add parser for pseudo-html to extract SMARTS rules into a DataFrame
Browse files- data/parse.txt +12 -3
- data/parser.py +99 -0
- data/smarts_examples.ff.txt +1338 -0
data/parse.txt
CHANGED
|
@@ -1,6 +1,15 @@
|
|
| 1 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
H2 without a number introduce subtopics (ignore badly formatted html)
|
| 3 |
H3 are sub-sub-topics
|
| 4 |
-
DT
|
|
|
|
| 5 |
if further DDs are encountered, they are comments
|
| 6 |
-
if several patterns appear in the DD separated by BR, split them
|
|
|
|
|
|
| 1 |
+
Your task is to parse the attached pseudo-html file into a data frame.
|
| 2 |
+
The file contains a list of SMARTS rules and descriptions, organized
|
| 3 |
+
as follows. The HTML tagging is not well-formed, so run tests until
|
| 4 |
+
the pandas dataframe looks right.
|
| 5 |
+
|
| 6 |
+
Rules are organised hierarchically:
|
| 7 |
+
|
| 8 |
+
H2 tags starting with a number are main topics
|
| 9 |
H2 without a number introduce subtopics (ignore badly formatted html)
|
| 10 |
H3 are sub-sub-topics
|
| 11 |
+
DT has rule name
|
| 12 |
+
DD rule contents (smarts)
|
| 13 |
if further DDs are encountered, they are comments
|
| 14 |
+
if several patterns appear in the DD separated by BR, split them
|
| 15 |
+
|
data/parser.py
ADDED
|
@@ -0,0 +1,99 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Your task is to parse the attached pseudo-html file into a data frame.
|
| 2 |
+
# The file contains a list of SMARTS rules and descriptions, organized
|
| 3 |
+
# as follows. The HTML tagging is not well-formed, so run tests until
|
| 4 |
+
# the pandas dataframe looks right.
|
| 5 |
+
|
| 6 |
+
# Rules are organised hierarchically:
|
| 7 |
+
|
| 8 |
+
# H2 tags starting with a number are main topics
|
| 9 |
+
# H2 without a number introduce subtopics (ignore badly formatted html)
|
| 10 |
+
# H3 are sub-sub-topics
|
| 11 |
+
# DT has rule name
|
| 12 |
+
# DD rule contents (smarts)
|
| 13 |
+
# if further DDs are encountered, they are comments
|
| 14 |
+
# if several patterns appear in the DD separated by BR, split them
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
from bs4 import BeautifulSoup
|
| 19 |
+
import pandas as pd
|
| 20 |
+
|
| 21 |
+
# read the pseudo-html file
|
| 22 |
+
with open("smarts_examples.ff.txt", "r", encoding="utf-8") as f:
|
| 23 |
+
html_content = f.read()
|
| 24 |
+
|
| 25 |
+
# use BeautifulSoup with the built-in parser (which can handle messy HTML)
|
| 26 |
+
soup = BeautifulSoup(html_content, "html.parser")
|
| 27 |
+
|
| 28 |
+
# variables to keep track of the current hierarchy
|
| 29 |
+
current_main_topic = None
|
| 30 |
+
current_subtopic = None
|
| 31 |
+
current_sub_sub_topic = None
|
| 32 |
+
|
| 33 |
+
rows = []
|
| 34 |
+
|
| 35 |
+
# iterate over all tags in document order
|
| 36 |
+
for element in soup.recursiveChildGenerator():
|
| 37 |
+
if hasattr(element, "name"):
|
| 38 |
+
# Process H2 tags
|
| 39 |
+
if element.name == "h2":
|
| 40 |
+
text = element.get_text(strip=True, separator=' ')
|
| 41 |
+
# if H2 text starts with a digit, it is a main topic
|
| 42 |
+
if text and text[0].isdigit():
|
| 43 |
+
current_main_topic = text
|
| 44 |
+
current_subtopic = None
|
| 45 |
+
current_sub_sub_topic = None
|
| 46 |
+
else:
|
| 47 |
+
# H2 that does not start with a number: treat as subtopic
|
| 48 |
+
current_subtopic = text
|
| 49 |
+
current_sub_sub_topic = None
|
| 50 |
+
|
| 51 |
+
# Process H3 tags as sub-sub-topics
|
| 52 |
+
elif element.name == "h3":
|
| 53 |
+
current_sub_sub_topic = element.get_text(strip=True, separator=' ')
|
| 54 |
+
|
| 55 |
+
# Process DT tags which contain the rule name
|
| 56 |
+
elif element.name == "dt":
|
| 57 |
+
rule_name = element.get_text(strip=True, separator=' ')
|
| 58 |
+
# Find the next DD sibling
|
| 59 |
+
dd = element.find_next_sibling("dd")
|
| 60 |
+
if dd:
|
| 61 |
+
# If the dd has <br> tags, split on them to get separate patterns.
|
| 62 |
+
if dd.find("br"):
|
| 63 |
+
# decode the inner HTML and split on <br>, ignoring newlines
|
| 64 |
+
raw_html = dd.decode_contents().replace('\n', '')
|
| 65 |
+
pattern_list = [part.strip() for part in raw_html.split("<br/>") if part.strip()]
|
| 66 |
+
# For multiple patterns, append index to rule name
|
| 67 |
+
if len(pattern_list) > 1:
|
| 68 |
+
rule_names = [f"{rule_name} ({i+1})" for i in range(len(pattern_list))]
|
| 69 |
+
else:
|
| 70 |
+
rule_names = [rule_name]
|
| 71 |
+
else:
|
| 72 |
+
pattern_list = [dd.get_text(strip=True, separator=' ')]
|
| 73 |
+
rule_names = [rule_name]
|
| 74 |
+
|
| 75 |
+
# Look for an additional DD that might contain comments and normalize whitespace
|
| 76 |
+
comment_dd = dd.find_next_sibling("dd")
|
| 77 |
+
if comment_dd:
|
| 78 |
+
# Replace newlines with spaces and normalize whitespace
|
| 79 |
+
comments = ' '.join(comment_dd.get_text(separator=' ').split())
|
| 80 |
+
else:
|
| 81 |
+
comments = ""
|
| 82 |
+
|
| 83 |
+
# Create a row for each pattern with its corresponding rule name
|
| 84 |
+
for pattern, name in zip(pattern_list, rule_names):
|
| 85 |
+
rows.append({
|
| 86 |
+
"Main Topic": current_main_topic,
|
| 87 |
+
"Subtopic": current_subtopic,
|
| 88 |
+
"Sub-sub-topic": current_sub_sub_topic,
|
| 89 |
+
"Rule Name": name,
|
| 90 |
+
"Pattern": pattern,
|
| 91 |
+
"Comments": comments
|
| 92 |
+
})
|
| 93 |
+
|
| 94 |
+
# build the DataFrame
|
| 95 |
+
df = pd.DataFrame(rows)
|
| 96 |
+
# display a sample of the dataframe
|
| 97 |
+
df.to_csv("smarts_examples_parsed.csv", index=False)
|
| 98 |
+
df.to_clipboard()
|
| 99 |
+
|
data/smarts_examples.ff.txt
ADDED
|
@@ -0,0 +1,1338 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
<td class="border-bot">
|
| 2 |
+
<center><h1>SMARTS Examples
|
| 3 |
+
</h1></center>
|
| 4 |
+
<a name="TOP"></a><h2>Table of Contents</h2>
|
| 5 |
+
|
| 6 |
+
<a href="#INTRO">1. Introduction</a><br>
|
| 7 |
+
<a href="#GROUP">2. Functional Groups by Element</a><br>
|
| 8 |
+
<a href="#STRUCTUAL">2. Gross Structual Features</a><br>
|
| 9 |
+
<a href="#META">4. Meta-SMARTS</a><br>
|
| 10 |
+
<a href="#E-">5. Electron & Proton Features</a><br>
|
| 11 |
+
<a href="#BREAK">6. Breakdown of Complex SMARTS</a><br>
|
| 12 |
+
<a href="#EXMPL">7. Interesting Example SMARTS</a><br>
|
| 13 |
+
<br>
|
| 14 |
+
<a name="INTRO"></a>
|
| 15 |
+
<h2>
|
| 16 |
+
1. Introduction
|
| 17 |
+
</h2>
|
| 18 |
+
When using SMARTS to do searches, it is often helpful to have
|
| 19 |
+
example queries from which to start. This document contains
|
| 20 |
+
many potentially useful example SMARTS which may be used to
|
| 21 |
+
perform searches. templates, examples and ideas.
|
| 22 |
+
<br><br>
|
| 23 |
+
These SMARTS have been tested, but they may still contain errors.
|
| 24 |
+
Please send corrections, improvements, additions, and questions to
|
| 25 |
+
<a href="mailto:support@daylight.com">support@daylight.com.</a>
|
| 26 |
+
|
| 27 |
+
<br><br>
|
| 28 |
+
<a name="GROUP"></a>
|
| 29 |
+
<h2>
|
| 30 |
+
2. Functional Groups by Element
|
| 31 |
+
</h2>
|
| 32 |
+
|
| 33 |
+
<table border="1" cols="8" width="750"><tbody><tr>
|
| 34 |
+
<td align="center"><a href="#C">C</a></td>
|
| 35 |
+
<td align="center"><a href="#CO">C&O</a></td>
|
| 36 |
+
<td align="center"><a href="#H">H</a></td>
|
| 37 |
+
<td align="center"><a href="#N">N</a></td>
|
| 38 |
+
<td align="center"><a href="#O">O</a></td>
|
| 39 |
+
<td align="center"><a href="#P">P</a></td>
|
| 40 |
+
<td align="center"><a href="#S">S</a></td>
|
| 41 |
+
<td align="center"><a href="#X">X</a></td></tr>
|
| 42 |
+
</tbody></table><br>
|
| 43 |
+
<a name="C"></a><h2>C</h2>
|
| 44 |
+
<h3> alkane </h3><dl>
|
| 45 |
+
<p></p><dt> Alkyl Carbon
|
| 46 |
+
</dt><dd> [CX4]<p></p></dd></dl><br>
|
| 47 |
+
<h3> alkene (-ene) </h3><dl>
|
| 48 |
+
<p></p><dt> Allenic Carbon
|
| 49 |
+
</dt><dd> [$([CX2](=C)=C)]
|
| 50 |
+
<p></p></dd><dt> Vinylic Carbon
|
| 51 |
+
</dt><dd> [$([CX3]=[CX3])]
|
| 52 |
+
</dd><dd> Ethenyl carbon <p></p></dd></dl><br>
|
| 53 |
+
<h3> alkyne (-yne) </h3><dl>
|
| 54 |
+
<p></p><dt> Acetylenic Carbon
|
| 55 |
+
</dt><dd> [$([CX2]#C)]<p></p></dd></dl><br>
|
| 56 |
+
<h3> arene (Ar , aryl-, aromatic hydrocarbons) </h3><dl>
|
| 57 |
+
<p></p><dt> Arene
|
| 58 |
+
</dt><dd> c <p></p></dd></dl><br>
|
| 59 |
+
<a name="CO"></a><h2>C & O</h2>
|
| 60 |
+
<h3>carbonyl</h3><dl>
|
| 61 |
+
<p></p><dt> Carbonyl group. Low specificity
|
| 62 |
+
</dt><dd> [CX3]=[OX1]
|
| 63 |
+
</dd><dd> Hits carboxylic acid, ester, ketone, aldehyde, carbonic
|
| 64 |
+
acid/ester,anhydride, carbamic acid/ester, acyl halide, amide.
|
| 65 |
+
<p></p></dd><dt> Carbonyl group
|
| 66 |
+
</dt><dd> [$([CX3]=[OX1]),$([CX3+]-[OX1-])]
|
| 67 |
+
</dd><dd> Hits either resonance structure
|
| 68 |
+
<p></p></dd><dt> Carbonyl with Carbon
|
| 69 |
+
</dt><dd> [CX3](=[OX1])C
|
| 70 |
+
</dd><dd> Hits aldehyde, ketone, carboxylic acid (except formic), anhydride
|
| 71 |
+
(except formic), acyl halides (acid halides). Won't hit carbamic
|
| 72 |
+
acid/ester, carbonic acid/ester.
|
| 73 |
+
<p></p></dd><dt> Carbonyl with Nitrogen.
|
| 74 |
+
</dt><dd> [OX1]=CN
|
| 75 |
+
</dd><dd> Hits amide, carbamic acid/ester, poly peptide
|
| 76 |
+
<p></p></dd><dt> Carbonyl with Oxygen.
