packages feed

BiobaseXNA 0.5.4.0 → 0.5.5.0

raw patch · 5 files changed

+504/−1 lines, 5 filesdep +containersdep +csvdep +file-embedPVP ok

version bump matches the API change (PVP)

Dependencies added: containers, csv, file-embed

API changes (from Hackage documentation)

+ Biobase.Secondary: baseP :: BaseSelect a b => a -> (b, b)
+ Biobase.Secondary: updL :: BaseSelect a b => b -> a -> a
+ Biobase.Secondary: updP :: BaseSelect a b => (b, b) -> a -> a
+ Biobase.Secondary: updR :: BaseSelect a b => b -> a -> a
+ Biobase.Secondary: updT :: BaseSelect a b => ExtPairAnnotation -> a -> a
+ Biobase.Secondary.Isostericity: class IsostericityLookup a
+ Biobase.Secondary.Isostericity: detailedCSV :: ByteString
+ Biobase.Secondary.Isostericity: getClasses :: IsostericityLookup a => a -> [String]
+ Biobase.Secondary.Isostericity: inClass :: IsostericityLookup a => String -> [a]
+ Biobase.Secondary.Isostericity: instance IsostericityLookup ExtPair
+ Biobase.Secondary.Isostericity: instance IsostericityLookup Pair

Files

Biobase/Secondary.hs view
@@ -225,25 +225,55 @@   baseL :: a -> b   -- | select second index or nucleotide   baseR :: a -> b+  -- | select both nucleotides as pair+  baseP :: a -> (b,b)   -- | select basepair type if existing or return default cWW   baseT :: a -> ExtPairAnnotation+  -- | update first index or nucleotide+  updL :: b -> a -> a+  -- | update second index or nucleotide+  updR :: b -> a -> a+  -- | update complete pair+  updP :: (b,b) -> a -> a+  -- | update basepair type, error if not possible due to type a+  updT :: ExtPairAnnotation -> a -> a  -- | extended pairtype annotation given  instance BaseSelect ((a,a),ExtPairAnnotation) a where   baseL ((a,_),_) = a   baseR ((_,b),_) = b+  baseP (lr   ,_) = lr   baseT (_,t) = t+  updL n ((_,y),t) = ((n,y),t)+  updR n ((x,_),t) = ((x,n),t)+  updP n (_,t)     = (n,t)+  updT n (xy,_) = (xy,n)   {-# INLINE baseL #-}   {-# INLINE baseR #-}+  {-# INLINE baseP #-}   {-# INLINE baseT #-}+  {-# INLINE updL #-}+  {-# INLINE updR #-}+  {-# INLINE updP #-}+  {-# INLINE updT #-}  -- | simple cis/wc-wc basepairs  instance BaseSelect (a,a) a where   baseL (a,_) = a   baseR (_,a) = a+  baseP = id   baseT _ = cWW+  updL n (_,y) = (n,y)+  updR n (x,_) = (x,n)+  updP n _     = n+  updT n xy = if n==cWW then xy else error $ "updT on standard pairs can not update to: " ++ show n   {-# INLINE baseL #-}   {-# INLINE baseR #-}+  {-# INLINE baseP #-}   {-# INLINE baseT #-}+  {-# INLINE updL #-}+  {-# INLINE updR #-}+  {-# INLINE updP #-}+  {-# INLINE updT #-}
+ Biobase/Secondary/Isostericity.hs view
@@ -0,0 +1,104 @@+{-# LANGUAGE PatternGuards #-}+{-# LANGUAGE FlexibleInstances #-}+{-# LANGUAGE TypeSynonymInstances #-}+{-# LANGUAGE TemplateHaskell #-}++-- | Provides detailed information on isostericity of RNA basepairs. All data+-- is extracted from csv files which were created from supplemental files in:+--+-- Frequency and isostericity of RNA base pairs+-- Jesse Stombaugh, Craig L. Zirbel, Eric Westhof, and Neocles B. Leontis+-- Nucl. Acids Res. (2009)+-- doi:10.1093/nar/gkp011++module Biobase.Secondary.Isostericity where++import Data.ByteString.Char8 (ByteString)+import Data.FileEmbed (embedFile)+import Data.List+import qualified Data.ByteString.Char8 as BS+import qualified Data.Map as M+import Text.CSV++import Biobase.Primary+import Biobase.Secondary++++-- | Methods to determine the isostericity classes for a given basepair type,+-- or alternatively which basepair types are in a certain isostericity class.