diff --git a/data/tabular/chem_caption_smarts/meta.yaml b/data/tabular/chem_caption_smarts/meta.yaml
new file mode 100644
index 000000000..57f8ecfbe
--- /dev/null
+++ b/data/tabular/chem_caption_smarts/meta.yaml
@@ -0,0 +1,41 @@
+---
+name: chem_caption_smarts
+description: |-
+    This dataset contains the count of substructures in molecules
+targets:
+    - id: smarts
+      type: text
+      description: substructure smarts
+      names:
+          - noun: SMARTS
+          - noun: SMiles ARbitrary Target Specification (SMARTS)
+    - id: completion
+      type: categorical
+      description: number of matches
+    - id: completion_labels
+      type: text
+      description: name of the substructure
+identifiers:
+    - id: representation
+      type: text
+      description: representation
+    - id: representation_type
+      type: text
+      description: representation type
+license: CC BY 4.0
+links:
+    - url: https://github.com/lamalab-org/chem-caption
+      description: Original codebase used to generate this dataset
+templates:
+    - |-
+      Question: {#How many times|How often!} does the {#molecule|chemical|compound|chemical structure!} with {representation_type#} {representation#} contain the substructure with the {smarts__names__noun} {#smarts#}?
+      Answer: {completion#}
+    - |-
+      Question: {#How many times|How often!} does the {#molecule|chemical|compound|chemical structure!} with {representation_type#} {representation#} contain a {completion#} substructure?
+      Answer: {smarts__names__noun} {#smarts#}
+    - |-
+      User: {#I want to|I have to|I must|I would like to!} know {#how many times|how often!} the {#molecule|chemical|compound|chemical structure!} with {representation_type#} {representation#} contains the substructure with the {smarts__names__noun} {#smarts#}.
+      Assistant: The {#molecule|chemical|compound|chemical structure!} with {representation_type#} {representation#} contains the substructure with the {smarts__names__noun} {#smarts#} {completion#} times.
+    - |-
+      User: {#I want to|I have to|I must|I would like to!} know how many times the {#molecule|chemical|compound|chemical structure!} with {representation_type#} {representation#} contains a {completion#} substructure.
+      Assistant: The {#molecule|chemical|compound|chemical structure!} contains the substructure with the {smarts__names__noun} {#smarts#} {completion#} times.
diff --git a/data/tabular/chem_caption_smarts/preprocess.py b/data/tabular/chem_caption_smarts/preprocess.py
new file mode 100644
index 000000000..06eeafe4e
--- /dev/null
+++ b/data/tabular/chem_caption_smarts/preprocess.py
@@ -0,0 +1,810 @@
+# flake8: noqa
+"""Preprocess the raw outputs from the text-output of chem-caption to a tabular dataset."""
+from glob import glob
+
+import pandas as pd
+from datasets import Dataset
+from tqdm import tqdm
+
+NAME_SMARTS_MAP = {
+    "tert-butyloxycarbonyl": "[#8]=[#6]-[#8]-[#6](-[#6])(-[#6])-[#6]",
+    "trityl": "[#6](-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1)(-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1)-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1",
+    "3,5-dimethoxyphenylisoproxycarbonyl": "[#6]-[#8]-[#6]1:[#6]:[#6](-[#6](-[#6])(-[#8]-[#6]=[#8])-[#6]):[#6]:[#6](-[#8]-[#6]):[#6]:1",
+    "2-(4-biphenyl)isopropoxycarbonyl": "[#6]-[#6](-[#6])(-[#8]-[#6]=[#8])-[#6]1:[#6]:[#6]:[#6](:[#6]:[#6]:1)-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1",
+    "2-nitrophenylsulfenyl": "[#16]-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1-[#7+](-[#8-])=[#8]",
+    "boc": "[#8]=[#6]-[#8]-[#6](-[#6])(-[#6])-[#6]",
+    "trt": "[#6](-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1)(-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1)-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1",
+    "ddz": "[#6]-[#8]-[#6]1:[#6]:[#6](-[#6](-[#6])(-[#8]-[#6]=[#8])-[#6]):[#6]:[#6](-[#8]-[#6]):[#6]:1",
+    "bpoc": "[#6]-[#6](-[#6])(-[#8]-[#6]=[#8])-[#6]1:[#6]:[#6]:[#6](:[#6]:[#6]:1)-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1",
+    "nps": "[#16]-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1-[#7+](-[#8-])=[#8]",
+    "9-fluorenylmethoxycarbonyl": "[#8]=[#6]-[#8]-[#6]-[#6]1-[#6]2:[#6](-[#6]3:[#6]-1:[#6]:[#6]:[#6]:[#6]:3):[#6]:[#6]:[#6]:[#6]:2",
+    "2-(4-nitrophenylsulfonyl)ethoxycarbonyl": "[#8]=[#6]-[#8]-[#6]-[#6]-[#16](=[#8])(-[#6]1:[#6]:[#6]:[#6](-[#7+](-[#8-])=[#8]):[#6]:[#6]:1)=[#8]",
+    "(1,1-dioxobenzo[b]thiophene-2-yl)methyloxycarbonyl": "[#8]=[#6]-[#8]-[#6]-[#6]1=[#6]-[#6]2:[#6]:[#6]:[#6]:[#6]:[#6]:2-[#16]-1(=[#8])=[#8]",
+    "(1,1-dioxonaptho[1,2-b]thiophene-2-yl)methyloxycarbonyl": "[#8]=[#6]-[#8]-[#6]-[#6]1=[#6]-[#6]2:[#6]:[#6]:[#6]3:[#6]:[#6]:[#6]:[#6]:[#6]:3:[#6]:2-[#16]-1(=[#8])=[#8]",
+    "1-(4,4-dimethyl-2,6-dioxocyclohex-1-ylidene)-3-methylbutyl": "[#6]-[#6](-[#6])-[#6]-[#6]=[#6]1-[#6](-[#6]-[#6](-[#6])(-[#6])-[#6]-[#6]-1=[#8])=[#8]",
+    "2,7-di-tert-butyl-fmoc": "[#6]-[#6]1:[#6]:[#6]2-[#6](-[#6]-[#8]-[#6]=[#8])-[#6]3:[#6](-[#6]:2:[#6]:[#6]:1):[#6]:[#6]:[#6](:[#6]:3)-[#6](-[#6])(-[#6])-[#6]",
+    "2-fluoro-fmoc": "[#9]-[#6]1:[#6]:[#6]2:[#6](-[#6]3:[#6]:[#6]:[#6]:[#6]:[#6]:3-[#6]-2-[#6]-[#8]-[#6]=[#8]):[#6]:[#6]:1",
+    "2-monoisooctyl-fmoc": "[#8]=[#6]-[#8]-[#6]-[#6]1-[#6]2:[#6](:[#6]:[#6]:[#6]:[#6]:2)-[#6]2:[#6]-1:[#6]:[#6](-[#6](-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6])=[#8]):[#6]:[#6]:2",
+    "2,7-diisooctyl-fmoc": "[#8]=[#6]-[#8]-[#6]-[#6]1-[#6]2:[#6](:[#6]:[#6]:[#6](-[#6](-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6])=[#8]):[#6]:2)-[#6]2:[#6]-1:[#6]:[#6](-[#6](-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6])=[#8]):[#6]:[#6]:2",
+    "tetrachlorophthaloyl": "[#8]=[#6]-[#6]1:[#6](-[#17]):[#6](-[#17]):[#6](-[#17]):[#6](-[#17]):[#6]:1-[#6]=[#8]",
+    "2-[phenyl(methyl)sulfonio])ethyloxycarbonyltetrafluoroborate": "[#6]-[#16+](-[#6]-[#6]-[#8]-[#6]=[#8])-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1",
+    "ethanesulfonylethoxycarbonyl": "[#8]=[#6]-[#8]-[#6](-[#16](=[#8])(-[#6]-[#6])=[#8])-[#6]",
+    "2-(4-sulfophenylsulfonyl)ethoxycarbonyl": "[#8]=[#6]-[#8]-[#6]-[#6]-[#16](=[#8])(-[#6]1:[#6]:[#6]:[#6](-[#16](=[#8])(-[#8])=[#8]):[#6]:[#6]:1)=[#8]",
+    "fmoc": "[#8]=[#6]-[#8]-[#6]-[#6]1-[#6]2:[#6](-[#6]3:[#6]-1:[#6]:[#6]:[#6]:[#6]:3):[#6]:[#6]:[#6]:[#6]:2",
+    "nsc": "[#8]=[#6]-[#8]-[#6]-[#6]-[#16](=[#8])(-[#6]1:[#6]:[#6]:[#6](-[#7+](-[#8-])=[#8]):[#6]:[#6]:1)=[#8]",
+    "bsmoc": "[#8]=[#6]-[#8]-[#6]-[#6]1=[#6]-[#6]2:[#6]:[#6]:[#6]:[#6]:[#6]:2-[#16]-1(=[#8])=[#8]",
+    "alpha-nsmoc": "[#8]=[#6]-[#8]-[#6]-[#6]1=[#6]-[#6]2:[#6]:[#6]:[#6]3:[#6]:[#6]:[#6]:[#6]:[#6]:3:[#6]:2-[#16]-1(=[#8])=[#8]",
+    "ivdde": "[#6]-[#6](-[#6])-[#6]-[#6]=[#6]1-[#6](-[#6]-[#6](-[#6])(-[#6])-[#6]-[#6]-1=[#8])=[#8]",
+    "fmoc*": "[#6]-[#6]1:[#6]:[#6]2-[#6](-[#6]-[#8]-[#6]=[#8])-[#6]3:[#6](-[#6]:2:[#6]:[#6]:1):[#6]:[#6]:[#6](:[#6]:3)-[#6](-[#6])(-[#6])-[#6]",
+    "fmoc(fmoc(2f))": "[#9]-[#6]1:[#6]:[#6]2:[#6](-[#6]3:[#6]:[#6]:[#6]:[#6]:[#6]:3-[#6]-2-[#6]-[#8]-[#6]=[#8]):[#6]:[#6]:1",
+    "mio-fmoc": "[#8]=[#6]-[#8]-[#6]-[#6]1-[#6]2:[#6](:[#6]:[#6]:[#6]:[#6]:2)-[#6]2:[#6]-1:[#6]:[#6](-[#6](-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6])=[#8]):[#6]:[#6]:2",
