diff --git a/BioInf/MutationOrder.hs b/BioInf/MutationOrder.hs
new file mode 100644
--- /dev/null
+++ b/BioInf/MutationOrder.hs
@@ -0,0 +1,411 @@
+
+-- | Run all steps of the HoxCluster algorithms in order.
+--
+-- This will produce the following:
+-- 
+-- 1. run the minimal distance algorithm, give the minimal distance score
+-- and return all co-optimal paths
+--
+-- 2. run the end-probability algorithm and return the probability that
+-- each node is the begin/end of a chain
+--
+-- 3. run the edge probability algorithm and give the probability for each
+-- @from :-> to@ edge
+--
+-- 4. with the edge probabilities, run the maximal probability path
+-- algorithm, return that probability and all co-optimal paths
+--
+-- TODO -Pretty should yield a structure to be given to the eps or svg
+-- generator. This allows more flexibility. Does diagrams offer
+-- serialization?
+--
+-- TODO All this should be wrapped and available as a function. not just
+-- providing output files.
+
+module BioInf.MutationOrder
+  ( module BioInf.MutationOrder
+  , FillWeight (..)
+  , FillStyle (..)
+  , ScaleFunction (..)
+  ) where
+
+import qualified Data.Vector.Unboxed as VU
+import           Data.Tuple (swap)
+import           Control.Monad (unless,forM_,when)
+import           Data.Bits
+import           Data.ByteString (ByteString)
+import           Data.Function (on)
+import           Data.List (groupBy,sortBy)
+import           Data.Ord (comparing)
+import           Numeric.Log
+import qualified Data.ByteString.Char8 as BS
+import qualified Data.HashMap.Strict as HM
+import qualified Data.Map.Strict as M
+import qualified Data.Text as T
+import qualified Data.Text.IO as T
+import           System.Directory (doesFileExist)
+import           System.Exit (exitFailure)
+import           Text.Printf
+import           Control.Arrow (first,second)
+import           System.IO (withFile,IOMode(WriteMode),hPutStrLn,Handle)
+import           System.Exit (exitSuccess)
+
+import           ADP.Fusion.Term.Edge.Type (From(..),To(..))
+import           Data.PrimitiveArray (fromEdgeBoundaryFst, EdgeBoundary(..), (:.)(..), getBoundary)
+import           Data.PrimitiveArray.ScoreMatrix
+import qualified Data.PrimitiveArray as PA
+import           Diagrams.TwoD.ProbabilityGrid
+import qualified Data.Bijection.HashMap as B
+import qualified ShortestPath.SHP.Edge.MinDist as SHP
+import           Biobase.Secondary.Diagrams (d1Distance)
+
+import           BioInf.MutationOrder.EdgeProb
+import           BioInf.MutationOrder.MinDist
+import           BioInf.MutationOrder.RNA
+
+
+
+runMutationOrder verbose fw fs fwdScaleFunction probScaleFunction cooptCount cooptPrint lkupFile outprefix workdb temperature equalStart [ancestralFP,currentFP] = do
+  -- only run if out file(s) do not exist
+  dfe <- doesFileExist (outprefix ++ ".run")
+  when dfe $ do
+    printf "%s.run exists, ending now!\n" outprefix
+    exitSuccess
+  withFile (outprefix ++ ".run") WriteMode $ \oH -> do
+    printf "%s.run job started!\n" outprefix
+    --
+    -- Initial stuff and debug information
+    --
+    ancestral <- stupidReader ancestralFP
+    current   <- stupidReader currentFP
+    lkup <- case lkupFile of {Nothing -> return Nothing; Just f -> Just <$> qlines f}
+    ls <- withDumpFile oH workdb ancestral current . fst $ createRNAlandscape lkup verbose ancestral current
+    let mpks = sortBy (comparing snd) . B.toList $ mutationPositions ls
+    let bitToNuc = M.fromList $ map (swap . first (+1)) mpks
+    let nn = length mpks
+    hPrintf oH "number of mutations: %d\n" $ mutationCount ls
+    hPrintf oH "\n%s\n\n" $ replicate 80 '='
+    --
+    -- Run co-optimal lowest energy changes
+    --
+    let (e,bs) = runCoOptDist fwdScaleFunction ls
+    let (ecount,countcount) = runCount fwdScaleFunction ls
+    -- split co-optimals into "want to print" and "want to count";
+    -- @countbs@ should be possible to stream
+    let (printbs,countbs) = splitAt cooptPrint bs
+    hPrintf oH "Best energy gain: %10.4f\n" e
+    hPrintf oH "Number of co-optimal paths: %10d\n" countcount -- ((length printbs) + (length $ take (cooptCount-cooptPrint) bs))
+    forM_ printbs (T.hPutStrLn oH)
+    hPrintf oH "%s\n\n" $ replicate 80 '='
+    --
+    -- Run @First@ probability algorithm to determine the probability for
+    -- each mutation to be the initial one
+    --
+    -- TODO this is completely wrong, because it still starts at the
+    -- ancestral sequence. We would have to start at the extant sequence.
+    -- Need to later think about this. But do not use any @First@ functions
+    -- now!
+    {-
+    hPrintf oH "Chain begin probabilities:\n"
+    let fps = boundaryPartFunFirst Nothing probScaleFunction ls
+    forM_ mpks $ \(mp,k) -> hPrintf oH "  %6d" (mp+1)
+    hPrintf oH "\n"
+    forM_ fps $ \(_, Exp p) -> hPrintf oH "  %6.4f" (exp p)
+    hPrintf oH "\n\n"
+    printf "\n"
+    -}
+    --
+    -- Run @Last@ probability algorithm to determine the probability for
+    -- each mutation to be the last one
+    --
+    hPrintf oH "Chain end probabilities:\n"
+    let fps = boundaryPartFunLast Nothing probScaleFunction ls
+    forM_ mpks $ \(mp,k) -> hPrintf oH "  %6d" (mp+1)
+    hPrintf oH "\n"
+    forM_ (bpNormalized fps) $ \(_, Exp p) -> hPrintf oH "  %6.4f" (exp p)
+    hPrintf oH "\n\n%s\n\n" $ replicate 80 '='
+    --printf "\n"
+    --
+    -- Run specialized versions of the above, restricting the first mutation
+    -- to the given one. Marginalized over the last probability, and rescaled
+    -- we get the first probability. Completely printed out, we get the joint
+    -- probability for each @i,j@ to be @first,last@ in the chain.
+    --
+    hPrintf oH "Restricted chain end probabilities\n"
+    let rbps = map (\(mp,k) -> (mp,k,boundaryPartFunLast (Just k) probScaleFunction ls)) mpks
+    {-
+    forM_ rbps $ \(mp,k,bp) -> do
+      hPrintf oH "%5d %5d\n" (mp+1) k
+      forM_ (bpUnnormalized bp) $ \(l,Exp p) -> hPrintf oH "%7d " (bitToNuc M.! getBoundary l)
+      hPrintf oH "\n"
+      forM_ (bpUnnormalized bp) $ \(l,p) -> hPrintf oH "%7.2f " (exp . ln $ p / bpTotal bp)
+      hPrintf oH "\n"
+    hPrintf oH "\n"
+    -}
+    -- collect all restricted partition function scores and prepare for
+    -- normalization
+    let firstlastUn = M.fromList [ ((mp+1,bitToNuc M.! getBoundary l), logp)
+                                 | (mp,k,bp) <- rbps, (l,logp) <- bpUnnormalized bp
+                                 ]
+    let firstlastZ = Numeric.Log.sum [ bpTotal bp | (_,_,bp) <- rbps ]
+    let firstlastLogP = M.map (/firstlastZ) firstlastUn
+    let firstlastP = M.map (exp . ln) firstlastLogP
+    -- rowMarginals gives the total probability that the mutation order
+    -- begins with this mutation.
+    let rowMarginals = M.mapKeysWith (+) fst firstlastP
+    -- colMarginals gives the total probability that the mutation order
+    -- ends with this mutation.
+    let colMarginals = M.mapKeysWith (+) snd firstlastP
+    hPrintf oH "       "
+    forM_ (M.elems bitToNuc) $ \mut -> hPrintf oH "%6d " mut
+    hPrintf oH "         Σ\n"
+    forM_ (M.elems bitToNuc) $ \frst -> do
+      hPrintf oH "%4d   " frst
+      forM_ (M.elems bitToNuc) $ \lst -> hPrintf oH "%6.4f " (firstlastP M.! (frst,lst))
+      hPrintf oH "    %6.4f\n" $ rowMarginals M.! frst
+    hPrintf oH "Σ      "
+    forM_ (M.elems colMarginals) $ hPrintf oH "%6.4f "
+    hPrintf oH "\n\n"
+    hPrintf oH "divergence from proper normalization: %10.8f\n" (1 - Prelude.sum firstlastP)
+    hPrintf oH "row marginal sum %10.8f\n" (Prelude.sum rowMarginals)
+    hPrintf oH "col marginal sum %10.8f\n" (Prelude.sum colMarginals)
+    hPrintf oH "\n%s\n\n" $ replicate 80 '='
+    -- debug on
+    {-
+    hPrintf oH "%f\n" $ ln firstlastZ
+    hPrintf oH "%s " $ replicate 10 ' '
+    forM_ (M.elems bitToNuc) $ \mut -> hPrintf oH "%10d " mut
+    hPrintf oH "\n"
+    forM_ (M.elems bitToNuc) $ \frst -> do
+      hPrintf oH "%8d   " frst
+      forM_ (M.elems bitToNuc) $ \lst -> hPrintf oH "%10.4f " (ln $ firstlastUn M.! (frst,lst))
+      hPrintf oH "\n"
+    hPrintf oH "\n"
+    hPrintf oH "%f\n" $ ln firstlastZ
+    hPrintf oH "%s " $ replicate 10 ' '
+    forM_ (M.elems bitToNuc) $ \mut -> hPrintf oH "%10d " mut
+    hPrintf oH "\n"
+    forM_ (M.elems bitToNuc) $ \frst -> do
+      hPrintf oH "%8d   " frst
+      forM_ (M.elems bitToNuc) $ \lst -> hPrintf oH "%10.4f " ((ln $ firstlastUn M.! (frst,lst)) - ln firstlastZ)
+      hPrintf oH "\n"
+    hPrintf oH "\n"
+    -}
+    -- debug off
+    -- debug on
+    -- calculate first weight, unnormalized
+  --  let firstUn = M.fromList [ ]
+    -- debug off
+    --
+    --
+    -- Run edge probability Inside/Outside calculations. These take quite
+    -- a while longer.