+--+-- TODO This requires a major cleanup: right now we are handling 'String's as+-- class descriptors, but we should really be newtype-wrapping or create enum+-- data constructors.++class IsostericityLookup a where+  -- | To which classes does a basepair+type belong+  getClasses :: a -> [String] -- TODO this should return [Class]+  -- | What basepairs+type are in a particular class+  inClass :: String -> [a]++-- | For extended basepairs, we take the default mapping and go from there.+--+-- TODO inClass missing++instance IsostericityLookup ExtPair where+  getClasses p+    | Just cs <- M.lookup p defaultIsostericityMap+    = cs+    | otherwise = []+  inClass x = map fst . filter ((x `elem`).snd) $ M.assocs defaultIsostericityMap++-- | Normal basepairs are assumed to have cWW basepairing.+--+-- TODO inClass missing++instance IsostericityLookup Pair where+  getClasses p+    | Just cs <- M.lookup (p,cWW) defaultIsostericityMap+    = cs+    | otherwise = []+  inClass x = map (baseP.fst) -- remove extended information+            . filter ((cWW==).baseT.fst) -- keep only cWW pairs (baseT-ype)+            . filter ((x `elem`).snd) -- select based on class+            $ M.assocs defaultIsostericityMap++++-- ** default data++-- | The default isostericity mapping.++defaultIsostericityMap = mkIsostericityMap parsedCSV++-- | Mapping of (pair,pairtype) to isostericity class.++mkIsostericityMap = M.fromListWith (\x y -> nub $ x++y) . mkIsostericityList++-- | Process CSV list-of-lists to get the isostericity data.++mkIsostericityList gs = concatMap f gs where+  f g = map (\e ->  ( ( let [x,y] = fst e+                        in (mkNuc x, mkNuc y), threeChar bpt+                      )+                    , nub $ snd e)+            ) $ map entry xs where+    bpt = head $ head g+    xs = tail g+    entry x = (x!!0, takeWhile ((=='I') . head) $ drop 2 x)++-- | Simple parsing of raw CSV data.++parsedCSV = filter (not . null) gs where+  gs = map (filter ((""/=).head)) . groupBy (\x y -> ""/= (head y)) $ csv+  Right csv = parseCSV "isostericity/detailed" $ BS.unpack detailedCSV++++-- ** Raw embeddings++-- | Raw CSV data, embedded into the library.++detailedCSV :: ByteString+detailedCSV = $(embedFile "sources/isostericity-detailed.csv")+
BiobaseXNA.cabal view
