+)
+Package graphics Info: Driver file: pdftex.def on input line 91.
+
+(/opt/local/share/texmf-texlive-dist/tex/latex/pdftex-def/pdftex.def
+File: pdftex.def 2011/05/27 v0.06d Graphics/color for pdfTeX
+
+(/opt/local/share/texmf-texlive-dist/tex/generic/oberdiek/infwarerr.sty
+Package: infwarerr 2010/04/08 v1.3 Providing info/warning/error messages (HO)
+)
+(/opt/local/share/texmf-texlive-dist/tex/generic/oberdiek/ltxcmds.sty
+Package: ltxcmds 2011/11/09 v1.22 LaTeX kernel commands for general use (HO)
+)
+\Gread@gobject=\count90
+))
+\Gin@req@height=\dimen111
+\Gin@req@width=\dimen112
+)
+(/opt/local/share/texmf-texlive-dist/tex/latex/amsfonts/amssymb.sty
+Package: amssymb 2009/06/22 v3.00
+
+(/opt/local/share/texmf-texlive-dist/tex/latex/amsfonts/amsfonts.sty
+Package: amsfonts 2009/06/22 v3.00 Basic AMSFonts support
+\@emptytoks=\toks16
+\symAMSa=\mathgroup4
+\symAMSb=\mathgroup5
+LaTeX Font Info: Overwriting math alphabet `\mathfrak' in version `bold'
+(Font) U/euf/m/n --> U/euf/b/n on input line 96.
+))
+(/opt/local/share/texmf-texlive-dist/tex/latex/amsmath/amsmath.sty
+Package: amsmath 2000/07/18 v2.13 AMS math features
+\@mathmargin=\skip43
+
+For additional information on amsmath, use the `?' option.
+(/opt/local/share/texmf-texlive-dist/tex/latex/amsmath/amstext.sty
+Package: amstext 2000/06/29 v2.01
+
+(/opt/local/share/texmf-texlive-dist/tex/latex/amsmath/amsgen.sty
+File: amsgen.sty 1999/11/30 v2.0
+\@emptytoks=\toks17
+\ex@=\dimen113
+))
+(/opt/local/share/texmf-texlive-dist/tex/latex/amsmath/amsbsy.sty
+Package: amsbsy 1999/11/29 v1.2d
+\pmbraise@=\dimen114
+)
+(/opt/local/share/texmf-texlive-dist/tex/latex/amsmath/amsopn.sty
+Package: amsopn 1999/12/14 v2.01 operator names
+)
+\inf@bad=\count91
+LaTeX Info: Redefining \frac on input line 211.
+\uproot@=\count92
+\leftroot@=\count93
+LaTeX Info: Redefining \overline on input line 307.
+\classnum@=\count94
+\DOTSCASE@=\count95
+LaTeX Info: Redefining \ldots on input line 379.
+LaTeX Info: Redefining \dots on input line 382.
+LaTeX Info: Redefining \cdots on input line 467.
+\Mathstrutbox@=\box26
+\strutbox@=\box27
+\big@size=\dimen115
+LaTeX Font Info: Redeclaring font encoding OML on input line 567.
+LaTeX Font Info: Redeclaring font encoding OMS on input line 568.
+\macc@depth=\count96
+\c@MaxMatrixCols=\count97
+\dotsspace@=\muskip10
+\c@parentequation=\count98
+\dspbrk@lvl=\count99
+\tag@help=\toks18
+\row@=\count100
+\column@=\count101
+\maxfields@=\count102
+\andhelp@=\toks19
+\eqnshift@=\dimen116
+\alignsep@=\dimen117
+\tagshift@=\dimen118
+\tagwidth@=\dimen119
+\totwidth@=\dimen120
+\lineht@=\dimen121
+\@envbody=\toks20
+\multlinegap=\skip44
+\multlinetaggap=\skip45
+\mathdisplay@stack=\toks21
+LaTeX Info: Redefining \[ on input line 2666.
+LaTeX Info: Redefining \] on input line 2667.