|
| 77 |
+
</dt><dd> [CX3](=[OX1])O
|
| 78 |
+
</dd><dd> Hits ester, carboxylic acid, carbonic acid or ester, carbamic acid
|
| 79 |
+
or ester, anhydride Won't hit aldehyde or ketone.
|
| 80 |
+
<p></p></dd><dt> Acyl Halide
|
| 81 |
+
</dt><dd> [CX3](=[OX1])[F,Cl,Br,I]
|
| 82 |
+
</dd><dd> acid halide, -oyl halide
|
| 83 |
+
<p></p></dd><dt> Aldehyde
|
| 84 |
+
</dt><dd> [CX3H1](=O)[#6]
|
| 85 |
+
</dd><dd> -al
|
| 86 |
+
<p></p></dd><dt> Anhydride
|
| 87 |
+
</dt><dd> [CX3](=[OX1])[OX2][CX3](=[OX1])
|
| 88 |
+
<p></p></dd><dt> Amide
|
| 89 |
+
</dt><dd> [NX3][CX3](=[OX1])[#6]
|
| 90 |
+
</dd><dd> -amide
|
| 91 |
+
<p></p></dd><dt> Amidinium
|
| 92 |
+
</dt><dd> [NX3][CX3]=[NX3+]
|
| 93 |
+
<p></p></dd><dt> Carbamate.
|
| 94 |
+
</dt><dd> [NX3,NX4+][CX3](=[OX1])[OX2,OX1-]
|
| 95 |
+
</dd><dd> Hits carbamic esters, acids, and zwitterions
|
| 96 |
+
<p></p></dd><dt> Carbamic ester
|
| 97 |
+
</dt><dd> [NX3][CX3](=[OX1])[OX2H0]
|
| 98 |
+
<p></p></dd><dt> Carbamic acid.
|
| 99 |
+
</dt><dd> [NX3,NX4+][CX3](=[OX1])[OX2H,OX1-]
|
| 100 |
+
</dd><dd> Hits carbamic acids and zwitterions.
|
| 101 |
+
<p></p></dd><dt> Carboxylate Ion.
|
| 102 |
+
</dt><dd> [CX3](=O)[O-]
|
| 103 |
+
</dd><dd> Hits conjugate bases of carboxylic, carbamic, and carbonic acids.
|
| 104 |
+
<p></p></dd><dt> Carbonic Acid or Carbonic Ester
|
| 105 |
+
</dt><dd> [CX3](=[OX1])(O)O
|
| 106 |
+
</dd><dd> Carbonic Acid, Carbonic Ester, or combination
|
| 107 |
+
<p></p></dd><dt> Carbonic Acid or Carbonic Acid-Ester
|
| 108 |
+
</dt><dd> [CX3](=[OX1])([OX2])[OX2H,OX1H0-1]
|
| 109 |
+
</dd><dd> Hits acid and conjugate base. Won't hit carbonic acid diester
|
| 110 |
+
<p></p></dd><dt> Carbonic Ester (carbonic acid diester)
|
| 111 |
+
</dt><dd> C[OX2][CX3](=[OX1])[OX2]C
|
| 112 |
+
</dd><dd> Won't hit carbonic acid or combination carbonic acid/ester
|
| 113 |
+
<p></p></dd><dt> Carboxylic acid
|
| 114 |
+
</dt><dd> [CX3](=O)[OX2H1]
|
| 115 |
+
</dd><dd> -oic acid, COOH
|
| 116 |
+
<p></p></dd><dt> Carboxylic acid or conjugate base.
|
| 117 |
+
</dt><dd> [CX3](=O)[OX1H0-,OX2H1]
|
| 118 |
+
<p></p></dd><dt> Cyanamide
|
| 119 |
+
</dt><dd> [NX3][CX2]#[NX1]
|
| 120 |
+
<p></p></dd><dt> Ester Also hits anhydrides
|
| 121 |
+
</dt><dd> [#6][CX3](=O)[OX2H0][#6]
|
| 122 |
+
</dd><dd> won't hit formic anhydride.
|
| 123 |
+
<p></p></dd><dt> Ketone
|
| 124 |
+
</dt><dd> [#6][CX3](=O)[#6]
|
| 125 |
+
</dd><dd> -one <p></p></dd></dl><br>
|
| 126 |
+
<h3> ether</h3><dl>
|
| 127 |
+
<p></p><dt> Ether
|
| 128 |
+
</dt><dd> [OD2]([#6])[#6]<p></p></dd></dl><br>
|
| 129 |
+
<a name="H"></a><h2>H</h2>
|
| 130 |
+
<h3> hydrogen atoms</h3><dl>
|
| 131 |
+
<p></p><dt> Hydrogen Atom
|
| 132 |
+
</dt><dd> [H]
|
| 133 |
+
</dd><dd> Hits SMILES that are hydrogen atoms: [H+] [2H] [H][H]
|
| 134 |
+
<p></p></dd><dt> Not a Hydrogen Atom
|
| 135 |
+
</dt><dd> [!#1]
|
| 136 |
+
</dd><dd> Hits SMILES that are not hydrogen atoms.
|
| 137 |
+
<p></p></dd><dt> Proton
|
| 138 |
+
</dt><dd> [H+]
|
| 139 |
+
</dd><dd> Hits positively charged hydrogen atoms: [H+]<p></p></dd></dl><br>
|
| 140 |
+
<h3> hydrogen count</h3><dl>
|
| 141 |
+
<p></p><dt> Mono-Hydrogenated Cation
|
| 142 |
+
</dt><dd> [+H]
|
| 143 |
+
</dd><dd> Hits atoms that have a positive charge and exactly one attached hydrogen: F[C+](F)[H]
|
| 144 |
+
<p></p></dd><dt> Not Mono-Hydrogenated
|
| 145 |
+
</dt><dd> [!H] or [!H1]
|
| 146 |
+
</dd><dd> Hits atoms that don't have exactly one attached hydrogen.<p></p></dd></dl><br>
|
| 147 |
+
<a name="N"></a><h2>N</h2>
|
| 148 |
+
<h3> amide see carbonyl<p></p><br>
|
| 149 |
+
mine (-amino) </h3><dl>
|
| 150 |
+
<p></p><dt> Primary or secondary amine, not amide.
|
| 151 |
+
</dt><dd> [NX3;H2,H1;!$(NC=O)]
|
| 152 |
+
</dd><dd> Not ammonium ion (N must be 3-connected), not ammonia (H count can't be 3). Primary or secondary is specified by N's H-count (H2 & H1 respectively). Also note that "&" (and) is the dafault opperator and is higher precedence that "," (or), which is higher precedence than ";" (and). Will hit cyanamides and thioamides
|
| 153 |
+
<p></p></dd><dt> Enamine
|
| 154 |
+
</dt><dd> [NX3][CX3]=[CX3]
|
| 155 |
+
<p></p></dd><dt> Primary amine, not amide.
|
| 156 |
+
</dt><dd> [NX3;H2;!$(NC=[!#6]);!$(NC#[!#6])][#6] Not amide (C not double bonded to a hetero-atom), not ammonium ion (N must be 3-connected), not ammonia (N's H-count can't be 3), not cyanamide (C not triple bonded to a hetero-atom)
|
| 157 |
+
<p></p></dd><dt> Two primary or secondary amines
|
| 158 |
+
</dt><dd> [NX3;H2,H1;!$(NC=O)].[NX3;H2,H1;!$(NC=O)]
|
| 159 |
+
</dd><dd> Here we use the disconnection symbol (".") to match two separate unbonded identical patterns.
|
| 160 |
+
<p></p></dd><dt> Enamine or Aniline Nitrogen
|
| 161 |
+
</dt><dd> [NX3][$(C=C),$(cc)]<p></p></dd></dl><br>
|
| 162 |
+
<h3> amino acids</h3><dl>
|
| 163 |
+
<p></p><dt> Generic amino acid: low specificity.
|
| 164 |
+
</dt><dd> [NX3,NX4+][CX4H]([*])[CX3](=[OX1])[O,N]
|
| 165 |
+
</dd><dd> For use w/ non-standard a.a. search. hits pro but not gly. Hits acids and conjugate bases. Hits single a.a.s and specific residues w/in polypeptides (internal, or terminal).
|
| 166 |
+
<p></p></dd><dt> Dipeptide group. generic amino acid: low specificity.
|
| 167 |
+
</dt><dd> [NX3H2,NH3X4+][CX4H]([*])[CX3](=[OX1])[NX3,NX4+][CX4H]([*])[CX3](=[OX1])[OX2H,OX1-]
|
| 168 |
+
</dd><dd> Won't hit pro or gly. Hits acids and conjugate bases.
|
| 169 |
+
<p></p></dd><dt> Amino Acid
|
| 170 |
+
</dt><dd> [$([NX3H2,NX4H3+]),$([NX3H](C)(C))][CX4H]([*])[CX3](=[OX1])[OX2H,OX1-,N]
|
| 171 |
+
</dd><dd> Replace * w/ a specific a.a. side chain from the 18_standard_side_chains list to hit a specific standard a.a. Won't work with Proline
|
| 172 |
+
or Glycine, they have their own SMARTS (see side chain list). Hits acids and conjugate bases. Hits single a.a.s and specific residues w/i
|
| 173 |
+
n polypeptides (internal, or terminal). {e.g. usage: Alanine side chain is [CH3X4] . Search is [$([NX3H2,NX4H3+]),$([NX3H](C)(C))][CX4H]([
|
| 174 |
+
CH3X4])[CX3](=[OX1])[OX2H,OX1-,N]}<p></p></dd></dl><br>
|
| 175 |
+
<h3> amino acid side chains</h3><dl>
|
| 176 |
+
<p></p><dt> Alanine side chain
|
| 177 |
+
</dt><dd> [CH3X4]
|
| 178 |
+
|
| 179 |
+
<p></p></dd><dt> Arginine side chain.
|
| 180 |
+
</dt><dd> [CH2X4][CH2X4][CH2X4][NHX3][CH0X3](=[NH2X3+,NHX2+0])[NH2X3]
|
| 181 |
+
</dd><dd> Hits acid and conjugate base.
|
| 182 |
+
|
| 183 |
+
<p></p></dd><dt> Aspargine side chain.
|
| 184 |
+
</dt><dd> [CH2X4][CX3](=[OX1])[NX3H2]
|
| 185 |
+
</dd><dd> Also hits Gln side chain when used alone.
|
| 186 |
+
|
| 187 |
+
<p></p></dd><dt> Aspartate (or Aspartic acid) side chain.
|
| 188 |
+
</dt><dd> [CH2X4][CX3](=[OX1])[OH0-,OH]
|
| 189 |
+
</dd><dd> Hits acid and conjugate base. Also hits Glu side chain when used alone.
|
| 190 |
+
|
| 191 |
+
<p></p></dd><dt> Cysteine side chain.
|
| 192 |
+
</dt><dd> [CH2X4][SX2H,SX1H0-]
|
| 193 |
+
</dd><dd> Hits acid and conjugate base
|
| 194 |
+
|
| 195 |
+
<p></p></dd><dt> Glutamate (or Glutamic acid) side chain.
|
| 196 |
+
</dt><dd> [CH2X4][CH2X4][CX3](=[OX1])[OH0-,OH]
|
| 197 |
+
</dd><dd> Hits acid and conjugate base.
|
| 198 |
+
|
| 199 |
+
<p></p></dd><dt> Glycine
|
| 200 |
+
</dt><dd> [$([$([NX3H2,NX4H3+]),$([NX3H](C)(C))][CX4H2][CX3](=[OX1])[OX2H,OX1-,N])]
|
| 201 |
+
<p></p></dd><dt> Histidine side chain.
|
| 202 |
+
</dt><dd> [CH2X4][#6X3]1:[$([#7X3H+,#7X2H0+0]:[#6X3H]:[#7X3H]),$([#7X3H])]:[#6X3H]:<br>[$([#7X3H+,#7X2H0+0]:[#6X3H]:[#7X3H]),$([#7X3H])]:[#6X3H]1
|
| 203 |
+
</dd><dd> Hits acid & conjugate base for either Nitrogen. Note that the Ns can be either ([(Cationic 3-connected with one H) or (Neutral
|
| 204 |
+
2-connected without any Hs)] where there is a second-neighbor who is [3-connected with one H]) or (3-connected with one H).
