diff --git a/LICENSE b/LICENSE new file mode 100644 --- /dev/null +++ b/LICENSE @@ -0,0 +1,340 @@ + GNU GENERAL PUBLIC LICENSE + Version 2, June 1991 + + Copyright (C) 1989, 1991 Free Software Foundation, Inc. + 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + Everyone is permitted to copy and distribute verbatim copies + of this license document, but changing it is not allowed. + + Preamble + + The licenses for most software are designed to take away your +freedom to share and change it. By contrast, the GNU General Public +License is intended to guarantee your freedom to share and change free +software--to make sure the software is free for all its users. This +General Public License applies to most of the Free Software +Foundation's software and to any other program whose authors commit to +using it. (Some other Free Software Foundation software is covered by +the GNU Library General Public License instead.) You can apply it to +your programs, too. + + When we speak of free software, we are referring to freedom, not +price. Our General Public Licenses are designed to make sure that you +have the freedom to distribute copies of free software (and charge for +this service if you wish), that you receive source code or can get it +if you want it, that you can change the software or use pieces of it +in new free programs; and that you know you can do these things. + + To protect your rights, we need to make restrictions that forbid +anyone to deny you these rights or to ask you to surrender the rights. +These restrictions translate to certain responsibilities for you if you +distribute copies of the software, or if you modify it. + + For example, if you distribute copies of such a program, whether +gratis or for a fee, you must give the recipients all the rights that +you have. You must make sure that they, too, receive or can get the +source code. And you must show them these terms so they know their +rights. + + We protect your rights with two steps: (1) copyright the software, and +(2) offer you this license which gives you legal permission to copy, +distribute and/or modify the software. + + Also, for each author's protection and ours, we want to make certain +that everyone understands that there is no warranty for this free +software. If the software is modified by someone else and passed on, we +want its recipients to know that what they have is not the original, so +that any problems introduced by others will not reflect on the original +authors' reputations. + + Finally, any free program is threatened constantly by software +patents. We wish to avoid the danger that redistributors of a free +program will individually obtain patent licenses, in effect making the +program proprietary. To prevent this, we have made it clear that any +patent must be licensed for everyone's free use or not licensed at all. + + The precise terms and conditions for copying, distribution and +modification follow. + + GNU GENERAL PUBLIC LICENSE + TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION + + 0. This License applies to any program or other work which contains +a notice placed by the copyright holder saying it may be distributed +under the terms of this General Public License. The "Program", below, +refers to any such program or work, and a "work based on the Program" +means either the Program or any derivative work under copyright law: +that is to say, a work containing the Program or a portion of it, +either verbatim or with modifications and/or translated into another +language. (Hereinafter, translation is included without limitation in +the term "modification".) Each licensee is addressed as "you". + +Activities other than copying, distribution and modification are not +covered by this License; they are outside its scope. The act of +running the Program is not restricted, and the output from the Program +is covered only if its contents constitute a work based on the +Program (independent of having been made by running the Program). +Whether that is true depends on what the Program does. + + 1. You may copy and distribute verbatim copies of the Program's +source code as you receive it, in any medium, provided that you +conspicuously and appropriately publish on each copy an appropriate +copyright notice and disclaimer of warranty; keep intact all the +notices that refer to this License and to the absence of any warranty; +and give any other recipients of the Program a copy of this License +along with the Program. + +You may charge a fee for the physical act of transferring a copy, and +you may at your option offer warranty protection in exchange for a fee. + + 2. You may modify your copy or copies of the Program or any portion +of it, thus forming a work based on the Program, and copy and +distribute such modifications or work under the terms of Section 1 +above, provided that you also meet all of these conditions: + + a) You must cause the modified files to carry prominent notices + stating that you changed the files and the date of any change. + + b) You must cause any work that you distribute or publish, that in + whole or in part contains or is derived from the Program or any + part thereof, to be licensed as a whole at no charge to all third + parties under the terms of this License. + + c) If the modified program normally reads commands interactively + when run, you must cause it, when started running for such + interactive use in the most ordinary way, to print or display an + announcement including an appropriate copyright notice and a + notice that there is no warranty (or else, saying that you provide + a warranty) and that users may redistribute the program under + these conditions, and telling the user how to view a copy of this + License. (Exception: if the Program itself is interactive but + does not normally print such an announcement, your work based on + the Program is not required to print an announcement.) + +These requirements apply to the modified work as a whole. If +identifiable sections of that work are not derived from the Program, +and can be reasonably considered independent and separate works in +themselves, then this License, and its terms, do not apply to those +sections when you distribute them as separate works. But when you +distribute the same sections as part of a whole which is a work based +on the Program, the distribution of the whole must be on the terms of +this License, whose permissions for other licensees extend to the +entire whole, and thus to each and every part regardless of who wrote it. + +Thus, it is not the intent of this section to claim rights or contest +your rights to work written entirely by you; rather, the intent is to +exercise the right to control the distribution of derivative or +collective works based on the Program. + +In addition, mere aggregation of another work not based on the Program +with the Program (or with a work based