+    --
+    let (ibs,eps) = edgeProbPartFun probScaleFunction ls
+    hPrintf oH "pairwise next mutation probabilities:\n\n"
+    hPrintf oH "       "
+    forM_ mpks $ \(mp,k) -> hPrintf oH " %6d" k
+    hPutStrLn oH ""
+    hPrintf oH "       "
+    forM_ mpks $ \(mp,k) -> hPrintf oH " %6d" (mp+1)
+    hPutStrLn oH ""
+    forM_ (zip (groupBy ((==) `on` (fromEdgeBoundaryFst . fst)) eps) mpks) $ \(rps,(mp,k)) -> do
+      let (eb,_) = head rps
+      hPrintf oH "%3d %3d" k (mp+1)
+      forM_ rps $ \(eb,Exp p) -> hPrintf oH (" %6.4f") (exp p)
+      hPrintf oH "   %6.4f" (Prelude.sum $ map (exp . ln . snd) rps)
+      hPrintf oH "\n"
+    let colSums = M.fromListWith (+) [ (c,p) | ((_ :-> c),p) <- eps ]
+    hPrintf oH "    Σ  "
+    forM_ (M.toList colSums) $ \(c,Exp p) -> hPrintf oH (" %6.4f") (exp p)
+    hPutStrLn oH "\n"
+    gridFile [SVG,EPS] (outprefix ++ "-edge") fw fs nn nn (map (show . (+1) . fst) mpks) (map (show . (+1) . fst) mpks) (map snd eps)
+    hPrintf oH "\n%s\n\n" $ replicate 80 '='
+    --
+    -- Generate the path with maximal edge probability
+    --
+    {-
+    let eprobsFirst = edgeProbScoreMatrix ls (Prelude.map (Exp . log) $ M.elems colMarginals) eps
+    let (Exp maxprob,mpbt) = SHP.runMaxEdgeProbFirst eprobsFirst
+    hPrintf oH "Maximal Edge Log-Probability Sum: %6.4f with at least %d co-optimal paths\n" maxprob (length $ take cooptCount mpbt)
+    hPutStrLn oH "first mutation to extant species\n"
+    forM_ (take cooptPrint mpbt) $ \bt -> do
+      let extractMut (SHP.BTnode (_:.To n)) = n
+          extractMut (SHP.BTedge (From ff:.To tt)) = ff
+      let mutationOrder = tail $ scanl (\set mut -> set `setBit` extractMut mut) zeroBits (reverse bt)
+      let prettyPrint mut k = do
+            let rna = rnas ls HM.! mut
+            hPrintf oH "   %3s  %s\n        %s   MFE %6.4f\n        %s   CNT %6.4f\n"
+                    (maybe "anc" (show . (+1) . fst . (!!) mpks) k)
+                    (BS.unpack $ primarySequence rna)
+                    (BS.unpack $ mfeStructure rna)
+                    (mfeEnergy rna)
+                    (BS.unpack $ centroidStructure rna)
+                    (centroidEnergy rna)
+            hPutStrLn oH $ replicate 8 ' ' ++ (take (BS.length $ primarySequence rna) . concat $ zipWith (\xs x -> xs ++ show x) (repeat $ "    .    ") (drop 1 $ cycle [0..9]))
+      prettyPrint zeroBits Nothing
+      forM_ (zip (reverse bt) mutationOrder) $ \case
+        (SHP.BTnode (_:.To n),mut) -> prettyPrint mut (Just n)
+        (SHP.BTedge (From ff:.To tt),mut) -> prettyPrint mut (Just ff)
+      hPutStrLn oH ""
+    hPutStrLn oH ""
+    -}
+    -- the rowMarginals hold the probabily to begin with a mutation. Since
+    -- @Last@ goes from first to last mutation, this is what we need.
+    let eplStartWeight = if equalStart
+          then Prelude.map (const 1) $ M.elems rowMarginals
+          else Prelude.map (Exp . log) $ M.elems rowMarginals
+    let eprobsLast = edgeProbScoreMatrix ls eplStartWeight eps
+    --print eprobsLast
+    --print $ PA.assocs $ scoreMatrix eprobsLast
+    let (Exp maxprobLast,lastLogProbs,mpbtLast') = SHP.runMaxEdgeProbLast eprobsLast
+    let mpbtLast = map reverse mpbtLast'
+    --print maxprobLast
+    --print lastLogProbs
+    --mapM_ print $ mpbtLast
+    hPrintf oH "Fraction of optimal choice for each final mutation:\n"
+    forM_ lastLogProbs $ \(PA.Boundary b, _) -> hPrintf oH "  %6d" $ bitToNuc M.! b
+    hPrintf oH "\n"
+    forM_ lastLogProbs $ \(_, p) -> hPrintf oH "  %6.4f" $ exp $ ln (p / Exp maxprobLast)
+    hPrintf oH "\n\n"
+    hPrintf oH "Maximal edge log-probability sum: %6.4f (P = %10.8f) with at least %d co-optimal paths\n" maxprobLast (exp maxprobLast) (length $ take cooptCount mpbtLast)
+    hPutStrLn oH "(first mutation to extant species)\n"
+    forM_ (take cooptPrint mpbtLast) $ \bt -> do
+      let extractMut (SHP.BTnode (_:.To n)) = n
+          extractMut (SHP.BTedge (From ff:.To tt)) = tt
+      let mutationOrder = tail $ scanl (\set mut -> set `setBit` extractMut mut) zeroBits bt
+      let prettyPrint mut k = do
+            let rna = rnas ls HM.! mut
+            hPrintf oH "   %3s  %s\n        %s   MFE %6.4f\n        %s   CNT %6.4f\n"
+                    (maybe "anc" (show . (+1) . fst . (!!) mpks) k)
+                    (BS.unpack $ primarySequence rna)
+                    (BS.unpack $ mfeStructure rna)
+                    (mfeEnergy rna)
+                    (BS.unpack $ centroidStructure rna)
+                    (centroidEnergy rna)
+            hPutStrLn oH $ replicate 8 ' ' ++ (take (BS.length $ primarySequence rna) . concat $ zipWith (\xs x -> xs ++ show x) (repeat $ "    .    ") (drop 1 $ cycle [0..9]))
+      prettyPrint zeroBits Nothing
+      forM_ (zip bt mutationOrder) $ \case
+        (SHP.BTnode (_:.To n),mut) -> prettyPrint mut (Just n)
+        (SHP.BTedge (From ff:.To tt),mut) -> prettyPrint mut (Just tt)
+      hPutStrLn oH ""
+    hPutStrLn oH ""
+    let meaOrder =
+          let go = \case SHP.BTnode (_:.To n) -> n
+                         SHP.BTedge (From ff:.To tt) -> tt
+          in  map go $ concat $ take 1 mpbtLast
+    let meaAnno = map (\k -> map (show . (+1) . fst) mpks !! k) meaOrder
+    let meaEps = [ (ee !! k) !! l | let ee = groupBy ((==) `on` (fromEdgeBoundaryFst . fst)) eps, k <- meaOrder, l <- meaOrder ]
+    gridFile [SVG,EPS] (outprefix ++ "-edge-meaorder") fw fs nn nn meaAnno meaAnno (map snd meaEps)
+    --print eps
+    --print meaEps
+    {-
+    let eprobsLast = edgeProbScoreMatrix ls (Prelude.map (Exp . log) $ M.elems rowMarginals) eps
+    let (Exp maxprobLast,lastLogProbs,mpbtLast) = SHP.runMaxEdgeProbLast eprobsLast
+    print maxprobLast
+    print $ map (\(k,Exp p) -> (k,exp $ p - maxprobLast)) lastLogProbs
+    mapM_ print $ concat $ take 2 mpbtLast
+    let eprobsLast = edgeProbScoreMatrix ls (Prelude.map (Exp . log) $ M.elems colMarginals) eps
+    let (Exp maxprobLast,lastLogProbs,mpbtLast) = SHP.runMaxEdgeProbLast eprobsLast
+    print maxprobLast
+    print $ map (\(k,Exp p) -> (k,exp $ p - maxprobLast)) lastLogProbs
+    mapM_ print $ concat $ take 2 mpbtLast
+    -}
+{-# NoInline runMutationOrder #-}
+
+posScaled :: Double -> Double -> ScaleFunction -> ScaleFunction
+posScaled l s = scaleByFunction go where
+  go d | d >= l    = d ** s
+       | otherwise = d
+  {-# Inline go #-}
+{-# Inlinable posScaled #-}
+
+-- | Basepair distance
+
+basepairDistanceMFE :: ScaleFunction
+basepairDistanceMFE frna trna = fromIntegral $ d1Distance (mfeD1S frna) (mfeD1S trna)
+
+basepairDistanceCentroid :: ScaleFunction
+basepairDistanceCentroid frna trna = fromIntegral $ d1Distance (centroidD1S frna) (centroidD1S trna)
+
+-- | Scale function for normal mfe delta energies
+
+mfeDelta :: ScaleFunction
+mfeDelta frna trna = mfeEnergy trna - mfeEnergy frna
+{-# Inlinable mfeDelta #-}
+
+-- | Scale function for normal centroid delta energies
+
+centroidDelta :: ScaleFunction
+centroidDelta frna trna = centroidEnergy trna - centroidEnergy frna
+{-# Inlinable centroidDelta #-}
+
+-- | Square positive "contributions", making bad moves more unlikely
+
+squaredPositive :: ScaleFunction -> ScaleFunction
+squaredPositive sf = scaleByFunction sp sf where
+  sp d
+    | d > 0     = d * d
+    | otherwise = d
+  {-# Inline sp #-}
+{-# Inlinable squaredPositive #-}
+
+-- | Scale by temperature (for probability stuff)
+
+scaleTemperature :: Double -> ScaleFunction -> ScaleFunction
+scaleTemperature t sf = scaleByFunction (/t) sf
+{-# Inlinable scaleTemperature #-}
+
+scaleByFunction f sf = \frna trna ->
+  let d = sf frna trna
+  in  f d
+{-# Inlinable scaleByFunction #-}
+
+-- | Basepair distance
+
+-- | Stupid fasta reader
+
+stupidReader :: FilePath -> IO ByteString
+stupidReader fp = do
+  inp <- BS.lines <$> BS.readFile fp
+  let xs = filter (\x -> not (BS.null x) && BS.head x /= '>') inp
+  return $ BS.concat xs
+
+-- | @withDumpFile@ is like @idIO :: a -> IO a@ in that it returns the data
+-- we give to the function. However, in case the dump file exists, we read
+-- it and return its contents, instead of recalculating. If it does not
+-- exist, we dump the data in addition to returning it. This forces the
+-- @Landscape@.
+
+withDumpFile
+  :: Handle
+  -> FilePath
+  -- ^ The path we store the serialized and compressed dump in
+  -> ByteString
+  -- ^ ancestral / origin sequence
+  -> ByteString
+  -- ^ destination sequence
+  -> Landscape
+  -- ^ the element which is to be serialized in the dump, or which would be
+  -- the data in the dump
+  -> IO Landscape
+  -- ^ the data we put in, but maybe taken from the dump file
+withDumpFile oH fp ancestral current l = do
+  dfe <- doesFileExist fp
+  if dfe then do
+    hPrintf oH "using database %s to load sequence information\n" fp
+    ls <- fromFileJSON fp
+    -- now we check if we have a sane DB file
+    unless (landscapeOrigin ls == ancestral && landscapeDestination ls == current) $ do
+      hPutStrLn oH "ancestral or target sequence do not match those stored in the work database"
+      hPutStrLn oH $ "given ancestral: " ++ BS.unpack ancestral
+      hPutStrLn oH $ "DB    ancestral: " ++ (BS.unpack $ landscapeOrigin ls)
+      hPutStrLn oH $ "given current:   " ++ BS.unpack current
+      hPutStrLn oH $ "DB    current:   " ++ (BS.unpack $ landscapeDestination ls)
+      exitFailure
+    return ls
+  else do
+    hPrintf oH "database %s does not exist! Folding all intermediate structures. This may take a while!\n" fp
+    toFileJSON fp l
+    return l
+
diff --git a/BioInf/MutationOrder/EdgeProb.hs b/BioInf/MutationOrder/EdgeProb.hs
new file mode 100644
--- /dev/null
+++ b/BioInf/MutationOrder/EdgeProb.hs
@@ -0,0 +1,140 @@
+
+module BioInf.MutationOrder.EdgeProb where
+
+import           Control.Arrow (second)
+import           Control.Monad (forM_)
+import           Data.List (nub,sort)
+import           Data.Text (Text,unpack)
+import           Data.Vector.Unboxed (Unbox)
+import           Numeric.Log
+import qualified Data.Text as T
+import qualified Data.Vector.Fusion.Stream.Monadic as SM
+import           Text.Printf
+import qualified Data.Vector as V
+import qualified Data.HashMap.Strict as HM
+import           Data.Bits
+import           Debug.Trace
+
+import qualified Data.Bijection.HashMap as B
+import           ADP.Fusion.Core
+import           ADP.Fusion.EdgeBoundary
+import           ADP.Fusion.Set1
+import           Data.PrimitiveArray hiding (toList)
+import           Data.PrimitiveArray.ScoreMatrix
+import           Diagrams.TwoD.ProbabilityGrid
+import           FormalLanguage
+import           ShortestPath.SHP.Grammar.EdgeProbIO
+import           Data.Vector.Generic.Unstream
+
+import           BioInf.MutationOrder.RNA
+import           BioInf.MutationOrder.MinDist (ScaleFunction(..))
