deletions | additions       diff --git a/subsection_Dataset_The_specific_modality__.tex b/subsection_Dataset_The_specific_modality__.tex  index cf7a559..3778e4c 100644  --- a/subsection_Dataset_The_specific_modality__.tex  +++ b/subsection_Dataset_The_specific_modality__.tex 
...
Of the 17 targets in the MUV dataset, we identified 10 that had a receptor-ligand structure in the Protein Data Bank (PDB) where the ligand had sub-$\mu$M affinity. The interaction diagrams of these structures are shown in Figure~\ref{targets}. For each of these structures we identified interacting fragments that could potentially serve as anchor fragments. For each target we consider a variety of fragments in order to evaluate the sensitivity of the approach to the choice of fragment. We selected relatively generic functional groups (at most \textbf{X} atoms) that were sufficiently common among both the actives and decoys to yield meaningful results and that were clearly forming interactions with the receptor.  \begin{table}   \begin{tabular}{} \begin{tabular}{ c c }  Fragment &  SMARTS Expression \\  Cathg1 &  c1ccccc1[R] \\  Cathg2 &  c1ccccc1[C] \\  Cathg3 &  c1ccccc1[!H] \\  Cathg4 &  a1aaaaa1[!H] \\  Cathg5 &  c1ccccc1[C] Eralpha_pot1 \\   Eralphapot1 &  c1ccccc1O Eralpha_pot2 \\   Eralphapot2 &  c1ccccc1[!H] Eralpha_pot3 \\   Eralphapot3 &  a1aaaaa1[!H] \\  Eralpha1 &  c1ccccc1O \\  Eralpha2 &  c1ccccc1N \\  Eralpha3 &  c1ccccc1[!H] \\  Eralpha4 &  a1aaaaa1[!H] \\  Erbeta1 &  c1ccccc1O \\  Erbeta2 &  c1ccccc1N \\  Erbeta3 &  c1ccccc1[!H] \\  Erbeta4 &  a1aaaaa1[!H] \\  Fak1 &  c1[c,n]cccn1 \\  Fak2 &  c1cccc([!H])c1 \\  Fak3 &  a1a([!H])aaaa1 \\  Fak4 &  n1[c,n][c,n]cc1 \\  Fxia1 a1aaan1 & a1aan1  \\  Fxia2 &  c1[c,n]cc[c,s]1 \\  Fxia3 &  c1[c,n]cc([!H])[c,s,o]1 \\  Fxia4 &  a1aaaa1[!H] \\  Hivrt1 &  a1aaan1 \\  Hivrt2 &  c1aacn1 \\  Hivrt3 &  c1aac([!H])n1 \\  Hivrt4 &  a1aaaa1[!H] \\  Hivrt5 &  c1ccccc1[Cl,O] \\  Hsp901 &  c1ccccc1O \\  Hsp902 &  c1ccccc1[!H] \\  Hsp903 &  a1aaaaa1[!H] \\  Pka1 &  c1[c,n]cccn1 \\  Pka2 &  a1ncccn1 \\  Pka3 &  a1([!H])ncccn1 \\  Pka4 &  c1[c,n]c([!H])ccn1 \\  Rho1 &  c1[c,n]cccn1 \\  Rho2 &  c1[c,n]c([!H])ccn1 \\  \end{tabular}   \end{table}