+    "dio-fmoc": "[#8]=[#6]-[#8]-[#6]-[#6]1-[#6]2:[#6](:[#6]:[#6]:[#6](-[#6](-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6])=[#8]):[#6]:2)-[#6]2:[#6]-1:[#6]:[#6](-[#6](-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6])=[#8]):[#6]:[#6]:2",
+    "tcp": "[#8]=[#6]-[#6]1:[#6](-[#17]):[#6](-[#17]):[#6](-[#17]):[#6](-[#17]):[#6]:1-[#6]=[#8]",
+    "pms": "[#6]-[#16+](-[#6]-[#6]-[#8]-[#6]=[#8])-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1",
+    "esc": "[#8]=[#6]-[#8]-[#6](-[#16](=[#8])(-[#6]-[#6])=[#8])-[#6]",
+    "sps": "[#8]=[#6]-[#8]-[#6]-[#6]-[#16](=[#8])(-[#6]1:[#6]:[#6]:[#6](-[#16](=[#8])(-[#8])=[#8]):[#6]:[#6]:1)=[#8]",
+    "benzyloxycarbonyl": "[#8]=[#6]-[#8]-[#6]-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1",
+    "allyloxycarbonyl": "[#8]=[#6]-[#8]-[#6]-[#6]=[#6]",
+    "o-nitrobenzenesulfonyl": "[#8]=[#16](-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1-[#7+](-[#8-])=[#8])=[#8]",
+    "2,4-dinitrobenzenesulfonyl": "[#8]=[#16](-[#6]1:[#6]:[#6]:[#6](-[#7+](-[#8-])=[#8]):[#6]:[#6]:1-[#7+](-[#8-])=[#8])=[#8]",
+    "benzothiazole-2-sulfonyl": "[#8]=[#16](-[#6]1:[#7]:[#6]2:[#6]:[#6]:[#6]:[#6]:[#6]:2:[#16]:1)=[#8]",
+    "2,2,2-trichloroethyloxycarbonyl": "[#8]=[#6]-[#8]-[#6]-[#6](-[#17])(-[#17])-[#17]",
+    "dithiasuccinoyl": "[#8]=[#6]-[#16]-[#16]-[#6]=[#8]",
+    "p-nitrobenzyloxycarbonyl": "[#8]=[#6]-[#8]-[#6]-[#6]1:[#6]:[#6]:[#6](-[#7+](-[#8-])=[#8]):[#6]:[#6]:1",
+    "alpha-azidoacids": "[#7-]=[#7+]=[#7]-[#6]-[#6](-[#8])=[#8]",
+    "proparglyoxycarbonyl": "[#6]#[#6]-[#8]-[#6](-[#6])=[#8]",
+    "o-nitrobenzylcarbonyl": "[#8]=[#6]-[#6]-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1-[#7+](-[#8-])=[#8]",
+    "4-nitroveratryloxycarbonyl": "[#8]=[#6]-[#8]-[#6]-[#6]1:[#6](-[#7+](-[#8-])=[#8]):[#6]:[#6](-[#8]-[#6]):[#6](-[#8]-[#6]):[#6]:1",
+    "2-(2-nitrophenyl)propyloxycarbonyl": "[#8]=[#6]-[#8]-[#6]-[#6](-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1-[#7+](-[#8-])=[#8])-[#6]",
+    "2-(3,4-methylenedioxy-6-nitrophenyl)propyloxycarbonyl": "[#8]=[#6]-[#8]-[#6]-[#6](-[#6]1:[#6]:[#6]2-[#8]-[#6]-[#8]-[#6]:2:[#6]:[#6]:1-[#7+](-[#8-])=[#8])-[#6]",
+    "9-(4-bromophenyl)-9-fluorenyl": "[#35]-[#6]1:[#6]:[#6]:[#6](-[#6]2-[#6]3:[#6](-[#6]4:[#6]-2:[#6]:[#6]:[#6]:[#6]:4):[#6]:[#6]:[#6]:[#6]:3):[#6]:[#6]:1",
+    "azidomethoxycarbonyl": "[#8]=[#6]-[#8]-[#6]-[#7]=[#7+]=[#7-]",
+    "hexafluoroacetone": "[#8]=[#6]1-[#8]-[#6](-[#6](-[#6](-[#9])(-[#9])-[#9])-[#6](-[#9])(-[#9])-[#9])-[#7]-[#6]-1",
+    "Z": "[#8]=[#6]-[#8]-[#6]-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1",
+    "alloc": "[#8]=[#6]-[#8]-[#6]-[#6]=[#6]",
+    "o-nbs": "[#8]=[#16](-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1-[#7+](-[#8-])=[#8])=[#8]",
+    "d-nbs": "[#8]=[#16](-[#6]1:[#6]:[#6]:[#6](-[#7+](-[#8-])=[#8]):[#6]:[#6]:1-[#7+](-[#8-])=[#8])=[#8]",
+    "bts": "[#8]=[#16](-[#6]1:[#7]:[#6]2:[#6]:[#6]:[#6]:[#6]:[#6]:2:[#16]:1)=[#8]",
+    "troc": "[#8]=[#6]-[#8]-[#6]-[#6](-[#17])(-[#17])-[#17]",
+    "dts": "[#8]=[#6]-[#16]-[#16]-[#6]=[#8]",
+    "pnz": "[#8]=[#6]-[#8]-[#6]-[#6]1:[#6]:[#6]:[#6](-[#7+](-[#8-])=[#8]):[#6]:[#6]:1",
+    "poc": "[#6]#[#6]-[#8]-[#6](-[#6])=[#8]",
+    "onz": "[#8]=[#6]-[#6]-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1-[#7+](-[#8-])=[#8]",
+    "nvoc": "[#8]=[#6]-[#8]-[#6]-[#6]1:[#6](-[#7+](-[#8-])=[#8]):[#6]:[#6](-[#8]-[#6]):[#6](-[#8]-[#6]):[#6]:1",
+    "nppoc": "[#8]=[#6]-[#8]-[#6]-[#6](-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1-[#7+](-[#8-])=[#8])-[#6]",
+    "mnppoc": "[#8]=[#6]-[#8]-[#6]-[#6](-[#6]1:[#6]:[#6]2-[#8]-[#6]-[#8]-[#6]:2:[#6]:[#6]:1-[#7+](-[#8-])=[#8])-[#6]",
+    "brphf": "[#35]-[#6]1:[#6]:[#6]:[#6](-[#6]2-[#6]3:[#6](-[#6]4:[#6]-2:[#6]:[#6]:[#6]:[#6]:4):[#6]:[#6]:[#6]:[#6]:3):[#6]:[#6]:1",
+    "azoc": "[#8]=[#6]-[#8]-[#6]-[#7]=[#7+]=[#7-]",
+    "hfa": "[#8]=[#6]1-[#8]-[#6](-[#6](-[#6](-[#9])(-[#9])-[#9])-[#6](-[#9])(-[#9])-[#9])-[#7]-[#6]-1",
+    "2-chlorobenzyloxycarbonyl": "[#8]=[#6]-[#8]-[#6]-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1-[#17]",
+    "4-methyltrityl": "[#6]-[#6]1:[#6]:[#6]:[#6](-[#6](-[#6]2:[#6]:[#6]:[#6]:[#6]:[#6]:2)-[#6]2:[#6]:[#6]:[#6]:[#6]:[#6]:2):[#6]:[#6]:1",
+    "cl-z": "[#8]=[#6]-[#8]-[#6]-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1-[#17]",
+    "mtt": "[#6]-[#6]1:[#6]:[#6]:[#6](-[#6](-[#6]2:[#6]:[#6]:[#6]:[#6]:[#6]:2)-[#6]2:[#6]:[#6]:[#6]:[#6]:[#6]:2):[#6]:[#6]:1",
+    "1-(4,4-dimethyl-2,6-dioxocylohex-1-ylidene)-3-methylbutyl": "[#8]=[#6]1-[#6](-[#6](-[#6]-[#6](-[#6])-[#6]-1)=[#8])=[#6]-[#6]-[#6](-[#6])-[#6]",
+    "trifluoroacetyl": "[#8]=[#6]-[#6](-[#9])(-[#9])-[#9]",
+    "2-(methylsulfonyl)ethoxycarbonyl": "[#8]=[#6]-[#8]-[#6]-[#6]-[#16](=[#8])(-[#6])=[#8]",
+    "tfa": "[#8]=[#6]-[#6](-[#9])(-[#9])-[#9]",
+    "msc": "[#8]=[#6]-[#8]-[#6]-[#6]-[#16](=[#8])(-[#6])=[#8]",
+    "phenyldisulphanylethyloxycarbonyl": "[#8]=[#6]-[#8]-[#6](-[#16]-[#16]-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1)-[#6]",
+    "2-pyridyldisulphanylethyloxycarbonyl": "[#8]=[#6]-[#8]-[#6](-[#16]-[#16]-[#6]1:[#7]:[#6]:[#6]:[#6]:[#6]:1)-[#6]",
+    "phdec": "[#8]=[#6]-[#8]-[#6](-[#16]-[#16]-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1)-[#6]",
+    "pydec": "[#8]=[#6]-[#8]-[#6](-[#16]-[#16]-[#6]1:[#7]:[#6]:[#6]:[#6]:[#6]:1)-[#6]",
+    "tert-butyl": "[#6]-[#6](-[#6])-[#6]",
+    "2-chlorotrityl": "[#17]-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1-[#6](-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1)-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1",
+    "2-4-dimethyoxybenzyl": "[#6]-[#6]1:[#6]:[#6](-[#8]-[#6]):[#6]:[#6](-[#8]-[#6]):[#6]:1",
+    "2-phenylisopropyl": "[#6]-[#6](-[#6])-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1",
+    "5-phenyl-3,4-ethylenedioxythenyl": "[#6]-[#6]1:[#6]2-[#8]-[#6]-[#6]-[#8]-[#6]:2:[#6](:[#16]:1)-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1",
+    "bu": "[#6]-[#6](-[#6])-[#6]",
+    "2-cl-trt": "[#17]-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1-[#6](-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1)-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1",
+    "dmb": "[#6]-[#6]1:[#6]:[#6](-[#8]-[#6]):[#6]:[#6](-[#8]-[#6]):[#6]:1",
+    "2-ph-pr": "[#6]-[#6](-[#6])-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1",
+    "phenyl-edotn": "[#6]-[#6]1:[#6]2-[#8]-[#6]-[#6]-[#8]-[#6]:2:[#6](:[#16]:1)-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1",
+    "9-fluorenylmethyl": "[#6]-[#6]1-[#6]2:[#6](-[#6]3:[#6]-1:[#6]:[#6]:[#6]:[#6]:3):[#6]:[#6]:[#6]:[#6]:2",
+    "4-(N-[1-(4,4-dimethyl-2,6-dioxocylocheylidene)-3-methylbutyl]-amino)benzyl": "[#6]-[#6]1(-[#6]-[#6](-[#6](=[#6](-[#7]-[#6]2:[#6]:[#6]:[#6](-[#6]):[#6]:[#6]:2)-[#6]-[#6](-[#6])-[#6])-[#6](-[#6]-1)=[#8])=[#8])-[#6]",
+    "methyl": "[#6H3]",
+    "ethyl": "[#6H2]-[#6]",
+    "carbamoylmethyl": "[#6]-[#6](-[#7])=[#8]",
+    "fm": "[#6]-[#6]1-[#6]2:[#6](-[#6]3:[#6]-1:[#6]:[#6]:[#6]:[#6]:3):[#6]:[#6]:[#6]:[#6]:2",
+    "dmab": "[#6]-[#6]1(-[#6]-[#6](-[#6](=[#6](-[#7]-[#6]2:[#6]:[#6]:[#6](-[#6]):[#6]:[#6]:2)-[#6]-[#6](-[#6])-[#6])-[#6](-[#6]-1)=[#8])=[#8])-[#6]",
+    "me": "[#6]",
+    "et": "[#6]-[#6]",
+    "cam": "[#6]-[#6](-[#7])=[#8]",