+)
+(/opt/local/share/texmf-texlive-dist/tex/latex/amscls/amsthm.sty
+Package: amsthm 2009/07/02 v2.20.1
+\thm@style=\toks22
+\thm@bodyfont=\toks23
+\thm@headfont=\toks24
+\thm@notefont=\toks25
+\thm@headpunct=\toks26
+\thm@preskip=\skip46
+\thm@postskip=\skip47
+\thm@headsep=\skip48
+\dth@everypar=\toks27
+)
+(/opt/local/share/texmf-texlive-dist/tex/latex/oberdiek/epstopdf.sty
+Package: epstopdf 2010/02/09 v2.5 Conversion with epstopdf on the fly (HO)
+
+(/opt/local/share/texmf-texlive-dist/tex/latex/oberdiek/epstopdf-base.sty
+Package: epstopdf-base 2010/02/09 v2.5 Base part for package epstopdf
+
+(/opt/local/share/texmf-texlive-dist/tex/latex/oberdiek/grfext.sty
+Package: grfext 2010/08/19 v1.1 Manage graphics extensions (HO)
+
+(/opt/local/share/texmf-texlive-dist/tex/generic/oberdiek/kvdefinekeys.sty
+Package: kvdefinekeys 2011/04/07 v1.3 Define keys (HO)
+))
+(/opt/local/share/texmf-texlive-dist/tex/latex/oberdiek/kvoptions.sty
+Package: kvoptions 2011/06/30 v3.11 Key value format for package options (HO)
+
+(/opt/local/share/texmf-texlive-dist/tex/generic/oberdiek/kvsetkeys.sty
+Package: kvsetkeys 2012/04/25 v1.16 Key value parser (HO)
+
+(/opt/local/share/texmf-texlive-dist/tex/generic/oberdiek/etexcmds.sty
+Package: etexcmds 2011/02/16 v1.5 Avoid name clashes with e-TeX commands (HO)
+
+(/opt/local/share/texmf-texlive-dist/tex/generic/oberdiek/ifluatex.sty
+Package: ifluatex 2010/03/01 v1.3 Provides the ifluatex switch (HO)
+Package ifluatex Info: LuaTeX not detected.
+)
+Package etexcmds Info: Could not find \expanded.
+(etexcmds) That can mean that you are not using pdfTeX 1.50 or
+(etexcmds) that some package has redefined \expanded.
+(etexcmds) In the latter case, load this package earlier.
+)))
+(/opt/local/share/texmf-texlive-dist/tex/generic/oberdiek/pdftexcmds.sty
+Package: pdftexcmds 2011/11/29 v0.20 Utility functions of pdfTeX for LuaTeX (HO
+)
+Package pdftexcmds Info: LuaTeX not detected.
+Package pdftexcmds Info: \pdf@primitive is available.
+Package pdftexcmds Info: \pdf@ifprimitive is available.
+Package pdftexcmds Info: \pdfdraftmode found.
+)
+Package grfext Info: Graphics extension search list:
+(grfext) [.png,.pdf,.jpg,.mps,.jpeg,.jbig2,.jb2,.PNG,.PDF,.JPG,.JPE
+G,.JBIG2,.JB2,.eps]
+(grfext) \AppendGraphicsExtensions on input line 452.
+
+(/opt/local/share/texmf-texlive-dist/tex/latex/latexconfig/epstopdf-sys.cfg
+File: epstopdf-sys.cfg 2010/07/13 v1.3 Configuration of (r)epstopdf for TeX Liv
+e
+)))
+(/opt/local/share/texmf-texlive-dist/tex/latex/tools/xspace.sty
+Package: xspace 2009/10/20 v1.13 Space after command names (DPC,MH)
+)
+(/opt/local/share/texmf-texlive-dist/tex/latex/natbib/natbib.sty
+Package: natbib 2010/09/13 8.31b (PWD, AO)
+\bibhang=\skip49
+\bibsep=\skip50
+LaTeX Info: Redefining \cite on input line 694.