@@ -1,5 +1,5 @@ name:           BiobaseXNA-version:        0.5.4.0+version:        0.5.5.0 author:         Christian Hoener zu Siederdissen maintainer:     choener@tbi.univie.ac.at homepage:       http://www.tbi.univie.ac.at/~choener/@@ -18,6 +18,26 @@                 folding tools. Extended RNA secondary structures can be                 represented as well.                 .+                Contains data from:+                .+                Frequency and isostericity of RNA base pairs+                .+                Jesse Stombaugh, Craig L. Zirbel, Eric Westhof, and Neocles B. Leontis+                .+                Nucl. Acids Res. (2009)+                .+                doi:10.1093/nar/gkp011+                .+                .+                .+                Changes since 0.5.4.0+                .+                * tuple-like updating (updL, updR, updP, updT)+                .+                * baseP pair selection+                .+                * isostericity data, loaded from csv files+                .                 Changes since 0.5.3.0                 .                 * tuple-like (selN) selection of basepairing elements (baseL,baseR,baseT)@@ -27,11 +47,16 @@                 * bonusTable for constrained folding  extra-source-files:+  sources/isostericity-matrices.csv+  sources/isostericity-detailed.csv  library   build-depends:     base >3 && <5,+    containers,     bytestring,+    csv,+    file-embed,     primitive,     text,     tuple,@@ -45,6 +70,7 @@     Biobase.Secondary     Biobase.Secondary.Constraint     Biobase.Secondary.Diagrams+    Biobase.Secondary.Isostericity     Biobase.Secondary.PseudoKnots     Biobase.Secondary.Vienna 
+ sources/isostericity-detailed.csv view
@@ -0,0 +1,173 @@+cWW,Family,LSW 2002 Isosteric Groups,Updated Isosteric Groups,Count,CC,UU,CA,UG,UA,AU,GC,CG,GU,AC,UU,CC,UC,CU,AA,GA,AG,AA+CC,cWw,I1.6,I1.6,8,0.00,2.37,4.49,5.06,5.30,5.39,5.56,5.49,6.25,5.91,4.31,3.02,8.25,7.97,9.77,8.86,8.82,9.05+UU,cwW,I1.6,I1.7,96,2.37,0.00,2.39,2.89,3.63,3.80,3.94,3.80,5.27,5.21,4.36,4.31,6.46,5.97,8.18,6.96,6.91,6.91+CA,cWW,I1.2,I1.2b,16,4.49,2.39,0.00,0.80,2.47,2.75,2.78,2.55,4.76,4.93,5.21,5.91,5.30,4.58,6.70,5.14,5.05,4.80+UG,cWW,I1.2,I1.2b,772,5.06,2.89,0.80,0.00,2.11,2.40,2.39,2.14,4.48,4.76,5.27,6.25,4.59,3.80,6.07,4.44,4.33,4.10+UA,cWW,I1.1,I1.1,2410,5.30,3.63,2.47,2.11,0.00,0.31,0.34,0.21,2.40,2.75,3.80,5.39,3.57,3.50,4.66,3.67,3.67,4.52+AU,cWW,I1.1,I1.1,2410,5.39,3.80,2.75,2.40,0.31,0.00,0.21,0.34,2.11,2.47,3.63,5.30,3.50,3.57,4.52,3.67,3.67,4.66+GC,cWW,I1.1,I1.1,7222,5.56,3.94,2.78,2.39,0.34,0.21,0.00,0.26,2.14,2.55,3.80,5.49,3.39,3.44,4.38,3.49,3.50,4.50+CG,cWW,I1.1,I1.1,7222,5.49,3.80,2.55,2.14,0.21,0.34,0.26,0.00,2.39,2.78,3.94,5.56,3.44,3.39,4.50,3.50,3.49,4.38+GU,cWW,i1.2,I1.2a,772,6.25,5.27,4.76,4.48,2.40,2.11,2.14,2.39,0.00,0.80,2.89,5.06,3.80,4.59,4.10,4.33,4.44,6.07+AC,cWW,i1.2,I1.2a,16,5.91,5.21,4.93,4.76,2.75,2.47,2.55,2.78,0.80,0.00,2.39,4.49,4.58,5.30,4.80,5.05,5.14,6.70+UU,cWw,I1.6,I1.7,96,4.31,4.36,5.21,5.27,3.80,3.63,3.80,3.94,2.89,2.39,0.00,2.37,5.97,6.46,6.91,6.91,6.96,8.18+CC,cwW,I1.6,I1.6,8,3.02,4.31,5.91,6.25,5.39,5.30,5.49,5.56,5.06,4.49,2.37,0.00,7.97,8.25,9.05,8.82,8.86,9.77+UC,cWW,I1.5,I1.5,12,8.25,6.46,5.30,4.59,3.57,3.50,3.39,3.44,3.80,4.58,5.97,7.97,0.00,1.53,2.71,2.25,2.33,3.77+CU,cWW,I1.5,I1.5,12,7.97,5.97,4.58,3.80,3.50,3.57,3.44,3.39,4.59,5.30,6.46,8.25,1.53,0.00,3.77,2.33,2.25,2.71+AA,cWw,I1.4,I1.4,3,9.77,8.18,6.70,6.07,4.66,4.52,4.38,4.50,4.10,4.80,6.91,9.05,2.71,3.77,0.00,2.18,2.41,4.52+GA,cWW,I1.3,I1.3,121,8.86,6.96,5.14,4.44,3.67,3.67,3.49,3.50,4.33,5.05,6.91,8.82,2.25,2.33,2.18,0.00,0.33,2.41+AG,cWW,I1.3,I1.3,121,8.82,6.91,5.05,4.33,3.67,3.67,3.50,3.49,4.44,5.14,6.96,8.86,2.33,2.25,2.41,0.33,0.00,2.18+AA,cwW,I1.4,I1.4,3,9.05,6.91,4.80,4.10,4.52,4.66,4.50,4.38,6.07,6.70,8.18,9.77,3.77,2.71,4.52,2.41,2.18,0.00+,,,,,,,,,,,,,,,,,,,,,,+tWW,Family,LSW 