+
+
+
+-- | Before using @aInside@ the @ScoreMat@ needs to be scaled
+--
+-- TODO the @Edge@ needs to be an @EdgeWithActive@ to get the active bits
+-- on the left in the set.
+
+aInside :: Monad m => ScaleFunction -> Landscape -> SigEdgeProb m (Log Double) (Log Double) (Int:.From:.To) (Int:.To)
+aInside scaled Landscape{..} = SigEdgeProb
+  { edge = \x (fset:.From f:.To t) ->
+      let frna = rnas HM.! (BitSet fset)
+          trna = rnas HM.! (BitSet fset `xor` bit t)
+          res' = scaled frna trna
+          res  = Exp . negate $ res'
+      in
+#ifdef ADPFUSION_DEBUGOUTPUT
+          traceShow ("Edge",(BitSet fset,f,t),frna,trna,' ',res',res,x,x*res) $
+#endif
+          x * res
+  , mpty = \() ->
+#ifdef ADPFUSION_DEBUGOUTPUT
+                  traceShow "empty" $
+#endif
+                  1
+  , node = \x (nset:.To n) ->
+      let frna = rnas HM.! (BitSet nset)
+          trna = rnas HM.! (BitSet nset `xor` bit n)
+          res' = scaled frna trna
+          res  = Exp . negate $ res'
+      in
+#ifdef ADPFUSION_DEBUGOUTPUT
+          traceShow ("Node",n,frna,trna,' ',res',res,x,res*x) $
+#endif
+          x * res
+  , fini = \l (fset:.From f:.To t) r ->
+      let frna = rnas HM.! (BitSet fset)
+          trna = rnas HM.! (BitSet fset `xor` bit t)
+          res' = scaled frna trna
+          res  = Exp . negate $ res'
+      in
+#ifdef ADPFUSION_DEBUGOUTPUT
+          traceShow ("Fini",(BitSet fset,f,t),frna,trna,' ',res',res,l,r,l*r*res) $
+#endif
+          l * r * res
+  , h    = SM.foldl' (+) 0
+--  , h    = \s -> do v :: V.Vector (Log Double) <- streamToVectorM s
+--                    return $ Numeric.Log.sum v
+  } where !n = fromIntegral mutationCount
+{-# Inline aInside #-}
+
+
+
+type TF1 x = TwITbl Id Unboxed EmptyOk (BS1 Last I)      x
+type TL1 x = TwITbl Id Unboxed EmptyOk (BS1 Last O)      x
+type EB  x = TwITbl Id Unboxed EmptyOk (EdgeBoundary C)   x
+
+
+
+-- | Extract the individual partition scores.
+
+edgeProbPartFun :: ScaleFunction -> Landscape -> ([(Boundary Last I, Log Double)], [(EdgeBoundary C, Log Double)])
+edgeProbPartFun scaled landscape =
+  let n       = mutationCount landscape
+      (Z:.sF:.sL:.sZ) = mutateTablesST $ gEdgeProb (aInside scaled landscape)
+                          (ITbl 0 0 EmptyOk (fromAssocs (BS1 0 (-1)) (BS1 (2^n-1) (Boundary $ n-1)) 0 []))
+                          (ITbl 1 0 EmptyOk (fromAssocs (BS1 0 (-1)) (BS1 (2^n-1) (Boundary $ n-1)) 0 []))
+                          (ITbl 2 0 EmptyOk (fromAssocs (0 :-> 0)    (0 :-> (n-1))                  0 []))
+                          EdgeWithSet
+                          Singleton
+                        :: Z:.TF1 (Log Double):.TL1 (Log Double):.EB (Log Double)
+      TW (ITbl _ _ _ pf ) _ = sZ
+      TW (ITbl _ _ _ lkF) _ = sF
+      TW (ITbl _ _ _ lkL) _ = sL
+      bs' = assocs pf
+      pssum  = (Numeric.Log.sum $ Prelude.map snd bs') / (fromIntegral n - 1)
+      ibs'   = [ (Boundary b, p) | b <- [0..n] , let p = lkF ! (BS1 (2^n-1) (Boundary b)) ]
+      obs'   = [ (Boundary b, p) | b <- [0..n] , let p = lkF ! (BS1 (2^n-1) (Boundary b)) ]
+      ibssum = Numeric.Log.sum $ Prelude.map snd ibs'
+      obssum = Numeric.Log.sum $ Prelude.map snd ibs'
+      ibs    = Prelude.map (second (/ibssum)) ibs'
+      bs     = Prelude.map (second (/ibssum)) bs'
+  in
+#ifdef ADPFUSION_DEBUGOUTPUT
+      traceShow (assocs lkF) $
+      traceShow (assocs lkL) $
+      traceShow (assocs pf) $
+      traceShow (ibssum,obssum) $
+      traceShow (bs',pssum,bs) $
+#endif
+      (ibs,bs)
+{-# NoInline edgeProbPartFun #-}
+
+-- | Turn the edge probabilities into a score matrix.
+
+edgeProbScoreMatrix :: Landscape -> [Log Double] -> [(EdgeBoundary C, Log Double)] -> ScoreMatrix (Log Double)
+edgeProbScoreMatrix Landscape{..} begs xs' = ScoreMatrix m nprobs names names
+  where m = fromAssocs l h 0 xs
+        l = (Z:.0:.0)
+        h = (Z:.maximum [f | (f :-> _,_) <- xs']:.maximum [t | (_ :-> t,_) <- xs'])
+        (Z:._:.hh) = h
+        xs = [ ((Z:.f:.t),p) | (f :-> t, p) <- xs' ]
+        (_,Z:._:.n) = bounds m
+        names = V.fromList [ T.pack . show . (+1)
+                           . maybe (error "MutationOrder.EdgeProb.edgeProbScoreMatrix") id
+                           $ B.lookupR mutationPositions k | k <- [0..n]
+                           ]
+        rowsums = HM.fromListWith (+) [ (f,p) | (f :-> t, p) <- xs' ]
+        nprobs = fromAssocs 0 hh 1 $ zip [0..hh] begs -- [ (f,1-p) | f <- [0..hh], let p = rowsums HM.! f ]
+
diff --git a/BioInf/MutationOrder/MinDist.hs b/BioInf/MutationOrder/MinDist.hs
new file mode 100644
--- /dev/null
+++ b/BioInf/MutationOrder/MinDist.hs
@@ -0,0 +1,303 @@
+
+-- | Calculate minimum-distance Hamiltonian Shortest Paths and
+-- probabilities for starting nodes.
+--
+-- NOTE: We explicitly model starting nodes. For symmetrical distance
+-- matrices, this reports begin/end probabilities. For asymmetrical
+-- distance matrices, a second instances with @Last@ instead of @First@
+-- boundary should be created to calculate begin/end probabilities
+-- separately.
+
+module BioInf.MutationOrder.MinDist where
+
+import           Control.Arrow (second)
+import           Control.Monad (forM_)
+import           Data.Bits
+import           Data.Data (Data)
+import           Data.List (nub,sort)
+import           Data.Text (Text)
+import           Data.Typeable(Typeable)
+import           Debug.Trace
+import           Numeric.Log
+import qualified Data.ByteString.Char8 as BS
+import qualified Data.HashMap.Strict as HM
+import qualified Data.Text as T
+import qualified Data.Vector.Fusion.Stream.Monadic as SM
+import           Text.Printf
+import qualified Data.Vector.Unboxed as VU
+import           Data.Maybe (fromJust)
+import qualified Data.Map.Strict as MS
+
+import qualified Data.Bijection.HashMap as B
+import           ADP.Fusion.Core
+import           ADP.Fusion.Set1
+import           ADP.Fusion.Unit
+import           Data.PrimitiveArray hiding (toList,map)
+import           FormalLanguage
+import           ShortestPath.SHP.Grammar.MinDist
+
+import           BioInf.MutationOrder.RNA
+
+
+
+-- | Given the 'RNA' we come from and the 'RNA' we mutate into, derive the
+-- gain or loss by a scaling function.
+
+type ScaleFunction = RNA -> RNA -> Double
+
+-- | Minimal distance algebra
+--
+-- TODO The two Ints are the indices of the nodes and could be replaced?
+
+aMinDist :: Monad m => ScaleFunction -> Landscape -> SigMinDist m Double Double (Int:.From:.To) (Int:.To)
+aMinDist scaled Landscape{..} = SigMinDist
+  { edge = \x (fset:.From f:.To t) -> let frna = rnas HM.! (BitSet fset)
+                                          trna = rnas HM.! (BitSet fset `setBit` f `setBit` t)
+                                      in  -- traceShow (BitSet fset, BitSet fset `setBit` f `setBit` t) $
+                                          -- x + scaleFunction scaled (centroidEnergy trna - centroidEnergy frna)
+                                          x + scaled frna trna
+  , mpty = \() -> 0
+  , node = \(nset:.To n) ->
+      let frna = rnas HM.! (BitSet 0)
+          trna = rnas HM.! (BitSet 0 `setBit` n)
+      in  -- scaleFunction scaled $ centroidEnergy trna - centroidEnergy frna
+          scaled frna trna
+  , fini = id
+  , h    = SM.foldl' min 999999
+  }
+{-# Inline aMinDist #-}
+
+-- | Fused co-optimal counter!
+--
+-- TODO for now, @Int@ is assumed to be big enough...
+
+aMinDistCount :: Monad m => ScaleFunction -> Landscape -> SigMinDist m (Double,Int) (Double,Int) (Int:.From:.To) (Int:.To)
+aMinDistCount scaled Landscape{..} = SigMinDist
+  { edge = \x (fset:.From f:.To t) -> let frna = rnas HM.! (BitSet fset)
+                                          trna = rnas HM.! (BitSet fset `setBit` f `setBit` t)
+                                      in  -- traceShow (BitSet fset, BitSet fset `setBit` f `setBit` t, f,t, fst x, scaled frna trna) $
+                                          -- x + scaleFunction scaled (centroidEnergy trna - centroidEnergy frna)
+                                          (fst x + scaled frna trna, snd x)
+  , mpty = \() -> (0,1)
+  , node = \(nset:.To n) ->
+      let frna = rnas HM.! (BitSet 0)
+          trna = rnas HM.! (BitSet 0 `setBit` n)
+      in  -- scaleFunction scaled $ centroidEnergy trna - centroidEnergy frna
+          (scaled frna trna,1)
+  , fini = id
+  , h    = \xs -> do cntr <- SM.foldl' (\m (k,c) -> MS.insertWith (+) k c m) MS.empty xs
+                     -- traceShow cntr .
+                     return $ maybe (999999,0) fst $ MS.minViewWithKey cntr
+  }
+{-# Inline aMinDistCount #-}
+
+-- | Sum over all states and collapse into boundary unscaled weights.
+
+aInside :: Monad m => Maybe Int -> ScaleFunction -> Landscape -> SigMinDist m (Log Double) (Log Double) (Int:.From:.To) (Int:.To)
+aInside restrictStartNode scaled Landscape{..} = SigMinDist
+  { edge = \x (fset:.From f:.To t) -> let frna = rnas HM.! (BitSet fset)
+                                          trna = rnas HM.! (BitSet fset `xor` bit t)
+                                          res' = Exp . negate $ scaled frna trna
+                                          res  = x * res'
+                                      in
+                                          -- traceShow ("edge",fset,f,t,frna,trna,scaled frna trna, res', res) $
+                                          maybe res (\k -> if k==t then 0 else res) restrictStartNode
+  , mpty = \() -> 1
+  , node = \(nset:.To n) ->
+      let frna = rnas HM.! (BitSet 0)
+          trna = rnas HM.! (BitSet 0 `xor` bit n)
+          res = Exp . negate $ scaled frna trna
+      in
+          -- traceShow ("node",nset,n, frna, trna, scaled frna trna, res) $
+          maybe res (\k -> if k==n then res else 0) restrictStartNode
+  , fini = id
+  , h    = SM.foldl' (+) 0
+  }
+{-# Inline aInside #-}
+
+-- | This should give the correct order of nodes independent of the
+-- underlying @Set1 First@ or @Set1 Last@ because the @(From:.To)@ system
+-- is agnostic over these.