on the Program) on a volume of +a storage or distribution medium does not bring the other work under +the scope of this License. + + 3. You may copy and distribute the Program (or a work based on it, +under Section 2) in object code or executable form under the terms of +Sections 1 and 2 above provided that you also do one of the following: + + a) Accompany it with the complete corresponding machine-readable + source code, which must be distributed under the terms of Sections + 1 and 2 above on a medium customarily used for software interchange; or, + + b) Accompany it with a written offer, valid for at least three + years, to give any third party, for a charge no more than your + cost of physically performing source distribution, a complete + machine-readable copy of the corresponding source code, to be + distributed under the terms of Sections 1 and 2 above on a medium + customarily used for software interchange; or, + + c) Accompany it with the information you received as to the offer + to distribute corresponding source code. (This alternative is + allowed only for noncommercial distribution and only if you + received the program in object code or executable form with such + an offer, in accord with Subsection b above.) + +The source code for a work means the preferred form of the work for +making modifications to it. For an executable work, complete source +code means all the source code for all modules it contains, plus any +associated interface definition files, plus the scripts used to +control compilation and installation of the executable. However, as a +special exception, the source code distributed need not include +anything that is normally distributed (in either source or binary +form) with the major components (compiler, kernel, and so on) of the +operating system on which the executable runs, unless that component +itself accompanies the executable. + +If distribution of executable or object code is made by offering +access to copy from a designated place, then offering equivalent +access to copy the source code from the same place counts as +distribution of the source code, even though third parties are not +compelled to copy the source along with the object code. + + 4. You may not copy, modify, sublicense, or distribute the Program +except as expressly provided under this License. Any attempt +otherwise to copy, modify, sublicense or distribute the Program is +void, and will automatically terminate your rights under this License. +However, parties who have received copies, or rights, from you under +this License will not have their licenses terminated so long as such +parties remain in full compliance. + + 5. You are not required to accept this License, since you have not +signed it. However, nothing else grants you permission to modify or +distribute the Program or its derivative works. These actions are +prohibited by law if you do not accept this License. Therefore, by +modifying or distributing the Program (or any work based on the +Program), you indicate your acceptance of this License to do so, and +all its terms and conditions for copying, distributing or modifying +the Program or works based on it. + + 6. Each time you redistribute the Program (or any work based on the +Program), the recipient automatically receives a license from the +original licensor to copy, distribute or modify the Program subject to +these terms and conditions. You may not impose any further +restrictions on the recipients' exercise of the rights granted herein. +You are not responsible for enforcing compliance by third parties to +this License. + + 7. If, as a consequence of a court judgment or allegation of patent +infringement or for any other reason (not limited to patent issues), +conditions are imposed on you (whether by court order, agreement or +otherwise) that contradict the conditions of this License, they do not +excuse you from the conditions of this License. If you cannot +distribute so as to satisfy simultaneously your obligations under this +License and any other pertinent obligations, then as a consequence you +may not distribute the Program at all. For example, if a patent +license would not permit royalty-free redistribution of the Program by +all those who receive copies directly or indirectly through you, then +the only way you could satisfy both it and this License would be to +refrain entirely from distribution of the Program. + +If any portion of this section is held invalid or unenforceable under +any particular circumstance, the balance of the section is intended to +apply and the section as a whole is intended to apply in other +circumstances. + +It is not the purpose of this section to induce you to infringe any +patents or other property right claims or to contest validity of any +such claims; this section has the sole purpose of protecting the +integrity of the free software distribution system, which is +implemented by public license practices. Many people have made +generous contributions to the wide range of software distributed +through that system in reliance on consistent application of that +system; it is up to the author/donor to decide if he or she is willing +to distribute software through any other system and a licensee cannot +impose that choice. + +This section is intended to make thoroughly clear what is believed to +be a consequence of the rest of this License. + + 8. If the distribution and/or use of the Program is restricted in +certain countries either by patents or by copyrighted interfaces, the +original copyright holder who places the Program under this License +may add an explicit geographical distribution limitation excluding +those countries, so that distribution is permitted only in or among +countries not thus excluded. In such case, this License incorporates +the limitation as if written in the body of this License. + + 9. The Free Software Foundation may publish revised and/or new versions +of the General Public License from time to time. Such new versions will +be similar in spirit to the present version, but may differ in detail to +address new problems or concerns. + +Each version is given a distinguishing version number. If the Program +specifies a version number of this License which applies to it and "any +later version", you have the option of following the terms and conditions +either of that version or of any later version published by the Free +Software Foundation. If the Program does not specify a version number of +this License, you may choose any version ever published by the Free Software +Foundation. + + 10. If you wish to incorporate parts of the Program into other free +programs whose distribution conditions are different, write to the author +to ask for permission. For software which is copyrighted by the Free +Software Foundation, write to the Free Software Foundation; we sometimes +make exceptions for this. Our decision