|
| 205 |
+
|
| 206 |
+
<p></p></dd><dt> Isoleucine side chain
|
| 207 |
+
</dt><dd> [CHX4]([CH3X4])[CH2X4][CH3X4]
|
| 208 |
+
|
| 209 |
+
<p></p></dd><dt> Leucine side chain
|
| 210 |
+
</dt><dd> [CH2X4][CHX4]([CH3X4])[CH3X4]
|
| 211 |
+
|
| 212 |
+
<p></p></dd><dt> Lysine side chain.
|
| 213 |
+
</dt><dd> [CH2X4][CH2X4][CH2X4][CH2X4][NX4+,NX3+0]
|
| 214 |
+
</dd><dd> Acid and conjugate base
|
| 215 |
+
|
| 216 |
+
<p></p></dd><dt> Methionine side chain
|
| 217 |
+
</dt><dd> [CH2X4][CH2X4][SX2][CH3X4]
|
| 218 |
+
|
| 219 |
+
<p></p></dd><dt> Phenylalanine side chain
|
| 220 |
+
</dt><dd> [CH2X4][cX3]1[cX3H][cX3H][cX3H][cX3H][cX3H]1
|
| 221 |
+
|
| 222 |
+
<p></p></dd><dt> Proline
|
| 223 |
+
</dt><dd> [$([NX3H,NX4H2+]),$([NX3](C)(C)(C))]1[CX4H]([CH2][CH2][CH2]1)[CX3](=[OX1])[OX2H,OX1-,N]
|
| 224 |
+
|
| 225 |
+
<p></p></dd><dt> Serine side chain
|
| 226 |
+
</dt><dd> [CH2X4][OX2H]
|
| 227 |
+
|
| 228 |
+
<p></p></dd><dt> Thioamide
|
| 229 |
+
</dt><dd> [NX3][CX3]=[SX1]
|
| 230 |
+
|
| 231 |
+
<p></p></dd><dt> Threonine side chain
|
| 232 |
+
</dt><dd> [CHX4]([CH3X4])[OX2H]
|
| 233 |
+
|
| 234 |
+
<p></p></dd><dt> Tryptophan side chain
|
| 235 |
+
</dt><dd> [CH2X4][cX3]1[cX3H][nX3H][cX3]2[cX3H][cX3H][cX3H][cX3H][cX3]12
|
| 236 |
+
|
| 237 |
+
<p></p></dd><dt> Tyrosine side chain.
|
| 238 |
+
</dt><dd> [CH2X4][cX3]1[cX3H][cX3H][cX3]([OHX2,OH0X1-])[cX3H][cX3H]1
|
| 239 |
+
</dd><dd> Acid and conjugate base
|
| 240 |
+
|
| 241 |
+
<p></p></dd><dt> Valine side chain
|
| 242 |
+
</dt><dd> [CHX4]([CH3X4])[CH3X4]
|
| 243 |
+
|
| 244 |
+
<p></p></dd><dt> Alanine side chain
|
| 245 |
+
</dt><dd> [CH3X4]
|
| 246 |
+
|
| 247 |
+
<p></p></dd><dt> Arginine side chain.
|
| 248 |
+
</dt><dd> [CH2X4][CH2X4][CH2X4][NHX3][CH0X3](=[NH2X3+,NHX2+0])[NH2X3]
|
| 249 |
+
</dd><dd> Hits acid and conjugate base.
|
| 250 |
+
|
| 251 |
+
<p></p></dd><dt> Aspargine side chain.
|
| 252 |
+
</dt><dd> [CH2X4][CX3](=[OX1])[NX3H2]
|
| 253 |
+
</dd><dd> Also hits Gln side chain when used alone.
|
| 254 |
+
|
| 255 |
+
<p></p></dd><dt> Aspartate (or Aspartic acid) side chain.
|
| 256 |
+
</dt><dd> [CH2X4][CX3](=[OX1])[OH0-,OH]
|
| 257 |
+
</dd><dd> Hits acid and conjugate base. Also hits Glu side chain when used alone.
|
| 258 |
+
|
| 259 |
+
<p></p></dd><dt> Cysteine side chain.
|
| 260 |
+
</dt><dd> [CH2X4][SX2H,SX1H0-]
|
| 261 |
+
</dd><dd> Hits acid and conjugate base
|
| 262 |
+
|
| 263 |
+
<p></p></dd><dt> Glutamate (or Glutamic acid) side chain.
|
| 264 |
+
</dt><dd> [CH2X4][CH2X4][CX3](=[OX1])[OH0-,OH]
|
| 265 |
+
</dd><dd> Hits acid and conjugate base.
|
| 266 |
+
|
| 267 |
+
<p></p></dd><dt> Glycine
|
| 268 |
+
</dt><dd> N[CX4H2][CX3](=[OX1])[O,N]
|
| 269 |
+
|
| 270 |
+
<p></p></dd><dt> Histidine side chain.
|
| 271 |
+
</dt><dd> [CH2X4][#6X3]1:[$([#7X3H+,#7X2H0+0]:[#6X3H]:[#7X3H]),$([#7X3H])]:[#6X3H]:<br>[$([#7X3H+,#7X2H0+0]:[#6X3H]:[#7X3H]),$([#7X3H])]:[#6X3H]1
|
| 272 |
+
</dd><dd> Hits acid & conjugate base for either Nitrogen. Note that the Ns can be either ([(Cationic 3-connected with one H) or (Neutral
|
| 273 |
+
2-connected without any Hs)] where there is a second-neighbor who is [3-connected
|
| 274 |
+
|
| 275 |
+
<p></p></dd><dt> Isoleucine side chain
|
| 276 |
+
</dt><dd> [CHX4]([CH3X4])[CH2X4][CH3X4]
|
| 277 |
+
|
| 278 |
+
<p></p></dd><dt> Leucine side chain
|
| 279 |
+
</dt><dd> [CH2X4][CHX4]([CH3X4])[CH3X4]
|
| 280 |
+
|
| 281 |
+
<p></p></dd><dt> Lysine side chain.
|
| 282 |
+
</dt><dd> [CH2X4][CH2X4][CH2X4][CH2X4][NX4+,NX3+0]
|
| 283 |
+
</dd><dd> Acid and conjugate base
|
| 284 |
+
|
| 285 |
+
<p></p></dd><dt> Methionine side chain
|
| 286 |
+
</dt><dd> [CH2X4][CH2X4][SX2][CH3X4]
|
| 287 |
+
|
| 288 |
+
<p></p></dd><dt> Phenylalanine side chain
|
| 289 |
+
</dt><dd> [CH2X4][cX3]1[cX3H][cX3H][cX3H][cX3H][cX3H]1
|
| 290 |
+
|
| 291 |
+
<p></p></dd><dt> Proline
|
| 292 |
+
</dt><dd> N1[CX4H]([CH2][CH2][CH2]1)[CX3](=[OX1])[O,N]
|
| 293 |
+
|
| 294 |
+
<p></p></dd><dt> Serine side chain
|
| 295 |
+
</dt><dd> [CH2X4][OX2H]
|
| 296 |
+
|
| 297 |
+
<p></p></dd><dt> Threonine side chain
|
| 298 |
+
</dt><dd> [CHX4]([CH3X4])[OX2H]
|
| 299 |
+
|
| 300 |
+
<p></p></dd><dt> Tryptophan side chain
|
| 301 |
+
</dt><dd> [CH2X4][cX3]1[cX3H][nX3H][cX3]2[cX3H][cX3H][cX3H][cX3H][cX3]12
|
| 302 |
+
|
| 303 |
+
<p></p></dd><dt> Tyrosine side chain.
|
| 304 |
+
</dt><dd> [CH2X4][cX3]1[cX3H][cX3H][cX3]([OHX2,OH0X1-])[cX3H][cX3H]1
|
| 305 |
+
</dd><dd> Acid and conjugate base
|
| 306 |
+
|
| 307 |
+
<p></p></dd><dt> Valine side chain
|
| 308 |
+
</dt><dd> [CHX4]([CH3X4])[CH3X4]<p></p></dd></dl><br>
|
| 309 |
+
|
| 310 |
+
<h3> azide (-azido) </h3><dl>
|
| 311 |
+
|
| 312 |
+
<p></p><dt> Azide group.
|
| 313 |
+
</dt><dd> [$(*-[NX2-]-[NX2+]#[NX1]),$(*-[NX2]=[NX2+]=[NX1-])]
|
| 314 |
+
</dd><dd> Hits any atom with an attached azide.
|
| 315 |
+
|
| 316 |
+
<p></p></dd><dt> Azide ion.
|
| 317 |
+
</dt><dd> [$([NX1-]=[NX2+]=[NX1-]),$([NX1]#[NX2+]-[NX1-2])]
|
| 318 |
+
</dd><dd> Hits N in azide ion<p></p></dd></dl><br>
|
| 319 |
+
|
| 320 |
+
<h3> azo </h3><dl>
|
| 321 |
+
|
| 322 |
+
<p></p><dt> Nitrogen.
|
| 323 |
+
</dt><dd> [#7]
|
| 324 |
+
</dd><dd> Nitrogen in N-containing compound. aromatic or aliphatic. Most general interpretation of "azo"
|
| 325 |
+
|
| 326 |
+
<p></p></dd><dt> Azo Nitrogen. Low specificity.
|
| 327 |
+
</dt><dd> [NX2]=N
|
| 328 |
+
</dd><dd> Hits diazene, azoxy and some diazo structures
|
| 329 |
+
|
| 330 |
+
<p></p></dd><dt> Azo Nitrogen.diazene
|
| 331 |
+
</dt><dd> [NX2]=[NX2]
|
| 332 |
+
</dd><dd> (diaza alkene)
|
| 333 |
+
|
| 334 |
+
<p></p></dd><dt> Azoxy Nitrogen.
|
| 335 |
+
</dt><dd> [$([NX2]=[NX3+]([O-])[#6]),$([NX2]=[NX3+0](=[O])[#6])]
|
| 336 |
+
|
| 337 |
+
<p></p></dd><dt> Diazo Nitrogen
|
| 338 |
+
</dt><dd> [$([#6]=[N+]=[N-]),$([#6-]-[N+]#[N])]
|
| 339 |
+
|
| 340 |
+
<p></p></dd><dt> Azole.
|
| 341 |
+
</dt><dd> [$([nr5]:[nr5,or5,sr5]),$([nr5]:[cr5]:[nr5,or5,sr5])]
|
| 342 |
+
</dd><dd> 5 member aromatic heterocycle w/ 2double bonds. contains N & another non C (N,O,S) subclasses are furo-, thio-, pyrro- (replace
|
| 343 |
+
CH o' furfuran, thiophene, pyrrol w/ N)<p></p></dd></dl><br>
|
| 344 |
+
|
| 345 |
+
<h3> hydrazine</h3><dl>
|
| 346 |
+
|
| 347 |
+
<p></p><dt> Hydrazine H2NNH2
|
| 348 |
+
</dt><dd> [NX3][NX3]<p></p></dd></dl><br>
|
| 349 |
+
|
| 350 |
+
<h3> hydrazone </h3><dl>
|
| 351 |
+
|
| 352 |
+
<p></p><dt> Hydrazone C=NNH2
|
| 353 |
+
</dt><dd> [NX3][NX2]=[*]<p></p></dd></dl><br>
|
| 354 |
+
|
| 355 |
+
<h3> imine </h3><dl>
|
| 356 |
+
|
| 357 |
+
<p></p><dt> Substituted imine
|
| 358 |
+
</dt><dd> [CX3;$([C]([#6])[#6]),$([CH][#6])]=[NX2][#6]
|
| 359 |
+
</dd><dd> Schiff base
|
| 360 |
+
|
| 361 |
+
<p></p></dd><dt> Substituted or un-substituted imine
|
| 362 |
+
</dt><dd> [$([CX3]([#6])[#6]),$([CX3H][#6])]=[$([NX2][#6]),$([NX2H])]
|
| 363 |
+
|
| 364 |
+
<p></p></dd><dt> Iminium
|
| 365 |
+
</dt><dd> [NX3+]=[CX3]<p></p></dd></dl><br>
|
| 366 |
+
|
| 367 |
+
<h3> imide </h3><dl>
|
| 368 |
+
|
| 369 |
+
<p></p><dt> Unsubstituted dicarboximide
|
| 370 |
+
</dt><dd> [CX3](=[OX1])[NX3H][CX3](=[OX1])
|
| 371 |
+
|
| 372 |
+
<p></p></dd><dt> Substituted dicarboximide
|
| 373 |
+
</dt><dd> [CX3](=[OX1])[NX3H0]([#6])[CX3](=[OX1])
|
| 374 |
+
|
| 375 |
+
<p></p></dd><dt> Dicarboxdiimide
|
| 376 |
+
</dt><dd> [CX3](=[OX1])[NX3H0]([NX3H0]([CX3](=[OX1]))[CX3](=[OX1]))[CX3](=[OX1])<p></p></dd></dl><br>
|
| 377 |
+
|
| 378 |
+
<h3> nitrate </h3><dl>
|
| 379 |
+
|
| 380 |
+
<p></p><dt> Nitrate group
|
| 381 |
+
</dt><dd> [$([NX3](=[OX1])(=[OX1])O),$([NX3+]([OX1-])(=[OX1])O)]
|
| 382 |
+
</dd><dd> Also hits nitrate anion
|
| 383 |
+
|
| 384 |
+
<p></p></dd><dt> Nitrate Anion
|
| 385 |
+
</dt><dd> [$([OX1]=[NX3](=[OX1])[OX1-]),$([OX1]=[NX3+]([OX1-])[OX1-])]<p></p></dd></dl><br>
|
| 386 |
+
|
| 387 |
+
<h3> nitrile </h3><dl>
|
| 388 |
+
|
| 389 |
+
<p></p><dt> Nitrile
|
| 390 |
+
</dt><dd> [NX1]#[CX2]
|
| 391 |
+
|
| 392 |
+
<p></p></dd><dt> Isonitrile
|
| 393 |
+
</dt><dd> [CX1-]#[NX2+]<p></p></dd></dl><br>
|
| 394 |
+
|
| 395 |
+
<h3> nitro </h3><dl>
|
| 396 |
+
|
| 397 |
+
<p></p><dt> Nitro group.