+    "allyl": "[#6H2]-[#6]=[#6]",
+    "benzyl": "[#6H2]-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1",
+    "phenacyl": "[#6H2]-[#6](-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1)=[#8]",
+    "p-nitrobenzyl": "[#6]-[#6]1:[#6]:[#6]:[#6](-[#7+](-[#8-])=[#8]):[#6]:[#6]:1",
+    "2-trimethylsilyethyl": "[#6]-[#6]-[#6]-[Si](-[#6])(-[#6])-[#6]",
+    "(2-phenyl-2-trimethylsilyl)ethyl": "[#6]-[#6](-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1)-[Si](-[#6])(-[#6])-[#6]",
+    "2-(trimethylsilyl)isopropyl": "[#6]-[#6](-[#6])(-[Si](-[#6])(-[#6])-[#6])-[#6]",
+    "2,2,2-trichloroethyl": "[#6]-[#6](-[#17])(-[#17])-[#17]",
+    "p-hydroxyphenacyl": "[#6]-[#6](-[#6]1:[#6]:[#6]:[#6](-[#8]):[#6]:[#6]:1)=[#8]",
+    "4,5-dimethyoxy-2-nitrobenzyl": "[#6]-[#6]1:[#6]:[#6](-[#8]-[#6]):[#6](-[#8]-[#6]):[#6]:[#6]:1-[#7+](-[#8-])=[#8]",
+    "1,1-dimethylallyl": "[#6]=[#6]-[#6](-[#6])-[#6]",
+    "pentaaminecobalt_III": "[#7]-[Co](-[#7])(-[#7])(-[#7])(-[#17])(-[#17])-[#7]",
+    "al": "[#6]-[#6]=[#6]",
+    "bn": "[#6]-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1",
+    "pac": "[#6]-[#6](-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1)=[#8]",
+    "pnb": "[#6]-[#6]1:[#6]:[#6]:[#6](-[#7+](-[#8-])=[#8]):[#6]:[#6]:1",
+    "tmse": "[#6]-[#6]-[#6]-[Si](-[#6])(-[#6])-[#6]",
+    "ptmse": "[#6]-[#6](-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1)-[Si](-[#6])(-[#6])-[#6]",
+    "tmsi": "[#6]-[#6](-[#6])(-[Si](-[#6])(-[#6])-[#6])-[#6]",
+    "tce": "[#6]-[#6](-[#17])(-[#17])-[#17]",
+    "php": "[#6]-[#6](-[#6]1:[#6]:[#6]:[#6](-[#8]):[#6]:[#6]:1)=[#8]",
+    "dmnb": "[#6]-[#6]1:[#6]:[#6](-[#8]-[#6]):[#6](-[#8]-[#6]):[#6]:[#6]:1-[#7+](-[#8-])=[#8]",
+    "dma": "[#6]=[#6]-[#6](-[#6])-[#6]",
+    "cyclohexyl": "[#6]1-[#6]-[#6]-[#6]-[#6]-[#6]-1",
+    "b-menthyl": "[#6]-[#6@H]1-[#6@H](-[#6](-[#6])-[#6])-[#6]-[#6]-[#6@@H](-[#6])-[#6]-1",
+    "b-3-methylpent-3-yl": "[#6]-[#6]-[#6](-[#6])-[#6]-[#6]",
+    "4-(3,6,9-trioxadecyl)oxybenzyl": "[#6]-[#6]1:[#6]:[#6]:[#6](-[#8]-[#6]-[#6]-[#8]-[#6]-[#6]-[#8]-[#6]-[#6]-[#8]-[#6]):[#6]:[#6]:1",
+    "chx": "[#6]1-[#6]-[#6]-[#6]-[#6]-[#6]-1",
+    "men": "[#6]-[#6H]1-[#6H](-[#6](-[#6])-[#6])-[#6]-[#6]-[#6H](-[#6])-[#6]-1",
+    "mpe": "[#6]-[#6]-[#6](-[#6])-[#6]-[#6]",
+    "tegbz": "[#6]-[#6]1:[#6]:[#6]:[#6](-[#8]-[#6]-[#6]-[#8]-[#6]-[#6]-[#8]-[#6]-[#6]-[#8]-[#6]):[#6]:[#6]:1",
+    "9-fluoroenylmethyl": "[#6]-[#6]1-[#6]2:[#6](-[#6]3:[#6]-1:[#6]:[#6]:[#6]:[#6]:3):[#6]:[#6]:[#6]:[#6]:2",
+    "4-(N-[1-(4,4-dimethyl-2,6-dioxocyclohexylidene)-3-methyl-butyl]-amino)benzyl": "[#6]-[#6]1(-[#6]-[#6](-[#6](=[#6](-[#7]-[#6]2:[#6]:[#6]:[#6](-[#6]):[#6]:[#6]:2)-[#6]-[#6](-[#6])-[#6])-[#6](-[#6]-1)=[#8])=[#8])-[#6]",
+    "trimethylsilylethyl": "[#6]-[#6]-[#6]-[Si](-[#6])(-[#6])-[#6]",
+    "4,5-dimethoxy-2-nitrobenzyloxycarbonyl": "[#6]-[#6]1:[#6]:[#6](-[#8]-[#6]):[#6](-[#8]-[#6]):[#6]:[#6]:1-[#7+](-[#8-])=[#8]",
+    "pseudoprolines": "[#6]-[#6]1(-[#6])-[#7]-[#6](-[#6](-[#8])=[#8])-[#6]-[#8]-1",
+    "2-hydroxy-4-methoxybenzyl": "[#6]-[#6]1:[#6]:[#6]:[#6](-[#8]-[#6]):[#6]:[#6]:1-[#8]",
+    "2,4-dimethoxybenzyl": "[#6]-[#6]1:[#6]:[#6]:[#6](-[#8]-[#6]):[#6]:[#6]:1-[#8]-[#6]",
+    "2,4,6-trimethoxybenzyl": "[#6]-[#6]1:[#6](-[#8]-[#6]):[#6]:[#6](-[#8]-[#6]):[#6]:[#6]:1-[#8]-[#6]",
+    "1-methyl-3-indolylmethyl": "[#6]-[#6]-[#6]1:[#6]:[#7H]:[#6]2:[#6]:1:[#6]:[#6]:[#6]:[#6]:2",
+    "3,4-ethylene-dioxy-2-thenyl": "[#6]-[#6]1:[#6]2-[#8]-[#6]-[#6]-[#8]-[#6]:2:[#6]:[#16]:1",
+    "hmb": "[#6]-[#6]1:[#6]:[#6]:[#6](-[#8]-[#6]):[#6]:[#6]:1-[#8]",
+    "tmob": "[#6]-[#6]1:[#6](-[#8]-[#6]):[#6]:[#6](-[#8]-[#6]):[#6]:[#6]:1-[#8]-[#6]",
+    "mim": "[#6]-[#6]-[#6]1:[#6]:[#7H]:[#6]2:[#6]:1:[#6]:[#6]:[#6]:[#6]:2",
+    "edot": "[#6]-[#6]1:[#6]2-[#8]-[#6]-[#6]-[#8]-[#6]:2:[#6]:[#16]:1",
+    "4-methoxy-2-nitro-benzyl": "[#6]-[#6]1:[#6]:[#6]:[#6](-[#8]-[#6]):[#6]:[#6]:1-[#7+](-[#8-])=[#8]",
+    "(6-hydroxy-3-oxido-1,3-benz[d]oxathiol-5-yl)methyl": "[#8]=[#16]1-[#6]-[#8]-[#6]2:[#6]-1:[#6]:[#6](-[#6]):[#6](-[#8]):[#6]:2",
+    "2-hydroxy-4-methoxy-5-(methylsulfinyl)benzyl": "[#6]-[#6]1:[#6]:[#6](-[#16](-[#6])=[#8]):[#6](-[#8]-[#6]):[#6]:[#6]:1-[#8]",
+    "n-boc-n-methyl[2-(methylamino)ethyl]carbamoyl-hmb": "[#6]-[#6](-[#6])(-[#8]-[#6](-[#7](-[#6]-[#6]-[#7](-[#6](-[#8]-[#6]1:[#6]:[#6](-[#8]-[#6]):[#6]:[#6]:[#6]:1)=[#8])-[#6])-[#6])=[#8])-[#6]",
+    "9-xanthenyl": "[#6]12-[#6]-[#6]3:[#6](:[#6]:[#6]:[#6]:[#6]:3)-[#8]-[#6]:1:[#6]:[#6]:[#6]:[#6]:2",
+    "cyclopropyldimethylcarbinyl": "[#6]-[#6](-[#6]1-[#6]-[#6]-1)-[#6]",
+    "4,4-dimethoxybenzhydryl": "[#6]-[#8]-[#6]1:[#6]:[#6]:[#6](:[#6]:[#6]:1)-[#6]-[#6]1:[#6]:[#6]:[#6](-[#8]-[#6]):[#6]:[#6]:1",
+    "xan": "[#6]12-[#6]-[#6]3:[#6](:[#6]:[#6]:[#6]:[#6]:3)-[#8]-[#6]:1:[#6]:[#6]:[#6]:[#6]:2",
+    "cpd": "[#6]-[#6](-[#6]1-[#6]-[#6]-1)-[#6]",
+    "mbh": "[#6]-[#8]-[#6]1:[#6]:[#6]:[#6](:[#6]:[#6]:1)-[#6]-[#6]1:[#6]:[#6]:[#6](-[#8]-[#6]):[#6]:[#6]:1",
+    "p-toluenesulfonyl": "[#8]=[#16](-[#6]1:[#6]:[#6]:[#6](-[#6]):[#6]:[#6]:1)=[#8]",
+    "2,2,5,7,8-pentamethylchroman-6-sulfonyl": "[#8]=[#16](-[#6]1:[#6](-[#6]):[#6]2-[#6]-[#6]-[#6](-[#6])(-[#6])-[#8]-[#6]:2:[#6](-[#6]):[#6]:1-[#6])=[#8]",
+    "2,2,4,6,7-pentamethyl-2,3-dihydrobenzofuran-5-sulfonyl": "[#8]=[#16](-[#6]1:[#6](-[#6]):[#6](-[#6]):[#6]2-[#8]-[#6](-[#6])(-[#6])-[#6]-[#6]:2:[#6]:1-[#6])=[#8]",
+    "mesityl-2-sulfonyl": "[#6]-[#6]1:[#6](-[#16](=[#8])(-[#7]-[#6](-[#7])=[#7])=[#8]):[#6](-[#6]):[#6]:[#6](-[#6]):[#6]:1",
+    "4-methoxy-2,3,6-trimethylphenylsulfonyl": "[#8]=[#16](-[#6]1:[#6](-[#6]):[#6]:[#6](-[#8]-[#6]):[#6](-[#6]):[#6]:1-[#6])=[#8]",
+    "1,2-dimethylindole-3-sulfonyl": "[#8]=[#16](-[#6]1:[#6](-[#6]):[#7](-[#6]):[#6]2:[#6]:1:[#6]:[#6]:[#6]:[#6]:2)=[#8]",
+    "w,w-bis-tert-butyloxycarbonyl": "[#6]-[#6](-[#6])(-[#8]-[#6](/[#7]=[#6](/[#7]-[#6](-[#8]-[#6](-[#6])(-[#6])-[#6])=[#8])-[#7])=[#8])-[#6]",
+    "5-dibenzosuberenyl": "[#6]12:[#6]:[#6]:[#6]:[#6]:[#6]:1-[#6]-[#6]-[#6]1-[#6]=[#6]-[#6]=[#6]-[#6]-1=[#6]-2",
+    "5-dibenzosuberyl": "[#6]12:[#6]:[#6]:[#6]:[#6]:[#6]:1-[#6]-[#6]-[#6]1:[#6](:[#6]:[#6]:[#6]:[#6]:1)-[#6]-2",
+    "2-methoxy-5-dibenzosuberyl": "[#6]-[#8]-[#6]1:[#6]:[#6]2-[#6]-[#6]-[#6]3:[#6](-[#6]-[#6]:2:[#6]:[#6]:1):[#6]:[#6]:[#6]:[#6]:3",
+    "nitro": "[#8]=[#7+]-[#8-]",
+    "tos": "[#8]=[#16](-[#6]1:[#6]:[#6]:[#6](-[#6]):[#6]:[#6]:1)=[#8]",
+    "pmc": "[#8]=[#16](-[#6]1:[#6](-[#6]):[#6]2-[#6]-[#6]-[#6](-[#6])(-[#6])-[#8]-[#6]:2:[#6](-[#6]):[#6]:1-[#6])=[#8]",
+    "pbf": "[#8]=[#16](-[#6]1:[#6](-[#6]):[#6](-[#6]):[#6]2-[#8]-[#6](-[#6])(-[#6])-[#6]-[#6]:2:[#6]:1-[#6])=[#8]",
+    "mts": "[#6]-[#6]1:[#6](-[#16](=[#8])(-[#7]-[#6](-[#7])=[#7])=[#8]):[#6](-[#6]):[#6]:[#6](-[#6]):[#6]:1",
+    "mtr": "[#8]=[#16](-[#6]1:[#6](-[#6]):[#6]:[#6](-[#8]-[#6]):[#6](-[#6]):[#6]:1-[#6])=[#8]",
+    "mis": "[#8]=[#16](-[#6]1:[#6](-[#6]):[#7](-[#6]):[#6]2:[#6]:1:[#6]:[#6]:[#6]:[#6]:2)=[#8]",
+    "bis-boc": "[#6]-[#6](-[#6])(-[#8]-[#6](/[#7]=[#6](/[#7]-[#6](-[#8]-[#6](-[#6])(-[#6])-[#6])=[#8])-[#7])=[#8])-[#6]",
+    "suben": "[#6]12:[#6]:[#6]:[#6]:[#6]:[#6]:1-[#6]-[#6]-[#6]1-[#6]=[#6]-[#6]=[#6]-[#6]-1=[#6]-2",
+    "sub": "[#6]12:[#6]:[#6]:[#6]:[#6]:[#6]:1-[#6]-[#6]-[#6]1:[#6](:[#6]:[#6]:[#6]:[#6]:1)-[#6]-2",