+\c@NAT@ctr=\count103
+)
+(/opt/local/share/texmf-texlive-dist/tex/latex/subfig/subfig.sty
+Package: subfig 2005/06/28 ver: 1.3 subfig package
+
+(/opt/local/share/texmf-texlive-dist/tex/latex/caption/caption.sty
+Package: caption 2012/02/19 v3.2f Customizing captions (AR)
+
+(/opt/local/share/texmf-texlive-dist/tex/latex/caption/caption3.sty
+Package: caption3 2012/01/12 v1.4b caption3 kernel (AR)
+\captionmargin=\dimen122
+\captionmargin@=\dimen123
+\captionwidth=\dimen124
+\caption@indent=\dimen125
+\caption@parindent=\dimen126
+\caption@hangindent=\dimen127
+)
+\c@ContinuedFloat=\count104
+)
+\c@KVtest=\count105
+\sf@farskip=\skip51
+\sf@captopadj=\dimen128
+\sf@capskip=\skip52
+\sf@nearskip=\skip53
+\c@subfigure=\count106
+\c@subfigure@save=\count107
+\c@lofdepth=\count108
+\c@subtable=\count109
+\c@subtable@save=\count110
+\c@lotdepth=\count111
+\sf@top=\skip54
+\sf@bottom=\skip55
+)
+(/opt/local/share/texmf-texlive-dist/tex/latex/base/inputenc.sty
+Package: inputenc 2008/03/30 v1.1d Input encoding file
+\inpenc@prehook=\toks28
+\inpenc@posthook=\toks29
+
+(/opt/local/share/texmf-texlive-dist/tex/latex/base/applemac.def
+File: applemac.def 2008/03/30 v1.1d Input encoding file
+))
+(./main_RECOMB.aux)
+\openout1 = `main_RECOMB.aux'.
+
+LaTeX Font Info: Checking defaults for OML/cmm/m/it on input line 65.
+LaTeX Font Info: ... okay on input line 65.
+LaTeX Font Info: Checking defaults for T1/cmr/m/n on input line 65.
+LaTeX Font Info: ... okay on input line 65.
+LaTeX Font Info: Checking defaults for OT1/cmr/m/n on input line 65.
+LaTeX Font Info: ... okay on input line 65.
+LaTeX Font Info: Checking defaults for OMS/cmsy/m/n on input line 65.
+LaTeX Font Info: ... okay on input line 65.
+LaTeX Font Info: Checking defaults for OMX/cmex/m/n on input line 65.
+LaTeX Font Info: ... okay on input line 65.
+LaTeX Font Info: Checking defaults for U/cmr/m/n on input line 65.
+LaTeX Font Info: ... okay on input line 65.
+
+*geometry* driver: auto-detecting
+*geometry* detected driver: pdftex
+*geometry* verbose mode - [ preamble ] result:
+* driver: pdftex
+* paper: letterpaper
+* layout: <same size as paper>
+* layoutoffset:(h,v)=(0.0pt,0.0pt)
+* modes:
+* h-part:(L,W,R)=(72.26999pt, 469.75502pt, 72.26999pt)
+* v-part:(T,H,B)=(72.26999pt, 650.43001pt, 72.26999pt)
+* \paperwidth=614.295pt
+* \paperheight=794.96999pt
+* \textwidth=469.75502pt
+* \textheight=650.43001pt
+* \oddsidemargin=0.0pt
+* \evensidemargin=0.0pt
+* \topmargin=-37.0pt
+* \headheight=12.0pt
+* \headsep=25.0pt
+* \topskip=11.0pt
+* \footskip=30.0pt
+* \marginparwidth=59.0pt
+* \marginparsep=10.0pt
+* \columnsep=10.0pt
+* \skip\footins=10.0pt plus 4.0pt minus 2.0pt
+* \hoffset=0.0pt
+* \voffset=0.0pt
+* \mag=1000
+* \@twocolumnfalse
+* \@twosidefalse
+* \@mparswitchfalse
+* \@reversemarginfalse
+* (1in=72.27pt=25.4mm, 1cm=28.453pt)
+
+(/opt/local/share/texmf-texlive-dist/tex/context/base/supp-pdf.mkii
+[Loading MPS to PDF converter (version 2006.09.02).]