|
| 398 |
+
</dt><dd> [$([NX3](=O)=O),$([NX3+](=O)[O-])][!#8] Hits both forms.
|
| 399 |
+
|
| 400 |
+
<p></p></dd><dt> Two Nitro groups
|
| 401 |
+
</dt><dd> [$([NX3](=O)=O),$([NX3+](=O)[O-])][!#8].[$([NX3](=O)=O),$([NX3+](=O)[O-])][!#8]<p></p></dd></dl><br>
|
| 402 |
+
|
| 403 |
+
<h3> nitroso </h3><dl>
|
| 404 |
+
|
| 405 |
+
<p></p><dt> Nitroso-group
|
| 406 |
+
</dt><dd> [NX2]=[OX1]<p></p></dd></dl><br>
|
| 407 |
+
|
| 408 |
+
<h3> n-oxide </h3><dl>
|
| 409 |
+
|
| 410 |
+
<p></p><dt> N-Oxide
|
| 411 |
+
</dt><dd> [$([#7+][OX1-]),$([#7v5]=[OX1]);!$([#7](~[O])~[O]);!$([#7]=[#7])]
|
| 412 |
+
</dd><dd> Hits both forms. Won't hit azoxy, nitro, nitroso,or nitrate.<p></p></dd></dl><br>
|
| 413 |
+
|
| 414 |
+
|
| 415 |
+
<a name="O"></a><h2>O</h2>
|
| 416 |
+
|
| 417 |
+
|
| 418 |
+
<h3> hydroxyl (includes alcohol, phenol) </h3><dl>
|
| 419 |
+
|
| 420 |
+
<p></p><dt> Hydroxyl
|
| 421 |
+
</dt><dd> [OX2H]
|
| 422 |
+
|
| 423 |
+
<p></p></dd><dt> Hydroxyl in Alcohol
|
| 424 |
+
</dt><dd> [#6][OX2H]
|
| 425 |
+
|
| 426 |
+
<p></p></dd><dt> Hydroxyl in Carboxylic Acid
|
| 427 |
+
</dt><dd> [OX2H][CX3]=[OX1]
|
| 428 |
+
|
| 429 |
+
<p></p></dd><dt> Hydroxyl in H-O-P-
|
| 430 |
+
</dt><dd> [OX2H]P
|
| 431 |
+
|
| 432 |
+
<p></p></dd><dt> Enol
|
| 433 |
+
</dt><dd> [OX2H][#6X3]=[#6]
|
| 434 |
+
|
| 435 |
+
<p></p></dd><dt> Phenol
|
| 436 |
+
</dt><dd> [OX2H][cX3]:[c]
|
| 437 |
+
|
| 438 |
+
<p></p></dd><dt> Enol or Phenol
|
| 439 |
+
</dt><dd> [OX2H][$(C=C),$(cc)]
|
| 440 |
+
|
| 441 |
+
<p></p></dd><dt> Hydroxyl_acidic
|
| 442 |
+
</dt><dd> [$([OH]-*=[!#6])]
|
| 443 |
+
</dd><dd> An acidic hydroxyl is a hydroxyl bonded to an atom which is multiply bonded to a hetero atom, this includes carboxylic, sulphur, phosphorous,
|
| 444 |
+
halogen and nitrogen oxyacids.<p></p></dd></dl><br>
|
| 445 |
+
|
| 446 |
+
<h3> peroxide </h3><dl>
|
| 447 |
+
|
| 448 |
+
<p></p><dt> Peroxide groups.
|
| 449 |
+
</dt><dd> [OX2,OX1-][OX2,OX1-]
|
| 450 |
+
</dd><dd> Also hits anions.<p></p></dd></dl><br>
|
| 451 |
+
|
| 452 |
+
|
| 453 |
+
<a name="P"></a><h2>P</h2>
|
| 454 |
+
|
| 455 |
+
|
| 456 |
+
<h3> phosphoric compounds </h3><dl>
|
| 457 |
+
|
| 458 |
+
<p></p><dt> Phosphoric_acid groups.
|
| 459 |
+
</dt><dd> [$(P(=[OX1])([$([OX2H]),$([OX1-]),$([OX2]P)])([$([OX2H]),$([OX1-]),$([OX2]P)])[$([OX2H]),$([OX1-]),$([OX2]P)]),$([P+]([OX1-])([$([OX2H]),$([OX1-]),$([OX2]P)])([$([OX2H]),$([OX1-]),$([OX2]P)])[$([OX2H]),$([OX1-]),$([OX2]P)])]
|
| 460 |
+
</dd><dd> Hits both depiction forms. Hits orthophosphoric acid and polyphosphoric acid anhydrides. Doesn't hit monophosphoric acid anhydride
|
| 461 |
+
esters (including acidic mono- & di- esters) but will hit some polyphosphoric acid anhydride esters (mono- esters on pyrophosphoric acid
|
| 462 |
+
and longer, di- esters on linear triphosphoric acid and longer).
|
| 463 |
+
|
| 464 |
+
<p></p></dd><dt> Phosphoric_ester groups.
|
| 465 |
+
</dt><dd> [$(P(=[OX1])([OX2][#6])([$([OX2H]),$([OX1-]),$([OX2][#6])])[$([OX2H]),$([OX1-]),$([OX2][#6]),$([OX2]P)]),$([P+]([OX1-])([OX2][#6])([$([OX2H]),$([OX1-]),$([OX2][#6])])[$([OX2H]),$([OX1-]),$([OX2][#6]),$([OX2]P)])]
|
| 466 |
+
</dd><dd> Hits both depiction forms. Doesn't hit non-ester phosphoric_acid groups.<p></p></dd></dl><br>
|
| 467 |
+
|
| 468 |
+
<a name="S"></a><h2>S</h2>
|
| 469 |
+
|
| 470 |
+
|
| 471 |
+
<h3>thio groups ( thio-, thi-, sulpho-, mercapto- )</h3><dl>
|
| 472 |
+
|
| 473 |
+
|
| 474 |
+
<p></p><dt> Carbo-Thiocarboxylate
|
| 475 |
+
</dt><dd> [S-][CX3](=S)[#6]
|
| 476 |
+
|
| 477 |
+
<p></p></dd><dt> Carbo-Thioester
|
| 478 |
+
</dt><dd> S([#6])[CX3](=O)[#6]
|
| 479 |
+
|
| 480 |
+
<p></p></dd><dt> Thio analog of carbonyl
|
| 481 |
+
</dt><dd> [#6X3](=[SX1])([!N])[!N]
|
| 482 |
+
</dd><dd> Where S replaces O. Not a thioamide.
|
| 483 |
+
|
| 484 |
+
<p></p></dd><dt> Thiol, Sulfide or Disulfide Sulfur
|
| 485 |
+
</dt><dd> [SX2]
|
| 486 |
+
|
| 487 |
+
<p></p></dd><dt> Thiol
|
| 488 |
+
</dt><dd> [#16X2H]
|
| 489 |
+
|
| 490 |
+
<p></p></dd><dt> Sulfur with at-least one hydrogen.
|
| 491 |
+
</dt><dd> [#16!H0]
|
| 492 |
+
|
| 493 |
+
<p></p></dd><dt> Thioamide
|
| 494 |
+
</dt><dd> [NX3][CX3]=[SX1]<p></p></dd></dl><br>
|
| 495 |
+
|
| 496 |
+
<h3>sulfide</h3><dl>
|
| 497 |
+
|
| 498 |
+
<p></p><dt> Sulfide
|
| 499 |
+
</dt><dd> [#16X2H0]
|
| 500 |
+
</dd><dd> -alkylthio Won't hit thiols. Hits disulfides.
|
| 501 |
+
|
| 502 |
+
<p></p></dd><dt> Mono-sulfide
|
| 503 |
+
</dt><dd> [#16X2H0][!#16]
|
| 504 |
+
</dd><dd> alkylthio- or alkoxy- Won't hit thiols. Won't hit disulfides.
|
| 505 |
+
|
| 506 |
+
<p></p></dd><dt> Di-sulfide
|
| 507 |
+
</dt><dd> [#16X2H0][#16X2H0]
|
| 508 |
+
</dd><dd> Won't hit thiols. Won't hit mono-sulfides.
|
| 509 |
+
|
| 510 |
+
<p></p></dd><dt> Two Sulfides
|
| 511 |
+
</dt><dd> [#16X2H0][!#16].[#16X2H0][!#16]
|
| 512 |
+
</dd><dd> Won't hit thiols. Won't hit mono-sulfides. Won't hit disulfides.<p></p></dd></dl><br>
|
| 513 |
+
|
| 514 |
+
<h3>sulfinate</h3><dl>
|
| 515 |
+
|
| 516 |
+
<p></p><dt> Sulfinate
|
| 517 |
+
</dt><dd> [$([#16X3](=[OX1])[OX2H0]),$([#16X3+]([OX1-])[OX2H0])]
|
| 518 |
+
</dd><dd> Won't hit Sulfinic Acid. Hits Both Depiction Forms.
|
| 519 |
+
|
| 520 |
+
<p></p></dd><dt> Sulfinic Acid
|
| 521 |
+
</dt><dd> [$([#16X3](=[OX1])[OX2H,OX1H0-]),$([#16X3+]([OX1-])[OX2H,OX1H0-])]
|
| 522 |
+
</dd><dd> Won't hit substituted Sulfinates. Hits Both Depiction Forms.
|
| 523 |
+
Hits acid and conjugate base (sulfinate).<p></p></dd></dl><br>
|
| 524 |
+
|
| 525 |
+
<h3>sulfone</h3><dl>
|
| 526 |
+
|
| 527 |
+
<p></p><dt> Sulfone. Low specificity.
|
| 528 |
+
</dt><dd> [$([#16X4](=[OX1])=[OX1]),$([#16X4+2]([OX1-])[OX1-])]
|
| 529 |
+
</dd><dd> Hits all sulfones, including heteroatom-substituted sulfones: sulfonic acid, sulfonate, sulfuric acid mono- & di- esters, sulfamic
|
| 530 |
+
acid, sulfamate, sulfonamide... Hits Both Depiction Forms.
|
| 531 |
+
|
| 532 |
+
<p></p></dd><dt> Sulfone. High specificity.
|
| 533 |
+
</dt><dd> [$([#16X4](=[OX1])(=[OX1])([#6])[#6]),$([#16X4+2]([OX1-])([OX1-])([#6])[#6])]
|
| 534 |
+
</dd><dd> Only hits carbo- sulfones (Won't hit herteroatom-substituted molecules). Hits Both Depiction Forms.
|
| 535 |
+
|
| 536 |
+
<p></p></dd><dt> Sulfonic acid. High specificity.
|
| 537 |
+
</dt><dd> [$([#16X4](=[OX1])(=[OX1])([#6])[OX2H,OX1H0-]),$([#16X4+2]([OX1-])([OX1-])([#6])[OX2H,OX1H0-])]
|
| 538 |
+
</dd><dd> Only hits carbo- sulfonic acids (Won't hit herteroatom-substituted molecules).
|
| 539 |
+
Hits acid and conjugate base. Hits Both Depiction Forms. Hits Arene sulfonic acids.