+--
+-- TODO Use text builder
+
+aPretty :: Monad m => ScaleFunction -> Landscape -> SigMinDist m Text [Text] (Int:.From:.To) (Int:.To)
+aPretty scaled Landscape{..} = SigMinDist
+  { edge = \x (fset:.From f:.To t) -> let frna = rnas HM.! (BitSet fset)
+                                          trna = rnas HM.! (BitSet fset `setBit` f `setBit` t)
+                                          eM = mfeEnergy trna - mfeEnergy frna
+                                          eC = centroidEnergy trna - centroidEnergy frna
+                                          eS = scaled frna trna
+                                          f' = fromJust $ B.lookupR mutationPositions f
+                                          t' = fromJust $ B.lookupR mutationPositions t
+                                      in  T.concat [x, showMut frna trna t' eM eC eS]
+  , mpty = \()  -> ""
+  , node = \(nset:.To n)  ->
+      let
+        frna = rnas HM.! (BitSet 0)
+        trna = rnas HM.! (BitSet 0 `setBit` n)
+        n'   = fromJust $ B.lookupR mutationPositions n
+        eM   = mfeEnergy trna - mfeEnergy frna
+        eC   = centroidEnergy trna - centroidEnergy frna
+        eS   = scaled frna trna
+      in  T.concat [showHdr frna n', showMut frna trna n' eM eC eS]
+  , fini = id
+  , h    = SM.toList
+  } where
+      showHdr frna n = T.concat
+        [ T.pack $ printf "mutation         mfe    centr  scfun  "
+        , T.pack $ VU.toList $ VU.replicate (BS.length $ primarySequence frna) ' ' VU.// (map (,'v') . sort . map fst $ B.toList mutationPositions)
+        , T.pack $ "\n" ++ replicate 38 ' '
+        , T.pack . take (BS.length $ primarySequence frna) . concat $ zipWith (\xs x -> xs ++ show x) (repeat $ "    .    ") (drop 1 $ cycle [0..9])
+        , "\n"
+        , T.pack $ printf "ancestral        %5.1f  %5.1f         " (mfeEnergy frna) (centroidEnergy frna)
+        , T.pack $ BS.unpack $ primarySequence frna
+        , "\n"
+        ]
+      showMut frna trna n eM eC eS = T.concat
+        [ T.pack $ printf "%5d            %5.1f  %5.1f  %5.1f  " (n+1) eM eC eS
+        , T.pack . BS.unpack $ primarySequence trna
+        , "\n"
+        ]
+{-# Inline aPretty #-}
+
+-- | Count co-optimals
+
+aCount :: Monad m => Landscape -> SigMinDist m Integer [Integer] (Int:.From:.To) (Int:.To)
+aCount Landscape{..} = SigMinDist
+  { edge = \x (fset:.From f:.To t) -> x
+  , mpty = \()  -> 1
+  , node = \n   -> 1
+  , fini = id
+  , h    = \xs -> SM.foldl' (+) 0 xs >>= \x -> return [x]
+  }
+{-# Inline aCount #-}
+
+
+
+type TS1 x = TwITbl Id Unboxed EmptyOk (BS1 First I)      x
+type U   x = TwITbl Id Unboxed EmptyOk (Unit I)           x
+type PF  x = TwITbl Id Unboxed EmptyOk (Boundary First I) x
+
+type TS1L x = TwITbl Id Unboxed EmptyOk (BS1 Last I)      x
+type PFL  x = TwITbl Id Unboxed EmptyOk (Boundary Last I) x
+
+type BT1 x b = TwITblBt Unboxed EmptyOk (BS1 First I) x Id Id b
+type BTU x b = TwITblBt Unboxed EmptyOk (Unit I)      x Id Id b
+
+type BT1L x b = TwITblBt Unboxed EmptyOk (BS1 Last I) x Id Id b
+
+
+
+-- | Run the minimal distance algebra.
+--
+-- This produces one-boundary sets. Meaning that for each boundary we get
+-- the total distance within the set.
+
+forwardMinDist1 :: ScaleFunction -> Landscape -> Z:.TS1L Double:.U Double
+forwardMinDist1 scaleFunction landscape =
+  let n = mutationCount landscape
+  in  mutateTablesST $ gMinDist (aMinDist scaleFunction landscape)
+        (ITbl 0 0 EmptyOk (fromAssocs (BS1 0 (-1)) (BS1 (2^n-1) (Boundary $ n-1)) (999999) []))
+        (ITbl 1 0 EmptyOk (fromAssocs Unit         Unit                           (999999) []))
+        EdgeWithSet
+        Singleton
+{-# NoInline forwardMinDist1 #-}
+
+backtrackMinDist1 :: ScaleFunction -> Landscape -> Z:.TS1L Double:.U Double -> [Text]
+backtrackMinDist1 scaleFunction landscape (Z:.ts1:.u) = unId $ axiom b
+  where !(Z:.bt1:.b) = gMinDist (aMinDist scaleFunction landscape <|| aPretty scaleFunction landscape)
+                            (toBacktrack ts1 (undefined :: Id a -> Id a))
+                            (toBacktrack u   (undefined :: Id a -> Id a))
+                            EdgeWithSet
+                            Singleton
+                        :: Z:.BT1L Double Text:.BTU Double Text
+{-# NoInline backtrackMinDist1 #-}
+
+-- | Count the number of co-optimals
+
+minDistCount :: ScaleFunction -> Landscape -> Z:.TS1L (Double,Int):.U (Double,Int)
+minDistCount scaleFunction landscape =
+  let n = mutationCount landscape
+  in  mutateTablesST $ gMinDist (aMinDistCount scaleFunction landscape)
+        (ITbl 0 0 EmptyOk (fromAssocs (BS1 0 (-1)) (BS1 (2^n-1) (Boundary $ n-1)) (999999,0) []))
+        (ITbl 1 0 EmptyOk (fromAssocs Unit         Unit                           (999999,0) []))
+        EdgeWithSet
+        Singleton
+{-# NoInline minDistCount #-}
+
+countBackMinDist1 :: ScaleFunction -> Landscape -> Z:.TS1L Double:.U Double -> [Integer]
+countBackMinDist1 scaleFunction landscape (Z:.ts1:.u) = unId $ axiom b
+  where !(Z:.bt1:.b) = gMinDist (aMinDist scaleFunction landscape <|| aCount landscape)
+                            (toBacktrack ts1 (undefined :: Id a -> Id a))
+                            (toBacktrack u   (undefined :: Id a -> Id a))
+                            EdgeWithSet
+                            Singleton
+                        :: Z:.BT1L Double Integer:.BTU Double Integer
+{-# NoInline countBackMinDist1 #-}
+
+-- | Given the @Set1@ produced in @forwardMinDist1@ we can now extract the
+-- co-optimal paths using the @Set1 -> ()@ index change.
+--
+-- TODO do we want this one explicitly or make life easy and just extract
+-- from all @forwardMinDist1@ paths?
+
+runCoOptDist :: ScaleFunction -> Landscape -> (Double,[Text])
+runCoOptDist scaleFunction landscape = (unId $ axiom fwdu,bs)
+  where !(Z:.fwd1:.fwdu) = forwardMinDist1 scaleFunction landscape
+        bs = backtrackMinDist1 scaleFunction landscape (Z:.fwd1:.fwdu)
+{-# NoInline runCoOptDist #-}
+
+runCount :: ScaleFunction -> Landscape -> (Double,Int)
+runCount scaleFunction landscape = (unId $ axiom fwdu)
+  where !(Z:.fwd1:.fwdu) = minDistCount scaleFunction landscape
+{-# NoInline runCount #-}
+
+-- | Extract the individual partition scores.
+
+boundaryPartFunFirst :: Maybe Int -> ScaleFunction -> Landscape -> [(Boundary First I,Log Double)]
+boundaryPartFunFirst restrictStartNode scaleFunction landscape =
+  let n       = mutationCount landscape
+      (Z:.sM:.bM) = mutateTablesST $ gMinDist (aInside restrictStartNode scaleFunction landscape)
+                      (ITbl 0 0 EmptyOk (fromAssocs (BS1 0 (-1)) (BS1 (2^n-1) (Boundary $ n-1)) (-999999) []))
+                      (ITbl 1 0 EmptyOk (fromAssocs (Boundary 0) (Boundary $ n-1)               (-999999) []))
+                      EdgeWithSet
+                      Singleton
+                    :: Z:.TS1 (Log Double):.PF (Log Double)
+      TW (ITbl _ _ _ pf) _ = bM
+      bs' = assocs pf
+      pssum = Numeric.Log.sum $ Prelude.map snd bs'
+      bs = Prelude.map (second (/pssum)) bs'
+  in bs
+{-# NoInline boundaryPartFunFirst #-}
+
+boundaryPartFunLast :: Maybe Int -> ScaleFunction -> Landscape -> BoundaryPart -- [(Boundary Last I,Log Double)]
+boundaryPartFunLast restrictStartNode scaleFunction landscape =
+  let n       = mutationCount landscape
+      (Z:.sM:.bM) = mutateTablesST $ gMinDist (aInside restrictStartNode scaleFunction landscape)
+                      (ITbl 0 0 EmptyOk (fromAssocs (BS1 0 (-1)) (BS1 (2^n-1) (Boundary $ n-1)) (-999999) []))
+                      (ITbl 1 0 EmptyOk (fromAssocs (Boundary 0) (Boundary $ n-1)               (-999999) []))
+                      EdgeWithSet
+                      Singleton
+                    :: Z:.TS1L (Log Double):.PFL (Log Double)
+      TW (ITbl _ _ _ pf) _ = bM
+--      bs' = assocs pf
+--      pssum = Numeric.Log.sum $ Prelude.map snd bs'
+--      bs = Prelude.map (second (/pssum)) bs'
+  in  boundaryPart $ assocs pf -- bs
+{-# NoInline boundaryPartFunLast #-}
+
+data BoundaryPart = BoundaryPart
+  { bpNormalized   :: [(Boundary Last I, Log Double)]
+  , bpUnnormalized :: [(Boundary Last I, Log Double)]
+  , bpTotal        :: Log Double
+  }
+  deriving (Show,Eq)
+
+boundaryPart ps = BoundaryPart
+  { bpNormalized   = Prelude.map (second (/pssum)) ps
+  , bpUnnormalized = ps
+  , bpTotal        = pssum
+  }
+  where pssum = Numeric.Log.sum $ Prelude.map snd ps
+
diff --git a/BioInf/MutationOrder/RNA.hs b/BioInf/MutationOrder/RNA.hs
new file mode 100644
--- /dev/null
+++ b/BioInf/MutationOrder/RNA.hs
@@ -0,0 +1,282 @@
+
+-- | Here we collect the necessary data structures for the RNAs to be
+-- compared. This data is serialized to disk once calculated, since it is
+-- most likely the part that takes longest.
+--
+-- TODO if the vienna wrapper allows, we should parallelize the
+-- calculations.
+--
+-- TODO nice interface counting up?
+
+module BioInf.MutationOrder.RNA where
+
+import           Data.Aeson as DA
+import           Data.Bits
+import           Codec.Compression.GZip (compress,decompress)
+import           Control.Arrow (second)
+import           Control.DeepSeq
+import           Control.Parallel.Strategies
+import           Data.ByteString (ByteString)
+import           Data.Maybe (catMaybes)
+import           Data.Serialize
+import           Data.Vector.Serialize
+import           Data.Vector.Strategies
+import           Debug.Trace
+import           GHC.Generics
+import qualified Data.ByteString.Char8 as BS
+import qualified Data.ByteString.Lazy as BSL
+import qualified Data.Vector as V
+import qualified Data.Vector.Unboxed as VU
+import           System.IO.Unsafe (unsafePerformIO)
+import qualified Data.HashMap.Strict as HM
+import           Data.Serialize.Instances
+import           Data.Text.Encoding (decodeUtf8, encodeUtf8)
+import           Data.Monoid
+import           Data.Char (isDigit)
+import           Data.Tuple (swap)
+
+import qualified Data.Bijection.HashMap as B
+import           BioInf.ViennaRNA.Bindings
+import qualified Data.PrimitiveArray as PA
+import           Biobase.Secondary.Diagrams (D1Secondary(..), mkD1S)
+
+
+
+-- | A single RNA with pre-calculated elements.