+\scratchcounter=\count112
+\scratchdimen=\dimen129
+\scratchbox=\box28
+\nofMPsegments=\count113
+\nofMParguments=\count114
+\everyMPshowfont=\toks30
+\MPscratchCnt=\count115
+\MPscratchDim=\dimen130
+\MPnumerator=\count116
+\makeMPintoPDFobject=\count117
+\everyMPtoPDFconversion=\toks31
+)
+Package caption Info: Begin \AtBeginDocument code.
+Package caption Info: subfig package v1.3 is loaded.
+Package caption Info: End \AtBeginDocument code.
+LaTeX Font Info: Try loading font information for U+msa on input line 66.
+ (/opt/local/share/texmf-texlive-dist/tex/latex/amsfonts/umsa.fd
+File: umsa.fd 2009/06/22 v3.00 AMS symbols A
+)
+LaTeX Font Info: Try loading font information for U+msb on input line 66.
+
+(/opt/local/share/texmf-texlive-dist/tex/latex/amsfonts/umsb.fd
+File: umsb.fd 2009/06/22 v3.00 AMS symbols B
+)
+
+Package natbib Warning: Citation `Waldispuhl2008' on page 1 undefined on input
+line 70.
+
+[1
+
+{/opt/local/var/db/texmf/fonts/map/pdftex/updmap/pdftex.map}]
+(./introduction_RECOMB.tex) (./methods_RECOMB.tex
+
+Package natbib Warning: Citation `Lari1990' on page 2 undefined on input line 1
+2.
+
+
+Package natbib Warning: Citation `Turner2010' on page 2 undefined on input line
+ 25.
+
+
+Package natbib Warning: Citation `Stombaugh2009' on page 2 undefined on input l
+ine 28.
+
+
+Package natbib Warning: Citation `Stombaugh2009' on page 2 undefined on input l
+ine 31.
+
+
+Package natbib Warning: Citation `Turner2010' on page 2 undefined on input line
+ 53.
+
+
+Package natbib Warning: Citation `Stombaugh2009' on page 2 undefined on input l
+ine 82.
+
+[2]
+Overfull \hbox (7.93922pt too wide) detected at line 126
+\OMS/cmsy/m/n/10.95 Z[] \OT1/cmr/m/n/10.95 := []
+ []
+
+[3]
+Overfull \hbox (13.54973pt too wide) detected at line 194
+\OMS/cmsy/m/n/10.95 Y[] \OT1/cmr/m/n/10.95 = []
+ []
+
+[4]
+Overfull \hbox (28.9141pt too wide) detected at line 280
+\U/msb/m/n/10.95 P\OT1/cmr/m/n/10.95 (\OML/cmm/m/it/10.95 s[] \OT1/cmr/m/n/10.9
+5 = \OML/cmm/m/it/10.95 x \OMS/cmsy/m/n/10.95 j \OML/cmm/m/it/10.95 s; \OT1/cmr
+/m/n/10.95
+\OML/cmm/m/it/10.95 ; S; M\OT1/cmr/m/n/10.95 ) := []
+ []
+
+[5]) (./results_RECOMB.tex
+
+Package natbib Warning: Citation `mpmath' on page 6 undefined on input line 6.
+
+) (./conclusion_RECOMB.tex) (./acknowledgments_RECOMB.tex) [6]
+No file main_RECOMB.bbl.
+
+Package natbib Warning: There were undefined citations.