2002 Isosteric Groups,Updated Isosteric Groups,Count,AA,GG,AC,GU,AU,CU,UC,CC,UU,CA,UG,UA,CG,GC,,,,+AA,tWW,I2.4,I2.7,61,0.00,1.09,3.48,4.15,4.76,6.33,6.21,4.69,4.11,2.67,3.34,4.30,7.01,7.44,,,,+GG,tWW,I2.4,I2.7,6,1.09,0.00,2.47,3.14,3.71,5.40,5.42,4.00,3.41,2.58,3.24,3.77,6.54,6.49,,,,+AC,tWW,I2.3,I2.4,3,3.48,2.47,0.00,0.69,2.53,4.36,4.83,3.54,2.84,3.93,4.40,4.39,7.04,5.55,,,,+GU,tWW,I2.3,I2.4,2(C),4.15,3.14,0.69,0.00,2.46,4.15,4.75,3.59,2.93,4.40,4.82,4.66,7.21,5.40,,,,+AU,tWW,I2.1,I2.2,47,4.76,3.71,2.53,2.46,0.00,2.51,3.16,3.29,3.29,4.39,4.66,3.33,5.23,3.22,,,,+CU,tWW,I2.5,I2.8,3,6.33,5.40,4.36,4.15,2.51,0.00,1.13,2.65,3.30,4.83,4.75,3.16,4.53,3.84,,,,+UC,tWW,I2.5,I2.8,3,6.21,5.42,4.83,4.75,3.16,1.13,0.00,2.37,3.23,4.36,4.15,2.51,3.84,4.53,,,,+CC,tWW,I2.6,I2.9,5(C),4.69,4.00,3.54,3.59,3.29,2.65,2.37,0.00,0.98,2.74,2.58,2.57,5.37,5.92,,,,+UU,tWW,I2.6,I2.9,1,4.11,3.41,2.84,2.93,3.29,3.30,3.23,0.98,0.00,2.54,2.58,3.08,6.07,6.23,,,,+CA,tWW,I2.3,I2.3,3,2.67,2.58,3.93,4.40,4.39,4.83,4.36,2.74,2.54,0.00,0.69,2.53,5.55,7.04,,,,+UG,tWW,I2.3,I2.3,2(C),3.34,3.24,4.40,4.82,4.66,4.75,4.15,2.58,2.58,0.69,0.00,2.46,5.40,7.21,,,,+UA,tWW,I2.1,I2.1,47,4.30,3.77,4.39,4.66,3.33,3.16,2.51,2.57,3.08,2.53,2.46,0.00,3.22,5.23,,,,+CG,tWW,I2.2,I2.6,44,7.01,6.54,7.04,7.21,5.23,4.53,3.84,5.37,6.07,5.55,5.40,3.22,0.00,5.28,,,,+GC,tWW,I2.2,I2.5,44,7.44,6.49,5.55,5.40,3.22,3.84,4.53,5.92,6.23,7.04,7.21,5.23,5.28,0.00,,,,+,,,,,,,,,,,,,,,,,,,,,,+cWH,Family,LSW 2002 Isosteric Groups,Updated Isosteric Groups,Count,UG,UA,CG,CU,CC,UU,GG,AG,GA,AU,,,,,,,,+UG,cWH,I3.1,I3.1,4,0.00,1.69,2.07,3.70,4.64,4.94,7.25,5.12,6.58,7.87,,,,,,,,+UA,cWH,I3.1,I3.1,60,1.69,0.00,1.05,2.08,3.11,3.35,5.64,3.49,4.95,6.30,,,,,,,,+CG,cWH,I3.1,I3.1,7(C),2.07,1.05,0.00,2.21,2.69,3.06,5.41,3.74,5.14,6.62,,,,,,,,+CU,cWH,(I3.1) ,(I3.2),0(M),3.70,2.08,2.21,0.00,1.59,1.86,3.67,1.63,3.01,4.52,,,,,,,,+CC,cWH,I3.2,I3.2,8,4.64,3.11,2.69,1.59,0.00,0.85,2.76,2.22,3.13,4.76,,,,,,,,+UU,cWH,I3.2,I3.2,24,4.94,3.35,3.06,1.86,0.85,0.00,2.58,1.99,2.80,4.32,,,,,,,,+GG,cWH,I3.4,I3.4,107,7.25,5.64,5.41,3.67,2.76,2.58,0.00,2.85,2.22,3.42,,,,,,,,+AG,cWH,I3.3,I3.3,3,5.12,3.49,3.74,1.63,2.22,1.99,2.85,0.00,1.47,2.90,,,,,,,,+GA,cWH,I3.3,I3.3,5,6.58,4.95,5.14,3.01,3.13,2.80,2.22,1.47,0.00,1.67,,,,,,,,+AU,cWH,(I3.3) ,(I3.3),0(M),7.87,6.30,6.62,4.52,4.76,4.32,3.42,2.90,1.67,0.00,,,,,,,,+,,,,,,,,,,,,,,,,,,,,,,+tWH,Family,LSW 2002 Isosteric Groups,Updated Isosteric