|
| 540 |
+
|
| 541 |
+
<p></p></dd><dt> Sulfonate
|
| 542 |
+
</dt><dd> [$([#16X4](=[OX1])(=[OX1])([#6])[OX2H0]),$([#16X4+2]([OX1-])([OX1-])([#6])[OX2H0])]
|
| 543 |
+
</dd><dd> (sulfonic ester) Only hits carbon-substituted sulfur
|
| 544 |
+
(Oxygen may be herteroatom-substituted). Hits Both Depiction Forms.
|
| 545 |
+
|
| 546 |
+
<p></p></dd><dt> Sulfonamide.
|
| 547 |
+
</dt><dd> [$([#16X4]([NX3])(=[OX1])(=[OX1])[#6]),$([#16X4+2]([NX3])([OX1-])([OX1-])[#6])]
|
| 548 |
+
</dd><dd> Only hits carbo- sulfonamide. Hits Both Depiction Forms.
|
| 549 |
+
|
| 550 |
+
<p></p></dd><dt> Carbo-azosulfone
|
| 551 |
+
</dt><dd> [SX4](C)(C)(=O)=N
|
| 552 |
+
</dd><dd> Partial N-Analog of Sulfone
|
| 553 |
+
|
| 554 |
+
<p></p></dd><dt> Sulfonamide
|
| 555 |
+
</dt><dd> [$([SX4](=[OX1])(=[OX1])([!O])[NX3]),$([SX4+2]([OX1-])([OX1-])([!O])[NX3])]
|
| 556 |
+
</dd><dd> (sulf drugs) Won't hit sulfamic acid or sulfamate. Hits Both Depiction Forms.<p></p></dd></dl><br>
|
| 557 |
+
|
| 558 |
+
<h3>sulfoxide</h3><dl>
|
| 559 |
+
|
| 560 |
+
<p></p><dt> Sulfoxide Low specificity.
|
| 561 |
+
</dt><dd> [$([#16X3]=[OX1]),$([#16X3+][OX1-])]
|
| 562 |
+
</dd><dd> ( sulfinyl, thionyl ) Analog of carbonyl where S replaces C.
|
| 563 |
+
Hits all sulfoxides, including heteroatom-substituted sulfoxides,
|
| 564 |
+
dialkylsulfoxides carbo-sulfoxides, sulfinate, sulfinic acids...
|
| 565 |
+
Hits Both Depiction Forms. Won't hit sulfones.
|
| 566 |
+
|
| 567 |
+
<p></p></dd><dt> Sulfoxide High specificity
|
| 568 |
+
</dt><dd> [$([#16X3](=[OX1])([#6])[#6]),$([#16X3+]([OX1-])([#6])[#6])]
|
| 569 |
+
</dd><dd> (sulfinyl , thionyl) Analog of carbonyl where S replaces C. Only hits carbo-sulfoxides
|
| 570 |
+
(Won't hit herteroatom-substituted molecules). Hits Both Depiction Forms. Won't hit sulfones.<p></p></dd></dl><br>
|
| 571 |
+
|
| 572 |
+
<h3>sulfate</h3><dl>
|
| 573 |
+
|
| 574 |
+
<p></p><dt> Sulfate
|
| 575 |
+
</dt><dd> [$([#16X4](=[OX1])(=[OX1])([OX2H,OX1H0-])[OX2][#6]),$([#16X4+2]([OX1-])([OX1-])([OX2H,OX1H0-])[OX2][#6])]
|
| 576 |
+
</dd><dd> (sulfuric acid monoester) Only hits when oxygen is carbon-substituted.
|
| 577 |
+
Hits acid and conjugate base. Hits Both Depiction Forms.
|
| 578 |
+
|
| 579 |
+
<p></p></dd><dt> Sulfuric acid ester (sulfate ester) Low specificity.
|
| 580 |
+
</dt><dd> [$([SX4](=O)(=O)(O)O),$([SX4+2]([O-])([O-])(O)O)]
|
| 581 |
+
</dd><dd> Hits sulfuric acid, sulfuric acid monoesters (sulfuric acids) and diesters (sulfates).
|
| 582 |
+
Hits acid and conjugate base. Hits Both Depiction Forms.
|
| 583 |
+
<p></p></dd><dt> Sulfuric Acid Diester.
|
| 584 |
+
</dt><dd> [$([#16X4](=[OX1])(=[OX1])([OX2][#6])[OX2][#6]),$([#16X4](=[OX1])(=[OX1])([OX2][#6])[OX2][#6])]
|
| 585 |
+
</dd><dd> Only hits when oxygen is carbon-substituted. Hits Both Depiction Forms.<p></p></dd></dl><br>
|
| 586 |
+
|
| 587 |
+
<h3>sulfamate</h3><dl>
|
| 588 |
+
|
| 589 |
+
<p></p><dt> Sulfamate.
|
| 590 |
+
</dt><dd> [$([#16X4]([NX3])(=[OX1])(=[OX1])[OX2][#6]),$([#16X4+2]([NX3])([OX1-])([OX1-])[OX2][#6])]
|
| 591 |
+
</dd><dd> Only hits when oxygen is carbon-substituted. Hits Both Depiction Forms.
|
| 592 |
+
|
| 593 |
+
<p></p></dd><dt> Sulfamic Acid.
|
| 594 |
+
</dt><dd> [$([#16X4]([NX3])(=[OX1])(=[OX1])[OX2H,OX1H0-]),$([#16X4+2]([NX3])([OX1-])([OX1-])[OX2H,OX1H0-])]
|
| 595 |
+
</dd><dd> Hits acid and conjugate base. Hits Both Depiction Forms.<p></p></dd></dl><br>
|
| 596 |
+
|
| 597 |
+
<h3>sulfene</h3><dl>
|
| 598 |
+
|
| 599 |
+
<p></p><dt> Sulfenic acid.
|
| 600 |
+
</dt><dd> [#16X2][OX2H,OX1H0-]
|
| 601 |
+
</dd><dd> Hits acid and conjugate base.
|
| 602 |
+
|
| 603 |
+
<p></p></dd><dt> Sulfenate.
|
| 604 |
+
</dt><dd> [#16X2][OX2H0]<p></p></dd></dl><br>
|
| 605 |
+
|
| 606 |
+
|
| 607 |
+
<a name="X"></a><h2>X</h2>
|
| 608 |
+
|
| 609 |
+
|
| 610 |
+
<h3> halide (-halo -fluoro -chloro -bromo -iodo) </h3><dl>
|
| 611 |
+
|
| 612 |
+
<p></p><dt> Any carbon attached to any halogen
|
| 613 |
+
</dt><dd> [#6][F,Cl,Br,I]
|
| 614 |
+
|
| 615 |
+
<p></p></dd><dt> Halogen
|
| 616 |
+
</dt><dd> [F,Cl,Br,I]
|
| 617 |
+
|
| 618 |
+
<p></p></dd><dt> Three_halides groups
|
| 619 |
+
</dt><dd> [F,Cl,Br,I].[F,Cl,Br,I].[F,Cl,Br,I]
|
| 620 |
+
</dd><dd> Hits SMILES that have three halides.<p></p></dd></dl><br>
|
| 621 |
+
|
| 622 |
+
<h3> acyl halide </h3><dl>
|
| 623 |
+
|
| 624 |
+
<p></p><dt> Acyl Halide
|
| 625 |
+
</dt><dd> [CX3](=[OX1])[F,Cl,Br,I]
|
| 626 |
+
</dd><dd> (acid halide, -oyl halide)<p></p></dd></dl><br>
|
| 627 |
+
|
| 628 |
+
|
| 629 |
+
<a name="STRUCTUAL"></a>
|
| 630 |
+
<h2>
|
| 631 |
+
3. Gross Structual Features
|
| 632 |
+
</h2><br><br>
|
| 633 |
+
|
| 634 |
+
|
| 635 |
+
<table border="" cols="6" width="750" nosave=""><tbody><tr>
|
| 636 |
+
<td align="center"><a href="#CHIRALITY">Chirality</a></td>
|
| 637 |
+
<td align="center"><a href="#ORBITAL">Orbital Configuration</a></td>
|
| 638 |
+
<td align="center"><a href="#CONNECT">Connectivity</a></td>
|
| 639 |
+
<td align="center"><a href="#CHAIN"> Chains & Branching</a></td>
|
| 640 |
+
<td align="center"><a href="#ROTATE">Rotation</a></td>
|
| 641 |
+
<td align="center"><a href="#CYCLE">Cyclic Features</a></td>
|
| 642 |
+
</tr></tbody></table><br><br>
|
| 643 |
+
|
| 644 |
+
|
| 645 |
+
<a name="CHIRALITY"></a><h2>Chirality</h2>
|
| 646 |
+
<dl>
|
| 647 |
+
<p></p><dt> Specified chiral carbon.
|
| 648 |
+
</dt><dd> [$([#6X4@](*)(*)(*)*),$([#6X4@H](*)(*)*)]
|
| 649 |
+
</dd><dd> Matches carbons whose chirality is specified (clockwise or anticlockwise) Will not match molecules whose chirality is unspecified b
|
| 650 |
+
ut that could otherwise be considered chiral. Also,therefore won't match molecules that would be chiral due to an implicit connection (i.e.i
|
| 651 |
+
mplicit H).
|
| 652 |
+
|
| 653 |
+
<p></p></dd><dt> "No-conflict" chiral match
|
| 654 |
+
</dt><dd> C[C@?](F)(Cl)Br
|
| 655 |
+
</dd><dd> Will match molecules with chiralities as specified or unspecified.
|
| 656 |
+
|
| 657 |
+
<p></p></dd><dt> "No-conflict" chiral match where an H is present
|
| 658 |
+
</dt><dd> C[C@?H](Cl)Br
|
| 659 |
+
</dd><dd> Will match molecules with chiralities as specified or unspecified.<p></p></dd></dl><br>
|
| 660 |
+
|
| 661 |
+
<a name="ORBITAL"></a><h2>Orbital Configuration</h2>
|
| 662 |
+
|
| 663 |
+
<dl>
|
| 664 |
+
<p></p><dt> sp2 cationic carbon
|
| 665 |
+
</dt><dd> [$([cX2+](:*):*)]
|
| 666 |
+
</dd><dd> Aromatic cationic sp2 carbon with a free electron in a non-bonding sp2 hybrid orbital
|
| 667 |
+
|
| 668 |
+
<p></p></dd><dt> Aromatic sp2 carbon.
|
| 669 |
+
</dt><dd> [$([cX3](:*):*),$([cX2+](:*):*)]
|
| 670 |
+
</dd><dd> The first recursive SMARTS matches carbons that are three-connected, the second case matches two-connected carbons (i.e cations with
|
| 671 |
+
a free electron in a non-bonding sp2 hybrid orbital)
|
| 672 |
+
|
| 673 |
+
<p></p></dd><dt> Any sp2 carbon.
|
| 674 |
+
</dt><dd> [$([cX3](:*):*),$([cX2+](:*):*),$([CX3]=*),$([CX2+]=*)]
|
| 675 |
+
</dd><dd> The first recursive SMARTS matches carbons that are three-connected and aromatic. The second case matches two-connected aromatic ca
|
| 676 |
+
rbons (i.e cations with a free electron in a non-bonding sp2 hybrid orbital). The third case matches three-connected non-aromatic carbons (
|
| 677 |
+
alkenes). The fourth case matches non-aromatic cationic alkene carbons.
|
| 678 |
+
|
| 679 |
+
<p></p></dd><dt> Any sp2 nitrogen.
|
| 680 |
+
</dt><dd> [$([nX3](:*):*),$([nX2](:*):*),$([#7X2]=*),$([NX3](=*)=*),$([#7X3+](-*)=*),$([#7X3+H]=*)]
|
| 681 |
+
|
| 682 |
+
</dd><dd> Can be aromatic 3-connected with 2 aromatic bonds (eg pyrrole,Pyridine-N-oxide), aromatic 2-connected with 2 aromatic bonds (and a free
|
| 683 |
+
pair of electrons in a nonbonding orbital, e.g.Pyridine), either aromatic or non-aromatic 2-connected with a double bond (and a free pair
|
| 684 |
+
of electrons in a nonbonding orbital, e.g. C=N ), non aromatic 3-connected with 2 double bonds (e.g. a nitro group; this form does not exist
|
| 685 |
+
in reality, SMILES can represent the charge-separated resonance structures as a single uncharged structure), either aromatic or non-aromatic
|
| 686 |
+
3-connected cation w/ 1 single bond and 1 double bond (e.g. a nitro group, here the individual charge-separated resonance structures are
|
| 687 |
+
specified), either aromatic or non-aromatic 3-connected hydrogenated cation with a double bond (as the previous case but R is hydrogen),
|
| 688 |
+
rspectively.