+--
+-- All calculations are done at 37 C.
+--
+-- TODO include the basepair probability matrix? Can we "compress" that
+-- one?
+--
+-- We do not encode D1S into the json
+
+data RNA = RNA
+  { mutationSet       :: !(VU.Vector (Int,Char))
+    -- ^ we store just the mutation set, since this is more sparse and
+    -- gives access to the mutational events.
+  , primarySequence   :: !ByteString
+    -- ^ store RNA sequence too, for now
+  , mfeStructure      :: !ByteString
+    -- ^ the mfe structure we get
+  , mfeD1S            :: !D1Secondary
+    -- ^ efficient structure encoding
+  , mfeEnergy         :: !Double
+    -- ^ mfe energy of the structure
+  , centroidStructure :: !ByteString
+    -- ^ the centroid structure
+  , centroidD1S       :: !D1Secondary
+    -- ^ efficient centroid structure encoding
+  , centroidEnergy    :: !Double
+  }
+  deriving (Show,Eq,Generic)
+
+instance NFData     RNA
+instance Serialize  RNA
+
+instance ToJSON RNA where
+  toJSON RNA{..} =
+    object [ "mutationSet"        .= mutationSet
+           , "primarySequence"    .= decodeUtf8 primarySequence
+           , "mfeStructure"       .= decodeUtf8 mfeStructure
+           , "mfeEnergy"          .= mfeEnergy
+           , "centroidStructure"  .= decodeUtf8 centroidStructure
+           , "centroidEnergy"     .= centroidEnergy
+           ]
+  toEncoding RNA{..} =
+    pairs (  "mutationSet"        .= mutationSet
+          <> "primarySequence"    .= decodeUtf8 primarySequence
+          <> "mfeStructure"       .= decodeUtf8 mfeStructure
+          <> "mfeEnergy"          .= mfeEnergy
+          <> "centroidStructure"  .= decodeUtf8 centroidStructure
+          <> "centroidEnergy"     .= centroidEnergy
+          )
+
+instance FromJSON RNA where
+  parseJSON (Object v) = do
+    mutationSet <- v .: "mutationSet"
+    primarySequence <- encodeUtf8 <$> v .: "primarySequence"
+    let (e,s) = second BS.pack . unsafePerformIO . mfeTemp 37 $ BS.unpack primarySequence
+    mfeStructure <- (fmap encodeUtf8 <$> v .:? "mfeStructure") .!= s
+    mfeEnergy <- v .:? "mfeEnergy" .!= e
+    let (ce,cs) = second BS.pack . unsafePerformIO . centroidTemp 37 $ BS.unpack primarySequence
+    centroidStructure <- (fmap encodeUtf8 <$> v .:? "centroidStructure") .!= cs
+    centroidEnergy <- v .:? "centroidEnergy" .!= ce
+    let mfeD1S = bldD1S mfeStructure
+    let centroidD1S = bldD1S centroidStructure
+    return RNA{..}
+
+bldD1S :: ByteString -> D1Secondary
+bldD1S x = mkD1S (["()"::String], BS.unpack x)
+
+-- | Given the primary sequence and the mutation set, fill the 'RNA'
+-- structure.
+--
+-- NOTE This wraps some @ViennaRNA-bindings@ calls that are in @IO@.
+--
+-- TODO check if these calls are *really* thread-safe!
+
+mkRNA
+  :: Maybe (HM.HashMap ByteString QLine)
+  -> ByteString
+  -- ^ primary sequence of the *origin* RNA
+  -> VU.Vector (Int,Char)
+  -- ^ set of mutations compared to the origin
+  -> RNA
+mkRNA lkup inp' ms = RNA
+  { mutationSet       = ms
+  , primarySequence   = inp
+  , mfeStructure      = mS
+  , mfeEnergy         = mE
+  , centroidStructure = cS
+  , centroidEnergy    = cE
+  , mfeD1S            = bldD1S mS
+  , centroidD1S       = bldD1S cS
+  }
+  where
+    inp   = insertMutations ms inp'
+    ((mE,mS),(cE,cS)) = maybe calculateHere lookup lkup
+    calculateHere = ( second BS.pack . unsafePerformIO . mfeTemp 37 $ BS.unpack inp
+                    , second BS.pack . unsafePerformIO . centroidTemp 37 $ BS.unpack inp
+                    )
+    lookup lkup =
+      case HM.lookup inp lkup of
+        Nothing -> traceShow ("WARNING! have RNA lookup table but have to calculate!", inp) calculateHere
+        Just QLine{..} -> (swap qlmfe,swap qlcentroid)
+
+-- | Insert a set of mutations in a @ByteString@.
+
+insertMutations :: VU.Vector (Int,Char) -> ByteString -> ByteString
+insertMutations ms s' = VU.foldl' go s' ms
+  where go s (k,c) =
+          let (h,t) = BS.splitAt k s
+          in  BS.concat [h, BS.singleton c, BS.drop 1 t]
+
+data Landscape = Landscape
+  { rnas                  :: HM.HashMap (PA.BitSet PA.I) RNA
+    -- ^ the individual RNA mutations. The index should be calculated from
+    -- @linearIndex 0 high mutationSet@
+  , mutationCount         :: !Int
+    -- ^ how many nucleotides are mutated in total
+  , landscapeOrigin       :: !ByteString
+    -- ^ the ancestral sequence
+  , landscapeDestination  :: !ByteString
+    -- ^ the final sequence
+  , mutationPositions     :: !(B.BimapHashMap Int Int)
+  }
+  deriving (Show,Eq,Generic)
+
+instance NFData     Landscape
+instance Serialize  Landscape
+
+instance ToJSON Landscape where
+  toJSON Landscape{..} =
+    object [ "rnas"                 .= rnas
+           , "mutationCount"        .= mutationCount
+           , "landscapeOrigin"      .= decodeUtf8 landscapeOrigin
+           , "landscapeDestination" .= decodeUtf8 landscapeDestination
+           , "mutationPositions"    .= mutationPositions
+           ]
+  toEncoding Landscape{..} =
+    pairs (  "rnas"                 .= rnas
+          <> "mutationCount"        .= mutationCount
+          <> "landscapeOrigin"      .= decodeUtf8 landscapeOrigin
+          <> "landscapeDestination" .= decodeUtf8 landscapeDestination
+          <> "mutationPositions"    .= mutationPositions
+          )
+
+instance FromJSON Landscape where
+  parseJSON (Object v) = do
+    rnas                  <- v .: "rnas"
+    mutationCount         <- v .: "mutationCount"
+    landscapeOrigin       <- encodeUtf8 <$> v .: "landscapeOrigin"
+    landscapeDestination  <- encodeUtf8 <$> v .: "landscapeDestination"
+    mutationPositions     <- v .: "mutationPositions"
+    return Landscape{..}
+
+-- |
+--
+-- TODO prime candidate for parallelization. ViennaRNA-bindings currently
+-- does not allow parallel runs! It would be possible to consider
+-- externalizing this, but for now we just run single-threaded.
+
+createRNAlandscape :: Maybe (HM.HashMap ByteString QLine) -> Bool -> ByteString -> ByteString -> (Landscape, [(Int,ByteString)])
+createRNAlandscape lkup verbose origin mutation = (ls, zipWith (\mm k -> (k,insertMutations mm origin)) mus [0..])
+  where
+    ls = Landscape
+          { rnas                  = rs -- `using` (parVector chunkSize)
+          , mutationCount         = length . filter (>1) . map length $ pms
+          , landscapeOrigin       = origin
+          , landscapeDestination  = mutation
+          , mutationPositions     = mutbit
+          }
+    rs  = HM.fromList . map pairWithBitSet $ zipWith talk mus [0..]
+    talk s c = (if (c `mod` 1000 == 0 && verbose) then traceShow c else id) mkRNA lkup origin s
+    mus = map (VU.fromList . catMaybes)
+        . sequence
+        $ pms
+    -- possible mutations
+    pms = zipWith3 genM (BS.unpack origin) (BS.unpack mutation) [0..]
+    genM a b k | a==b = [Nothing]
+               | otherwise = [Nothing,Just (k,b)]
+    -- pair each @RNA@ with the correct bitset
+    pairWithBitSet r = (calcBitSet zeroBits . map fst . VU.toList $ mutationSet r, r)
+    -- calculate the bitset pattern for this mutation
+    calcBitSet bs [] = bs
+    calcBitSet bs (x':xs) =
+      let x = maybe (error $ "calcBitSet") id $ B.lookupL mutbit x'
+      in  calcBitSet (bs `setBit` x) xs
+    -- bijection between mutation position and bit position
+    -- @BitSet Bit   <->   Mutated Bit@
+    mutbit = B.fromList
+           . zipWith (flip (,)) [0 :: Int ..]
+           . catMaybes $ zipWith3 genB (BS.unpack origin) (BS.unpack mutation) [0 :: Int ..]
+    genB a b k | a == b    = Nothing
+               | otherwise = Just $ k
+
+-- | Write a generated landscape to disk.
+
+toFile :: FilePath -> Landscape -> IO ()
+toFile fp = BSL.writeFile fp . compress . encodeLazy
+
+toFileJSON :: FilePath -> Landscape -> IO ()
+toFileJSON fp = BSL.writeFile fp . compress . DA.encode
+
+fromFile :: FilePath -> IO Landscape
+fromFile fp = (decodeLazy . decompress) <$> BSL.readFile fp >>= \case
+  Left err -> error $ "BioInf.MutationOrder.RNA.fromFile: " ++ err
+  Right ls -> return ls
+
+fromFileJSON :: FilePath -> IO Landscape
+fromFileJSON fp = (DA.eitherDecode' . decompress) <$> BSL.readFile fp >>= \case
+  Left err -> error $ "BioInf.MutationOrder.RNA.fromFile: " ++ err
+  Right ls -> return ls
+
+
+-- stupid parsing for quintuple rnafold lines
+
+data QLine = QLine
+  { qlSequence  :: ByteString
+  , qlmfe       :: (ByteString,Double)
+  , qlensemble  :: (ByteString,Double)
+  , qlcentroid  :: (ByteString,Double)
+  }
+  deriving (Show)
+
+
+
+qlines f = do
+  ls <- BS.lines <$> BS.readFile f
+  return $ qlhm $ go ls
+  where go [] = []
+        go ls = let (hs,ts) = splitAt 5 ls
+                in  parseql hs : go ts
+        parseql [s,m,e,c,_] =
+              QLine s
+                    (stupid m)
+                    (stupid e)
+                    (stupid c)
+        stupid bs = let (h:ts) = BS.words bs
+                        r = BS.dropWhile (\c -> not $ isDigit c || c=='-') $ BS.unwords ts
+                    in (h, read $ BS.unpack $ BS.takeWhile (\c -> isDigit c || c =='-' || c=='.') r)
+        qlhm xs = HM.fromList $ map (\q -> (qlSequence q, q)) xs
diff --git a/LICENSE b/LICENSE
new file mode 100644
--- /dev/null
+++ b/LICENSE
@@ -0,0 +1,675 @@
+              GNU GENERAL PUBLIC LICENSE
+                Version 3, 29 June 2007
+
+ Copyright (C) 2007 Free Software Foundation, Inc. <http://fsf.org/>
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+                     Preamble
+
+  The GNU General Public License is a free, copyleft license for
+software and other kinds of works.