Groups,Count,AA,AG,GU,UU,CA,CG,CC,UA,GG,UG,,,,,,,,+AA,tWH,I4.4,I4.3,56,0.00,1.54,1.94,2.82,2.91,3.27,4.82,4.27,3.04,3.42,,,,,,,,+AG,tWH,I4.4,I4.2/4.3,11,1.54,0.00,1.25,1.69,1.77,2.08,3.97,3.78,3.11,4.00,,,,,,,,+GU,tWH,I4.4,I4.3,9(C),1.94,1.25,0.00,2.49,2.70,3.11,4.04,4.20,3.00,4.35,,,,,,,,+UU,tWH,I4.2,I4.2,10(C),2.82,1.69,2.49,0.00,0.39,1.02,2.68,2.44,2.83,3.72,,,,,,,,+CA,tWH,I4.2,I4.2,62,2.91,1.77,2.70,0.39,0.00,0.66,2.96,2.64,3.14,3.87,,,,,,,,+CG,tWH,I4.2,I4.2,4,3.27,2.08,3.11,1.02,0.66,0.00,3.42,3.11,3.78,4.38,,,,,,,,+CC,tWH,I4.1,I4.1,11(C),4.82,3.97,4.04,2.68,2.96,3.42,0.00,1.69,2.75,4.15,,,,,,,,+UA,tWH,I4.1,I4.1,341,4.27,3.78,4.20,2.44,2.64,3.11,1.69,0.00,2.26,2.82,,,,,,,,+GG,tWH,I4.5,I4.5,14,3.04,3.11,3.00,2.83,3.14,3.78,2.75,2.26,0.00,2.07,,,,,,,,+UG,tWH,I4.3,I4.4,1,3.42,4.00,4.35,3.72,3.87,4.38,4.15,2.82,2.07,0.00,,,,,,,,+,,,,,,,,,,,,,,,,,,,,,,+cWS,Family,LSW 2002 Isosteric Groups,Updated Isosteric Groups,Count,UG,UA,UC,UU,CU,CC,CG,CA,GG,AA,AC,AU,AG,GA,GC,GU,,+UG,cWS,I5.4,I5.4,7,0.00,1.60,3.01,3.22,4.04,3.91,3.98,3.88,6.23,6.92,6.63,6.18,7.32,6.75,6.17,7.75,,+UA,cWS,I5.4,I5.4,13(C),1.60,0.00,1.60,1.81,3.17,2.91,3.01,2.79,4.98,5.66,5.45,4.96,6.23,5.44,4.79,6.42,,+UC,cWS,(I5.4) ,I5.4,1(CM),3.01,1.60,0.00,0.26,3.49,3.27,3.35,3.01,4.49,5.07,5.09,4.59,6.00,4.45,3.51,5.01,,+UU,cWS,(I5.4) ,I5.4,2(CM),3.22,1.81,0.26,0.00,3.49,3.28,3.35,3.00,4.41,4.93,4.98,4.49,5.90,4.32,3.32,4.79,,+CU,cWS,I5.2,I5.2,2,4.04,3.17,3.49,3.49,0.00,0.87,0.81,1.00,3.30,3.40,2.94,2.63,3.49,4.76,4.40,5.97,,+CC,cWS,I5.2,I5.2,5,3.91,2.91,3.27,3.28,0.87,0.00,0.47,0.50,2.98,3.38,2.89,2.49,3.49,4.43,4.24,5.91,,+CG,cWS,I5.2,I5.2,9,3.98,3.01,3.35,3.35,0.81,0.47,0.00,0.41,3.22,3.34,2.87,2.57,3.46,4.65,4.36,5.98,,+CA,cWS,I5.2,I5.2,13,3.88,2.79,3.01,3.00,1.00,0.50,0.41,0.00,3.04,3.26,2.86,2.49,3.53,4.34,4.02,5.66,,+GG,cWS,I5.5,I5.5,6(C),6.23,4.98,4.49,4.41,3.30,2.98,3.22,3.04,0.00,2.09,1.95,1.38,2.66,2.11,2.85,4.26,,+AA,cWS,I5.1,I5.1,52,6.92,5.66,5.07,4.93,3.40,3.38,3.34,3.26,2.09,0.00,0.84,1.16,1.58,3.27,3.29,4.22,,+AC,cWS,I5.1,I5.1,43,6.63,5.45,5.09,4.98,2.94,2.89,2.87,2.86,1.95,0.84,0.00,0.70,1.00,3.59,3.78,4.91,,+AU,cWS,I5.1,I5.1,17,6.18,4.96,4.59,4.49,2.63,2.49,2.57,2.49,1.38,1.16,0.70,0.00,1.57,3.15,3.37,4.68,,+AG,cWS,I5.1,I5.1,3(C),7.32,6.23,6.00,5.90,3.49,3.49,3.46,3.53,2.66,1.58,1.00,1.57,0.00,4.39,4.71,5.74,,+GA,cWS,(I5.3) ,I5.3,2,6.75,5.44,4.45,4.32,4.76,4.43,4.65,4.34,2.11,3.27,3.59,3.15,4.39,0.00,1.68,2.76,,+GC,cWS,I5.3,I5.3,3,6.17,4.79,3.51,3.32,4.40,4.24,4.36,4.02,2.85,3.29,3.78,3.37,4.71,1.68,0.00,1.82,,+GU,cWS,I5.3,I5.3,5,7.75,6.42,5.01,4.79,5.97,5.91,5.98,5.66,4.26,4.22,4.91,4.68,5.74,2.76,1.82,0.00,,+,,,,,,,,,,,,,,,,,,,,,,+tWS,Family,LSW 2002 Isosteric Groups,Updated Isosteric Groups,Count,UG,UU,UC,UA,CG,GC,GU,CU,CC,AA,AU,AG,AC,CA,,,,+UG,tWS,I6.4,I6.4,2,0.00,1.86,2.41,3.50,4.62,3.81,3.31,5.20,5.13,5.69,6.31,6.55,6.77,6.73,,,,+UU,tWS,(I6.3) ,I6.4,1,1.86,0.00,1.56,3.24,4.66,4.46,3.79,4.73,4.75,5.69,6.32,6.83,7.15,6.95,,,,+UC,tWS,I6.3,I6.4,1,2.41,1.56,0.00,2.06,3.18,3.38,2.57,3.36,3.32,4.20,4.85,5.42,5.82,5.65,,,,+UA,tWS,I6.3,I6.3,11,3.50,3.24,2.06,0.00,1.95,2.33,2.62,3.83,3.59,3.87,4.39,4.02,4.26,3.82,,,,+CG,tWS,I6.1,I6.3,11,4.62,4.66,3.18,1.95,0.00,1.96,2.07,2.94,2.57,2.20,2.63,2.32,2.84,2.76,,,,+GC,tWS,I6.2,I6.3,4,3.81,4.46,3.38,2.33,1.96,0.00,1.79,4.15,3.80,3.47,3.76,3.00,3.05,3.33,,,,+GU,tWS,I6.2,I6.3,53,3.31,3.79,2.57,2.62,2.07,1.79,0.00,2.83,2.56,2.61,3.15,3.67,4.12,4.48,,,,+CU,tWS,(I6.1) ,(I6.1),0(M),5.20,4.73,3.36,3.83,2.94,4.15,2.83,0.00,0.42,1.84,2.36,4.33,5.12