will be guided by the two goals +of preserving the free status of all derivatives of our free software and +of promoting the sharing and reuse of software generally. + + NO WARRANTY + + 11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY +FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN +OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES +PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED +OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF +MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS +TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU. SHOULD THE +PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING, +REPAIR OR CORRECTION. + + 12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING +WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR +REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, +INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING +OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED +TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY +YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER +PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE +POSSIBILITY OF SUCH DAMAGES. + + END OF TERMS AND CONDITIONS + + How to Apply These Terms to Your New Programs + + If you develop a new program, and you want it to be of the greatest +possible use to the public, the best way to achieve this is to make it +free software which everyone can redistribute and change under these terms. + + To do so, attach the following notices to the program. It is safest +to attach them to the start of each source file to most effectively +convey the exclusion of warranty; and each file should have at least +the "copyright" line and a pointer to where the full notice is found. + + + Copyright (C) + + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program; if not, write to the Free Software + Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + + +Also add information on how to contact you by electronic and paper mail. + +If the program is interactive, make it output a short notice like this +when it starts in an interactive mode: + + Gnomovision version 69, Copyright (C) year name of author + Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'. + This is free software, and you are welcome to redistribute it + under certain conditions; type `show c' for details. + +The hypothetical commands `show w' and `show c' should show the appropriate +parts of the General Public License. Of course, the commands you use may +be called something other than `show w' and `show c'; they could even be +mouse-clicks or menu items--whatever suits your program. + +You should also get your employer (if you work as a programmer) or your +school, if any, to sign a "copyright disclaimer" for the program, if +necessary. Here is a sample; alter the names: + + Yoyodyne, Inc., hereby disclaims all copyright interest in the program + `Gnomovision' (which makes passes at compilers) written by James Hacker. + + , 1 April 1989 + Ty Coon, President of Vice + +This General Public License does not permit incorporating your program into +proprietary programs. If your program is a subroutine library, you may +consider it more useful to permit linking proprietary applications with the +library. If this is what you want to do, use the GNU Library General +Public License instead of this License. diff --git a/RBR/FreqTable.lhs b/RBR/FreqTable.lhs new file mode 100644 --- /dev/null +++ b/RBR/FreqTable.lhs @@ -0,0 +1,94 @@ +\section{FreqTable} + +Building a Frequency Table for keys. + +Constructs the table of all possible keys, so be careful. + +\begin{code} + +module RBR.FreqTable (FreqTable(..) + ,freqtable_int,freqtable_integer -- constructors + ,sparsetable_int, sparsetable_integer + ) where + +import Bio.Sequence + +import Data.IntMap as IM +import Data.Map as M +import Data.List as L + +data FreqTable a = FT { count :: a -> Int + , counts :: [(a,Int)] + } + +\end{code} + +\subsection{Constructing the frequency table} + +Frequency table, counting occurences. + +\begin{code} + +freqtable_int :: HashF Int -> [Sequence] -> FreqTable Int +freqtable_int kf ss = FT (\k -> IM.findWithDefault 0 k idx) (IM.toList idx) + where + idx = foldl' myupdate IM.empty $ concatMap (L.map fst . hashes kf . seqdata) ss + myupdate m k = let x = 1 + IM.findWithDefault 0 k m + in x `seq` IM.insert k x m + +freqtable_integer :: HashF Integer -> [Sequence] -> FreqTable Integer +freqtable_integer kf ss = FT (\k -> M.findWithDefault 0 k idx) (M.toList idx) + where + idx = foldl' myupdate M.empty $ concatMap (L.map fst . hashes kf . seqdata) ss + myupdate m k = let x = 1 + M.findWithDefault 0 k m + in x `seq` M.insert k x m + + +-- alternative: use +-- accumArray (+) 0 (minBound, maxBound) . (map (\x->(x,1))) + +\end{code} + +\subsection{Sparse maps} + +For parameter k, increment all existing keys, insert new keys only +when a gap larger than k would otherwise result. Keys are added +weight according to distance to next inserted key, so that the sum +weight of a sequence in the map is independent of k. + +For this to be useful, masking must be performed against a sliding +average. (How will this work against libraries?) + +Invariant: sparsetable_int 1 == freqtable_int + +\begin{code} + +sparsetable_int :: Int -> HashF Int -> [Sequence] -> FreqTable Int +sparsetable_int step kf ss = FT (\k -> find k idx) (IM.toList idx) + where + find = IM.findWithDefault 0 + idx = foldl' ins1 IM.empty ss + ins1 ix s = let ks = L.map fst $ hashes kf $ seqdata s + in go ix (step-1) ks + -- insert keys that already exist, or when the skip-counter is zero + go ix' n (k:ks) | n==0 || find k ix' /= 0 + || L.null ks = let x = find k ix'+step-n + in x `seq` go (IM.insert k x ix') (step-1) ks + | True = go ix' (n-1) ks + go ix' _n [] = ix' + +sparsetable_integer :: Int -> HashF Integer -> [Sequence] -> FreqTable Integer +sparsetable_integer step kf ss = FT (\k -> find k idx) (M.toList idx) + where + find = M.findWithDefault 0 + idx = foldl' ins1 M.empty ss + ins1 ix s = let ks = L.map fst $ hashes kf $ seqdata s + in go ix (step-1) ks + -- insert keys that already exist, or when the skip-counter is zero + go ix' n (k:ks) | n==0 || find k ix' /= 0 + || L.null ks = let x = find k ix'+step-n + in x `seq` go (M.insert k x ix') (step-1) ks + | True = go ix' (n-1) ks + go ix' _n [] = ix' + +\end{code} diff --git a/RBR/MCT.lhs b/RBR/MCT.lhs new file mode 100644 --- /dev/null +++ b/RBR/MCT.lhs @@ -0,0 +1,105 @@ +\section{MaskCount} + +Examine each nucleotide from two data sets, and count the Ns (or Xs?). +Separate into A AB B 0. Also (optionally?) count masked region sizes +to generate gnuplot'able histograms. + +TODO: + - parameter to specify lower case/N/X as masked + - justify columns in output + - output percentages + +\begin{code} +{-# LANGUAGE BangPatterns, FlexibleContexts #-} +module Main where + +import Bio.Sequence + +import