|
| 689 |
+
|
| 690 |
+
<p></p></dd><dt> Explicit Hydrogen on sp2-Nitrogen
|
| 691 |
+
</dt><dd> [$([#1X1][$([nX3](:*):*),$([nX2](:*):*),$([#7X2]=*),$([NX3](=*)=*),$([#7X3+](-*)=*),$([#7X3+H]=*)])]
|
| 692 |
+
</dd><dd> (H must be an isotope or ion)
|
| 693 |
+
|
| 694 |
+
<p></p></dd><dt> sp3 nitrogen
|
| 695 |
+
</dt><dd> [$([NX4+]),$([NX3]);!$(*=*)&!$(*:*)]
|
| 696 |
+
</dd><dd> One atom that is (a 4-connected N cation or a 3-connected N) and is not double bonded and is not aromatically bonded.
|
| 697 |
+
|
| 698 |
+
<p></p></dd><dt> Explicit Hydrogen on an sp3 N.
|
| 699 |
+
</dt><dd> [$([#1X1][$([NX4+]),$([NX3]);!$(*=*)&!$(*:*)])]
|
| 700 |
+
</dd><dd> One atom that is a 1-connected H that is bonded to an sp3 N. (H must be an isotope or ion)
|
| 701 |
+
|
| 702 |
+
<p></p></dd><dt> sp2 N in N-Oxide
|
| 703 |
+
</dt><dd> [$([$([NX3]=O),$([NX3+][O-])])]
|
| 704 |
+
|
| 705 |
+
<p></p></dd><dt> sp3 N in N-Oxide Exclusive:
|
| 706 |
+
</dt><dd> [$([$([NX4]=O),$([NX4+][O-])])]
|
| 707 |
+
</dd><dd> Only hits if O is explicitly present. Won't hit if * is in SMILES in place of O.
|
| 708 |
+
|
| 709 |
+
<p></p></dd><dt> sp3 N in N-Oxide Inclusive:
|
| 710 |
+
</dt><dd> [$([$([NX4]=O),$([NX4+][O-,#0])])]
|
| 711 |
+
</dd><dd> Hits if O could be present. Hits if * if used in place of O in smiles.<p></p></dd></dl><br>
|
| 712 |
+
|
| 713 |
+
|
| 714 |
+
<a name="CONNECT"></a><h2>Connectivity</h2>
|
| 715 |
+
|
| 716 |
+
<dl>
|
| 717 |
+
<p></p><dt> Quaternary Nitrogen
|
| 718 |
+
</dt><dd> [$([NX4+]),$([NX4]=*)]
|
| 719 |
+
</dd><dd> Hits non-aromatic Ns.
|
| 720 |
+
<p></p></dd><dt> Tricoordinate S double bonded to N.
|
| 721 |
+
</dt><dd> [$([SX3]=N)]
|
| 722 |
+
|
| 723 |
+
<p></p></dd><dt> S double-bonded to Carbon
|
| 724 |
+
</dt><dd> [$([SX1]=[#6])]
|
| 725 |
+
</dd><dd> Hits terminal (1-connected S)
|
| 726 |
+
|
| 727 |
+
<p></p></dd><dt> Triply bonded N
|
| 728 |
+
</dt><dd> [$([NX1]#*)]
|
| 729 |
+
|
| 730 |
+
<p></p></dd><dt> Divalent Oxygen
|
| 731 |
+
</dt><dd> [$([OX2])]<p></p></dd></dl><br>
|
| 732 |
+
|
| 733 |
+
|
| 734 |
+
<a name="CHAIN"></a><h2>Chains & Branching </h2>
|
| 735 |
+
|
| 736 |
+
<dl>
|
| 737 |
+
<p></p><dt> Unbranched_alkane groups.
|
| 738 |
+
</dt><dd> [R0;D2][R0;D2][R0;D2][R0;D2]
|
| 739 |
+
</dd><dd> Only hits alkanes (single-bond chains). Only hits chains of at-least 4 members. All non-(implicit-hydrogen) atoms count as branches
|
| 740 |
+
(e.g. halide substituted chains count as branched).
|
| 741 |
+
|
| 742 |
+
<p></p></dd><dt> Unbranched_chain groups.
|
| 743 |
+
</dt><dd> [R0;D2]~[R0;D2]~[R0;D2]~[R0;D2]
|
| 744 |
+
</dd><dd> Hits any bond (single, double, triple). Only hits chains of at-least 4 members. All non-(implicit-hydrogen) atoms count as branches
|
| 745 |
+
(e.g. halide substituted chains count as branched).
|
| 746 |
+
|
| 747 |
+
<p></p></dd><dt> Long_chain groups.
|
| 748 |
+
</dt><dd> [AR0]~[AR0]~[AR0]~[AR0]~[AR0]~[AR0]~[AR0]~[AR0]
|
| 749 |
+
</dd><dd> Aliphatic chains at-least 8 members long.
|
| 750 |
+
|
| 751 |
+
<p></p></dd><dt> Atom_fragment
|
| 752 |
+
</dt><dd> [!$([#6+0]);!$(C(F)(F)F);!$(c(:[!c]):[!c])!$([#6]=,#[!#6])]
|
| 753 |
+
</dd><dd> (CLOGP definition) A fragment atom is a not an isolating carbon
|
| 754 |
+
|
| 755 |
+
<p></p></dd><dt> Carbon_isolating
|
| 756 |
+
</dt><dd> [$([#6+0]);!$(C(F)(F)F);!$(c(:[!c]):[!c])!$([#6]=,#[!#6])]
|
| 757 |
+
</dd><dd> This definition is based on that in CLOGP, so it is a charge-neutral carbon, which is not a CF3 or an aromatic C between two aromati
|
| 758 |
+
c hetero atoms eg in tetrazole, it is not multiply bonded to a hetero atom.
|
| 759 |
+
|
| 760 |
+
<p></p></dd><dt> Terminal S bonded to P
|
| 761 |
+
</dt><dd> [$([SX1]~P)]
|
| 762 |
+
|
| 763 |
+
<p></p></dd><dt> Nitrogen on -N-C=N-
|
| 764 |
+
</dt><dd> [$([NX3]C=N)]
|
| 765 |
+
|
| 766 |
+
<p></p></dd><dt> Nitrogen on -N-N=C-
|
| 767 |
+
</dt><dd> [$([NX3]N=C)]
|
| 768 |
+
|
| 769 |
+
<p></p></dd><dt> Nitrogen on -N-N=N-
|
| 770 |
+
</dt><dd> [$([NX3]N=N)]
|
| 771 |
+
|
| 772 |
+
<p></p></dd><dt> Oxygen in -O-C=N-
|
| 773 |
+
</dt><dd> [$([OX2]C=N)] <p></p></dd></dl><br>
|
| 774 |
+
|
| 775 |
+
|
| 776 |
+
<a name="ROTATE"></a><h2>Rotation</h2>
|
| 777 |
+
|
| 778 |
+
<dl>
|
| 779 |
+
<p></p><dt> Rotatable bond
|
| 780 |
+
</dt><dd> [!$(*#*)&!D1]-!@[!$(*#*)&!D1]
|
| 781 |
+
</dd><dd> An atom which is not triply bonded and not one-connected i.e.terminal connected by a single non-ring bond to and equivalent atom. Note
|
| 782 |
+
that logical operators can be applied to bonds ("-&!@"). Here, the overall SMARTS consists of two atoms and one bond. The bond is "site
|
| 783 |
+
and not ring". *#* any atom triple bonded to any atom. By enclosing this SMARTS in parentheses and preceding with $, this enables us to
|
| 784 |
+
use $(*#*) to write a recursive SMARTS using that string as an atom primitive. The purpose is to avoid bonds such as c1ccccc1-C#C which wo
|
| 785 |
+
be considered rotatable without this specification.<p></p></dd></dl><br>
|
| 786 |
+
|
| 787 |
+
|
| 788 |
+
<a name="CYCLE"></a><h2>Cyclic Features</h2>
|
| 789 |
+
|
| 790 |
+
<dl>
|
| 791 |
+
<p></p><dt> Bicyclic
|
| 792 |
+
</dt><dd> [$([*R2]([*R])([*R])([*R]))].[$([*R2]([*R])([*R])([*R]))]
|
| 793 |
+
</dd><dd> Bicyclic compounds have 2 bridgehead atoms with 3 arms connecting the bridgehead atoms.
|
| 794 |
+
|
| 795 |
+
<p></p></dd><dt> Ortho
|
| 796 |
+
</dt><dd> *-!:aa-!:*
|
| 797 |
+
</dd><dd> Ortho-substituted ring
|
| 798 |
+
|
| 799 |
+
<p></p></dd><dt> Meta
|
| 800 |
+
</dt><dd> *-!:aaa-!:*
|
| 801 |
+
</dd><dd> Meta-substituted ring
|
| 802 |
+
|
| 803 |
+
<p></p></dd><dt> Para
|
| 804 |
+
</dt><dd> *-!:aaaa-!:*
|
| 805 |
+
</dd><dd> Para-substituted ring
|
| 806 |
+
|
| 807 |
+
<p></p></dd><dt> Acylic-bonds
|
| 808 |
+
</dt><dd> *!@*
|
| 809 |
+
|
| 810 |
+
<p></p></dd><dt> Single bond and not in a ring
|
| 811 |
+
</dt><dd> *-!@*
|
| 812 |
+
|
| 813 |
+
<p></p></dd><dt> Non-ring atom
|
| 814 |
+
</dt><dd> [R0] or [!R]
|
| 815 |
+
|
| 816 |
+
<p></p></dd><dt> Macrocycle groups.
|
| 817 |
+
</dt><dd> [r;!r3;!r4;!r5;!r6;!r7]
|
| 818 |
+
|
| 819 |
+
<p></p></dd><dt> S in aromatic 5-ring with lone pair
|
| 820 |
+
</dt><dd> [sX2r5]
|
| 821 |
+
|
| 822 |
+
<p></p></dd><dt> Aromatic 5-Ring O with Lone Pair
|
| 823 |
+
</dt><dd> [oX2r5]
|
| 824 |
+
|
| 825 |
+
<p></p></dd><dt> N in 5-sided aromatic ring
|
| 826 |
+
</dt><dd> [nX2r5]
|
| 827 |
+
|
| 828 |
+
<p></p></dd><dt> Spiro-ring center
|
| 829 |
+
</dt><dd> [X4;R2;r4,r5,r6](@[r4,r5,r6])(@[r4,r5,r6])(@[r4,r5,r6])@[r4,r5,r6]rings size 4-6
|
| 830 |
+
|
| 831 |
+
<p></p></dd><dt> N in 5-ring arom
|
| 832 |
+
</dt><dd> [$([nX2r5]:[a-]),$([nX2r5]:[a]:[a-])] anion
|
| 833 |
+
|
| 834 |
+
<p></p></dd><dt> CIS or TRANS double bond in a ring
|
| 835 |
+
</dt><dd> */,\[R]=;@[R]/,\*
|
| 836 |
+
</dd><dd> An isomeric SMARTS consisting of four atoms and three bonds.
|
| 837 |
+
|
| 838 |
+
<p></p></dd><dt> CIS or TRANS double or aromatic bond in a ring
|
| 839 |
+
</dt><dd> */,\[R]=,:;@[R]/,\*
|
| 840 |
+
|
| 841 |
+
<p></p></dd><dt> Unfused benzene ring
|
| 842 |
+
</dt><dd> [cR1]1[cR1][cR1][cR1][cR1][cR1]1
|
| 843 |
+
</dd><dd> To find a benzene ring which is not fused, we write a SMARTS of 6 aromatic carbons in a ring where each atom is only in one ring:
|
| 844 |
+
|
| 845 |
+
<p></p></dd><dt> Multiple non-fused benzene rings
|
| 846 |
+
</dt><dd> [cR1]1[cR1][cR1][cR1][cR1][cR1]1.[cR1]1[cR1][cR1][cR1][cR1][cR1]1
|
| 847 |
+
|
| 848 |
+
<p></p></dd><dt> Fused benzene rings
|
| 849 |
+
</dt><dd> c12ccccc1cccc2<p></p></dd></dl><br>
|
| 850 |
+
|
| 851 |
+
|
| 852 |
+
<a name="META"></a>
|
| 853 |
+
<h2>
|
| 854 |
+
4. Meta-SMARTS
|
| 855 |
+
</h2><br><br>
|
| 856 |
+
|
| 857 |
+
<table border="" cols="3" width="750" nosave=""><tbody><tr>
|
| 858 |
+
<td align="center"><a href="#AA">Amino Acids </a></td>
|
| 859 |
+
<td align="center"><a href="#RECUR"> Recursive or Multiple </a></td>
|
| 860 |
+
<td align="center"><a href="#TOOL">Tools &Tricks </a></td>
|
| 861 |
+
</tr></tbody></table><br><br>
|
| 862 |
+
|
| 863 |
+
|
| 864 |
+
<a name="AA"></a><h2>Amino Acids</h2>
|
| 865 |
+
|
| 866 |
+
<dl>
|
| 867 |
+
<p></p><dt> Generic amino acid: low specificity.