,5.36,,,,+CC,tWS,I6.1,I6.1,9,5.13,4.75,3.32,3.59,2.57,3.80,2.56,0.42,0.00,1.49,2.03,3.92,4.71,4.96,,,,+AA,tWS,I6.1,I6.1,13,5.69,5.69,4.20,3.87,2.20,3.47,2.61,1.84,1.49,0.00,0.88,2.78,3.66,4.11,,,,+AU,tWS,(I6.1) ,I6.1,2(CM),6.31,6.32,4.85,4.39,2.63,3.76,3.15,2.36,2.03,0.88,0.00,2.53,3.40,4.03,,,,+AG,tWS,I6.1,I6.2,51,6.55,6.83,5.42,4.02,2.32,3.00,3.67,4.33,3.92,2.78,2.53,0.00,0.95,1.75,,,,+AC,tWS,(I6.1) ,I6.2,1,6.77,7.15,5.82,4.26,2.84,3.05,4.12,5.12,4.71,3.66,3.40,0.95,0.00,1.40,,,,+CA,tWS,I6.1,I6.2,1,6.73,6.95,5.65,3.82,2.76,3.33,4.48,5.36,4.96,4.11,4.03,1.75,1.40,0.00,,,,+,,,,,,,,,,,,,,,,,,,,,,+cHH,Family,LSW 2002 Isosteric Groups,Updated Isosteric Groups,Count,AG,GA,GG,GC,CG,GG,,,,,,,,,,,,+AG,cHH,I7.2,I7.2,2,0.00,3.43,14.42,14.03,13.64,13.88,,,,,,,,,,,,+GA,cHH,I7.2,I7.3,2,3.43,0.00,13.88,13.64,14.03,14.42,,,,,,,,,,,,+GG,cHh,I7.1,I7.1,2,14.42,13.88,0.00,1.70,10.51,11.46,,,,,,,,,,,,+GC,cHH,I7.1,I7.1b,1,14.03,13.64,1.70,0.00,9.40,10.51,,,,,,,,,,,,+CG,cHH,I7.1,I7.1a,1,13.64,14.03,10.51,9.40,0.00,1.70,,,,,,,,,,,,+GG,chH,I7.1,I7.1,2,13.88,14.42,11.46,10.51,1.70,0.00,,,,,,,,,,,,+,,,,,,,,,,,,,,,,,,,,,,+tHH,Family,LSW 2002 Isosteric Groups,Updated Isosteric Groups,Count,GG,AG,AU,CU,AC,GC,AA,AA,CG,CA,UC,UA,GA,GG,,,,+GG,thH,I8.3,I8.4,2,0.00,6.57,7.02,6.38,5.09,5.49,6.43,6.78,7.29,7.52,8.67,9.78,9.68,11.37,,,,+AG,tHH,I8.2,I8.3,3(C),6.57,0.00,1.44,2.41,4.16,3.48,3.43,3.73,4.71,5.50,4.59,4.86,5.02,9.68,,,,+AU,tHH,I8.2,I8.3,4,7.02,1.44,0.00,1.63,4.04,3.49,3.42,3.67,4.60,5.29,4.02,4.34,4.86,9.78,,,,+CU,tHH,I8.2,I8.3,4,6.38,2.41,1.63,0.00,2.60,2.17,2.26,2.53,3.35,3.91,3.13,4.02,4.59,8.67,,,,+AC,tHH,I8.1,I8.1,4,5.09,4.16,4.04,2.60,0.00,1.02,1.90,2.17,2.59,2.73,3.91,5.29,5.50,7.52,,,,+GC,tHH,I8.1,I8.1,2,5.49,3.48,3.49,2.17,1.02,0.00,1.06,1.41,2.08,2.59,3.35,4.60,4.71,7.29,,,,+AA,thH,I8.1,I8.1,97,6.43,3.43,3.42,2.26,1.90,1.06,0.00,0.44,1.41,2.17,2.53,3.67,3.73,6.78,,,,+AA,tHh,I8.1,I8.1,97,6.78,3.73,3.67,2.53,2.17,1.41,0.44,0.00,1.06,1.90,2.26,3.42,3.43,6.43,,,,+CG,tHH,I8.1,I8.1,2,7.29,4.71,4.60,3.35,2.59,2.08,1.41,1.06,0.00,1.02,2.17,3.49,3.48,5.49,,,,+CA,tHH,I8.1,I8.1,4,7.52,5.50,5.29,3.91,2.73,2.59,2.17,1.90,1.02,0.00,2.60,4.04,4.16,5.09,,,,+UC,tHH,I8.2,I8.2,4,8.67,4.59,4.02,3.13,3.91,3.35,2.53,2.26,2.17,2.60,0.00,1.63,2.41,6.38,,,,+UA,tHH,I8.2,I8.2,4,9.78,4.86,4.34,4.02,5.29,4.60,3.67,3.42,3.49,4.04,1.63,0.00,1.44,7.02,,,,+GA,tHH,I8.2,I8.2,3(C),9.68,5.02,4.86,4.59,5.50,4.71,3.73,3.43,3.48,4.16,2.41,1.44,0.00,6.57,,,,+GG,tHh,I8.3,I8.4,2,11.37,9.68,9.78,8.67,7.52,7.29,6.78,6.43,5.49,5.09,6.38,7.02,6.57,0.00,,,,+,,,,,,,,,,,,,,,,,,,,,,+cHS,Family,LSW 2002 Isosteric Groups,Updated Isosteric Groups,Count,AG,CC,GA,GG,CU,UU,UG,UC,AC,CA,AA,AU,CG,UA,,,,+AG,cHS,I9.1,I9.1,2(C),0.00,1.93,2.54,2.61,2.96,2.67,3.18,3.27,3.67,3.58,4.13,4.73,5.80,5.30,,,,+CC,cHS,I9.1/9.2,I9.1,0(C),1.93,0.00,1.01,1.85,1.92,1.99,2.78,2.72,2.53,2.54,3.08,3.46,4.68,4.15,,,,+GA,cHS,(I9.1),I9.1,3(C),2.54,1.01,0.00,1.14,1.10,1.44,2.32,2.28,1.91,1.81,2.36,2.51,3.75,3.70,,,,+GG,cHS,I9.1,I9.1,10(C),2.61,1.85,1.14,0.00,0.63,0.81,1.64,1.76,1.80,1.48,2.06,2.43,3.55,4.23,,,,+CU,cHS,I9.1/9.2,I9.1,10,2.96,1.92,1.10,0.63,0.00,0.65,1