+
+(./main_RECOMB.aux) )
+Here is how much of TeX's memory you used:
+ 4516 strings out of 494993
+ 65871 string characters out of 3179410
+ 138374 words of memory out of 3000000
+ 7634 multiletter control sequences out of 15000+200000
+ 12174 words of font info for 46 fonts, out of 3000000 for 9000
+ 36 hyphenation exceptions out of 8191
+ 44i,14n,42p,324b,199s stack positions out of 5000i,500n,10000p,200000b,50000s
+</opt/local/share/texmf-texlive-dist/fonts/type1/public/am
+sfonts/cm/cmbx10.pfb></opt/local/share/texmf-texlive-dist/fonts/type1/public/am
+sfonts/cm/cmbx12.pfb></opt/local/share/texmf-texlive-dist/fonts/type1/public/am
+sfonts/cm/cmex10.pfb></opt/local/share/texmf-texlive-dist/fonts/type1/public/am
+sfonts/cm/cmmi10.pfb></opt/local/share/texmf-texlive-dist/fonts/type1/public/am
+sfonts/cm/cmmi6.pfb></opt/local/share/texmf-texlive-dist/fonts/type1/public/ams
+fonts/cm/cmmi8.pfb></opt/local/share/texmf-texlive-dist/fonts/type1/public/amsf
+onts/cm/cmr10.pfb></opt/local/share/texmf-texlive-dist/fonts/type1/public/amsfo
+nts/cm/cmr17.pfb></opt/local/share/texmf-texlive-dist/fonts/type1/public/amsfon
+ts/cm/cmr6.pfb></opt/local/share/texmf-texlive-dist/fonts/type1/public/amsfonts
+/cm/cmr8.pfb></opt/local/share/texmf-texlive-dist/fonts/type1/public/amsfonts/c
+m/cmsy10.pfb></opt/local/share/texmf-texlive-dist/fonts/type1/public/amsfonts/c
+m/cmsy6.pfb></opt/local/share/texmf-texlive-dist/fonts/type1/public/amsfonts/cm
+/cmsy8.pfb></opt/local/share/texmf-texlive-dist/fonts/type1/public/amsfonts/cm/
+cmti10.pfb></opt/local/share/texmf-texlive-dist/fonts/type1/public/amsfonts/cm/
+cmtt10.pfb></opt/local/share/texmf-texlive-dist/fonts/type1/public/amsfonts/sym
+bols/msbm10.pfb>
+Output written on main_RECOMB.pdf (6 pages, 192436 bytes).
+PDF statistics:
+ 87 PDF objects out of 1000 (max. 8388607)
+ 62 compressed objects within 1 object stream
+ 0 named destinations out of 1000 (max. 500000)
+ 1 words of extra memory for PDF output out of 10000 (max. 10000000)
+
View
BIN Recomb/main_RECOMB.pdf
Binary file not shown.
View
BIN Recomb/main_RECOMB.synctex.gz
Binary file not shown.
View
2 Recomb/main_RECOMB.tex
@@ -47,7 +47,7 @@
\newcommand{\Kron}{\delta}
\newcommand{\ub}{\bullet}
-\title{RNApyro}
+\title{An inside-outside algorithms for mutant RNAs with applications to error detections in structured RNAs}
\author{}
\date{}
View
3,560 benchmark/RF00001.seed.afa.txt
0 additions, 3,560 deletions not shown because the diff is too large. Please use a local Git client to view these changes.
View
9 benchmark/runbenchmark.sh
@@ -1,9 +0,0 @@
-python ../scripts/benchmark.py -i RF00001_0.ref -o RF00001_0_alpha_50.out
-python ../scripts/benchmark.py -i RF00001_1.ref -o RF00001_1_alpha_50.out
-python ../scripts/benchmark.py -i RF00001_2.ref -o RF00001_2_alpha_50.out
-python ../scripts/benchmark.py -i RF00001_3.ref -o RF00001_3_alpha_50.out
-python ../scripts/benchmark.py -i RF00001_4.ref -o RF00001_4_alpha_50.out
-python ../scripts/benchmark.py -i RF00001_5.ref -o RF00001_5_alpha_50.out
-python ../scripts/benchmark.py -i RF00001_6.ref -o RF00001_6_alpha_50.out
-python ../scripts/benchmark.py -i RF00001_7.ref -o RF00001_7_alpha_50.out