RBR.TextFormat + +import Control.Monad (when) +import Data.Char (isLower) +import Data.List (foldl',intersperse,partition) +import System.Environment (getArgs) +import System.Exit (exitWith,ExitCode(..)) +import Text.Printf (printf, PrintfType) + +main :: IO () +main = do + (opts,[a,b]) <- parseArgs + as <- readFasta a + bs <- readFasta b + let res = zipComp as bs + when (elem 'l' opts) + (do + putStrLn ("# fraction of masked positions: "++a++" both "++b++"none") + putStrLn $ unlines $ map printres res) + when (elem 's' opts) + (do + putStrLn "# Summary:" + putStrLn $ printSum a b $ foldl' add (CS 0 0 0 0) (map snd res)) + +parseArgs :: IO (String, [String]) +parseArgs = do + as <- getArgs + let (opts,files) = partition ((=='-').head) as + when (length files /= 2) usage + let short = concat $ map tail opts + return (short,files) + +usage :: IO a +usage = do putStrLn "mc: compare two FASTA files for masked nucleotides" + putStrLn "usage: mc [-s|-l] file_1 file_2" + exitWith $ ExitFailure 1 + +data CompStruct = CS !Int !Int !Int !Int + +add :: CompStruct -> CompStruct -> CompStruct +add (CS a ab b o) (CS a' ab' b' o') = CS (a+a') (ab+ab') (b+b') (o+o') + +-- construct the percentage similar nucleotides +printres :: (String, CompStruct) -> String +printres (s,CS a ab b o) = let tot = a+ab+b+o + in concat $ intersperse " " + $ s : map (percent tot) [a,ab,b,o] + +printSum :: String -> String -> CompStruct -> String +printSum a b (CS ca cab cb co) = unlines (["Summary for "++a++" vs. "++b++":\n"] + ++ columns " " [ map (" "++) ["unmasked in both:","masked in both:" + ,"masked in "++a++":","masked in "++b++":"] + , map show [co, cab, ca, cb] + , map (paren . percent tot) [co,cab,ca,cb ]]) + ++ "Pearson's phi: "++printf "%.3f" (phi :: Double) + where tot = co+cab+ca+cb + phi = let [a,b,ab,o] = map ((/(fromIntegral tot)) . fromIntegral) [ca,cb,cab,co] + in (ab*o-a*b)/sqrt((ab+a)*(ab+b)*(a+o)*(b+o)) + +paren :: String -> String +paren s = "("++s++"%)" + +percent :: (PrintfType (Double -> t), Integral a, Integral a1) => a1 -> a -> t +percent tot x = printf "%.2f" (100*fromIntegral x/fromIntegral tot :: Double) + +zipComp :: [Sequence] -> [Sequence] -> [(String,CompStruct)] +zipComp as bs = map (z1 (CS 0 0 0 0)) $ zipSeqs as bs + +z1 :: CompStruct -> (Sequence, Sequence) -> (String, CompStruct) +z1 cs (a,b) = (toStr $ seqlabel a, foldl' collect cs $ zip (get a) (get b)) + where get s = map isLower $ map (s!) [0..seqlength s-1] + -- s/isLower/isN/ for N detect. + +zipSeqs :: [Sequence] -> [Sequence] -> [(Sequence,Sequence)] +zipSeqs [] [] = [] +zipSeqs (a:as) (b:bs) = + if seqlabel a == seqlabel b then (a,b):zipSeqs as bs + else error ("sequence sets differ (offending sequences: '" + ++ toStr (seqlabel a) ++ "' and '" ++ toStr (seqlabel b) ++"'.") +zipSeqs _ _ = error "extraneous sequences" + +collect :: CompStruct -> (Bool, Bool) -> CompStruct +collect (CS a ab b o) (True,True) = (CS a (ab+1) b o) +collect (CS a ab b o) (True,False) = (CS (a+1) ab b o) +collect (CS a ab b o) (False,True) = (CS a ab (b+1) o) +collect (CS a ab b o) (False,False) = (CS a ab b (o+1)) + +\end{code} diff --git a/RBR/Options.lhs b/RBR/Options.lhs new file mode 100644 --- /dev/null +++ b/RBR/Options.lhs @@ -0,0 +1,74 @@ +\subsection{Option handling} + +You know the drill... + +\begin{code} + +module RBR.Options (version,usage,getOptions,Opts(..),parseargs,MaskWith(..)) where + +import System.Environment (getArgs) +import System.Console.GetOpt +import System.Exit + +version, usagemsg :: String +version = "0.8.4" +usagemsg = "Usage: rbr [-k ] [options] FILE.." + +getOptions :: IO ([Opts -> IO Opts], [String], [String]) +getOptions = getArgs >>= (return . getOpt Permute options) + +usage :: [String] -> String +usage errs = usageInfo (concat errs ++ usagemsg) options + +data MaskWith = Lower | Ns | Xs + +options :: [OptDescr (Opts -> IO Opts)] +options = [Option ['k'] ["word-size"] (ReqArg (\arg opt -> return opt { kval = read arg }) "Int") "Word size" + ,Option [] ["sparse-keys"] (ReqArg (\arg opt -> return opt { skip = read arg }) "Int") "Skip length" +-- ,Option [] ["shape"] (ReqArg ...) "Key shape" + ,Option ['N'] ["no-stats"] (NoArg (\opt -> return opt { stats = False })) "Omit statistical masking" + ,Option ['g'] ["gapclosing"] (ReqArg (\arg opt -> return opt { gap = read arg }) "Int") "Close gaps" + ,Option ['s'] ["stringency"] (ReqArg (\arg opt -> return opt { string = read arg }) "Float") "Mask stringecy" + ,Option ['t'] ["threshold"] (ReqArg (\arg opt -> return opt { thresh = read arg }) "Float") "Mask threshold" + ,Option [] ["preserve-lower-case"] (NoArg (\opt -> return opt { preserve_lower = True })) "Preserve lower case in input sequences" + + ,Option ['D'] ["distribution"] (NoArg (\opt -> return opt { distr = True })) "Distribution output" + ,Option ['l'] ["library"] (ReqArg (\arg opt -> return opt {lib = Just arg}) "file") "Mask words from library" + ,Option ['L'] ["lower-case"] (NoArg (\opt -> return opt { lower = Lower })) "Mask using lower case letters" + ,Option ['n'] ["n-mask"] (NoArg (\opt -> return opt { lower = Ns })) "Mask using 'n's" + ,Option ['x'] ["x-mask"] (NoArg (\opt -> return opt { lower = Xs })) "Mask using 'X's" + ,Option [] ["server"] (NoArg (\opt -> return opt { server = True })) "Run in server mode" + ,Option ['o'] ["output-file"] (ReqArg (\arg opt -> return opt { ofile = Just arg }) "file") "Output file" + ,Option ['v'] ["verbose"] (NoArg (\opt -> return opt { verb = True })) "Display progress" + + ,Option ['h'] ["help"] (NoArg (\_ -> do {putStrLn $ usage []; exitWith ExitSuccess })) "Display help" + ,Option ['V'] ["version"] (NoArg (\_ -> do {putStrLn $ "rbr version "++version; exitWith ExitSuccess })) "Display version" + ] + +data Opts = Opts { kval :: Int, ofile :: Maybe FilePath + , stats, preserve_lower :: Bool + , thresh, string :: Double + , gap :: Int + , lower :: MaskWith + , distr, verb, server :: Bool + , lib :: Maybe FilePath + , skip :: Int + } + +defaultopts :: Opts +defaultopts = Opts 16 Nothing True False 0 0 0 Lower False False False Nothing 0 + +parseargs :: [Opts -> IO Opts] -> IO Opts +parseargs args = foldl (>>=) (return defaultopts) args >>= fixS >>= fixT + where fixS opts = return $ case (string opts,lower opts) of -- sensible(?) defaults + (0,Ns) -> opts { string = 2.0 } + (0,Xs) -> opts { string = 2.0 } + (0,Lower) -> opts { string = 1.1 } + _ -> opts + fixT opts = return $ case (thresh opts,lower opts) of -- sensible(?) defaults + (0,Ns) -> opts { thresh = 8.0 } + (0,Xs) -> opts { thresh = 8.0 } + (0,Lower) -> opts { thresh = 5.0 } + _ -> opts + +\end{code} diff --git a/RBR/RBR.lhs b/RBR/RBR.lhs new file mode 100644 --- /dev/null +++ b/RBR/RBR.lhs @@ -0,0 +1,385 @@ +\section{RBR - RepeatBeater revisited} + +RBR works by examining word frequencies in EST data, and +based on the assumption that expression of positions within each gene +is relatively uniform, identifies