.43,1.43,1.21,0.93,1.49,2.08,3.50,4.29,,,,+UU,cHS,I9.1,I9.1,2,2.67,1.99,1.44,0.81,0.65,0.00,0.92,0.98,1.28,1.05,1.57,2.61,4.07,4.84,,,,+UG,cHS,I9.1/9.2,I9.1,81,3.18,2.78,2.32,1.64,1.43,0.92,0.00,0.39,1.37,1.21,1.44,3.02,4.56,5.65,,,,+UC,cHS,(I9.1),I9.1,1(CM),3.27,2.72,2.28,1.76,1.43,0.98,0.39,0.00,1.11,1.06,1.22,2.93,4.61,5.63,,,,+AC,cHS,I9.1,I9.1,4,3.67,2.53,1.91,1.80,1.21,1.28,1.37,1.11,0.00,0.51,0.67,2.23,4.02,4.99,,,,+CA,cHS,I9.1,I9.1,12,3.58,2.54,1.81,1.48,0.93,1.05,1.21,1.06,0.51,0.00,0.66,2.01,3.72,4.80,,,,+AA,cHS,I9.1/9.2,I9.1,33,4.13,3.08,2.36,2.06,1.49,1.57,1.44,1.22,0.67,0.66,0.00,2.04,3.87,5.17,,,,+AU,cHS,I9.1,I9.1,3,4.73,3.46,2.51,2.43,2.08,2.61,3.02,2.93,2.23,2.01,2.04,0.00,2.08,3.56,,,,+CG,cHS,I9.1,I9.2,1,5.80,4.68,3.75,3.55,3.50,4.07,4.56,4.61,4.02,3.72,3.87,2.08,0.00,3.10,,,,+UA,cHS,I9.2,I9.3,1,5.30,4.15,3.70,4.23,4.29,4.84,5.65,5.63,4.99,4.80,5.17,3.56,3.10,0.00,,,,+,,,,,,,,,,,,,,,,,,,,,,+tHS,Family,LSW 2002 Isosteric Groups,Updated Isosteric Groups,Count,CC,CA,AG,AU,CU,AC,AA,GG,UG,UA,,,,,,,,+CC,tHS,I10.1,I10.1,11,0.00,1.07,1.12,1.11,1.21,1.60,2.23,4.39,3.75,4.54,,,,,,,,+CA,tHS,I10.1,I10.1,7,1.07,0.00,0.45,0.65,1.38,1.54,1.99,3.76,2.91,3.62,,,,,,,,+AG,tHS,I10.1,I10.1,501,1.12,0.45,0.00,0.62,1.07,1.11,1.56,3.50,2.85,3.46,,,,,,,,+AU,tHS,I10.1,I10.1,6,1.11,0.65,0.62,0.00,1.50,1.40,1.88,4.01,3.35,3.75,,,,,,,,+CU,tHS,I10.1,I10.1,3,1.21,1.38,1.07,1.50,0.00,0.77,1.26,3.36,3.12,3.88,,,,,,,,+AC,tHS,I10.1,I10.1,20,1.60,1.54,1.11,1.40,0.77,0.00,0.66,3.23,3.20,3.56,,,,,,,,+AA,tHS,I10.1,I10.1,47,2.23,1.99,1.56,1.88,1.26,0.66,0.00,2.73,2.99,3.16,,,,,,,,+GG,tHS,I10.2,I10.2,33,4.39,3.76,3.50,4.01,3.36,3.23,2.73,0.00,1.81,2.14,,,,,,,,+UG,tHS,I10.2,I10.2,17,3.75,2.91,2.85,3.35,3.12,3.20,2.99,1.81,0.00,2.02,,,,,,,,+UA,tHS,I10.2,I10.2,23,4.54,3.62,3.46,3.75,3.88,3.56,3.16,2.14,2.02,0.00,,,,,,,,+,,,,,,,,,,,,,,,,,,,,,,+cSS,Family,LSW 2002 Isosteric Groups,Updated Isosteric Groups,Count,UC,UU,GA,AA,CA,UA,AC,UG,AG,CG,AU,CC,GU,CU,GG,GC,,+UC,cSs,I11.1,I11.1,2,0.00,2.12,1.66,1.90,1.95,1.95,1.68,1.67,1.84,1.59,1.19,2.56,2.91,1.94,2.40,2.70,,+UU,cSs,(I11.1) ,(I11.1),0(M),2.12,0.00,0.89,0.84,0.90,0.97,1.48,1.43,1.51,1.48,1.63,1.81,1.84,2.41,2.18,3.12,,+GA,cSs,I11.1,I11.1,65,1.66,0.89,0.00,0.33,0.36,0.38,0.77,0.82,0.89,0.98,0.95,1.45,1.76,1.97,1.77,2.57,,+AA,cSs,I11.1,I11.1,32,1.90,0.84,0.33,0.00,0.21,0.23,0.80,0.88,0.86,0.99,1.08,1.31,1.57,2.01,1.68,2.58,,+CA,cSs,I11.1,I11.1,133,1.95,0.90,0.36,0.21,0.00,0.09,0.72,0.76,0.77,0.95,1.06,1.16,1.46,1.96,1.60,2.46,,+UA,cSs,I11.1,I11.1,78,1.95,0.97,0.38,0.23,0.09,0.00,0.67,0.74,0.74,0.96,1.04,1.14,1.44,1.94,1.57,2.42,,+AC,cSs,I11.1,I11.1,201,1.68,1.48,0.77,0.80,0.72,0.67,0.00,0.32,0.41,0.70,0.59,1.01,1.42,1.47,1.22,1.85,,+UG,cSs,I11.1,I11.1,23,1.67,1.43,0.82,0.88,0.76,0.74,0.32,0.00,0.40,0.61,0.60,0.96,1.38,1.34,1.14,1.77,,+AG,cSs,I11.1,I11.1,35,1.84,1.51,0.89,0.86,0.77,0.74,0.41,0.40,0.00,0.49,0.71,0.93,1.40,1.30,0.92,1.80,,+CG,cSs,I11.1,I11.1,13,1.59,1.48,0.98,0.99,0.95,0.96,0.70,0.61,0.49,0.00,0.58,1.19,1.64,1.23,1.03,1.89,,+AU,cSs,I11.1,I11.1,3,1.19,1.63,0.95,1.08,1.06,1.04,0.59,0.60,0.71,0.58,0.00,1.42,1.88,1.36,1.39,1.89,,+CC,cSs,(I