+
+  The licenses for most software and other practical works are designed
+to take away your freedom to share and change the works.  By contrast,
+the GNU General Public License is intended to guarantee your freedom to
+share and change all versions of a program--to make sure it remains free
+software for all its users.  We, the Free Software Foundation, use the
+GNU General Public License for most of our software; it applies also to
+any other work released this way by its authors.  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
+them 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 prevent others from denying you
+these rights or asking you to surrender the rights.  Therefore, you have
+certain responsibilities if you distribute copies of the software, or if
+you modify it: responsibilities to respect the freedom of others.
+
+  For example, if you distribute copies of such a program, whether
+gratis or for a fee, you must pass on to the recipients the same
+freedoms that you received.  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.
+
+  Developers that use the GNU GPL protect your rights with two steps:
+(1) assert copyright on the software, and (2) offer you this License
+giving you legal permission to copy, distribute and/or modify it.
+
+  For the developers' and authors' protection, the GPL clearly explains
+that there is no warranty for this free software.  For both users' and
+authors' sake, the GPL requires that modified versions be marked as
+changed, so that their problems will not be attributed erroneously to
+authors of previous versions.
+
+  Some devices are designed to deny users access to install or run
+modified versions of the software inside them, although the manufacturer
+can do so.  This is fundamentally incompatible with the aim of
+protecting users' freedom to change the software.  The systematic
+pattern of such abuse occurs in the area of products for individuals to
+use, which is precisely where it is most unacceptable.  Therefore, we
+have designed this version of the GPL to prohibit the practice for those
+products.  If such problems arise substantially in other domains, we
+stand ready to extend this provision to those domains in future versions
+of the GPL, as needed to protect the freedom of users.
+
+  Finally, every program is threatened constantly by software patents.
+States should not allow patents to restrict development and use of
+software on general-purpose computers, but in those that do, we wish to
+avoid the special danger that patents applied to a free program could
+make it effectively proprietary.  To prevent this, the GPL assures that
+patents cannot be used to render the program non-free.
+
+  The precise terms and conditions for copying, distribution and
+modification follow.
+
+                TERMS AND CONDITIONS
+
+  0. Definitions.
+
+  "This License" refers to version 3 of the GNU General Public License.
+
+  "Copyright" also means copyright-like laws that apply to other kinds of
+works, such as semiconductor masks.
+ 
+  "The Program" refers to any copyrightable work licensed under this
+License.  Each licensee is addressed as "you".  "Licensees" and
+"recipients" may be individuals or organizations.
+
+  To "modify" a work means to copy from or adapt all or part of the work
+in a fashion requiring copyright permission, other than the making of an
+exact copy.  The resulting work is called a "modified version" of the
+earlier work or a work "based on" the earlier work.
+
+  A "covered work" means either the unmodified Program or a work based
+on the Program.
+
+  To "propagate" a work means to do anything with it that, without
+permission, would make you directly or secondarily liable for
+infringement under applicable copyright law, except executing it on a
+computer or modifying a private copy.  Propagation includes copying,
+distribution (with or without modification), making available to the
+public, and in some countries other activities as well.
+
+  To "convey" a work means any kind of propagation that enables other
+parties to make or receive copies.  Mere interaction with a user through
+a computer network, with no transfer of a copy, is not conveying.
+
+  An interactive user interface displays "Appropriate Legal Notices"
+to the extent that it includes a convenient and prominently visible
+feature that (1) displays an appropriate copyright notice, and (2)
+tells the user that there is no warranty for the work (except to the
+extent that warranties are provided), that licensees may convey the
+work under this License, and how to view a copy of this License.  If
+the interface presents a list of user commands or options, such as a
+menu, a prominent item in the list meets this criterion.
+
+  1. Source Code.
+
+  The "source code" for a work means the preferred form of the work
+for making modifications to it.  "Object code" means any non-source
+form of a work.
+
+  A "Standard Interface" means an interface that either is an official
+standard defined by a recognized standards body, or, in the case of
+interfaces specified for a particular programming language, one that
+is widely used among developers working in that language.
+
+  The "System Libraries" of an executable work include anything, other
+than the work as a whole, that (a) is included in the normal form of
+packaging a Major Component, but which is not part of that Major
+Component, and (b) serves only to enable use of the work with that
+Major Component, or to implement a Standard Interface for which an
+implementation is available to the public in source code form.  A
+"Major Component", in this context, means a major essential component
+(kernel, window system, and so on) of the specific operating system
+(if any) on which the executable work runs, or a compiler used to
+produce the work, or an object code interpreter used to run it.
+
+  The "Corresponding Source" for a work in object code form means all
+the source code needed to generate, install, and (for an executable
+work) run the object code and to modify the work, including scripts to
+control those activities.  However, it does not include the work's
+System Libraries, or general-purpose tools or generally available free
+programs which are used unmodified in performing those activities but
+which are not part of the work.  For example, Corresponding Source
+includes interface definition files associated with source files for
+the work, and the source code for shared libraries and dynamically
+linked subprograms that the work is specifically designed to require,
+such as by intimate data communication or control flow between those
+subprograms and other parts of the work.
+
+  The Corresponding Source need not include anything that users
+can regenerate automatically from other parts of the Corresponding
+Source.
+
+  The Corresponding Source for a work in source code form is that
+same work.
+
+  2. Basic Permissions.
+
+  All rights granted under this License are granted for the term of
+copyright on the Program, and are irrevocable provided the stated
+conditions are met.  This License explicitly affirms your unlimited
+permission to run the unmodified Program.  The output from running a
+covered work is covered by this License only if the output, given its
+content, constitutes a covered work.  This License acknowledges your
+rights of fair use or other equivalent, as provided by copyright law.
+
+  You may make, run and propagate covered works that you do not
+convey, without conditions so long as your license otherwise remains
+in force.  You may convey covered works to others for the sole purpose
+of having them make modifications exclusively for you, or provide you
+with facilities for running those works, provided that you comply with
+the terms of this License in conveying all material for which you do
+not control copyright.  Those thus making or running the covered works
+for you must do so exclusively on your behalf, under your direction
+and control, on terms that prohibit them from making any copies of
+your copyrighted material outside their relationship with you.
+
+  Conveying under any other circumstances is permitted solely under
+the conditions stated below.  Sublicensing is not allowed; section 10
+makes it unnecessary.
+
+  3. Protecting Users' Legal Rights From Anti-Circumvention Law.
+
+  No covered work shall be deemed part of an effective technological
+measure under any applicable law fulfilling obligations under article
+11 of the WIPO copyright treaty adopted on 20 December 1996, or
+similar laws prohibiting or restricting circumvention of such
+measures.
+
+  When you convey a covered work, you waive any legal power to forbid
+circumvention of technological measures to the extent such circumvention
+is effected by exercising rights under this License with respect to
+the covered work, and you disclaim any intention to limit operation or
+modification of the work as a means of enforcing, against the work's
+users, your or third parties' legal rights to forbid circumvention of
+technological measures.
+
+  4. Conveying Verbatim Copies.
+
+  You may convey 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;
+keep intact all notices stating that this License and any
+non-permissive terms added in accord with section 7 apply to the code;
+keep intact all notices of the absence of any warranty; and give all
+recipients a copy of this License along with the Program.
+
+  You may charge any price or no price for each copy that you convey,
+and you may offer support or warranty protection for a fee.
+
+  5. Conveying Modified Source Versions.
+
+  You may convey a work based on the Program, or the modifications to
+produce it from the Program, in the form of source code under the
+terms of section 4, provided that you also meet all of these conditions:
+
+    a) The work must carry prominent notices stating that you modified
+    it, and giving a relevant date.
+
+    b) The work must carry prominent notices stating that it is
+    released under this License and any conditions added under section
+    7.  This requirement modifies the requirement in section 4 to
+    "keep intact all notices".
+
+    c) You must license the entire work, as a whole, under this
+    License to anyone who comes into possession of a copy.  This
+    License will therefore apply, along with any applicable section 7
+    additional terms, to the whole of the work, and all its parts,
+    regardless of how they are packaged.  This License gives no
+    permission to license the work in any other way, but it does not
+    invalidate such permission if you have separately received it.
+
+    d) If the work has interactive user interfaces, each must display
+    Appropriate Legal Notices; however, if the Program has interactive
+    interfaces that do not display Appropriate Legal Notices, your
+    work need not make them do so.
+
+  A compilation of a covered work with other separate and independent
+works, which are not by their nature extensions of the covered work,
+and which are not combined with it such as to form a larger program,
+in or on a volume of a storage or distribution medium, is called an
+"aggregate" if the compilation and its resulting copyright are not
+used to limit the access or legal rights of the compilation's users
+beyond what the individual works permit.  Inclusion of a covered work
+in an aggregate does not cause this License to apply to the other
+parts of the aggregate.
+
+  6. Conveying Non-Source Forms.
+
+  You may convey a covered work in object code form under the terms
+of sections 4 and 5, provided that you also convey the
+machine-readable Corresponding Source under the terms of this License,
+in one of these ways:
+
+    a) Convey the object code in, or embodied in, a physical product
+    (including a physical distribution medium), accompanied by the
+    Corresponding Source fixed on a durable physical medium
+    customarily used for software interchange.
+
+    b) Convey the object code in, or embodied in, a physical product
+    (including a physical distribution medium), accompanied by a
+    written offer, valid for at least three years and valid for as
+    long as you offer spare parts or customer support for that product
+    model, to give anyone who possesses the object code either (1) a
+    copy of the Corresponding Source for all the software in the
+    product that is covered by this License, on a durable physical
+    medium customarily used for software interchange, for a price no
+    more than your reasonable cost of physically performing this
+    conveying of source, or (2) access to copy the
+    Corresponding Source from a network server at no charge.
+
+    c) Convey individual copies of the object code with a copy of the
+    written offer to provide the Corresponding Source.  This
+    alternative is allowed only occasionally and noncommercially, and
+    only if you received the object code with such an offer, in accord
+    with subsection 6b.
+
+    d) Convey the object code by offering access from a designated
+    place (gratis or for a charge), and offer equivalent access to the
+    Corresponding Source in the same way through the same place at no
+    further charge.  You need not require recipients to copy the
+    Corresponding Source along with the object code.  If the place to
+    copy the object code is a network server, the Corresponding Source
+    may be on a different server (operated by you or a third party)
+    that supports equivalent copying facilities, provided you maintain
+    clear directions next to the object code saying where to find the
+    Corresponding Source.  Regardless of what server hosts the
+    Corresponding Source, you remain obligated to ensure that it is
+    available for as long as needed to satisfy these requirements.
+
+    e) Convey the object code using peer-to-peer transmission, provided
+    you inform other peers where the object code and Corresponding
+    Source of the work are being offered to the general public at no
+    charge under subsection 6d.
+
+  A separable portion of the object code, whose source code is excluded
+from the Corresponding Source as a System Library, need not be
+included in conveying the object code work.
+
+  A "User Product" is either (1) a "consumer product", which means any
+tangible personal property which is normally used for personal, family,
+or household purposes, or (2) anything designed or sold for incorporation
+into a dwelling.  In determining whether a product is a consumer product,
+doubtful cases shall be resolved in favor of coverage.  For a particular
+product received by a particular user, "normally used" refers to a
+typical or common use of that class of product, regardless of the status
+of the particular user or of the way in which the particular user
+actually uses, or expects or is expected to use, the product.  A product
+is a consumer product regardless of whether the product has substantial
+commercial, industrial or non-consumer uses, unless such uses represent
+the only significant mode of use of the product.
+
+  "Installation Information" for a User Product means any methods,
+procedures, authorization keys, or other information required to install
+and execute modified versions of a covered work in that User Product from
+a modified version of its Corresponding Source.  The information must
+suffice to ensure that the continued functioning of the modified object
+code is in no case prevented or interfered with solely because
+modification has been made.
+
+  If you convey an object code work under this section in, or with, or
+specifically for use in, a User Product, and the conveying occurs as
+part of a transaction in which the right of possession and use of the
+User Product is transferred to the recipient in perpetuity or for a
+fixed term (regardless of how the transaction is characterized), the
+Corresponding Source conveyed under this section must be accompanied
+by the Installation Information.  But this requirement does not apply
+if neither you nor any third party retains the ability to install
+modified object code on the User Product (for example, the work has
+been installed in ROM).