+    "mesub": "[#6]-[#8]-[#6]1:[#6]:[#6]2-[#6]-[#6]-[#6]3:[#6](-[#6]-[#6]:2:[#6]:[#6]:1):[#6]:[#6]:[#6]:[#6]:3",
+    "no2": "[#8]=[#7+]-[#8-]",
+    "w,w-bis-benzyloxycarbonyl": "[#8]=[#6](/[#7]=[#6](/[#7]-[#6](-[#8]-[#6]-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1)=[#8])-[#7])-[#8]-[#6]-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1",
+    "w,w-bis-allyloxycarbonyl": "[#8]=[#6](/[#7]=[#6](/[#7]-[#6](-[#8]-[#6]-[#6]=[#6])=[#8])-[#7])-[#8]-[#6]-[#6]=[#6]",
+    "z-small": "[#8]=[#6](/[#7]=[#6](/[#7]-[#6](-[#8]-[#6]-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1)=[#8])-[#7])-[#8]-[#6]-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1",
+    "p-methylbenzyl": "[#6]-[#6]1:[#6]:[#6]:[#6](-[#6]):[#6]:[#6]:1",
+    "p-methoxybenzyl": "[#6]-[#6]1:[#6]:[#6]:[#6](-[#8]-[#6]):[#6]:[#6]:1",
+    "monomethoxytrityl": "[#6]-[#8]-[#6]1:[#6]:[#6]:[#6](-[#6](-[#6]2:[#6]:[#6]:[#6]:[#6]:[#6]:2)-[#6]2:[#6]:[#6]:[#6]:[#6]:[#6]:2):[#6]:[#6]:1",
+    "trimethoxybenzyl": "[#6]-[#6]1:[#6](-[#8]-[#6]):[#6]:[#6](-[#8]-[#6]):[#6]:[#6]:1-[#8]-[#6]",
+    "2,2,4,6,7-pentamethyl-5-dihydrobenzofuranylmethyl": "[#6]-[#6]1:[#6](-[#6]):[#6](-[#6]):[#6]2-[#8]-[#6](-[#6])(-[#6])-[#6]-[#6]:2:[#6]:1-[#6]",
+    "1-adamantyl": "[#6]12-[#6]-[#6]3-[#6]-[#6](-[#6]-1)-[#6]-[#6](-[#6]-3)-[#6]-2",
+    "meb": "[#6]-[#6]1:[#6]:[#6]:[#6](-[#6]):[#6]:[#6]:1",
+    "mob": "[#6]-[#6]1:[#6]:[#6]:[#6](-[#8]-[#6]):[#6]:[#6]:1",
+    "mmt": "[#6]-[#8]-[#6]1:[#6]:[#6]:[#6](-[#6](-[#6]2:[#6]:[#6]:[#6]:[#6]:[#6]:2)-[#6]2:[#6]:[#6]:[#6]:[#6]:[#6]:2):[#6]:[#6]:1",
+    "pmbf": "[#6]-[#6]1:[#6](-[#6]):[#6](-[#6]):[#6]2-[#8]-[#6](-[#6])(-[#6])-[#6]-[#6]:2:[#6]:1-[#6]",
+    "1-ada": "[#6]12-[#6]-[#6]3-[#6]-[#6](-[#6]-1)-[#6]-[#6](-[#6]-3)-[#6]-2",
+    "2-(2,4-dinitrophenyl)ethyl": "[#6]-[#6]-[#6]1:[#6]:[#6]:[#6](-[#7+](-[#8-])=[#8]):[#6]:[#6]:1-[#7+](-[#8-])=[#8]",
+    "9-fluororenylmethoxycarbonyl": "[#8]=[#6]-[#8]-[#6]-[#6]1-[#6]2:[#6](-[#6]3:[#6]-1:[#6]:[#6]:[#6]:[#6]:3):[#6]:[#6]:[#6]:[#6]:2",
+    "dnpe": "[#6]-[#6]-[#6]1:[#6]:[#6]:[#6](-[#7+](-[#8-])=[#8]):[#6]:[#6]:1-[#7+](-[#8-])=[#8]",
+    "acetamidomethyl": "[#6]-[#7]-[#6](-[#6])=[#8]",
+    "phenylacetamidomethyl": "[#6]-[#7]-[#6](-[#6]-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1)=[#8]",
+    "5-tert-butylmercapto": "[#6]-[#6](-[#6])(-[#16])-[#6]",
+    "3-nitro-2-pyridinesulfenyl": "[#16]-[#6]1:[#7]:[#6]:[#6]:[#6]:[#6]:1-[#7+](-[#8-])=[#8]",
+    "2-pyridinesulfenyl": "[#16]-[#6]1:[#7]:[#6]:[#6]:[#6]:[#6]:1",
+    "N-allyloxycarbonyl-N-[2,3,5,6-tetrafluoro-4-(phenylthio)phenyl]]aminomethyl": "[#9]-[#6]1:[#6](-[#9]):[#6](-[#16]-[#6]2:[#6]:[#6]:[#6]:[#6]:[#6]:2):[#6](-[#9]):[#6](-[#9]):[#6]:1-[#7](-[#6](-[#8]-[#6]-[#6]=[#6])=[#8])-[#6]",
+    "o-nitrobenzyl": "[#6]-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1-[#7+](-[#8-])=[#8]",
+    "4-picolyl": "[#6]-[#6]1:[#6]:[#6]:[#7]:[#6]:[#6]:1",
+    "ninhydrin": "[#8]=[#6]1-[#6]2(-[#16]-[#6]-[#6](-[#6](-[#8])=[#8])-[#7]-2)-[#6](-[#6]2:[#6]-1:[#6]:[#6]:[#6]:[#6]:2)=[#8]",
+    "acm": "[#6]-[#7]-[#6](-[#6])=[#8]",
+    "phacm": "[#6]-[#7]-[#6](-[#6]-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1)=[#8]",
+    "sbu": "[#6]-[#6](-[#6])(-[#16])-[#6]",
+    "npys": "[#16]-[#6]1:[#7]:[#6]:[#6]:[#6]:[#6]:1-[#7+](-[#8-])=[#8]",
+    "s-pyr": "[#16]-[#6]1:[#7]:[#6]:[#6]:[#6]:[#6]:1",
+    "fsam": "[#9]-[#6]1:[#6](-[#9]):[#6](-[#16]-[#6]2:[#6]:[#6]:[#6]:[#6]:[#6]:2):[#6](-[#9]):[#6](-[#9]):[#6]:1-[#7](-[#6](-[#8]-[#6]-[#6]=[#6])=[#8])-[#6]",
+    "onb": "[#6]-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1-[#7+](-[#8-])=[#8]",
+    "nin": "[#8]=[#6]1-[#6]2(-[#16]-[#6]-[#6](-[#6](-[#8])=[#8])-[#7]-2)-[#6](-[#6]2:[#6]-1:[#6]:[#6]:[#6]:[#6]:2)=[#8]",
+    "n-tosyl": "[#8]=[#16](-[#7]1:[#6]:[#6]:[#7]:[#6]:1)(-[#6]1:[#6]:[#6]:[#6](-[#6]):[#6]:[#6]:1)=[#8]",
+    "n-trityl": "[#7]1(-[#6](-[#6]2:[#6]:[#6]:[#6]:[#6]:[#6]:2)(-[#6]2:[#6]:[#6]:[#6]:[#6]:[#6]:2)-[#6]2:[#6]:[#6]:[#6]:[#6]:[#6]:2):[#6]:[#6]:[#7]:[#6]:1",
+    "n-monomethoxytrityl": "[#6]-[#8]-[#6]1:[#6]:[#6]:[#6](:[#6]:[#6]:1)-[#6](-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1)(-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1)-[#7]1:[#6]:[#6]:[#7]:[#6]:1",
+    "n-methyltrityl": "[#6]-[#6]1:[#6]:[#6]:[#6](:[#6]:[#6]:1)-[#6](-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1)(-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1)-[#7]1:[#6]:[#6]:[#7]:[#6]:1",
+    "n-tert-butyloxycarbonyl": "[#8]=[#6](-[#8]-[#6](-[#6])(-[#6])-[#6])-[#7]1:[#6]:[#6]:[#7]:[#6]:1",
+    "n-2,4-dimethylpent-3-yloxycarbonyl": "[#8]=[#6](-[#8]-[#6](-[#6](-[#6])-[#6])-[#6](-[#6])-[#6])-[#7]1:[#6]:[#6]:[#7]:[#6]:1",
+    "n-benzyloxymethyl": "[#7+]1(-[#6]-[#8]-[#6]-[#6]2:[#6]:[#6]:[#6]:[#6]:[#6]:2):[#6]:[#7H]:[#6]:[#6]:1",
+    "n-tert-butoxymethyl": "[#6]-[#6](-[#6])(-[#6])-[#8]-[#6]-[#7+]1:[#6]:[#7H]:[#6]:[#6]:1",
+    "ntos": "[#8]=[#16](-[#7]1:[#6]:[#6]:[#7]:[#6]:1)(-[#6]1:[#6]:[#6]:[#6](-[#6]):[#6]:[#6]:1)=[#8]",
+    "ntrt": "[#7]1(-[#6](-[#6]2:[#6]:[#6]:[#6]:[#6]:[#6]:2)(-[#6]2:[#6]:[#6]:[#6]:[#6]:[#6]:2)-[#6]2:[#6]:[#6]:[#6]:[#6]:[#6]:2):[#6]:[#6]:[#7]:[#6]:1",
+    "nmtt": "[#6]-[#8]-[#6]1:[#6]:[#6]:[#6](:[#6]:[#6]:1)-[#6](-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1)(-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1)-[#7]1:[#6]:[#6]:[#7]:[#6]:1",
+    "nmmt": "[#6]-[#6]1:[#6]:[#6]:[#6](:[#6]:[#6]:1)-[#6](-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1)(-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1)-[#7]1:[#6]:[#6]:[#7]:[#6]:1",
+    "nboc": "[#8]=[#6](-[#8]-[#6](-[#6])(-[#6])-[#6])-[#7]1:[#6]:[#6]:[#7]:[#6]:1",
+    "ndoc": "[#8]=[#6](-[#8]-[#6](-[#6](-[#6])-[#6])-[#6](-[#6])-[#6])-[#7]1:[#6]:[#6]:[#7]:[#6]:1",
+    "nbom": "[#7+]1(-[#6]-[#8]-[#6]-[#6]2:[#6]:[#6]:[#6]:[#6]:[#6]:2):[#6]:[#7H]:[#6]:[#6]:1",
+    "nbum": "[#6]-[#6](-[#6])(-[#6])-[#8]-[#6]-[#7+]1:[#6]:[#7H]:[#6]:[#6]:1",
+    "N-9-fluorenylmethoxycarbonyl": "[#8]=[#6](-[#8]-[#6]1-[#6]2:[#6]:[#6]:[#6]:[#6]:[#6]:2-[#6]2:[#6]-1:[#6]:[#6]:[#6]:[#6]:2)-[#7]1:[#6]:[#6]:[#7]:[#6]:1",
+    "N-2,6-dimethoxybenzoyl": "[#8]=[#6](-[#6]1:[#6](-[#8]-[#6]):[#6]:[#6]:[#6]:[#6]:1-[#8]-[#6])-[#7]1:[#6]:[#6]:[#7]:[#6]:1",
+    "dmbz": "[#8]=[#6](-[#6]1:[#6](-[#8]-[#6]):[#6]:[#6]:[#6]:[#6]:1-[#8]-[#6])-[#7]1:[#6]:[#6]:[#7]:[#6]:1",
+    "N-2,4-dinitrophenyl": "[#8]=[#6](-[#6]1:[#6](-[#7+](-[#8-])=[#8]):[#6]:[#6](-[#7+](-[#8-])=[#8]):[#6]:[#6]:1)-[#7]1:[#6]:[#6]:[#7]:[#6]:1",
+    "dnp": "[#8]=[#6](-[#6]1:[#6](-[#7+](-[#8-])=[#8]):[#6]:[#6](-[#7+](-[#8-])=[#8]):[#6]:[#6]:1)-[#7]1:[#6]:[#6]:[#7]:[#6]:1",
+    "cyclohexyl;": "[#6]1-[#6]-[#6]-[#6]-[#6]-[#6]-1",
+    "tert-butyldimethylsilyl": "[#6]-[Si](-[#6](-[#6])(-[#6])-[#6])-[#6]",
+    "tbdms": "[#6]-[Si](-[#6](-[#6])(-[#6])-[#6])-[#6]",
+    "tert-butyldiphenylsilyl": "[#6]-[#6](-[Si](-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1)-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1)(-[#6])-[#6]",
+    "propargyloxycarbonyl": "[#6]#[#6]-[#8]-[#6](-[#6])=[#8]",
+    "tbdps": "[#6]-[#6](-[Si](-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1)-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1)(-[#6])-[#6]",
+    "2,6-dichlorobenzyl": "[#6]-[#6]1:[#6](-[#17]):[#6]:[#6]:[#6]:[#6]:1-[#17]",