extremely common words as potential +repeats. + +A predecessor to RBR was implemented as some scripts parsing +\texttt{xsact} output, this is a revised, standalone implmentation. + +\begin{code} +{-# LANGUAGE CPP #-} + +module Main (main) where + +import Bio.Sequence + +import RBR.FreqTable +import RBR.Stats hiding (median,uv_add) +import RBR.Util (interactl) +import RBR.Options + +-- import Text.Printf +import qualified Data.ByteString.Lazy.Char8 as B (map) + +import System.IO +import System.IO.Unsafe +import Control.Monad +import Data.List as List +import Data.Char as Char + +import Data.Map hiding (null,filter,map,elems,keys) + +#define perror (\s->error ("Program error in function \""++s++"\" at "++__FILE__++":"++show (__LINE__::Int)++\ +"\nPlease report this incident to .")) + +main :: IO () +main = do + (opt1,non,err) <- getOptions + -- print (opt1,non,err) + when ((null non && null opt1) || not (null err)) (error $ usage err) + opts <- parseargs opt1 + case non of [] -> do ss <- hReadFasta stdin + main_real opts ("", return ss) + [f1] -> main_real opts (f1, readFasta f1) + fs -> error ("Only supply one input file (you supplied: "++show fs++")") + +header :: Opts -> [FilePath] -> String +header opts _inputs = "# rbr version "++version++", mask="++(case (lower opts) of Lower -> "L"; Ns -> "n"; Xs -> "X")++ + " k="++show (kval opts)++" stringency="++show (string opts)++ + " thresh="++show (thresh opts)++" g="++show (gap opts) ++ " skip="++ show (skip opts) + +\end{code} + +\subsection{The real main} + +\begin{code} + +debug :: Bool -> String -> IO () +debug p m = when p $ hPutStr stderr m + +countIO :: String -> String -> Int -> [a] -> IO [a] +countIO msg post step xs = sequence $ map unsafeInterleaveIO ((blank >> outmsg (0::Int) >> c):cs) + where (c:cs) = ct 0 xs + output = hPutStr stderr + blank = output ('\r':take 70 (repeat ' ')) + outmsg x = output ('\r':msg++show x) >> hFlush stderr + ct s ys = let (a,b) = splitAt (step-1) ys + next = s+step + in case b of [b1] -> map return a ++ [outmsg (s+step) >> hPutStr stderr post >> return b1] + [] -> map return (init a) ++ [outmsg (s+length a) >> hPutStr stderr post >> return (last a)] + _ -> map return a ++ [outmsg s >> return (head b)] ++ ct next (tail b) + +main_real :: Opts -> (String, IO [Sequence]) -> IO () +main_real opts (ifile,ssio) = do + when (verb opts || distr opts) $ putStrLn $ header opts [ifile] + when (verb opts) $ do + debug (verb opts) ("Reading file: "++ifile++"\n") + ss <- ssio + debug (verb opts) ("Number of sequences: "++show (length ss)++"\n") + if kval opts <= 16 then main_cont make_ft_int opts ssio + else main_cont make_ft_integer opts ssio + +main_cont :: Integral a => MkFT a -> Opts -> IO [Sequence] -> IO () +main_cont make_ft opts ssio = do + mask1 <- mask_func make_ft opts ssio + ss'' <- if (verb opts) then countIO " ...masking sequences: " ", done.\n" 100 =<< ssio + else ssio + if (server opts) then do + ft <- make_ft "Building index array" (verb opts) (skip opts) (kval opts) ssio + interactl "READY: " (concatMap (main_server opts ft ss'') . words) + else do if (distr opts) then main_coverage make_ft opts ssio + else main_masked opts mask1 ss'' + +type MkFT a = String -> Bool -> Int -> Int -> IO [Sequence] -> IO (FreqTable a) + +make_ft_int :: MkFT Int +make_ft_int msg vb skp k ssio = do + ss' <- if vb then countIO (" "++msg++": ") ", done.\n" 100 =<< ssio + else ssio + if skp > 0 then return (sparsetable_int skp (rcontig k) ss') + else return (freqtable_int (rcontig k) ss') + +make_ft_integer :: MkFT Integer +make_ft_integer msg vb skp k ssio = do + ss' <- if vb then countIO (" "++msg++": ") ", done.\n" 100 =<< ssio + else ssio + if skp>0 then return (sparsetable_integer skp (rcontig k) ss') + else return (freqtable_integer (rcontig k) ss') + +main_coverage :: Integral a => MkFT a -> Opts -> IO [Sequence] -> IO () +main_coverage make_ft opts ssio = do + ft <- make_ft "Building index array" (verb opts) (skip opts) (kval opts) ssio + let k = kval opts + sk = skip opts + (stdevs,b2,strg) = (thresh opts, 5, string opts) + seq_cov s = let cv = coverage k sk (rcontig k) ft s + ls = sortv $ blunt b2 + $ map (\l->(fromIntegral $ head l,length l)) $ group $ sort cv + (mu,stdv) = distrib strg ls + t = mu + max b2 (stdevs*stdv) + in (seqheader s, if null cv || null ls then (0,0,0) else (mu,stdv,t),cv) -- todo: round! + write = case ofile opts of Nothing -> putStrLn; Just f -> writeFile f + debug (verb opts) "Calculating coverage\n" + ss <- ssio + write $ unlines $ map show $ map seq_cov ss + +main_masked :: Opts -> (Sequence->Sequence) -> [Sequence] -> IO () +main_masked opts mf ss = do + let ms = if kval opts == 0 then ss else map mf ss + write = case ofile opts of Nothing -> hWriteFasta stdout + Just f -> writeFasta f + write ms + +mask_func :: Integral a => MkFT a -> Opts -> IO [Sequence] -> IO (Sequence -> Sequence) +mask_func make_ft opts ssio = + do let k = kval opts + g = gap opts + sk = skip opts + gc = if g > 0 then closegaps (g+k-1) else id + sparm = (thresh opts, 5, string opts) + upcase = if preserve_lower opts then id else upcaseSequence + ms <- do case stats opts of + False -> return [] + True -> do ft <- make_ft "Indexing input" (verb opts) sk k ssio + return [mask_stat k sk sparm ft] + mt <- case lib opts of + Nothing -> return [] + Just f -> do lft <- make_ft "Indexing repeat library" (verb opts) sk k $ readFasta f + return [mask_table k sk lft] + return ((case ms++mt of [] -> id + xs -> mask_generic (lower opts) (k+if sk==0 then 0 else sk-1) + (gc . min_mask ((sk+2) `div` 2) . combine xs)) . upcase) + +upcaseSequence :: Sequence -> Sequence +upcaseSequence (Seq l d q) = (Seq l (B.map toUpper d) q) + +-- sparse keys can give aberrant counts, so require more than one consequtive +-- todo: really really convert to RLL-encoded whitelist +min_mask :: Int -> [Bool] -> [Bool] +min_mask _ [] = [] +min_mask sk xs@(True:_) = let (t,f) = span id xs in t ++ min_mask sk f +min_mask sk xs@(False:_) = let (f,t) = span not xs in (if length f >= sk then f + else take (length f) (repeat True)) ++ min_mask sk t + +combine :: [a -> [Bool]] -> (a -> [Bool]) +combine [] = perror "combine" +combine [f] = f +combine (f1:f2:fs) = let f = \s -> zipWith (&&) (f1 s) (f2 s) in combine (f:fs) + + +main_server :: Integral a => Opts -> FreqTable a -> [Sequence] -> (String -> String) +main_server opts ft ss = + let sidx = fromList $ map (\s->(seqlabel s,s)) ss + (k,sk,gc,ps) = (kval opts, skip opts,if gap opts > 0 then closegaps (k+gap opts-1) else id, (thresh opts,5,string opts)) + in (\s -> case Data.Map.lookup (fromStr s) sidx of + Nothing -> ("input error: "++s++" not found\n") + Just sq -> let cover = show $ coverage k sk (rcontig k) ft sq + masked_ = show $ mask_generic (lower opts) (if sk==0 then k else k+sk-1) (gc . mask_stat k (skip opts) ps ft) sq + -- mask_stat (lower opts) k g ps ft sq + unmasked = show $ seqdata sq + in unlines [masked_, cover,unmasked]) + +\end{code} + +Generic masking function. The list of Bool is a whitelist, so that +True corresponds to retained nucleotides, while False indicates +nucleotides to be masked. + +(TODO: Run-length encode the boolean list?) + +\begin{code} + +mask_generic :: MaskWith -> Int -> (Sequence -> [Bool]) -> Sequence -> Sequence +mask_generic b sz fn s@(Seq l sd mq) = Seq l (fromStr . masked b sz (fn s) . toStr $ sd) mq + +\end{code} + +Mask all words from a dictionary (i.e. a library of known repeats) + +\begin{code} + +mask_table :: Integral a => Int -> Int -> FreqTable a -> Sequence -> [Bool] +mask_table k skp rlib s = let + cv = coverage k skp (rcontig k) rlib s -- slight abuse of 'coverage' + in map (==0) cv + +\end{code} + +Masking sequences from frequency counts. + +\begin{code} + +type MPars = (Double,Double,Double) -- stdevs thres, 1-elim, stringency + +-- calculate the 'whitelist' +mask_stat :: Integral a => Int -> Int -> MPars -> FreqTable a -> Sequence -> [Bool] +mask_stat k sk (stdevs,b2,strg) ft s = + let cv = coverage k sk (rcontig k) ft s + ls = sortv $ blunt b2 + $ map (\l->(fromIntegral $ head l,length l)) $ group $ sort cv + (mu,stdv) = distrib strg ls + t = mu + max b2 (stdevs*stdv) + in if null cv || null ls then take (1-k+fromIntegral (seqlength s)) $ repeat True + else map ((<=t) . fromIntegral) cv + +-- distrib calculates the base distribution +distrib :: Double -> [(Double,Int)] -> (Double,Double) +distrib strg ls = distr' ls (uv_mk []) + where + distr' [] _ + = perror "distrib" + distr' ((mag,cnt):ls') ustd = + let ustd' = uv_add mag cnt ustd + u = uniVar ustd' + score = variance u / stdev u + in if score >= strg || null ls' + then (mean u,stdev u) + else distr' ls' ustd' + +-- s {seqannot = seqannot s +-- ++[UKV "Threshold" $ printf "%.2f" t] +-- ,seqdata = listArray (bounds $ seqdata s) ms} + +-- compensate for 1% error rate by reducing number of ones by k% +-- this is inaccurate, but possibly a workable estimate nonetheless +blunt :: Double -> [(Double,Int)] -> [(Double,Int)] +blunt k = reduce1s . dropWhile ((==0).fst) + where reduce1s all_@((a,x):ls) = if a==1 + then (1,max 0 (x-floor k*(sum $ map snd all_) `div` 100)):ls + else all_ + reduce1s [] = [] -- sequence contains no words + +-- sort ls around the centre or the modal interval +sortv :: [(Double,Int)] -> [(Double,Int)] +sortv ls = let m = scaled_modal ls + in sortBy (\(a,_) (c,_) -> compare (abs (a-m)) (abs (c-m))) ls + +-- NB: 1 = error - chose mode ignoring 1s? (see C.e. seq. 24) + +-- for each window of occurrence frequencies (n..sqrt n), find the one with most positions +scaled_modal :: [(Double,Int)] -> Double +scaled_modal = modal . map window . tails' + +window :: [(Double,Int)] -> (Double,Int) +window [] = perror "window" +window ((mag,cnt):ls) = + let top = mag + sqrt mag + xs = (mag,cnt) : takeWhile (( [[a]] +tails' [] = [] +tails' x@(_:xs) = x : tails' xs + +{- +windowize ((mag,count):ls) = + let (this,rest) = break ((> mag+sqrt mag) . fst) ls + in (mag+sqrt mag,count+sum (map snd this)) : windowize rest +windowize [] = [] +-} + +modal :: Ord b => [(a,b)] -> a +modal = fst . maximumBy (\x y -> compare (snd x) (snd y)) + +median :: [(Double,Int)] -> Double +median ls = let n = (`div` 2) $ sum $ map snd ls + in nquant n ls + +nquant :: Int -> [(Double,Int)] -> Double +nquant n ((v,c):vs) | n < c = v + | otherwise = nquant (n-c) vs +nquant _ [] = perror "median of an empty list is impossible!" + + +-- faster(?) replacements for Stats.uv and uv_del +type UV = (Int,Double,Double,Double,Double) + +uv_mk :: [(Double,Int)] -> UV +uv_mk = foldr uv1 (0,0,0,0,0) + where uv1 (m,cnt) (n,x,x2,x3,x4) = let c = fromIntegral cnt in + (n+cnt,x+m*c,x2+m*m*c,x3+m*m*m*c,x4+m*m*m*m*c) + +uv_sub, uv_add :: Double -> Int -> UV -> UV +uv_sub m cnt (n,x,x2,x3,x4) = let c = fromIntegral cnt in + (n-cnt,x-m*c,x2-m*m*c,x3-m*m*m*c,x4-m*m*m*m*c) + +uv_add m cnt (n,x,x2,x3,x4) = let c = fromIntegral cnt in + (n+cnt,x+m*c,x2+m*m*c,x3+m*m*m*c,x4+m*m*m*m*c) + +-- masked takes mask type, kval, threshold, a whitelist ('False' means mask) +-- and the (nucleotides in the) sequence +masked :: MaskWith -> Int -> [Bool] -> String -> String +masked Lower = masked' toLower 0 +masked Ns = masked' (const 'n') 0 +masked Xs = masked' (const 'X') 0 + +-- mask using an arbitrary masking function +-- the 'ns' parameter keeps track of any remaining masked word, so that +-- we finish masking out the whole over-represented word +masked' :: (Char->Char) -> Int -> Int -> [Bool] -> String -> String +masked' _ _ _ (_:_) [] = + perror "masked' (1)" +masked' mf ns _ [] es = map mf (take ns es) ++ drop ns es +masked' mf ns k (b:bs) (e:es) + | ns == 0 && b = e : masked' mf 0 k bs es + | ns > 0 && b = mf e : masked' mf (ns-1) k bs es + | not b = mf e : masked' mf k k bs es + | otherwise = perror "masked' (2)" + +-- close gaps of less than 'g' unmasked words between groups of masked characters +-- 'False' corresponds to words to mask (whitelist) +closegaps :: Int -> [Bool] -> [Bool] +closegaps g = close g True . partitions + +-- always starts with a (possibly empty) unmasked group +partitions :: [Bool] -> [Int] +partitions es = map List.length $ if head es == False then []:partitions' es else partitions' es + where partitions' = List.groupBy (\x y -> x == False && y == False || x /= False && y /= False) + +-- convert runs of <=g Trues to Falses +close :: Int -> Bool -> [Int] -> [Bool] +close _ _ [] = [] +close g True (c:cs) = take c (repeat (if c>g then True else False)) ++ close g False cs +close g False (c:cs) = (take c $ repeat False) ++ close g True cs + +\end{code} + +\subsection{Coverage} + +Calculating the coverage over a sequence + +For sparse indices, this should be a sliding average. + +\begin{code} + +coverage :: Integral a => Int -> Int -> HashF a -> FreqTable a -> Sequence -> [Int] +coverage k skp kf tb s = if skp > 0 then sliding_avg skp raw_counts else raw_counts + where + raw_counts = map mcount $ padkeys (seqlength s-fromIntegral k+1) 0 $ hashes kf $ seqdata s + mcount (Just k1) = count tb k1 + mcount Nothing = 0 + +padkeys :: Offset -> Offset -> [(k,Offset)] -> [Maybe k] +padkeys top cur [] = take (fromIntegral (top - cur)) $ repeat Nothing +padkeys top cur ((k,p):ks) = if cur == p then Just k : padkeys top (cur+1) ks + else Nothing : padkeys top (cur+1) ((k,p):ks) + + +-- or just: +-- sliding_avg k = map ((`div` k) . sum . take k) . tails + +sliding_avg :: Int -> [Int] -> [Int] +sliding_avg s xs = let x1 = take s xs + in if length x1 == s then slav s (sum x1) xs (drop s xs) + else [sum x1 `div` length x1] + +-- todo: use floats? +slav :: Int -> Int -> [Int] -> [Int] -> [Int] +slav s tmp hd tl@(_:_) = tmp `div` s : slav s (tmp-head hd+head tl) (tail hd) (tail tl) +slav s tmp _ [] = [tmp `div` s] + +\end{code} + diff --git a/RBR/Stats.hs b/RBR/Stats.hs new file mode 100644 --- /dev/null +++ b/RBR/Stats.hs @@ -0,0 +1,136 @@ +{-# LANGUAGE CPP, Rank2Types #-} +module RBR.Stats (UniVar(..),uniVar,uv,uv_add,uv_del + ,Quantiles(..),quantiles) where -- ,histogram,display) where + +import Data.List (sort, sortBy, group) +-- import FiniteMap + +class Statistic s where + samples :: s -> Int + +data UniVar = UV { uv_samples :: Int + , mean :: Double + , stdev :: Double + , variance :: Double + , skewness :: Double + , kurtosis :: Double + , sumSq :: Double + , coeffVar :: Double + , stdErrMn :: Double + } + +instance Statistic UniVar where samples = uv_samples + +instance Show UniVar where + show u = adjust + [["Samples", (show $ samples u)] + , ["Mean", (show $ mean u)] + , ["Standard dev", (show $ stdev u)] + , ["Variance", (show $ variance u)] + , ["Skewness", (show $ skewness u)] + , ["Kurtosis", (show $ kurtosis u)] + , ["Sum of squares", (show $ sumSq u)] + , ["Coeff. of var", (show $ coeffVar u)] + , ["Std err mean", (show $ stdErrMn u)] + ] + +adjust :: [[String]] -> String +adjust [] = [] +adjust ([a,b]:xs) = (a++":"++take (15-length a) (repeat ' ')++b) ++ "\n" ++ adjust xs +adjust _ = error "Pattern matching error in 'adjust'" + +type UVTMP = (Int,Double,Double,Double,Double) + +-- | more or less the univariate function from SAS +-- calculate by tracking n, sum of x, of x², x^3, x^4 +uniVar :: (Int, Double, Double, Double, Double) -> UniVar +uniVar (n',x,x2,x3,x4) = + let n = fromIntegral n' + m = x/n + m2 = m*m + m3 = m*m2 + var = (x2-m2*n)/(n-1) + s = sqrt(var) + skew = (x3 - 3*m*x2 + 2*m3*n)/(s*s*s*n) + kurt = (x4 - 4*m*x3 + 6*m2*x2 - 4*m3*x + n*m*m3)/(s*s*s*s*n) - 3 + cv = s/m + in UV n' m s var skew kurt x2 cv (s/sqrt n) + +uv_add, uv_del :: Real a => a -> UVTMP -> UVTMP +uv_add = uv_upd (+) +uv_del = uv_upd (-) + +-- requires -fglasgow-exts +uv_upd :: (Real a) => (forall b . Real b => b -> b -> b) + -> a -> UVTMP -> UVTMP +uv_upd f d' (n,x,x2,x3,x4) = let d = toFloat d' in n `seq` x `seq` x2 + `seq` x3 `seq` x4 `seq` (f n 1,f x d,f x2 (d*d),f x3 (d*d*d),f x4 (d*d*d*d)) + where toFloat = fromRational . toRational + + +uv :: Real a => [a] -> UVTMP +uv ds = foldr uv_add (0,0,0,0,0) ds + +data Quantiles = Qs { wsamples :: Int + , smallest :: Double + , quartile1 :: Double + , median :: Double + , mode :: [Double] + , quartile3 :: Double + , greatest :: Double + } + +instance Statistic Quantiles where samples = wsamples + +instance Show Quantiles where + show w = adjust + [["Samples", (show $ samples w)] + , ["Smallest", (show $ smallest w)] + , ["Q1", (show $ quartile1 w)] + , ["Median", (show $ median w)] + , ["Modes", (show $ mode w)] + , ["Q3", (show $ quartile3 w)] + , ["Greatest", (show $ greatest w)]] + +quantiles :: [Double] -> Quantiles +quantiles ds = let + n = length ds + sorted = sort ds + q1 = case n `quotRem` 4 of (q,0) -> ((sorted!!(q-1))+(sorted!!q))/2.0 + (q,_) -> sorted!!q + q2 = case n `quotRem` 2 of (q,0) -> ((sorted!!(q-1))+(sorted!!q))/2.0 + (q,_) -> sorted!!q + q3 = case (3*n) `quotRem` 4 of (q,0) -> ((sorted!!(q-1))+(sorted!!q))/2.0 + (q,_) -> sorted!!q + modes = let + ms = sortOn (negate.fst) $ map (\x->(length x,head x))$ group sorted + in (snd $ head ms) : map snd + (takeWhile (\x->fst x==fst (head ms)) (tail ms)) + in + Qs n (head sorted) q1 q2 modes q3 (last sorted) + +sortOn :: Ord b => (a->b) -> [a] -> [a] +sortOn f = sortBy (\x y -> compare (f x) (f y)) + +{- +type Histogram = FiniteMap Double Int + +-- | histogram builds a histogram given the list of midpoints +histogram :: [Double] -> [Double] -> Histogram +histogram ms xs = foldl (insert ms) emptyFM' xs + where + emptyFM' = foldl (\s v -> addToFM s v 0) emptyFM ms + insert :: [Double] -> Histogram -> Double -> Histogram + insert (m1:m2:ms) s x = if abs (m1-x) <= abs (m2-x) + then addToFM_C (+) s m1 1 else insert (m2:ms) s x + insert [m1] s x = addToFM_C (+) s m1 1 + insert [] _ _ = error "Must provide at least one midpoint" + +-- todo: speed up with strict foldl' + +display :: Histogram -> String +display h = unlines $ map disp1 $ fmToList h + where disp1 (v,n) = show v ++ (take (7-(length $ show v)) (repeat ' ')) ++ + ": " ++ (take n $ repeat '*') + +-} diff --git a/RBR/TextFormat.lhs b/RBR/TextFormat.lhs new file mode 100644 --- /dev/null +++ b/RBR/TextFormat.lhs @@ -0,0 +1,24 @@ +\begin{code} + +-- todo: support uneven column lengths + +module RBR.TextFormat where + +import Data.List + +columns :: String -> [[String]] -> [String] +columns delim = map (concat . intersperse delim) . transpose . extend + +extend :: [[String]] -> [[String]] +extend cs = zipWith pad (sizes cs) cs + +-- mkrow rsizes = concat . intersperse "^" . zipWith pad rsizes + +pad :: Int -> [String] -> [String] +pad n = map (pad1 n) + where pad1 o text = text ++ take (o - length text) (repeat ' ') + +sizes :: [[String]] -> [Int] +sizes = map (maximum . map length) + +\end{code} diff --git a/RBR/Util.hs b/RBR/Util.hs new file mode 100644 --- /dev/null +++ b/RBR/Util.hs @@ -0,0 +1,18 @@ +module RBR.Util where + +import System.IO + +interactl :: String -> (String -> String) -> IO () +interactl p f = do + putStr p + hFlush stdout + ls <- getContents + i' p f (lines ls) + +i' :: String -> (t -> String) -> [t] -> IO () +i' _ _ [] = return () +i' p f (l:ls) = do + putStr (f l) + putStr p + hFlush stdout + i' p f ls diff --git a/RBR/hooks.c b/RBR/hooks.c new file mode 100644 --- /dev/null +++ b/RBR/hooks.c @@ -0,0 +1,15 @@ +/* after a tip from David Roundy */ +#include +#include +#include + +void defaultsHook (void) { + RtsFlags.GcFlags.maxStkSize = 8*10000002 / sizeof(W_); /* 80M */ + +#ifdef _SC_PHYS_PAGES + unsigned long long pagesize = sysconf(_SC_PAGESIZE); + unsigned long long numpages = sysconf(_SC_PHYS_PAGES); + unsigned long long mhs = numpages*pagesize*8/10; + RtsFlags.GcFlags.maxHeapSize = 1ULL+mhs/BLOCK_SIZE_W; +#endif +} diff --git a/README b/README new file mode 100644 --- /dev/null +++ b/README @@ -0,0 +1,105 @@ + New in this version (0.8) + ------------------------- + +Mostly a maintenance release, but at least we have + +* Cabalized install + +* Sparse mode completed and optimized + +* More reasonable default parameters + + Acquiring RBR + ------------- + +I'll try to keep a selection of source and binaries at: + + http://www.ii.uib.no/~ketil/bioinformatics/downloads/software + +If you need binaries for other architectures, drop me a mail at +. The latest version should always be available from +my darcs repo: + + darcs get http://www.ii.uib.no/~ketil/bioinformatics/repos/rbr + + + Installation instructions + ------------------------- + +I'm working on a smoother installation process, but this is how it +currently works. + +You need GHC (http://haskell.org/ghc). Everything is tested against +version 6.6, but version 6.4.x might also work. Expect to do some +modifications in the code for earlier versions than that. + +You first need to get my 'bio' library, it is available from the same +website, and install that. You can use cabal to install the binary, +at