+
+  The requirement to provide Installation Information does not include a
+requirement to continue to provide support service, warranty, or updates
+for a work that has been modified or installed by the recipient, or for
+the User Product in which it has been modified or installed.  Access to a
+network may be denied when the modification itself materially and
+adversely affects the operation of the network or violates the rules and
+protocols for communication across the network.
+
+  Corresponding Source conveyed, and Installation Information provided,
+in accord with this section must be in a format that is publicly
+documented (and with an implementation available to the public in
+source code form), and must require no special password or key for
+unpacking, reading or copying.
+
+  7. Additional Terms.
+
+  "Additional permissions" are terms that supplement the terms of this
+License by making exceptions from one or more of its conditions.
+Additional permissions that are applicable to the entire Program shall
+be treated as though they were included in this License, to the extent
+that they are valid under applicable law.  If additional permissions
+apply only to part of the Program, that part may be used separately
+under those permissions, but the entire Program remains governed by
+this License without regard to the additional permissions.
+
+  When you convey a copy of a covered work, you may at your option
+remove any additional permissions from that copy, or from any part of
+it.  (Additional permissions may be written to require their own
+removal in certain cases when you modify the work.)  You may place
+additional permissions on material, added by you to a covered work,
+for which you have or can give appropriate copyright permission.
+
+  Notwithstanding any other provision of this License, for material you
+add to a covered work, you may (if authorized by the copyright holders of
+that material) supplement the terms of this License with terms:
+
+    a) Disclaiming warranty or limiting liability differently from the
+    terms of sections 15 and 16 of this License; or
+
+    b) Requiring preservation of specified reasonable legal notices or
+    author attributions in that material or in the Appropriate Legal
+    Notices displayed by works containing it; or
+
+    c) Prohibiting misrepresentation of the origin of that material, or
+    requiring that modified versions of such material be marked in
+    reasonable ways as different from the original version; or
+
+    d) Limiting the use for publicity purposes of names of licensors or
+    authors of the material; or
+
+    e) Declining to grant rights under trademark law for use of some
+    trade names, trademarks, or service marks; or
+
+    f) Requiring indemnification of licensors and authors of that
+    material by anyone who conveys the material (or modified versions of
+    it) with contractual assumptions of liability to the recipient, for
+    any liability that these contractual assumptions directly impose on
+    those licensors and authors.
+
+  All other non-permissive additional terms are considered "further
+restrictions" within the meaning of section 10.  If the Program as you
+received it, or any part of it, contains a notice stating that it is
+governed by this License along with a term that is a further
+restriction, you may remove that term.  If a license document contains
+a further restriction but permits relicensing or conveying under this
+License, you may add to a covered work material governed by the terms
+of that license document, provided that the further restriction does
+not survive such relicensing or conveying.
+
+  If you add terms to a covered work in accord with this section, you
+must place, in the relevant source files, a statement of the
+additional terms that apply to those files, or a notice indicating
+where to find the applicable terms.
+
+  Additional terms, permissive or non-permissive, may be stated in the
+form of a separately written license, or stated as exceptions;
+the above requirements apply either way.
+
+  8. Termination.
+
+  You may not propagate or modify a covered work except as expressly
+provided under this License.  Any attempt otherwise to propagate or
+modify it is void, and will automatically terminate your rights under
+this License (including any patent licenses granted under the third
+paragraph of section 11).
+
+  However, if you cease all violation of this License, then your
+license from a particular copyright holder is reinstated (a)
+provisionally, unless and until the copyright holder explicitly and
+finally terminates your license, and (b) permanently, if the copyright
+holder fails to notify you of the violation by some reasonable means
+prior to 60 days after the cessation.
+
+  Moreover, your license from a particular copyright holder is
+reinstated permanently if the copyright holder notifies you of the
+violation by some reasonable means, this is the first time you have
+received notice of violation of this License (for any work) from that
+copyright holder, and you cure the violation prior to 30 days after
+your receipt of the notice.
+
+  Termination of your rights under this section does not terminate the
+licenses of parties who have received copies or rights from you under
+this License.  If your rights have been terminated and not permanently
+reinstated, you do not qualify to receive new licenses for the same
+material under section 10.
+
+  9. Acceptance Not Required for Having Copies.
+
+  You are not required to accept this License in order to receive or
+run a copy of the Program.  Ancillary propagation of a covered work
+occurring solely as a consequence of using peer-to-peer transmission
+to receive a copy likewise does not require acceptance.  However,
+nothing other than this License grants you permission to propagate or
+modify any covered work.  These actions infringe copyright if you do
+not accept this License.  Therefore, by modifying or propagating a
+covered work, you indicate your acceptance of this License to do so.
+
+  10. Automatic Licensing of Downstream Recipients.
+
+  Each time you convey a covered work, the recipient automatically
+receives a license from the original licensors, to run, modify and
+propagate that work, subject to this License.  You are not responsible
+for enforcing compliance by third parties with this License.
+
+  An "entity transaction" is a transaction transferring control of an
+organization, or substantially all assets of one, or subdividing an
+organization, or merging organizations.  If propagation of a covered
+work results from an entity transaction, each party to that
+transaction who receives a copy of the work also receives whatever
+licenses to the work the party's predecessor in interest had or could
+give under the previous paragraph, plus a right to possession of the
+Corresponding Source of the work from the predecessor in interest, if
+the predecessor has it or can get it with reasonable efforts.
+
+  You may not impose any further restrictions on the exercise of the
+rights granted or affirmed under this License.  For example, you may
+not impose a license fee, royalty, or other charge for exercise of
+rights granted under this License, and you may not initiate litigation
+(including a cross-claim or counterclaim in a lawsuit) alleging that
+any patent claim is infringed by making, using, selling, offering for
+sale, or importing the Program or any portion of it.
+
+  11. Patents.
+
+  A "contributor" is a copyright holder who authorizes use under this
+License of the Program or a work on which the Program is based.  The
+work thus licensed is called the contributor's "contributor version".
+
+  A contributor's "essential patent claims" are all patent claims
+owned or controlled by the contributor, whether already acquired or
+hereafter acquired, that would be infringed by some manner, permitted
+by this License, of making, using, or selling its contributor version,
+but do not include claims that would be infringed only as a
+consequence of further modification of the contributor version.  For
+purposes of this definition, "control" includes the right to grant
+patent sublicenses in a manner consistent with the requirements of
+this License.
+
+  Each contributor grants you a non-exclusive, worldwide, royalty-free
+patent license under the contributor's essential patent claims, to
+make, use, sell, offer for sale, import and otherwise run, modify and
+propagate the contents of its contributor version.
+
+  In the following three paragraphs, a "patent license" is any express
+agreement or commitment, however denominated, not to enforce a patent
+(such as an express permission to practice a patent or covenant not to
+sue for patent infringement).  To "grant" such a patent license to a
+party means to make such an agreement or commitment not to enforce a
+patent against the party.
+
+  If you convey a covered work, knowingly relying on a patent license,
+and the Corresponding Source of the work is not available for anyone
+to copy, free of charge and under the terms of this License, through a
+publicly available network server or other readily accessible means,
+then you must either (1) cause the Corresponding Source to be so
+available, or (2) arrange to deprive yourself of the benefit of the
+patent license for this particular work, or (3) arrange, in a manner
+consistent with the requirements of this License, to extend the patent
+license to downstream recipients.  "Knowingly relying" means you have
+actual knowledge that, but for the patent license, your conveying the
+covered work in a country, or your recipient's use of the covered work
+in a country, would infringe one or more identifiable patents in that
+country that you have reason to believe are valid.
+  
+  If, pursuant to or in connection with a single transaction or
+arrangement, you convey, or propagate by procuring conveyance of, a
+covered work, and grant a patent license to some of the parties
+receiving the covered work authorizing them to use, propagate, modify
+or convey a specific copy of the covered work, then the patent license
+you grant is automatically extended to all recipients of the covered
+work and works based on it.
+
+  A patent license is "discriminatory" if it does not include within
+the scope of its coverage, prohibits the exercise of, or is
+conditioned on the non-exercise of one or more of the rights that are
+specifically granted under this License.  You may not convey a covered
+work if you are a party to an arrangement with a third party that is
+in the business of distributing software, under which you make payment
+to the third party based on the extent of your activity of conveying
+the work, and under which the third party grants, to any of the
+parties who would receive the covered work from you, a discriminatory
+patent license (a) in connection with copies of the covered work
+conveyed by you (or copies made from those copies), or (b) primarily
+for and in connection with specific products or compilations that
+contain the covered work, unless you entered into that arrangement,
+or that patent license was granted, prior to 28 March 2007.
+
+  Nothing in this License shall be construed as excluding or limiting
+any implied license or other defenses to infringement that may
+otherwise be available to you under applicable patent law.
+
+  12. No Surrender of Others' Freedom.
+
+  If 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 convey a
+covered work so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you may
+not convey it at all.  For example, if you agree to terms that obligate you
+to collect a royalty for further conveying from those to whom you convey
+the Program, the only way you could satisfy both those terms and this
+License would be to refrain entirely from conveying the Program.
+
+  13. Use with the GNU Affero General Public License.
+
+  Notwithstanding any other provision of this License, you have
+permission to link or combine any covered work with a work licensed
+under version 3 of the GNU Affero General Public License into a single
+combined work, and to convey the resulting work.  The terms of this
+License will continue to apply to the part which is the covered work,
+but the special requirements of the GNU Affero General Public License,
+section 13, concerning interaction through a network will apply to the
+combination as such.
+
+  14. Revised Versions of this License.
+
+  The Free Software Foundation may publish revised and/or new versions of
+the GNU 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 that a certain numbered version of the GNU General
+Public License "or any later version" applies to it, you have the
+option of following the terms and conditions either of that numbered
+version or of any later version published by the Free Software
+Foundation.  If the Program does not specify a version number of the
+GNU General Public License, you may choose any version ever published
+by the Free Software Foundation.
+
+  If the Program specifies that a proxy can decide which future
+versions of the GNU General Public License can be used, that proxy's
+public statement of acceptance of a version permanently authorizes you
+to choose that version for the Program.
+
+  Later license versions may give you additional or different
+permissions.  However, no additional obligations are imposed on any
+author or copyright holder as a result of your choosing to follow a
+later version.
+
+  15. Disclaimer of Warranty.
+
+  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.
+
+  16. Limitation of Liability.
+
+  IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
+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.
+
+  17. Interpretation of Sections 15 and 16.
+
+  If the disclaimer of warranty and limitation of liability provided
+above cannot be given local legal effect according to their terms,
+reviewing courts shall apply local law that most closely approximates
+an absolute waiver of all civil liability in connection with the
+Program, unless a warranty or assumption of liability accompanies a
+copy of the Program in return for a fee.
+
+              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
+state the exclusion of warranty; and each file should have at least
+the "copyright" line and a pointer to where the full notice is found.
+
+    <one line to give the program's name and a brief idea of what it does.>
+    Copyright (C) <year>  <name of author>
+
+    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 3 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, see <http://www.gnu.org/licenses/>.
+
+Also add information on how to contact you by electronic and paper mail.
+
+  If the program does terminal interaction, make it output a short
+notice like this when it starts in an interactive mode:
+
+    <program>  Copyright (C) <year>  <name of author>
+    This program 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, your program's commands
+might be different; for a GUI interface, you would use an "about box".
+
+  You should also get your employer (if you work as a programmer) or school,
+if any, to sign a "copyright disclaimer" for the program, if necessary.
+For more information on this, and how to apply and follow the GNU GPL, see
+<http://www.gnu.org/licenses/>.
+
+  The GNU 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 Lesser General
+Public License instead of this License.  But first, please read
+<http://www.gnu.org/philosophy/why-not-lgpl.html>.