+    "2-bromobenzyl": "[#6]-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1-[#35]",
+    "2-bromobenzyloxycarbonyl": "[#8]=[#6]-[#8]-[#6]-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1-[#35]",
+    "3-pentyl": "[#6]-[#6]-[#6]-[#6]-[#6]",
+    "dcb": "[#6]-[#6]1:[#6](-[#17]):[#6]:[#6]:[#6]:[#6]:1-[#17]",
+    "brbn": "[#6]-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1-[#35]",
+    "brz": "[#8]=[#6]-[#8]-[#6]-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1-[#35]",
+    "pen": "[#6]-[#6]-[#6]-[#6]-[#6]",
+    "tegb": "[#6]-[#6]1:[#6]:[#6]:[#6](-[#8]-[#6]-[#6]-[#8]-[#6]-[#6]-[#8]-[#6]-[#6]-[#8]-[#6]):[#6]:[#6]:1",
+    "boc-n-methyl-n-[2-(methylamino)ethyl]carbamoyl": "[#8]=[#6](-[#6](-[#8]-[#6](-[#6])(-[#6])-[#6])=[#8])-[#7](-[#6])-[#6]-[#6]-[#7]-[#6]",
+    "boc-nmec": "[#8]=[#6](-[#6](-[#8]-[#6](-[#6])(-[#6])-[#6])=[#8])-[#7](-[#6])-[#6]-[#6]-[#7]-[#6]",
+    "formyl": "[#6H]=[#8]",
+    "cyclohexyloxycarbonyl": "[#8]=[#6]-[#8]-[#6]1-[#6]-[#6]-[#6]-[#6]-[#6]-1",
+    "for": "[#6]=[#8]",
+    "hoc": "[#8]=[#6]-[#8]-[#6]1-[#6]-[#6]-[#6]-[#6]-[#6]-1",
+    "cyclopropane": "[#6]1-[#6]-[#6]-1",
+    "spiropentane": "[#6]1-[#6]-[#6]-12-[#6]-[#6]-2",
+    "cyclobutane": "[#6]1-[#6]-[#6]-[#6]-1",
+    "cyclopentane": "[#6]1-[#6]-[#6]-[#6]-[#6]-1",
+    "furan": "[#6]1:[#6]:[#6]:[#6]:[#8]:1",
+    "thiophene": "[#6]1:[#6]:[#6]:[#6]:[#16]:1",
+    "pyrrole": "[#7H]1:[#6]:[#6]:[#6]:[#6]:1",
+    "2H-pyrrole": "[#7]1=[#6]-[#6]=[#6]-[#6]-1",
+    "3H-pyrrole": "[#7]1=[#6]-[#6]-[#6]=[#6]-1",
+    "pyrazole": "[#7H]1:[#7]:[#6]:[#6]:[#6]:1",
+    "2H-imidazole": "[#6]1-[#7]=[#6]-[#6]=[#7]-1",
+    "1,2,3-triazole": "[#7H]1:[#7]:[#7]:[#6]:[#6]:1",
+    "1,2,4-triazole": "[#6]1:[#7]:[#6]:[#7]:[#7H]:1",
+    "1,2-dithiole": "[#16]1-[#16]-[#6]=[#6]-[#6]-1",
+    "1,3-dithiole": "[#16]1-[#6]-[#16]-[#6]=[#6]-1",
+    "3H-1,2-oxathiole": "[#8]1-[#16]-[#6]-[#6]=[#6]-1",
+    "isoxazole": "[#8]1:[#7]:[#6]:[#6]:[#6]:1",
+    "oxazole": "[#8]1:[#6]:[#7]:[#6]:[#6]:1",
+    "thiazole": "[#16]1:[#6]:[#7]:[#6]:[#6]:1",
+    "isothiazole": "[#16]1:[#7]:[#6]:[#6]:[#6]:1",
+    "1,2,3-oxadiazole": "[#8]1:[#7]:[#7]:[#6]:[#6]:1",
+    "1,2,4-oxadiazole": "[#8]1:[#7]:[#6]:[#7]:[#6]:1",
+    "1,2,5-oxadiazole": "[#8]1:[#7]:[#6]:[#6]:[#7]:1",
+    "1,3,4-oxadiazole": "[#8]1:[#6]:[#7]:[#7]:[#6]:1",
+    "1,2,3,4-oxatriazole": "[#8]1:[#7]:[#7]:[#7]:[#6]:1",
+    "1,2,3,5-oxatriazole": "[#8]1:[#7]:[#7]:[#6]:[#7]:1",
+    "3H-1,2,3-dioxazole": "[#8]1-[#8]-[#7]-[#6]=[#6]-1",
+    "1,2,4-dioxazole": "[#8]1-[#8]-[#6]=[#7]-[#6]-1",
+    "1,3,2-dioxazole": "[#8]1-[#7]-[#8]-[#6]=[#6]-1",
+    "1,3,4-dioxazole": "[#8]1-[#6]-[#8]-[#7]=[#6]-1",
+    "5H-1,2,5-oxathiazole": "[#8]1-[#16]-[#6]=[#6]-[#7]-1",
+    "1,3-oxathiole": "[#8]1-[#6]-[#16]-[#6]=[#6]-1",
+    "benzene": "[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1",
+    "cyclohexane": "[#6]1-[#6]-[#6]-[#6]-[#6]-[#6]-1",
+    "2H-pyran": "[#6]1-[#6]=[#6]-[#6]=[#6]-[#8]-1",
+    "4H-pyran": "[#6]1=[#6]-[#6]-[#6]=[#6]-[#8]-1",
+    "2H-pyran-2-one": "[#8]=[#6]1:[#6]:[#6]:[#6]:[#6]:[#8]:1",
+    "4H-pyran-4-one": "[#8]=[#6]1:[#6]:[#6]:[#8]:[#6]:[#6]:1",
+    "1,2-dioxin": "[#8]1-[#8]-[#6]=[#6]-[#6]=[#6]-1",
+    "1,3-dioxin": "[#8]1-[#6]-[#8]-[#6]=[#6]-[#6]-1",
+    "pyridine": "[#6]1:[#6]:[#6]:[#7]:[#6]:[#6]:1",
+    "pyridazine": "[#6]1:[#7]:[#7]:[#6]:[#6]:[#6]:1",
+    "pyrimidine": "[#6]1:[#7]:[#6]:[#6]:[#6]:[#7]:1",
+    "pyrazine": "[#6]1:[#7]:[#6]:[#6]:[#7]:[#6]:1",
+    "piperazine": "[#7]1-[#6]-[#6]-[#7]-[#6]-[#6]-1",
+    "1,3,5-triazine": "[#7]1:[#6]:[#7]:[#6]:[#7]:[#6]:1",
+    "1,2,4-triazine": "[#7]1:[#7]:[#6]:[#7]:[#6]:[#6]:1",
+    "1,2,3-triazine": "[#7]1:[#7]:[#7]:[#6]:[#6]:[#6]:1",
+    "4H-1,2-Oxazine": "[#8]1-[#7]=[#6]-[#6]-[#6]=[#6]-1",
+    "2H-1,3-Oxazine": "[#8]1-[#6]-[#7]=[#6]-[#6]=[#6]-1",
+    "6H-1,3-Oxazine": "[#8]1-[#6]=[#7]-[#6]=[#6]-[#6]-1",
+    "6H-1,2-Oxazine": "[#8]1-[#7]=[#6]-[#6]=[#6]-[#6]-1",
+    "1,4-Oxazine": "[#8]1-[#6]=[#6]-[#7]=[#6]-[#6]-1",
+    "2H-1,2-Oxazine": "[#8]1-[#7]-[#6]=[#6]-[#6]=[#6]-1",
+    "4H-1,4-Oxazine": "[#8]1-[#6]=[#6]-[#7]-[#6]=[#6]-1",
+    "1,2,5-Oxathiazine": "[#8]1-[#16]-[#6]=[#6]-[#7]=[#6]-1",
+    "1,2,6-Oxathiazine": "[#8]1-[#16]-[#6]=[#6]-[#6]=[#7]-1",
+    "1,2,4-Oxadiazine": "[#8]1-[#7]-[#6]=[#7]-[#6]=[#6]-1",
+    "1,3,5-Oxadiazine": "[#8]1-[#6]=[#7]-[#6]=[#7]-[#6]-1",
+    "morpholine": "[#7]1-[#6]-[#6]-[#8]-[#6]-[#6]-1",
+    "azepine": "[#7]1-[#6]=[#6]-[#6]=[#6]-[#6]=[#6]-1",
+    "oxepin": "[#8]1-[#6]=[#6]-[#6]=[#6]-[#6]=[#6]-1",
+    "thiepin": "[#16]1-[#6]=[#6]-[#6]=[#6]-[#6]=[#6]-1",
+    "4H-1,2-diazepine": "[#7]1=[#6]-[#6]=[#6]-[#6]-[#6]=[#7]-1",
+    "indene": "[#6]12:[#6](-[#6]-[#6]=[#6]-1):[#6]:[#6]:[#6]:[#6]:2",
+    "2H-indene": "[#6]12=[#6]-[#6]-[#6]=[#6]:1:[#6]:[#6]:[#6]:[#6]:2",
+    "benzofuran": "[#6]12:[#6]:[#6]:[#6]:[#6]:[#6]:1:[#6]:[#6]:[#8]:2",
+    "isobenzofuran": "[#6]12:[#6]:[#8]:[#6]:[#6]:1:[#6]:[#6]:[#6]:[#6]:2",
+    "benzo[b]thiophene": "[#6]12:[#6]:[#6]:[#6]:[#6]:[#6]:1:[#6]:[#6]:[#16]:2",
+    "benzo[c]thiophene": "[#6]12:[#6]:[#16]:[#6]:[#6]:1:[#6]:[#6]:[#6]:[#6]:2",
+    "indole": "[#6]12:[#6]:[#6]:[#6]:[#6]:[#6]:1:[#6]:[#6]:[#7H]:2",
+    "3H-indole": "[#6]12:[#6](-[#7]=[#6]-[#6]-1):[#6]:[#6]:[#6]:[#6]:2",
+    "1H-indole": "[#6]12:[#6](:[#7H]:[#6]:[#6]:1):[#6]:[#6]:[#6]:[#6]:2",
+    "cyclopenta[b]pyridine": "[#6]12:[#6]:[#6]:[#6]:[#6]-1:[#6]:[#6]:[#6]:[#7H]:2",
+    "pyrano[3,4-b]-pyrrole": "[#6]12:[#6]:[#8]:[#6]:[#6]:[#6]-1:[#6]:[#6]:[#7]:2",
+    "indazole": "[#6]12:[#6](:[#7H]:[#7]:[#6]:1):[#6]:[#6]:[#6]:[#6]:2",
+    "benzisoxazole": "[#6]12:[#7]:[#8]:[#6]:[#6]:1:[#6]:[#6]:[#6]:[#6]:2",
+    "benzoxazole": "[#6]12:[#6]:[#6]:[#6]:[#6]:[#6]:1:[#8]:[#6]:[#7]:2",
+    "2,1-benzisoxazole": "[#6]12:[#6]:[#8]:[#7]:[#6]:1:[#6]:[#6]:[#6]:[#6]:2",
+    "naphthalene": "[#6]12:[#6]:[#6]:[#6]:[#6]:[#6]:1:[#6]:[#6]:[#6]:[#6]:2",
+    "1,2,3,4-tetrahydronaphthalene": "[#6]12:[#6](-[#6]-[#6]-[#6]-[#6]-1):[#6]:[#6]:[#6]:[#6]:2",
+    "octahydronaphthalene": "[#6]12-[#6]-[#6]-[#6]-[#6]-[#6]-1=[#6]-[#6]-[#6]-[#6]-2",
+    "2H-1-benzopyran": "[#6]12:[#6]:[#6]:[#6]:[#6]:[#6]:1-[#8]-[#6]-[#6]=[#6]-2",
+    "2H-1-benzopyran-2-one": "[#8]=[#6]1:[#6]:[#6]:[#6]2:[#6]:[#6]:[#6]:[#6]:[#6]:2:[#8]:1",
+    "4H-1-benzopyran-4-one": "[#8]=[#6]1:[#6]:[#6]:[#8]:[#6]2:[#6]:[#6]:[#6]:[#6]:[#6]:1:2",
+    "1H-2-benzopyran-1-one": "[#8]=[#6]1:[#6]2:[#6]:[#6]:[#6]:[#6]:[#6]:2:[#6]:[#6]:[#8]:1",
+    "3H-2-benzopyran-1-one": "[#8]=[#6]1-[#6]2:[#6]:[#6]:[#6]:[#6]:[#6]:2-[#6]-[#6]-[#8]-1",
+    "quinoline": "[#6]12:[#6]:[#6]:[#6]:[#6]:[#6]:1:[#7]:[#6]:[#6]:[#6]:2",
+    "isoquinoline": "[#6]12:[#6](:[#6]:[#7]:[#6]:[#6]:1):[#6]:[#6]:[#6]:[#6]:2",
+    "cinnoline": "[#6]12:[#6]:[#6]:[#7]:[#7]:[#6]:1:[#6]:[#6]:[#6]:[#6]:2",
+    "quinazoline": "[#6]12:[#6]:[#7]:[#6]:[#7]:[#6]:1:[#6]:[#6]:[#6]:[#6]:2",
+    "1,8-napthyhridine": "[#6]1:[#6]:[#6]2:[#6](:[#7]:[#6]:1):[#7]:[#6]:[#6]:[#6]:2",
+    "1,7-napththyridine": "[#6]1:[#6]:[#6]2:[#6](:[#6]:[#7]:[#6]:[#6]:2):[#7]:[#6]:1",
+    "1,5-napththridine": "[#6]1:[#6]:[#6]2:[#6](:[#6]:[#6]:[#6]:[#7]:2):[#7]:[#6]:1",
+    "1,6-napthyridine": "[#6]1:[#6]:[#6]2:[#6](:[#6]:[#6]:[#7]:[#6]:2):[#7]:[#6]:1",