|
| 868 |
+
</dt><dd> [NX3,NX4+][CX4H]([*])[CX3](=[OX1])[O,N]
|
| 869 |
+
</dd><dd> For use w/ non-standard a.a. search. hits pro but not gly. Hits acids and conjugate bases. Hits single a.a.s and specific residues
|
| 870 |
+
w/in polypeptides (internal, or terminal).
|
| 871 |
+
|
| 872 |
+
<p></p></dd><dt> A.A. Template for 20 standard a.a.s
|
| 873 |
+
</dt><dd> [$([$([NX3H,NX4H2+]),$([NX3](C)(C)(C))]1[CX4H]([CH2][CH2][CH2]1)[CX3](=[OX1])[OX2H,OX1-,N]),<br>$([$([NX3H2,NX4H3+]),$([NX3H](C)(C))][CX4H2][CX3](=[OX1])[OX2H,OX1-,N]),$([$([NX3H2,NX4H3+]),$([NX3H](C)(C))][CX4H]([*])[CX3](=[OX1])[OX2H,OX1-,N])]
|
| 874 |
+
|
| 875 |
+
</dd><dd> Pro, Gly, Other. Replace * w/ the entire 18_standard_side_chains list to get "any standard a.a." Hits acids and conjugate bases.
|
| 876 |
+
Hits single a.a.s and specific residues w/in polypeptides (internal, or terminal).
|
| 877 |
+
|
| 878 |
+
<p></p></dd><dt> Proline
|
| 879 |
+
</dt><dd> [$([NX3H,NX4H2+]),$([NX3](C)(C)(C))]1[CX4H]([CH2][CH2][CH2]1)[CX3](=[OX1])[OX2H,OX1-,N]
|
| 880 |
+
|
| 881 |
+
<p></p></dd><dt> Glycine
|
| 882 |
+
</dt><dd> [$([$([NX3H2,NX4H3+]),$([NX3H](C)(C))][CX4H2][CX3](=[OX1])[OX2H,OX1-,N])]
|
| 883 |
+
|
| 884 |
+
<p></p></dd><dt> Other a.a.
|
| 885 |
+
</dt><dd> [$([NX3H2,NX4H3+]),$([NX3H](C)(C))][CX4H]([*])[CX3](=[OX1])[OX2H,OX1-,N]
|
| 886 |
+
</dd><dd> Replace * w/ a specific a.a. side chain from the 18_standard_side_chains list to hit a specific standard a.a. Won't work with Proline
|
| 887 |
+
or Glycine, they have their own SMARTS (see side chain list). Hits acids and conjugate bases. Hits single a.a.s and specific residues w/i
|
| 888 |
+
polypeptides (internal, or terminal).<br>
|
| 889 |
+
Example usage:<br>
|
| 890 |
+
Alanine side chain is [CH3X4] <br>
|
| 891 |
+
Alanine Search is [$([NX3H2,NX4H3+]),$([NX3H](C)(C))][CX4H]([CH3X4])[CX3](=[OX1])[OX2H,OX1-,N]
|
| 892 |
+
|
| 893 |
+
<p></p></dd><dt> 18_standard_aa_side_chains.
|
| 894 |
+
</dt><dd> ([$([CH3X4]),$([CH2X4][CH2X4][CH2X4][NHX3][CH0X3](=[NH2X3+,NHX2+0])[NH2X3]),<br>
|
| 895 |
+
$([CH2X4][CX3](=[OX1])[NX3H2]),$([CH2X4][CX3](=[OX1])[OH0-,OH]),<br>
|
| 896 |
+
$([CH2X4][SX2H,SX1H0-]),$([CH2X4][CH2X4][CX3](=[OX1])[OH0-,OH]),<br>
|
| 897 |
+
$([CH2X4][#6X3]1:[$([#7X3H+,#7X2H0+0]:[#6X3H]:[#7X3H]),$([#7X3H])]:<br>
|
| 898 |
+
[#6X3H]:[$([#7X3H+,#7X2H0+0]:[#6X3H]:[#7X3H]),$([#7X3H])]:[#6X3H]1),<br>
|
| 899 |
+
$([CHX4]([CH3X4])[CH2X4][CH3X4]),$([CH2X4][CHX4]([CH3X4])[CH3X4]),<br>
|
| 900 |
+
$([CH2X4][CH2X4][CH2X4][CH2X4][NX4+,NX3+0]),$([CH2X4][CH2X4][SX2][CH3X4]),<br>
|
| 901 |
+
$([CH2X4][cX3]1[cX3H][cX3H][cX3H][cX3H][cX3H]1),$([CH2X4][OX2H]),<br>
|
| 902 |
+
$([CHX4]([CH3X4])[OX2H]),$([CH2X4][cX3]1[cX3H][nX3H][cX3]2[cX3H][cX3H][cX3H][cX3H][cX3]12),<br>
|
| 903 |
+
$([CH2X4][cX3]1[cX3H][cX3H][cX3]([OHX2,OH0X1-])[cX3H][cX3H]1),$([CHX4]([CH3X4])[CH3X4])])
|
| 904 |
+
</dd><dd>Can be any of the standard 18 (Pro & Gly are treated separately) Hits acids and conjugate bases.
|
| 905 |
+
|
| 906 |
+
<p></p></dd><dt> N in Any_standard_amino_acid.
|
| 907 |
+
</dt><dd> [$([$([NX3H,NX4H2+]),$([NX3](C)(C)(C))]1[CX4H]([CH2][CH2][CH2]1)[CX3]<br>
|
| 908 |
+
(=[OX1])[OX2H,OX1-,N]),$([$([NX3H2,NX4H3+]),$([NX3H](C)(C))][CX4H2][CX3]<br>
|
| 909 |
+
(=[OX1])[OX2H,OX1-,N]),$([$([NX3H2,NX4H3+]),$([NX3H](C)(C))][CX4H]([$([CH3X4]),<br>
|
| 910 |
+
$([CH2X4][CH2X4][CH2X4][NHX3][CH0X3](=[NH2X3+,NHX2+0])[NH2X3]),$<br>
|
| 911 |
+
([CH2X4][CX3](=[OX1])[NX3H2]),$([CH2X4][CX3](=[OX1])[OH0-,OH]),<br>
|
| 912 |
+
$([CH2X4][SX2H,SX1H0-]),$([CH2X4][CH2X4][CX3](=[OX1])[OH0-,OH]),<br>
|
| 913 |
+
$([CH2X4][#6X3]1:[$([#7X3H+,#7X2H0+0]:[#6X3H]:[#7X3H]),$([#7X3H])]:<br>
|
| 914 |
+
[#6X3H]:[$([#7X3H+,#7X2H0+0]:[#6X3H]:[#7X3H]),$([#7X3H])]:[#6X3H]1),<br>
|
| 915 |
+
$([CHX4]([CH3X4])[CH2X4][CH3X4]),$([CH2X4][CHX4]([CH3X4])[CH3X4]),<br>
|
| 916 |
+
$([CH2X4][CH2X4][CH2X4][CH2X4][NX4+,NX3+0]),$([CH2X4][CH2X4][SX2][CH3X4]),<br>
|
| 917 |
+
$([CH2X4][cX3]1[cX3H][cX3H][cX3H][cX3H][cX3H]1),$([CH2X4][OX2H]),<br>
|
| 918 |
+
$([CHX4]([CH3X4])[OX2H]),$([CH2X4][cX3]1[cX3H][nX3H][cX3]2[cX3H][cX3H][cX3H][cX3H][cX3]12),<br>
|
| 919 |
+
$([CH2X4][cX3]1[cX3H][cX3H][cX3]([OHX2,OH0X1-])[cX3H][cX3H]1),<br>
|
| 920 |
+
$([CHX4]([CH3X4])[CH3X4])])[CX3](=[OX1])[OX2H,OX1-,N])]
|
| 921 |
+
</dd><dd> Format is A.A.Template for 20 standard a.a.s. where * is replaced by the entire 18_standard_side_chains list (or'd together). A gen
|
| 922 |
+
eric amino acid with any of the 18 side chains or, proline or glycine. Hits "standard" amino acids that have terminally appended groups (i.e
|
| 923 |
+
. "standard" refers to the side chains). (Pro, Gly, or 18 normal a.a.s.) Hits single a.a.s and specific residues w/in polypeptides (intern
|
| 924 |
+
al, or terminal).
|
| 925 |
+
|
| 926 |
+
<p></p></dd><dt> Non-standard amino acid.