+
diff --git a/MutationOrder.cabal b/MutationOrder.cabal
new file mode 100644
--- /dev/null
+++ b/MutationOrder.cabal
@@ -0,0 +1,166 @@
+name:           MutationOrder
+version:        0.0.0.1
+author:         Maria Beatriz Walter Costa, Christian Hoener zu Siederdissen, 2017
+copyright:      Christian Hoener zu Siederdissen, 2017
+homepage:       https://github.com/choener/MutationOrder
+bug-reports:    https://github.com/choener/MutationOrder/issues
+maintainer:     choener@bioinf.uni-leipzig.de
+category:       Bioinformatics
+license:        GPL-3
+license-file:   LICENSE
+build-type:     Simple
+stability:      experimental
+cabal-version:  >= 1.10.0
+tested-with:    GHC == 7.10.3, GHC == 8.0.1
+synopsis:       Most likely order of mutation events in RNA
+description:
+                Determine the most likely order in which single nucleotide
+                mutations happened between two RNA sequences.
+                .
+                Developed to analyse the @HAR 1@ region.
+                .
+                As long as the two input RNAs are small enough enough (couple
+                hundred nucleotides) and the number of mutations is small
+                enough (around 20-26, since the algorithm is exponential in
+                this number) the algorithm should work for similar problems
+                without changes.
+
+
+
+Extra-Source-Files:
+  README.md
+  changelog.md
+
+
+
+flag debug
+  description:  Enable bounds checking and various other debug operations at the cost of a significant performance penalty.
+  default:      False
+  manual:       True
+
+flag debugoutput
+  description:  Enable debug output, which spams the screen full of index information
+  default:      False
+  manual:       True
+
+
+
+library
+  build-depends: base                   >= 4.7    &&  < 5.0
+               , aeson                  >= 1.1
+               , bytestring
+               , cereal                 >= 0.5
+               , cereal-vector          >= 0.2
+               , containers
+               , deepseq                >= 1.4
+               , directory
+               , filepath
+               , log-domain             >= 0.10
+               , parallel               >= 3.2
+               , serialize-instances    >= 0.1
+               , text                   >= 1.0
+               , unordered-containers   >= 0.2.7
+               , vector                 >= 0.11
+               , vector-strategies      >= 0.4
+               , zlib                   >= 0.6
+               --
+               , ADPfusion              == 0.5.2.*
+               , ADPfusionSet           == 0.0.0.*
+               , bimaps                 == 0.1.0.*
+               , BiobaseXNA             == 0.9.3.*
+               , DPutils                == 0.0.1.*
+               , FormalGrammars         == 0.3.1.*
+               , PrimitiveArray         == 0.8.0.*
+               , PrimitiveArray-Pretty  == 0.0.0.*
+               , ShortestPathProblems   == 0.0.0.*
+               , ViennaRNA-bindings     == 0.233.1.*
+  exposed-modules:
+    BioInf.MutationOrder
+    BioInf.MutationOrder.EdgeProb
+    BioInf.MutationOrder.MinDist
+    BioInf.MutationOrder.RNA
+  default-extensions: BangPatterns
+                    , CPP
+                    , DeriveDataTypeable
+                    , DeriveGeneric
+                    , FlexibleContexts
+                    , GADTs
+                    , LambdaCase
+                    , MultiParamTypeClasses
+                    , OverloadedStrings
+                    , QuasiQuotes
+                    , RecordWildCards
+                    , ScopedTypeVariables
+                    , TemplateHaskell
+                    , TupleSections
+                    , TypeFamilies
+                    , TypeOperators
+  default-language:
+    Haskell2010
+  ghc-options:
+    -O2 -funbox-strict-fields
+  if flag(debug)
+    cpp-options: -DADPFUSION_CHECKS
+    ghc-options: -fno-ignore-asserts -O0
+  if flag(debugoutput)
+    cpp-options: -DADPFUSION_DEBUGOUTPUT
+
+
+
+executable MutationOrder
+  build-depends: base
+               , bytestring
+               , cmdargs      >= 0.10
+               , filepath
+               --
+               , MutationOrder
+  hs-source-dirs:
+    src
+  default-extensions: BangPatterns
+                    , DeriveDataTypeable
+                    , RecordWildCards
+  main-is:
+    MutationOrder.hs
+  default-language:
+    Haskell2010
+  ghc-options:
+    -O2 -rtsopts
+--    -threaded
+
+
+
+test-suite properties
+  type:
+    exitcode-stdio-1.0
+  main-is:
+    properties.hs
+  ghc-options:
+    -threaded -rtsopts -with-rtsopts=-N
+  hs-source-dirs:
+    tests
+  default-language:
+    Haskell2010
+  default-extensions: BangPatterns
+                    , CPP
+                    , FlexibleContexts
+                    , FlexibleInstances
+                    , MultiParamTypeClasses
+                    , ScopedTypeVariables
+                    , TemplateHaskell
+                    , TypeFamilies
+                    , TypeOperators
+                    , TypeSynonymInstances
+  build-depends: base
+               , QuickCheck
+               , tasty                        >= 0.11
+               , tasty-quickcheck             >= 0.8
+               , tasty-th                     >= 0.1
+               , vector
+               --
+               , MutationOrder
+
+
+source-repository head
+  type: git
+  location: git://github.com/choener/MutationOrder
+
diff --git a/README.md b/README.md
new file mode 100644
--- /dev/null
+++ b/README.md
@@ -0,0 +1,48 @@
+[![Build Status](https://travis-ci.org/choener/MutationOrder.svg?branch=master)](https://travis-ci.org/choener/MutationOrder)
+
+Determine the most likely order of mutations from one RNA sequence to another.
+
+1.  Walter Costa, Maria Beatriz and Hoener zu Siederdissen, Christian and Tulpan, Dan and Stadler, Peter F. and Nowick, Katja  
+    *Uncovering the Structural Evolution of the Human Accelerated Region 1*  
+    2017, submitted  
+    [preprint](http://www.bioinf.uni-leipzig.de/~choener/pdfs/wal-hoe-2017.pdf)  
+
+# Usage instructions
+
+We assume that you have two Fasta files, *from.fa* and *to.fa* but they can be
+named however is convenient (say *chimp.fa* and *human.fa*).  Each file has to
+contain exactly one sequence and both sequences have to be of the same length.
+
+We then run
+
+```./MutationOrder --workdb from-to.json.gz --scoretype pairdistcen --onlypositive --outputprefix test```
+
+This will generate ```test.run```, ```test-edge.eps```, and
+```test-meaorder.eps```. The ```test.run``` file provides extensive output of
+the optimal path, the first-last probabilities, the edge probabilities, and the
+mea output. The two ```eps``` files give a graphical representation of the edge
+probabilities, for the ```meaorder``` in order of the path of maximum expected
+accuracy.
+
+The ```--scoretype``` allows for ```mfe```, ```centroid```, ```pairdistcen```,
+and ```pairdistmfe```, which analyse possible evoluationary paths according to
+mfe energy, centroid energy, smallest base pair distances for each step in the
+```cen```troid or ```mfe``` case.
+
+
+
+# Installation
+
+Follow [this
+link](http://www.bioinf.uni-leipzig.de/~choener/software/MutationOrder.html) to
+the bottom of the page. Binaries are available for download and installation
+from sources via *Haskell Stack* are described.
+
+
+#### Contact
+
+Christian Hoener zu Siederdissen  
+Leipzig University, Leipzig, Germany  
+choener@bioinf.uni-leipzig.de  
+http://www.bioinf.uni-leipzig.de/~choener/  
+
diff --git a/Setup.hs b/Setup.hs
new file mode 100644
--- /dev/null
+++ b/Setup.hs
@@ -0,0 +1,2 @@
+import Distribution.Simple
+main = defaultMain
diff --git a/changelog.md b/changelog.md
new file mode 100644
--- /dev/null
+++ b/changelog.md
@@ -0,0 +1,6 @@
+0.0.0.1
+-------
+
+- initial checkin
+- travis-ci integration
+
diff --git a/src/MutationOrder.hs b/src/MutationOrder.hs
new file mode 100644
--- /dev/null
+++ b/src/MutationOrder.hs
@@ -0,0 +1,100 @@
+
+{-# Options_GHC -fno-cse #-}
+
+module Main where
+
+import System.Console.CmdArgs
+import System.FilePath
+import qualified Data.ByteString.Char8 as BS
+import Control.Monad
+
+import BioInf.MutationOrder
+import BioInf.MutationOrder.RNA (createRNAlandscape)
+
+data ScoreType
+  = Mfe
+  | Centroid
+  | PairDistMfe
+  | PairDistCen
+  deriving (Show,Data,Typeable)
+
+data Options
+  = Options
+    { infiles       :: [FilePath]
+    , workdb        :: FilePath
+    , temperature   :: Double
+    , fillweight    :: FillWeight
+    , fillstyle     :: FillStyle
+    , cooptcount    :: Int
+    , cooptprint    :: Int
+    , outprefix     :: FilePath
+    , scoretype     :: ScoreType
+    , positivesquared :: Bool
+    , onlypositive  :: Bool
+    , equalStart    :: Bool
+    , posscaled :: Maybe (Double,Double)
+    , lkupfile :: Maybe FilePath
+    }
+  | GenSequences
+    { infiles :: [FilePath]
+    }
+  deriving (Show,Data,Typeable)
+
+oOptions = Options
+  { infiles       = def &= args
+  , workdb        = "work.db" &= help "name of the database to store intermediates in"
+  , temperature   = 1.0  &= help "lower temperatures favor the more optimal paths, defaults to 1.0"
+  , fillweight    = FWlog
+  , fillstyle     = FSfull
+  , cooptcount    = 100000
+  , cooptprint    = 2
+  , outprefix     = "tmp"
+  , scoretype     = Centroid &= help "choose 'mfe', 'centroid', 'pairdistmfe', or 'pairdistcen' for the evaluation of each mutational step"
+  , positivesquared = False &= help "square positive energies to penalize worse structures"
+  , onlypositive  = False &= help "minimize only over penalties, not energy gains"
+  , equalStart    = False
+  , posscaled     = Nothing
+  , lkupfile = Nothing
+  }
+
+oGenSequences = GenSequences
+  { infiles = def &= args
+  }
+
+main :: IO ()
+main = do
+  o <- cmdArgs $ modes [oOptions, oGenSequences] &= verbosity
+  case o of
+    Options{} -> mainProgram o
+    GenSequences{} -> genSequences o
+
+genSequences o = do
+  let GenSequences{..} = o
+  ancestral <- stupidReader $ infiles !! 0
+  current   <- stupidReader $ infiles !! 1
+  let ls = snd $ createRNAlandscape Nothing False ancestral current
+  forM_ ls $ \(k,sq) -> BS.putStrLn sq
+  return ()
+
+mainProgram oOptions = do
+  let Options{..} = oOptions
+  isL <- isLoud
+  let fwdScaleFunction
+        = (if positivesquared then squaredPositive else id)
+        . (maybe id (uncurry posScaled) posscaled)
+        . (if onlypositive then (scaleByFunction (max 0)) else id)
+        $ (case scoretype of Mfe -> mfeDelta
+                             Centroid -> centroidDelta
+                             PairDistMfe -> basepairDistanceMFE
+                             PairDistCen -> basepairDistanceCentroid)
+  let insideScaleFunction
+        = scaleTemperature temperature
+        . (if positivesquared then squaredPositive else id)
+        . (maybe id (uncurry posScaled) posscaled)
+        . (if onlypositive then (scaleByFunction (max 0)) else id)
+        $ (case scoretype of Mfe -> mfeDelta
+                             Centroid -> centroidDelta
+                             PairDistMfe -> basepairDistanceMFE
+                             PairDistCen -> basepairDistanceCentroid)
+  runMutationOrder isL fillweight fillstyle fwdScaleFunction insideScaleFunction cooptcount cooptprint lkupfile outprefix workdb temperature equalStart infiles
+
diff --git a/tests/properties.hs b/tests/properties.hs
new file mode 100644
--- /dev/null
+++ b/tests/properties.hs
@@ -0,0 +1,14 @@
+
+module Main where
+
+import Test.Tasty
+import Test.Tasty.TH
+
+
+
+main :: IO ()
+main = do
+  defaultMain $ testGroup ""
+    [
+    ]
+