+    "2H-1,3-benzoxazine": "[#6]12:[#6]:[#6]:[#6]:[#6]:[#6]:1-[#8]-[#6]-[#7]=[#6]-2",
+    "2H-1,4-benzoxazine": "[#6]12:[#6]:[#6]:[#6]:[#6]:[#6]:1-[#8]-[#6]-[#6]=[#7]-2",
+    "1H-2,3-benzoxazine": "[#6]12:[#6]:[#6]:[#6]:[#6]:[#6]:1-[#6]-[#8]-[#7]=[#6]-2",
+    "4H-3,1-benzoxazine": "[#6]12:[#6]:[#6]:[#6]:[#6]:[#6]:1-[#7]=[#6]-[#8]-[#6]-2",
+    "2H-1,2-benzoxazine": "[#6]12:[#6]:[#6]:[#6]:[#6]:[#6]:1-[#8]-[#7]-[#6]=[#6]-2",
+    "4H-1,3-benzoxazine": "[#6]12:[#6]:[#6]:[#6]:[#6]:[#6]:1-[#8]-[#6]=[#7]-[#6]-2",
+    "anthracene": "[#6]12:[#6]:[#6]:[#6]:[#6]:[#6]:1:[#6]:[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1:[#6]:2",
+    "phenanthrene": "[#6]12:[#6]:[#6]:[#6]:[#6]:[#6]:1:[#6]:[#6]:[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:2:1",
+    "phenalene": "[#6]12:[#6]3:[#6](-[#6]-[#6]=[#6]-1):[#6]:[#6]:[#6]:[#6]:3:[#6]:[#6]:[#6]:2",
+    "fluorene": "[#6]12-[#6]-[#6]3:[#6](:[#6]:[#6]:[#6]:[#6]:3)-[#6]:1:[#6]:[#6]:[#6]:[#6]:2",
+    "carbazole": "[#6]12:[#7H]:[#6]3:[#6](:[#6]:[#6]:[#6]:[#6]:3):[#6]:1:[#6]:[#6]:[#6]:[#6]:2",
+    "xanthene": "[#6]12-[#6]-[#6]3:[#6](:[#6]:[#6]:[#6]:[#6]:3)-[#8]-[#6]:1:[#6]:[#6]:[#6]:[#6]:2",
+    "acridine": "[#6]12:[#7]:[#6]3:[#6]:[#6]:[#6]:[#6]:[#6]:3:[#6]:[#6]:1:[#6]:[#6]:[#6]:[#6]:2",
+    "norpinane": "[#6]12-[#6]-[#6](-[#6]-[#6]-[#6]-1)-[#6]-2",
+    "7H-purine": "[#6]12:[#7]:[#6]:[#7]:[#6]:[#6]:1:[#7H]:[#6]:[#7]:2",
+    "steroid_ring_system": "[#6]12-[#6]-[#6]-[#6]-[#6]-[#6]-1-[#6]1-[#6](-[#6]3-[#6]-[#6]-[#6]-[#6]-3-[#6]-[#6]-1)-[#6]-[#6]-2",
+    "imidazole": "[#6]1:[#6]:[#7]:[#6]:[#7H]:1",
+    "thiazol-2-amine": "[#7]-[#6]1:[#7]:[#6]:[#6]:[#16]:1",
+    "tetrazole": "[#6]1:[#7]:[#7]:[#7]:[#7H]:1",
+    "cytosine": "[#8]=[#6]1:[#7]:[#6](-[#7]):[#6]:[#6]:[#7H]:1",
+    "adenine": "[#7]-[#6]1:[#7]:[#6]:[#7]:[#6]2:[#6]:1:[#7]:[#6]:[#7H]:2",
+    "5-methylindole": "[#6]-[#6]1:[#6]:[#6]:[#6]2:[#6](:[#6]:[#6]:[#7H]:2):[#6]:1",
+    "isocaffeine": "[#8]=[#6]1:[#7](-[#6]):[#6](:[#6]2:[#6](:[#7H]:1):[#7H]:[#6]:[#7]:2)=[#8]",
+    "tetrazolethiol": "[#16]-[#7]1:[#7]:[#7]:[#7]:[#6]:1",
+    "3-methylisoxazole": "[#6]1:[#6]:[#6]:[#7]:[#8]:1",
+    "1-methylimidazole": "[#6]-[#7]1:[#6]:[#7]:[#6]:[#6]:1",
+    "2-methylimidazole": "[#6]-[#6]1:[#7]:[#6]:[#6]:[#7H]:1",
+    "guanine": "[#7]-[#6]1:[#7H]:[#6](:[#6]2:[#6](:[#7]:1):[#7H]:[#6]:[#7]:2)=[#8]",
+    "tosufloxacin": "[#7]-[#6]1:[#6](-[#9]):[#6]:[#6]2:[#6](:[#7H]:[#6]:[#6](-[#6](-[#8])=[#8]):[#6]:2=[#8]):[#7]:1",
+    "acetamido": "[#8]=[#6](-[#7])-[#6]",
+    "acetoacetyl": "[#8]=[#6](-[#6])-[#6]-[#6](=[#8])-[#8]",
+    "acetyl": "[#6](-[#6])=[#8]",
+    "acryloyl": "[#6]=[#6]-[#6](-[#6])=[#8]",
+    "alanyl": "[#7]-[#6H](-[#6])-[#6](-[#6])=[#8]",
+    "beta-alanyl": "[#7]-[#6]-[#6]-[#6](-[#6])=[#8]",
+    "allylidene": "[#6H]-[#6]=[#6]",
+    "amidino": "[#7]-[#6]=[#7]",
+    "amino": "[#7]",
+    "amyl": "[#6H2]-[#6]-[#6]-[#6]-[#6]",
+    "anilino": "[#7]-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1",
+    "anisidino": "[#7]-[#6]1:[#6]:[#6]:[#6](-[#8]-[#6]):[#6]:[#6]:1",
+    "anthranoyl": "[#7]-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1-[#6](-[#6])=[#8]",
+    "arsino": "[AsH3]",
+    "azelaoyl": "[#8]=[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]=[#8]",
+    "azido": "[#7]=[#7+]=[#7-]",
+    "azo": "[#6]/[#7]=[#7]/[#6]",
+    "azoxy": "[#6]/[#7]=[#7+](\\[#8-])-[#6]",
+    "benzal": "[#6H]-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1",
+    "benzamido": "[#8]=[#6](-[#7])-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1",
+    "benzhydrol": "[#8]-[#6](-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1)-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1",
+    "benzoxy": "[#8]-[#6]-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1",
+    "benzoyl": "[#8]=[#6]-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1",
+    "benzylidene": "[#6H]-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1",
+    "benzylidyne": "[#6]-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1",
+    "biphenylyl": "[#6]1(-[#6]2:[#6]:[#6]:[#6]:[#6]:[#6]:2):[#6]:[#6]:[#6]:[#6]:[#6]:1",
+    "biphenylene": "[#6]12=[#6]3:[#6]:[#6]:[#6]:[#6]:[#6]:3=[#6]:1:[#6]:[#6]:[#6]:[#6]:2",
+    "butoxy": "[#8]-[#6]-[#6]-[#6]-[#6]",
+    "sec-butoxy": "[#8]-[#6](-[#6])-[#6]-[#6]",
+    "tert-butoxy": "[#8]-[#6](-[#6])(-[#6])-[#6]",
+    "butyl": "[#6H2]-[#6]-[#6]-[#6]",
+    "sec-butyl": "[#6]-[#6]-[#6H]-[#6]",
+    "butyryl": "[#8]=[#6]-[#6]-[#6]-[#6]",
+    "caproyl": "[#6]-[#6]-[#6]-[#6]-[#6]-[#6]=[#8]",
+    "capryl": "[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]",
+    "capryloyl": "[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]=[#8]",
+    "carbamido": "[#6](=[#8])(-[#7])-[#7]",
+    "carbamoyl": "[#7]-[#6]=[#8]",
+    "carbamyl": "[#7]-[#6]=[#8]",
+    "carbazoyl": "[#7]-[#7]-[#6]=[#8]",
+    "carbethoxy": "[#8]=[#6]-[#8]-[#6]-[#6]",
+    "carbonyl": "[CX3]=[OX1]",
+    "carboxy": "[#8]=[#6]-[#8]",
+    "cetyl": "[#6H2]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]",
+    "chloroformyl": "[#8]=[#6]-[#17]",
+    "cinnamoyl": "[#8]=[#6]-[#6]=[#6]-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1",
+    "cinnamyl": "[#6H2]-[#6]=[#6]-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1",
+    "cinnamylidene": "[#6H]-[#6]=[#6]-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1",
+    "cresyl": "[#8]-[#6]1:[#6]:[#6]:[#6](-[#6]):[#6]:[#6]:1",
+    "crotonoyl": "[#6]/[#6]=[#6]/[#6]=[#8]",
+    "crotyl": "[#6H2]/[#6]=[#6]/[#6]",
+    "cyanamido": "[#7H]-[#6]#[#7]",
+    "cyanato": "[#8]-[#6]#[#7]",
+    "cyano": "[#6]#[#7]",
+    "decanedioyl": "[#8]=[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]=[#8]",
+    "decanoyl": "[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]=[#8]",
+    "diazo": "[#7+]=[#7-]",
+    "diazoamino": "[#7]=[#7]-[#7]",
+    "disilanyl": "[SiH2]-[SiH3]",
+    "disiloxanyloxy": "[#8]-[SiH2]-[#8]-[SiH3]",
+    "disulfinyl": "[#8]=[#16]-[#16]=[#8]",
+    "dithio": "[#16]-[#16]",
+    "enanthoyl": "[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]=[#8]",
+    "epoxy": "[#8]",
+    "ethenyl": "[#6H]=[#6]",
+    "ethynyl": "[#6]#[#6]",
+    "ethoxy": "[#8]-[#6]-[#6]",
+    "ethylene": "[#6]=[#6]",
+    "ethylidene": "[#6H]-[#6]",
+    "ethylthio": "[#16]-[#6]-[#6]",
+    "formamido": "[#8]=[#6]-[#7H]",
+    "furmaroyl": "[#8]=[#6]-[#8]",
+    "furfuryl": "[#6H2]-[#6]1:[#6]:[#6]:[#6]:[#8]:1",
+    "furfurylidene": "[#6H]-[#6]1:[#6]:[#6]:[#6]:[#8]:1",
+    "glutamoyl": "[#7]-[#6@@H](-[#6]-[#6]-[#6]=[#8])-[#6]=[#8]",
+    "glutaryl": "[#8]=[#6]-[#6]-[#6]-[#6]-[#6]=[#8]",
+    "glycylamino": "[#7H]-[#6](-[#6]-[#7])=[#8]",
+    "glycoloyl": "[#8]-[#6]-[#6]=[#8]",
+    "glycyl": "[#7]-[#6]-[#6]=[#8]",
+    "glyoxyoyl": "[#8]=[#6]-[#6]=[#8]",
+    "guanidino": "[#7H]-[#6](-[#7])=[#7]",
+    "guanyl": "[#7]=[#6]-[#7]",
+    "heptadecanoyl": "[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]=[#8]",
+    "heptanamido": "[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6](-[#7H])=[#8]",
+    "heptanoyl": "[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]=[#8].[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6](-[#7H])=[#8]",