11.1) ,I11.1,0(C),2.56,1.81,1.45,1.31,1.16,1.14,1.01,0.96,0.93,1.19,1.42,0.00,0.76,1.84,1.13,1.71,,+GU,cSs,(I11.1) ,I11.1,9,2.91,1.84,1.76,1.57,1.46,1.44,1.42,1.38,1.40,1.64,1.88,0.76,0.00,2.11,1.45,2.06,,+CU,cSs,I11.1,I11.1,4,1.94,2.41,1.97,2.01,1.96,1.94,1.47,1.34,1.30,1.23,1.36,1.84,2.11,0.00,0.96,1.47,,+GG,cSs,I11.1,I11.1,4(C),2.40,2.18,1.77,1.68,1.60,1.57,1.22,1.14,0.92,1.03,1.39,1.13,1.45,0.96,0.00,1.39,,+GC,cSs,(I11.1) ,I11.1,8(C),2.70,3.12,2.57,2.58,2.46,2.42,1.85,1.77,1.80,1.89,1.89,1.71,2.06,1.47,1.39,0.00,,+,,,,,,,,,,,,,,,,,,,,,,+tSS,Family,LSW 2002 Isosteric Groups,Updated Isosteric Groups,Count,GA,GG,GC,GU,AU,AG,AA,AC,,,,,,,,,,+GA,tSs,(I12.2),I12.2,2,0.00,1.06,1.94,2.71,4.29,3.99,4.49,4.69,,,,,,,,,,+GG,tSs,I12.2,I12.2,16,1.06,0.00,1.05,2.13,3.66,3.20,3.64,3.92,,,,,,,,,,+GC,tSs,I12.2,I12.2,6,1.94,1.05,0.00,1.86,3.59,2.93,3.17,3.54,,,,,,,,,,+GU,tSs,I12.2,I12.2,3,2.71,2.13,1.86,0.00,2.22,1.93,2.17,2.30,,,,,,,,,,+AU,tSs,I12.1,I12.1,41,4.29,3.66,3.59,2.22,0.00,1.00,1.48,1.11,,,,,,,,,,+AG,tSs,I12.1,I12.1,335,3.99,3.20,2.93,1.93,1.00,0.00,0.79,0.89,,,,,,,,,,+AA,tSs,I12.1,I12.1,22,4.49,3.64,3.17,2.17,1.48,0.79,0.00,0.60,,,,,,,,,,+AC,tSs,I12.1,I12.1,75(C),4.69,3.92,3.54,2.30,1.11,0.89,0.60,0.00,,,,,,,,,,
+ sources/isostericity-matrices.csv view
@@ -0,0 +1,170 @@+Isostericity Matrix,,,,+cWW,A,C,G,U+A,I1.4,I1.2a,I1.3,I1.1+C,I1.2b,I1.6,I1.1,I1.5+G,I1.3,I1.1,,I1.2a+U,I1.1,I1.5,I1.2b,I1.7+,,,,+,,,,+,,,,+,,,,+,,,,+,,,,+,,,,+,,,,+,,,,+,,,,+,,,,+,,,,+,,,,+,,,,+Isostericity Matrix,,,,+tWW,A,C,G,U+A,I2.7,I2.4,,I2.2+C,I2.3,I2.9,I2.6,I2.8+G,,I2.5,I2.7,I2.4+U,I2.1,I2.8,I2.3,I2.9+,,,,+,,,,+,,,,+,,,,+,,,,+,,,,+,,,,+,,,,+,,,,+,,,,+Isostericity Matrix,,,,+cWH,A,C,G,U+A,,,I3.3,(I3.3)+C,,I3.2,I3.1,(I3.2)+G,I3.3,,I3.4,+U,I3.1,,I3.1,I3.2+,,,,+,,,,+,,,,+,,,,+,,,,+,,,,+Isostericity Matrix,,,,+tWH,A,C,G,U+A,I4.3,,I4.3/4.2,+C,I4.2,I4.1,I4.2,+G,,,I4.5,I4.3+U,I4.1,,I4.4,I4.2+,,,,+,,,,+,,,,+,,,,+,,,,+,,,,+Isostericity Matrix,,,,+cWS,A,C,G,U+A,I5.1,I5.1,I5.1,I5.1+C,I5.2,I5.2,I5.2,I5.2+G,I5.3,I5.3,I5.5,I5.3+U,I5.4,I5.4,I5.4,I5.4+,,,,+,,,,+,,,,+,,,,+,,,,+,,,,+,,,,+,,,,+,,,,+,,,,+,,,,+,,,,+Isostericity Matrix,,,,+tWS,A,C,G,U+A,I6.1,I6.2,I6.2,I6.1+C,I6.2,I6.1,I6.3,(I6.1)+G,,I6.3,,I6.3+U,I6.3,I6.4,I6.4,I6.4+,,,,+,,,,+,,,,+,,,,+,,,,+,,,,+,,,,+,,,,+,,,,+,,,,+Isostericity Matrix,,,,+cHH,A,C,G,U+A,,,I7.2,+C,,,I7.1a,+G,I7.3,I7.1b,I7.1,+U,,,,+,,,,+,,,,+Isostericity Matrix,,,,+tHH,A,C,G,U+A,I8.1,I8.1,I8.3,I8.3+C,I8.1,,I8.1,I8.3+G,I8.2,I8.1,I8.4,+U,I8.2,I8.2,,+,,,,+,,,,+,,,,+,,,,+,,,,+,,,,+,,,,+,,,,+,,,,+,,,,+Isostericity Matrix,,,,+cHS,A,C,G,U+A,I9.1,I9.1,I9.1,I9.1+C,I9.1,I9.1,I9.2,I9.1+G,I9.1,,I9.1,+U,I9.3,I9.1,I9.1,I9.1+,,,,+,,,,+,,,,+,,,,+,,,,+,,,,+,,,,+,,,,+,,,,+,,,,+Isostericity Matrix,,,,+tHS,A,C,G,U+A,I10.1,I10.1,I10.1,I10.1+C,I10.1,I10.1,,I10.1+G,,,I10.2,+U,I10.2,,I10.2,+,,,,+,,,,+,,,,+,,,,+,,,,+,,,,+Isostericity Matrix,,,,+cSS,A,C,G,U+A,I11.1,I11.1,I11.1,I11.1+C,I11.1,I11.1,I11.1,I11.1+G,I11.1,I11.1,I11.1,I11.1+U,I11.1,I11.1,I11.1,(I11.1)+,,,,+,,,,+,,,,+,,,,+,,,,+,,,,+,,,,+,,,,+,,,,+,,,,+,,,,+,,,,+Isostericity Matrix,,,,+tSS,A,C,G,U+A,I12.1,I12.1,I12.1,I12.1+C,,,,+G,I12.2,I12.2,I12.2,I12.2+U,,,,