-python ../scripts/benchmark.py -i RF00001_8.ref -o RF00001_8_alpha_50.out
View
9 benchmark/runtest.py
@@ -6,11 +6,12 @@ def main(nmut,alpha,prefix):
infile = "RF00001_%d.in" % numex
if os.path.exists(infile):
alphanorm = int (alpha * 100)
- commandline1="python ../src/RNAPyroEx.py RF00001_%d.in %d %.1f > RF00001_%d_alpha_%d.out" % (numex,nmut,alpha,numex,alphanorm)
+ commandline1="python ../src/RNAPyroEx.py RF00001_%d.in %d %.1f > RF00001_%d_nmut_%d_alpha_%d.out" % (numex,nmut,alpha,numex,nmut,alphanorm)
+ print commandline1
os.system(commandline1)
- commandline1="python ../scripts/benchmark.py -i RF00001_%d.ref -o RF00001_%d_alpha_%d.out" % (numex,numex,alphanorm)
- os.system(commandline1)
-
+ commandline2="python ../scripts/benchmark.py -i RF00001_%d.ref -o RF00001_%d_nmut_%d_alpha_%d.out" % (numex,numex,nmut,alphanorm)
+ print commandline2
+ os.system(commandline2)
###############################################################################
View
8 benchmark/runtest.sh
@@ -1,8 +0,0 @@
-python ../src/RNAPyroEx.py RF00001_1.in 10 0.5 > RF00001_1_alpha_50.out
-python ../src/RNAPyroEx.py RF00001_2.in 10 0.5 > RF00001_2_alpha_50.out
-python ../src/RNAPyroEx.py RF00001_3.in 10 0.5 > RF00001_3_alpha_50.out
-python ../src/RNAPyroEx.py RF00001_4.in 10 0.5 > RF00001_4_alpha_50.out
-python ../src/RNAPyroEx.py RF00001_5.in 10 0.5 > RF00001_5_alpha_50.out
-python ../src/RNAPyroEx.py RF00001_6.in 10 0.5 > RF00001_6_alpha_50.out
-python ../src/RNAPyroEx.py RF00001_7.in 10 0.5 > RF00001_7_alpha_50.out
-python ../src/RNAPyroEx.py RF00001_8.in 10 0.5 > RF00001_8_alpha_50.out
View
100 scripts/RfamParser.py
@@ -182,7 +182,7 @@ def clusterUnGapped(data):
#################################################################################
-def main(filename,nmut,idc,listflag,out):
+def main(filename,nmut,idc,listflag,out,select,cluster):
seqline_re = re.compile("(\S+)(\s+)(\S+)");
@@ -242,11 +242,42 @@ def main(filename,nmut,idc,listflag,out):
sys.exit(1)
hcode=idMap['num2code'][idc]
- if out=="":
- listout = []
- listout.append(random.randint(0,len(cleandata[hcode])-1))
+ myRawCluster=cleandata[hcode]
+
+ if cluster:
+ # cluster 80% of seq similarity using cd-hit
+ f = open('all.fasta','w')
+ for myid,myseq in myRawCluster.iteritems():
+ cleanseq,cleanssa = fitstruct2seq(myseq,info['consensus'],False)
+ print >>f, '> ' + str(myid)
+ print >>f, cleanseq
+ f.close()
+ commandline = ' ~/local/cd-hit/cd-hit-est -i all.fasta -o filter.fasta -c 0.8 -n 4 > /dev/null'
+ os.system(commandline)
+ myCleanCluster = {}
+ f = open('filter.fasta','r')
+ for line in f:
+ selected_ids = []
+ if line.startswith('>'):
+ id = line[1:].strip()
+ myCleanCluster[id] = myRawCluster[id]
+ f.close()
+ print len(myCleanCluster),'sequences selected'
+ else:
+ myCleanCluster = myRawCluster
+
+
+
+ if select==-1:
+ listout = range(len(myCleanCluster))
+ elif select==0:
+ listout = [-1]
else:
- listout = range(len(cleandata[hcode]))
+ listout = []
+ while (len(listout)<select):
+ index = random.randint(0,len(myCleanCluster)-1)
+ if not index in listout:
+ listout.append(index)
for iseqout in listout:
ssamatch=True
@@ -258,10 +289,14 @@ def main(filename,nmut,idc,listflag,out):
fout_in = sys.stdout
fout_ref = sys.stdout
else:
- fout_in = open(out + "_" + str(iseqout) + ".in","w")
- fout_ref = open(out + "_" + str(iseqout) + ".ref","w")
-
- for myid,myseq in cleandata[hcode].iteritems():
+ if select!=0:
+ fout_in = open(out + "_" + str(iseqout) + ".in","w")
+ fout_ref = open(out + "_" + str(iseqout) + ".ref","w")
+ else:
+ fout_in = open(out + "_all.fasta","w")
+ fout_ref = open(out + "_all.ref","w")
+
+ for myid,myseq in myCleanCluster.iteritems():
cleanseq,cleanssa = fitstruct2seq(myseq,info['consensus'],False)
if cmpt!=iseqout:
print >>fout_in, '> ' + str(myid)
@@ -272,23 +307,24 @@ def main(filename,nmut,idc,listflag,out):
cmpt+=1
if prevssa != '' and prevssa != cleanssa:
ssamatch=False
- print >>fout_in, '> structure'
- print >>fout_in, prevssa
- if out!="":
+ if select!=0:
+ print >>fout_in, '> structure'
+ print >>fout_in, prevssa
print >>fout_ref, '> structure'
print >>fout_ref, prevssa
+
+ cleanseq = myCleanCluster[idout].replace('.','')
+ mutant = mutate(cleanseq,nmut)
+ print >>fout_in, '> ' + str(idout) + ' (' + str(nmut) + '-mutant) read'
+ print >>fout_in, mutant
+ if out!="":
+ print >>fout_ref, '> ' + str(idout) + ' (' + str(nmut) + '-mutant) read'
+ print >>fout_ref, mutant
+ print >>fout_ref, '> ' + str(idout) + ' target'
+ print >>fout_ref, cleanseq
+
if not ssamatch:
print 'WARNING: Structure do not match'
-
- cleanseq = cleandata[hcode][idout].replace('.','')
- mutant = mutate(cleanseq,nmut)
- print >>fout_in, '> ' + str(idout) + ' (' + str(nmut) + '-mutant) read'
- print >>fout_in, mutant
- if out!="":
- print >>fout_ref, '> ' + str(idout) + ' (' + str(nmut) + '-mutant) read'
- print >>fout_ref, mutant
- print >>fout_ref, '> ' + str(idout) + ' target'
- print >>fout_ref, cleanseq
sys.exit(1)
@@ -297,7 +333,7 @@ def main(filename,nmut,idc,listflag,out):
if __name__ == '__main__':
try:
- opts, args = getopt.getopt(sys.argv[1:], "hf:m:n:lo:", ["help", "file=", "mut=", "id=", "list", "out="]);
+ opts, args = getopt.getopt(sys.argv[1:], "hf:m:n:lo:s:c", ["help", "file=", "mut=", "id=", "list", "out=","select=","cluster"]);
except getopt.GetoptError:
usage(sys.argv[0]);
@@ -306,6 +342,8 @@ def main(filename,nmut,idc,listflag,out):
id=0;
listflag=False;
out="";
+ select=-1;
+ cluster=False;
argStart=len(sys.argv);
for o,a in opts:
@@ -314,20 +352,26 @@ def main(filename,nmut,idc,listflag,out):
if o in ("-f", "--file"):
filename = a;
argStart-=2;
- if o in ("-m", "--file"):
+ if o in ("-m", "--mut"):
nmut = int(a);
argStart -=2;
- if o in ("-n", "--file"):
+ if o in ("-n", "--num"):
id = int(a);
argStart-=2;
if o in ("-l", "--list"):
listflag = True;
argStart-=1;
if o in ("-o", "--out"):
- out = a;
- argStart-=2;
+ out = a;
+ argStart-=2;
+ if o in ("-s", "--select"):
+ select = int(a);
+ argStart-=2;
+ if o in ("-c", "--cluster"):
+ cluster = True;
+ argStart-=1;
- main(filename,nmut,id,listflag,out);
+ main(filename,nmut,id,listflag,out,select,cluster);

0 comments on commit eb8eade

Please sign in to comment.
Something went wrong with that request. Please try again.