+    "hexadecanoyl": "[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]=[#8].[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]=[#8].[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6](-[#7H])=[#8]",
+    "hexamethylene": "[#6]-[#6]-[#6]-[#6]-[#6]-[#6]",
+    "hexanedioyl": "[#8]=[#6]-[#6]-[#6]-[#6]-[#6]-[#6]=[#8]",
+    "hippuryl": "[#6H2]-[#6]-[#7]-[#6](-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1)=[#8]",
+    "hydrazino": "[#7]-[#7H]",
+    "hydrazo": "[#7]-[#7]",
+    "hydrocinnamoyl": "[#8]=[#6]-[#6]-[#6]-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1",
+    "hydroperoxy": "[#8]-[#8]",
+    "hydroxyamino": "[#7H]-[#8]",
+    "imino": "[#7H]",
+    "iodoso": "[#53]=[#8]",
+    "iodyl": "[#8]=[#53]=[#8]",
+    "isoamyl": "[#6H2]-[#6]-[#6](-[#6])-[#6]",
+    "isobutenyl": "[#6H]=[#6](-[#6])-[#6]",
+    "isobutoxy": "[#8]-[#6]-[#6](-[#6])-[#6]",
+    "isobutyl": "[#6H2]-[#6](-[#6])-[#6]",
+    "isobutylidene": "[#6H]-[#6](-[#6])-[#6]",
+    "isobutyryl": "[#8]=[#6]-[#6](-[#6])-[#6]",
+    "isocyanato": "[#7]=[#6]=[#8]",
+    "isocyano": "[#7+]#[#6-]",
+    "isohexyl": "[#6H2]-[#6]-[#6]-[#6](-[#6])-[#6]",
+    "isoleucyl": "[#7]-[#6@@H](-[#6@@H](-[#6])-[#6]-[#6])-[#6]=[#8]",
+    "isonitroso": "[#7]-[#8]",
+    "isopentyl": "[#6H2]-[#6]-[#6](-[#6])-[#6]",
+    "isopentylidene": "[#6H]-[#6]-[#6](-[#6])-[#6]",
+    "isopropenyl": "[#6]=[#6]-[#6]",
+    "isopropoxy": "[#8]-[#6](-[#6])-[#6]",
+    "isopropyl": "[#6]-[#6H]-[#6]",
+    "isopropylidene": "[#6]-[#6]-[#6]",
+    "isothiocynato": "[#7]=[#6]=[#16]",
+    "isovaleryl": "[#8]=[#6]-[#6]-[#6](-[#6])-[#6]",
+    "lactoyl": "[#8]-[#6](-[#6])-[#6]=[#8]",
+    "lauroyl": "[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]=[#8]",
+    "lauryl": "[#6H2]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]",
+    "leucyl": "[#7]-[#6@@H](-[#6]-[#6](-[#6])-[#6])-[#6]=[#8]",
+    "levulinoyl": "[#8]=[#6](-[#6])-[#6]-[#6]-[#6]=[#8]",
+    "malonyl": "[#8]=[#6]-[#6]-[#6]=[#8]",
+    "mandeloyl": "[#8]-[#6](-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1)-[#6]=[#8]",
+    "mercapto": "[#16H]",
+    "mesityl": "[#6]-[#6]1:[#6]:[#6](-[#6]):[#6]:[#6](-[#6]):[#6]:1",
+    "methacryloyl": "[#6]-[#6](-[#6]=[#8])=[#6]",
+    "methallyl": "[#6H2]-[#6](-[#6])=[#6]",
+    "methionyl": "[#7]-[#6@@H](-[#6]-[#6]-[#16]-[#6])-[#6]=[#8]",
+    "methoxy": "[#8]-[#6]",
+    "methylene": "[#6H2]",
+    "methylthio": "[#16]-[#6]",
+    "myristoyl": "[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]=[#8]",
+    "myristyl": "[#6H2]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]",
+    "naphthyl": "[#6]12:[#6]:[#6]:[#6]:[#6]:[#6]:1:[#6]:[#6]:[#6]:[#6]:2",
+    "naphthylene": "[#6]12:[#6]:[#6]:[#6]:[#6]:[#6]:1:[#6]:[#6]:[#6]:[#6]:2",
+    "neopentyl": "[#6H2]-[#6](-[#6])(-[#6])-[#6]",
+    "nitramino": "[#7H]-[#7+](-[#8-])=[#8]",
+    "nitrosamino": "[#7H]-[#7]=[#8]",
+    "nitroso": "[#7]=[#8]",
+    "nonanoyl": "[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]=[#8]",
+    "oleoyl": "[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]/[#6]=[#6]\\[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]=[#8]",
+    "oxalyl": "[#8]=[#6]-[#6]=[#8]",
+    "oxo": "[#8]",
+    "palmitoyl": "[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]=[#8]",
+    "pentamethylene": "[#8]=[#6]1-[#6](-[#6]=[#6])-[#6@H]2-[#16]-[#6]-[#6]-[#7]-1-2",
+    "pentyl": "[#6H2]-[#6]-[#6]-[#6]-[#6]",
+    "tert-pentyl": "[#6]-[#6]-[#6](-[#6])-[#6]",
+    "phenacylidene": "[#6H]-[#6](-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1)=[#8]",
+    "phenethyl": "[#6H2]-[#6]-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1",
+    "phenoxy": "[#8]-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1",
+    "phenyl": "[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1",
+    "phenylene": "[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1",
+    "phosphino": "[#15H2]",
+    "phosphinyl": "[#15H2]=[#8]",
+    "phospho": "[#8]=[#15](-[#8])-[#8]",
+    "phosphono": "[#8]=[#15](-[#8])-[#8]",
+    "phthaloyl": "[#8]=[#6]-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1-[#6]=[#8]",
+    "picryl": "[#8-]-[#7+](-[#6]1:[#6]:[#6](-[#7+](-[#8-])=[#8]):[#6]:[#6](-[#7+](-[#8-])=[#8]):[#6]:1)=[#8]",
+    "pimeloyl": "[#8]=[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]=[#8]",
+    "piperidino": "[#7]1-[#6]-[#6]-[#6]-[#6]-[#6]-1",
+    "pivaloyl": "[#6]-[#6](-[#6])(-[#6])-[#6]=[#8]",
+    "prenyl": "[#6H2]-[#6]=[#6](-[#6])-[#6]",
+    "propargyl": "[#6H2]-[#6]#[#6]",
+    "1-propenyl": "[#6H]=[#6]-[#6]",
+    "2-propenyl": "[#6H2]-[#6]=[#6]",
+    "propionyl": "[#8]=[#6]-[#6]-[#6]",
+    "propoxy": "[#8]-[#6]-[#6]-[#6]",
+    "propyl": "[#6H2]-[#6]-[#6]",
+    "propylidene": "[#6H]-[#6]-[#6]",
+    "pyrryl": "[#7H]1:[#6]:[#6]:[#6]:[#6]:1",
+    "salicyloyl": "[#8]-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1-[#6]=[#8]",
+    "selenyl": "[SeH]",
+    "seryl": "[#7]-[#6@@H](-[#6]-[#8])-[#6]=[#8]",
+    "siloxy": "[#8]-[SiH3]",
+    "silyl": "[SiH3]",
+    "silyene": "[SiH2]",
+    "sorboyl": "[#6]-[#6]=[#6]-[#6]=[#6]-[#6](-[#8])=[#8]",
+    "stearoyl": "[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]=[#8]",
+    "stearyl": "[#6H2]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]",
+    "styryl": "[#6H]=[#6]-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1",
+    "suberoyl": "[#8]=[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]-[#6]=[#8]",
+    "succinyl": "[#8]=[#6]-[#6]-[#6]-[#6]=[#8]",
+    "sulfamino": "[#7H]-[#16](=[#8])(-[#8])=[#8]",
+    "sulfamoyl": "[#8]=[#16](-[#7])=[#8]",
+    "sulfanilyl": "[#8]=[#16](-[#6]1:[#6]:[#6]:[#6](-[#7]):[#6]:[#6]:1)=[#8]",
+    "sulfeno": "[#16]-[#8]",
+    "sulfhydryl": "[#16H]",
+    "sulfinyl": "[#16]=[#8]",
+    "sulfo": "[#8]=[#16](-[#8])=[#8]",
+    "sulfonyl": "[#8]=[#16]=[#8]",
+    "terephthaloyl": "[#8]=[#6]-[#6]1:[#6]:[#6]:[#6](-[#6]=[#8]):[#6]:[#6]:1",
+    "tetramethylene": "[#6]-[#6]-[#6]-[#6]",
+    "thienyl": "[#6]1:[#6]:[#6]:[#6]:[#16]:1",
+    "thiocarbonyl": "[#6H]=[#16]",
+    "thiocarboxy": "[#16]=[#6]-[#8]",
+    "thiocyanato": "[#16]-[#6]#[#7]",
+    "thionyl": "[#16]=[#8]",
+    "threonyl": "[#7]-[#6@@H](-[#6@H](-[#8])-[#6])-[#6]=[#8]",
+    "toluidino": "[#7H]-[#6]1:[#6]:[#6]:[#6](-[#6]):[#6]:[#6]:1",
+    "toluoyl": "[#6]-[#6]1:[#6]:[#6]:[#6](-[#6]=[#8]):[#6]:[#6]:1",
+    "tolyl": "[#6]-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1",
+    "alpha-tolyl": "[#6]-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1",
+    "tolylene": "[#6H]-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1",
+    "tosyl": "[#8]=[#16](-[#6]1:[#6]:[#6]:[#6](-[#6]):[#6]:[#6]:1)=[#8]",
+    "triazano": "[#7H]-[#7]-[#7H]",
+    "trimethylene": "[#6]-[#6]-[#6]",
+    "valeryl": "[#8]=[#6]-[#6]-[#6]-[#6]-[#6]",
+    "valyl": "[#7]-[#6@@H](-[#6](-[#6])-[#6])-[#6]=[#8]",
+    "vinyl": "[#6H]=[#6]",
+    "vinylidene": "[#6]=[#6]",
+    "xylidino": "[#7H]-[#6]1:[#6]:[#6]:[#6](-[#6]):[#6]:[#6]:1-[#6]",
+    "xylyl": "[#6]-[#6]1:[#6]:[#6]:[#6]:[#6](-[#6]):[#6]:1",
+    "xylylene": "[#7]-[#6]-[#6]1:[#6]:[#6]:[#6]:[#6](-[#6]-[#7]):[#6]:1",
+    "propiolamide": "[#6]#[#6]-[#6](-[#7])=[#8]",
+    "fumarate ester": "[#7]-[#6](/[#6]=[#6]/[#6]-[#6](-[#8]-[#6])=[#8])=[#8]",