the top level, do + + chmod +x Setup.hs + ./Setup.hs configure (add --prefix=$HOME if you don't have root access) + ./Setup.hs build + ./Setup.hs install + +If you want to go the more manual route, cd to the src subdirectory, and + + make rbr -- builds a dynamically linked executable +or: make rbr_s -- builds a statically linked executable + +The main development platform is Linux/x86, so expect that to be most +well supported. In order to build on an aging Sun with an old gcc +(2.95), I had to comment out 'hooks.o' from the Makefile, and static +build didn't work either. I'm investigating this, but perhaps it +suffices to have a current GCC available, and/or a newer Solaris. + + + Usage + ----- + +I've no real manual page yet, but 'rbr --help' should list the +available options. Basically, masking is determined by examining word +frequencies of a certain word length (-k), estimating a distribution +around the "modal interval" of the word frequencies with a certain +stringency (-s), and masking words with frequencies exceeding the mean +of this distribution by a certain standard deviations (-t). Defaults +are -k 16 -s 1.1 -t 5.0 if -L (lower case masking) is specified and +-k 16 -s 2.0 -t 8.0 if -n (masking with 'n') is specified. Lower case +is now the default. + +To mask more agressively, you can either try to reduce stringency, or +a lower deviation, or both. Conversely if you want more conservative +masking. In general, the differences are small, and typically you can +compensate for a decrease in one parameter with an increase in the +other. + +Shorter word length will be more tolerant against SNPs and read +errors, but increase the variance. Longer will be less tolarant, but +have less variance. In addition, word lengths beyond 16 will be +slower. + +There's also a --sparse=X option that will store a fraction (but at +least every X'th) of the words. This will reduce memory consumption proportionally. + +RBR's memory usage can be limited with options to the run time +system's garbage collector. I good rule of thumb may be to limit it +to 80-90% of available physcal memory, which will avoid paging to +disk. If RBR is compiled with hooks.o linked in, this will be the +default, but if other behaviour is desired, you can use "+RTS -MxxxM +-RTS" to limit heap use to xxxMB¹. See the GHC documentation +(http://haskell.org/ghc) for more on this. Usually, you'll get better +performance by supplying -HxxxM as well (this will reduce GC time, +again see the GHC docs). + +The -v option gives some feedback while RBR runs, which is nice if +you're using it interactively. + +There is also a server mode, where RBR will index a data set, and +listen on stdin for sequence names, and answer on stdout with the +original sequence, the masked sequence, and the distribution of word +frequencies along the sequence. + + +¹) GHC version 6.6 and earlier had a bug that would cause memory +consumption to be measured incorrectly if the system allocated it in +an unusual order. The fix will be in subsequent releases of GHC. diff --git a/Setup.hs b/Setup.hs new file mode 100644 --- /dev/null +++ b/Setup.hs @@ -0,0 +1,5 @@ +#!/usr/bin/env runhaskell + +import Distribution.Simple +main = defaultMain + diff --git a/TODO b/TODO new file mode 100644 --- /dev/null +++ b/TODO @@ -0,0 +1,26 @@ +TODO: Check out options for freqtable data structure. + Things to try out: fmindex/afi, hashtable, accumArray, HsJudy + And perhaps combining key and count into an Int(|eger|64)? + +---------------------------------------- + +TODO: support shaped keys +TODO: Repeat ID: + output report (.tbl, .out) + * calculate 1..k'th order entropy + * other? + +TODO: Mask against library + +TODO: three-pass: build FT, build library, mask against it + +TODO: calculate distrib and mask over windows (w=200? 400?) + avoids different treatment of different length sequences + +- Clustering + +- Clustering with (SG/Lee) assembly + + -> statistics to use when clustering: + 1. mode of word counts distribution (= coverage) + 2. estimated p value (1-var/mu) (= avg. overlap) diff --git a/idea.txt b/idea.txt new file mode 100644 --- /dev/null +++ b/idea.txt @@ -0,0 +1,47 @@ +A comprehensive pipeline for EST analysis (?) + +IDEA: based on a word map, + - identify repeats (RB-style) + - mask RB-repeats and against libraries + - cluster + - assemble + +Stages: + + 1. FASTA parser (Parsec) + 2. word map builder (using arrays) + 3 a) cluster all-against-all + b) detect repeats (word frequency aberrances) + c) position sequence against a reference + 4. linear assembly (xtract replacement(?)) + - and feature output + +(thought on RB: +alt splicing may cause different expression levels along the EST -- +but each exon should give a region of constant expression level, +possibly tapering off. + + * identify exons and relative expression level? + * use region-based "background expression level" to find repeats +) +(thought: determine sequence quality based on low match number?) + +(thoughts on visualization: align sequences (and curves)?) + +(thought: use the length of the sequence to get an idea about +quality? mail Stephen Rudd, ask what happens if he turns sequences +around in the quality experiment) + +How to handle unkeyable words (i.e. with Ns in them)? + - zero (current tack) + - average of prec/succ + - average of possible interpretations + +Call mc something else - mc is midnight commander (or something) + +Current status (check darcs!): + +f3 - does a bit of debugging output +rb - does masking based on contiguous words, + and can output freqs along a sequence +mc - compares maskings diff --git a/rbr.cabal b/rbr.cabal new file mode 100644 --- /dev/null +++ b/rbr.cabal @@ -0,0 +1,44 @@ +Name: rbr +Version: 0.8.3 +License: GPL +License-File: LICENSE +Stability: Beta +Author: Ketil Malde +Maintainer: Ketil Malde +Category: Bioinformatics +Synopsis: Mask nucleotide (EST) sequences in Fasta format +Description: RBR is a tool for masking EST sequences. It uses a + statistical model to identify suspicious sequence parts, + and masks them. The README has more details. + . + The Darcs repository is at . +Homepage: http://malde.org/~ketil/ + +Cabal-Version: >= 1.2 +Tested-With: GHC==6.8.2 +-- add fps for ghc-6.4.2 +Build-Depends: base, bio >= 0.3.1, QuickCheck, binary, bytestring, containers +Build-Type: Simple + +data-files: idea.txt, README, TODO + +Library + Exposed-Modules: RBR.Options, RBR.Util, RBR.Stats, RBR.FreqTable, RBR.TextFormat + C-sources: RBR/hooks.c + Build-Depends: base>3, containers, bio + Extensions: + Ghc-Options: -Wall -funbox-strict-fields + +Executable rbr + Executable: rbr + Main-Is: RBR/RBR.lhs + build-depends: bytestring + Extensions: CPP + Ghc-Options: -Wall -funbox-strict-fields + +Executable mct + Executable: mct + Main-Is: RBR/MCT.lhs + build-depends: bytestring + Extensions: BangPatterns, FlexibleContexts + Ghc-Options: -Wall -funbox-strict-fields