+    "allenamide": "[#7]-[#6](-[#6]=[#6]=[#6])=[#8]",
+    "propiolonitrile": "[#6]#[#6]-[#6]#[#7]",
+    "propargylamide": "[#6]#[#6]-[#6]-[#6](-[#7])=[#8]",
+    "arylsulfonyl bicyclobutane": "[#8]=[#16](-[#6]12-[#6]-[#6]-1-[#6]-2)(-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1)=[#8]",
+    "haloalkane": "[#6]-[#35]",
+    "alpha-halomethyl": "[#6]-[#6](-[#6]-[#17])=[#8]",
+    "alpha-haloamide": "[#7]-[#6](-[#6]-[#17])=[#8]",
+    "alpha-haloester": "[#8]=[#6](-[#6]-[#17])-[#8]-[#6]",
+    "epoxide": "[#6]1-[#6]-[#8]-1",
+    "aziridine": "[#7]1-[#6]-[#6]-1",
+    "nitroalkane": "[#6]-[#6]-[#7+](-[#8-])=[#8]",
+    "acrylamide": "[#6]=[#6]-[#6](-[#7])=[#8]",
+    "cyanoenone": "[#8]=[#6](-[#6])-[#6](-[#6]#[#7])=[#6]",
+    "aldehyde": "[#8]=[#6H]-[#6]",
+    "ketone": "[#6][CX3](=O)[#6]",
+    "nitrile": "[#7]#[#6]-[#6]",
+    "cyanamide": "[#7]-[#6]#[#7]",
+    "isothicyanate": "[#7-]=[#6]=[#16]",
+    "sulfone": "[#6]-[#16]=[#8]",
+    "sulfonyl fluoride": "[#8]=[#16](-[#9])=[#8]",
+    "sulfonimidoyl fluoride": "[#7]=[#16](-[#9])(-[#9])=[#8]",
+    "aryl fluorosulfate": "[#8]=[#16](-[#8]-[#6]-[#6]-[#6]-[#6]-[#6])(-[#9])=[#8]",
+    "ester": "[#6]-[#6](-[#8]-[#6])=[#8]",
+    "sulfonamide": "[#8]=[#16](-[#7])=[#8]",
+    "2-carbonyl arylboronic acid": "[#8]=[#6](-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1-[#5](-[#8])-[#8])-[#6]",
+    "n-methyl isoxazolium": "[#6]-[#7+]1:[#6]:[#6]:[#6]:[#8]:1",
+    "oxaziridine": "[#8]1-[#7]-[#6]-1",
+    "carboxyl": "[CX3](=O)[OX2H1]",
+    "ether": "[OD2]([#6])[#6]",
+    "alkanol": "[#6][OX2H]",
+    "thiol": "[#16X2H]",
+    "halogen": "[F,Cl,Br,I]",
+    "amine": "[NX3;H2,H1;!$(NC=O)]",
+    "amide": "[NH2]",
+}
+
+
+def process(chemcaption_data):
+    df = pd.read_json(chemcaption_data, lines=True)
+
+    trustworthy_smarts = [
+        "carboxyl",
+        "carbonyl",
+        "ether",
+        "alkanol",
+        "thiol",
+        "halogen",
+        "amine",
+        "amide",
+        "ketone",
+        "cyclopropane",
+        "spiropentane",
+        "cyclobutane",
+        "cyclopentane",
+        "furan",
+        "thiophene",
+        "pyrrole",
+        "2H-pyrrole",
+        "3H-pyrrole",
+        "pyrazole",
+        "2H-imidazole",
+        "1,2,3-triazole",
+        "1,2,4-triazole",
+        "1,2-dithiole",
+        "1,3-dithiole",
+        "3H-1,2-oxathiole",
+        "isoxazole",
+        "oxazole",
+        "thiazole",
+        "isothiazole",
+        "1,2,3-oxadiazole",
+        "1,2,4-oxadiazole",
+        "1,2,5-oxadiazole",
+        "1,3,4-oxadiazole",
+        "1,2,3,4-oxatriazole",
+        "1,2,3,5-oxatriazole",
+        "3H-1,2,3-dioxazole",
+        "1,2,4-dioxazole",
+        "1,3,2-dioxazole",
+        "1,3,4-dioxazole",
+        "5H-1,2,5-oxathiazole",
+        "1,3-oxathiole",
+        "benzene",
+        "cyclohexane",
+        "2H-pyran",
+        "4H-pyran",
+        "2H-pyran-2-one",
+        "4H-pyran-4-one",
+        "1,2-dioxin",
+        "1,3-dioxin",
+        "pyridine",
+        "pyridazine",
+        "pyrimidine",
+        "pyrazine",
+        "piperazine",
+        "1,3,5-triazine",
+        "1,2,4-triazine",
+        "1,2,3-triazine",
+        "4H-1,2-Oxazine",
+        "2H-1,3-Oxazine",
+        "6H-1,3-Oxazine",
+        "6H-1,2-Oxazine",
+        "1,4-Oxazine",
+        "2H-1,2-Oxazine",
+        "4H-1,4-Oxazine",
+        "1,2,5-Oxathiazine",
+        "1,2,6-Oxathiazine",
+        "1,2,4-Oxadiazine",
+        "1,3,5-Oxadiazine",
+        "morpholine",
+        "azepine",
+        "oxepin",
+        "thiepin",
+        "4H-1,2-diazepine",
+        "indene",
+        "2H-indene",
+        "benzofuran",
+        "isobenzofuran",
+        "benzo[b]thiophene",
+        "benzo[c]thiophene",
+        "indole",
+        "3H-indole",
+        "1H-indole",
+        "cyclopenta[b]pyridine",
+        "pyrano[3,4-b]-pyrrole",
+        "indazole",
+        "benzisoxazole",
+        "benzoxazole",
+        "2,1-benzisoxazole",
+        "naphthalene",
+        "1,2,3,4-tetrahydronaphthalene",
+        "octahydronaphthalene",
+        "2H-1-benzopyran",
+        "2H-1-benzopyran-2-one",
+        "4H-1-benzopyran-4-one",
+        "1H-2-benzopyran-1-one",
+        "3H-2-benzopyran-1-one",
+        "quinoline",
+        "isoquinoline",
+        "cinnoline",
+        "quinazoline",
+        "1,8-napthyhridine",
+        "1,7-napththyridine",
+        "1,5-napththridine",
+        "1,6-napthyridine",
+        "2H-1,3-benzoxazine",
+        "2H-1,4-benzoxazine",
+        "1H-2,3-benzoxazine",
+        "4H-3,1-benzoxazine",
+        "2H-1,2-benzoxazine",
+        "4H-1,3-benzoxazine",
+        "anthracene",
+        "phenanthrene",
+        "phenalene",
+        "fluorene",
+        "carbazole",
+        "xanthene",
+        "acridine",
+        "norpinane",
+        "7H-purine",
+        "steroid_ring_system",
+    ]
+
+    subset = df[df["filled_prompt"].str.contains("|".join(trustworthy_smarts))]
+
+    subset["completion_labels"] = subset["completion_labels"].apply(lambda x: x[0])
+    subset["completion"] = subset["completion"].apply(lambda x: x[0])
+    subset["smarts"] = subset["completion_labels"].apply(
+        lambda x: NAME_SMARTS_MAP[x.replace("_count", "")]
+    )
+
+    relevant_frame = subset[
+        [
+            "representation",
+            "representation_type",
+            "completion",
+            "completion_labels",
+            "smarts",
+        ]
+    ]
+
+    # subsample relevant frame such that completion 0 and completion 1 are approximately equal
+    # this is to avoid biasing the model towards 0
+    completion_0 = relevant_frame[relevant_frame["completion"] == 0]
+    completion_1 = relevant_frame[relevant_frame["completion"] == 1]
+    completion_other = relevant_frame[relevant_frame["completion"] != 0]
+
+    completion_0 = completion_0.sample(n=len(completion_1), random_state=42)
+    relevant_frame = pd.concat([completion_0, completion_1, completion_other])
+
+    return relevant_frame
+    relevant_frame.to_csv("data_clean.csv", index=False)
+
+
+if __name__ == "__main__":
+    all_files = glob("*.jsonl")
+    all_data = []
+
+    for file in tqdm(all_files):
+        try:
+            all_data.append(process(file))
+        except Exception as e:
+            print(file, e)
+    df = pd.concat(all_data)
+
+    ds = Dataset.from_pandas(df)
+    ds.push_to_hub(repo_id="kjappelbaum/chemnlp-chem-caption", config_name="smarts")
diff --git a/data/tabular/chem_caption_smarts/transform.py b/data/tabular/chem_caption_smarts/transform.py
new file mode 100644
index 000000000..7259da626
--- /dev/null
+++ b/data/tabular/chem_caption_smarts/transform.py
@@ -0,0 +1,17 @@
+import pandas as pd
+
+
+def process():
+    # get the smarts config
+    df = pd.read_parquet(
+        "https://huggingface.co/datasets/kjappelbaum/chemnlp-chem-caption/resolve/main/smarts/train-00000-of-00001-71cef18c6383b463.parquet"  # noqa
+    )
+    df["completion_labels"] = df["completion_labels"].astype(str)
+    df["completion_labels"] = df["completion_labels"].str.replace(
+        "_count", "", regex=True
+    )
+    df.to_csv("data_clean.csv", index=False)
+
+
+if __name__ == "__main__":
+    process()