|
| 927 |
+
</dt><dd> [$([NX3,NX4+][CX4H]([*])[CX3](=[OX1])[O,N]);!$([$([$([NX3H,NX4H2+]),<br>
|
| 928 |
+
$([NX3](C)(C)(C))]1[CX4H]([CH2][CH2][CH2]1)[CX3](=[OX1])[OX2H,OX1-,N]),<br>
|
| 929 |
+
$([$([NX3H2,NX4H3+]),$([NX3H](C)(C))][CX4H2][CX3](=[OX1])[OX2H,OX1-,N]),<br>
|
| 930 |
+
$([$([NX3H2,NX4H3+]),$([NX3H](C)(C))][CX4H]([$([CH3X4]),$([CH2X4][CH2X4][CH2X4][NHX3][CH0X3]<br>
|
| 931 |
+
(=[NH2X3+,NHX2+0])[NH2X3]),$([CH2X4][CX3](=[OX1])[NX3H2]),$([CH2X4][CX3](=[OX1])[OH0-,OH]),<br>
|
| 932 |
+
$([CH2X4][SX2H,SX1H0-]),$([CH2X4][CH2X4][CX3](=[OX1])[OH0-,OH]),$([CH2X4][#6X3]1:<br>
|
| 933 |
+
[$([#7X3H+,#7X2H0+0]:[#6X3H]:[#7X3H]),$([#7X3H])]:<br>
|
| 934 |
+
[#6X3H]:[$([#7X3H+,#7X2H0+0]:[#6X3H]:[#7X3H]),<br>
|
| 935 |
+
$([#7X3H])]:[#6X3H]1),$([CHX4]([CH3X4])[CH2X4][CH3X4]),$([CH2X4][CHX4]([CH3X4])[CH3X4]),<br>
|
| 936 |
+
$([CH2X4][CH2X4][CH2X4][CH2X4][NX4+,NX3+0]),$([CH2X4][CH2X4][SX2][CH3X4]),<br>
|
| 937 |
+
$([CH2X4][cX3]1[cX3H][cX3H][cX3H][cX3H][cX3H]1),$([CH2X4][OX2H]),$([CHX4]([CH3X4])[OX2H]),<br>
|
| 938 |
+
$([CH2X4][cX3]1[cX3H][nX3H][cX3]2[cX3H][cX3H][cX3H][cX3H][cX3]12),<br>
|
| 939 |
+
$([CH2X4][cX3]1[cX3H][cX3H][cX3]([OHX2,OH0X1-])[cX3H][cX3H]1),<br>
|
| 940 |
+
$([CHX4]([CH3X4])[CH3X4])])[CX3](=[OX1])[OX2H,OX1-,N])])]
|
| 941 |
+
</dd><dd> Generic amino acid but not a "standard" amino acid ("standard" refers to the 20 normal side chains). Won't hit amino acids that are
|
| 942 |
+
non-standard due solely to the fact that groups are terminally-appended to the polypeptide chain (N or C term). format is [$(generic a.a.);
|
| 943 |
+
!$(not a standard one)] Hits single a.a.s and specific residues w/in polypeptides (internal, or terminal).<p></p></dd></dl><br>
|
| 944 |
+
|
| 945 |
+
|
| 946 |
+
<a name="RECUR"></a><h2>Recursive or Multiple </h2>
|
| 947 |
+
|
| 948 |
+
<h3> Recursive SMARTS: Atoms connected to particular SMARTS</h3><dl>
|
| 949 |
+
|
| 950 |
+
<p></p><dt> Ortho
|
| 951 |
+
</dt><dd>[SMARTS_expression]-!:aa-!:[SMARTS_expression]
|
| 952 |
+
|
| 953 |
+
<p></p></dd><dt> Meta
|
| 954 |
+
</dt><dd> [SMARTS_expression]-!:aaa-!:[SMARTS_expression]
|
| 955 |
+
|
| 956 |
+
<p></p></dd><dt> Para
|
| 957 |
+
</dt><dd> [SMARTS_expression]-!:aaaa-!:[SMARTS_expression]
|
| 958 |
+
|
| 959 |
+
<p></p></dd><dt> Hydrogen
|
| 960 |
+
</dt><dd> [$([#1][SMARTS_expression])]
|
| 961 |
+
</dd><dd> Hydrogen must be explicit i.e. an isotope or charged
|
| 962 |
+
|
| 963 |
+
<p></p></dd><dt> Nitrogen
|
| 964 |
+
</dt><dd> [$([#7][SMARTS_expression])]
|
| 965 |
+
|
| 966 |
+
<p></p></dd><dt> Oxygen
|
| 967 |
+
</dt><dd> [$([#8][SMARTS_expression])]
|
| 968 |
+
|
| 969 |
+
<p></p></dd><dt> Fluorine
|
| 970 |
+
</dt><dd> [$([#9][SMARTS_expression])]<p></p></dd></dl><br>
|
| 971 |
+
|
| 972 |
+
<h3> Recursive SMARTS: Multiple groups</h3><dl>
|
| 973 |
+
|
| 974 |
+
<p></p><dt> Two possible groups
|
| 975 |
+
</dt><dd> [$(SMARTS_expression_A),$(SMARTS_expression_B)]
|
| 976 |
+
</dd><dd> Hits atoms in either environment or group of interest, A or B.<br>
|
| 977 |
+
Example usages:<br>
|
| 978 |
+
Azide group is : [$(*-[NX2-]-[NX2+]#[NX1]),$(*-[NX2]=[NX2+]=[NX1-])]<br>
|
| 979 |
+
Azide ion is: [$([NX1-]=[NX2+]=[NX1-]),$([NX1]#[NX2+]-[NX1-2])]<br>
|
| 980 |
+
Azide or azide ion is: [$([$(*-[NX2-]-[NX2+]#[NX1]),$(*-[NX2]=[NX2+]=[NX1-])]),$([$([NX1-]=[NX2+]=[NX1-]),$(
|
| 981 |
+
[NX1]#[NX2+]-[NX1-2])])]
|
| 982 |
+
|
| 983 |
+
<p></p></dd><dt> Recursive SMARTS
|
| 984 |
+
</dt><dd> [$([atom_that_gets_hit][other_atom][other_atom])]
|
| 985 |
+
</dd><dd> Hits first atom within parenthesis
|
| 986 |
+
Example usages:<br>
|
| 987 |
+
[$([CX3]=[OX1])] hits Carbonyl Carbon
|
| 988 |
+
[$([OX1]=[CX3])] hits Carbonyl Oxygen <p></p></dd></dl><br>
|
| 989 |
+
|
| 990 |
+
<h3> Single only, Double only, Single or Double</h3><dl>
|
| 991 |
+
|
| 992 |
+
<p></p><dt> Sulfide
|
| 993 |
+
</dt><dd> [#16X2H0]
|
| 994 |
+
</dd><dd> (-alkylthio) Won't hit thiols. Hits disulfides too.
|
| 995 |
+
|
| 996 |
+
<p></p></dd><dt> Mono-sulfide
|
| 997 |
+
</dt><dd> [#16X2H0][!#16]
|
| 998 |
+
</dd><dd> (alkylthio- or alkoxy-) R-S-R Won't hit thiols. Won't hit disulfides.
|
| 999 |
+
|
| 1000 |
+
<p></p></dd><dt> Di-sulfide
|
| 1001 |
+
</dt><dd> [#16X2H0][#16X2H0]
|
| 1002 |
+
</dd><dd> Won't hit thiols. Won't hit mono-sulfides.
|
| 1003 |
+
|
| 1004 |
+
<p></p></dd><dt> Two sulfides
|
| 1005 |
+
</dt><dd> [#16X2H0][!#16].[#16X2H0][!#16]
|
| 1006 |
+
|
| 1007 |
+
</dd><dd> Won't hit thiols. Won't hit mono-sulfides. Won't hit disulfides.
|
| 1008 |
+
|
| 1009 |
+
<p></p></dd><dt> Acid/conj-base
|
| 1010 |
+
</dt><dd> [OX2H,OX1H0-]
|
| 1011 |
+
</dd><dd> Hits acid and conjugate base. acid/base
|
| 1012 |
+
|
| 1013 |
+
<p></p></dd><dt> Non-acid Oxygen
|
| 1014 |
+
</dt><dd> [OX2H0]
|
| 1015 |
+
|
| 1016 |
+
<p></p></dd><dt> Acid/base
|
| 1017 |
+
</dt><dd> [H1,H0-]
|
| 1018 |
+
</dd><dd> Works for any atom if base form has no Hs & acid has only one.<p></p></dd></dl><br>
|
| 1019 |
+
|
| 1020 |
+
<h3> Muntiple Disconnected Groups</h3><dl>
|
| 1021 |
+
|
| 1022 |
+
<p></p><dt> Two disconnected SMARTS fragments
|
| 1023 |
+
</dt><dd> ([Cl!$(Cl~c)].[c!$(c~Cl)])
|
| 1024 |
+
</dd><dd> A molecule that contains a chlorine and an aromatic carbon but which are not connected to each other. Uses component-level SMARTS. B
|
| 1025 |
+
oth SMARTS fragments must be in the same SMILES target fragment.
|
| 1026 |
+
|
| 1027 |
+
<p></p></dd><dt> Two disconnected SMARTS fragments
|
| 1028 |
+
</dt><dd> ([Cl]).([c])
|
| 1029 |
+
</dd><dd> Hits SMILES that contain a chlorine and an aromatic carbon but which are in different SMILES fragments.
|
| 1030 |
+
|
| 1031 |
+
<p></p></dd><dt> Two not-necessarily connected SMARTS fragments
|
| 1032 |
+
</dt><dd> ([Cl].[c])
|
| 1033 |
+
</dd><dd> Uses component-level SMARTS. Both SMARTS fragments must be in the same SMILES target fragment.
|
| 1034 |
+
|
| 1035 |
+
<p></p></dd><dt> Two not-necessarily connected fragments
|
| 1036 |
+
</dt><dd> ([SMARTS_expression]).([SMARTS_expression])
|
| 1037 |
+
</dd><dd> Uses component-level SMARTS. SMARTS fragments are each in different SMILES target fragments.
|
| 1038 |
+
|
| 1039 |
+
<p></p></dd><dt> Two primary or secondary amines
|
| 1040 |
+
</dt><dd> [NX3;H2,H1;!$(NC=O)].[NX3;H2,H1;!$(NC=O)]
|
| 1041 |
+
</dd><dd> Here we use the "disconnection" symbol (".") to match two separate not-necessarily bonded identical patterns.<p></p></dd></dl><br>
|
| 1042 |
+
|
| 1043 |
+
|
| 1044 |
+
<a name="TOOL"></a><h2>Tools &Tricks</h2>
|
| 1045 |
+
|
| 1046 |
+
<h3> Alternative/Equivalent Representations </h3><dl>
|
| 1047 |
+
|
| 1048 |
+
<p></p><dt> Any carbon aromatic or non-aromatic
|
| 1049 |
+
</dt><dd> [#6] or [c,C]
|
| 1050 |
+
|
| 1051 |
+
<p></p></dd><dt> SMILES wildcard
|
| 1052 |
+
</dt><dd> [#0]
|
| 1053 |
+
</dd><dd> This SMARTS hits the SMILES *
|
| 1054 |
+
|
| 1055 |
+
<p></p></dd><dt> Factoring
|
| 1056 |
+
</dt><dd> [OX2,OX1-][OX2,OX1-] or [O;X2,X1-][O;X2,X1-]
|
| 1057 |
+
</dd><dd> Factor out common atomic expressions in the recursive SMARTS. May improve human readability.
|
| 1058 |
+
|
| 1059 |
+
<p></p></dd><dt> High-precidence "and"
|
| 1060 |
+
</dt><dd> [N&X4&+,N&X3&+0] or [NX4+,NX3+0]
|
| 1061 |
+
</dd><dd> High-precidence "and" (&) is the default logical operator. "Or" (,) is higher precidence than & and low-precidence "and" (;)
|
| 1062 |
+
is lower precidence than &. <p></p></dd></dl><br>
|
| 1063 |
+
|
| 1064 |
+
<h3> Hydrogens </h3><dl>
|
| 1065 |
+
|
| 1066 |
+
<p></p><dt> Any atom w/ at-least 1 H
|
| 1067 |
+
</dt><dd> [*!H0,#1]
|
| 1068 |
+
</dd><dd> In SMILES and SMARTS, Hydrogen is not considered an atom (unless it is specified as an isotope). The hydrogen count is instead consi
|
| 1069 |
+
dered a property of an atom. This SMARTS provides a way to effectively hit Hs themselves.
|
| 1070 |
+
|
| 1071 |
+
<p></p></dd><dt> Hs on Carbons
|
| 1072 |
+
</dt><dd> [#6!H0,#1]
|
| 1073 |
+
|
| 1074 |
+
<p></p></dd><dt> Atoms w/ 1 H
|
| 1075 |
+
</dt><dd> [H,#1] <p></p></dd></dl><br>
|
| 1076 |
+
|
| 1077 |
+
|
| 1078 |
+
<a name="E-"></a>
|
| 1079 |
+
<h2>
|
| 1080 |
+
5. Electron & Proton Features
|
| 1081 |
+
</h2><br><br>
|
| 1082 |
+
|
| 1083 |
+
<table border="" cols="3" width="750" nosave=""><tbody><tr>
|
| 1084 |
+
<td align="center"><a href="#ACID">Acids & Bases </a></td>
|
| 1085 |
+
<td align="center"><a href="#CHARGE">Charge</a></td>
|
| 1086 |
+
<td align="center"><a href="#H_BOND"> H-bond Donors & Acceptors</a></td>
|
| 1087 |
+
<td align="center"><a href="#RAD"> Radicals </a></td>
|
| 1088 |
+
</tr></tbody></table><br><br>
|
| 1089 |
+
|
| 1090 |
+
|
| 1091 |
+
<a name="ACID"></a><h2> Acids & Bases </h2>
|
| 1092 |
+
|
| 1093 |
+
<dl>
|
| 1094 |
+
<p></p><dt> Acid
|
| 1095 |
+
</dt><dd> [!H0;F,Cl,Br,I,N+,$([OH]-*=[!#6]),+]
|
| 1096 |
+
</dd><dd> Proton donor
|
| 1097 |
+
|
| 1098 |
+
<p></p></dd><dt> Carboxylic acid
|
| 1099 |
+
</dt><dd> [CX3](=O)[OX2H1]
|
| 1100 |
+
</dd><dd> (-oic acid, COOH)
|
| 1101 |
+
|
| 1102 |
+
<p></p></dd><dt> Carboxylic acid or conjugate base.
|
| 1103 |
+
</dt><dd> [CX3](=O)[OX1H0-,OX2H1]
|
| 1104 |
+
|
| 1105 |
+
<p></p></dd><dt> Hydroxyl_acidic
|
| 1106 |
+
</dt><dd> [$([OH]-*=[!#6])]
|
| 1107 |
+
</dd><dd> An acidic hydroxyl is a hydroxyl bonded to an atom which is multiply bonded to a hetero atom, this includes carboxylic, sulphur, pho
|
| 1108 |
+
sphorous, halogen and nitrogen oxyacids
|
| 1109 |
+
|
| 1110 |
+
<p></p></dd><dt> Phosphoric_Acid
|
| 1111 |
+
</dt><dd> [$(P(=[OX1])([$([OX2H]),$([OX1-]),$([OX2]P)])([$([OX2H]),$([OX1-]),$([OX2]P)])[$([OX2H]),$([OX1-]),$([OX2]P)]),$([P+]([OX1-])([$([OX2H]),$([OX1-]),$([OX2]P)])([$([OX2H]),$([OX1-]),$([OX2]P)])[$([OX2H]),$([OX1-]),$([OX2]P)])]
|
| 1112 |
+
</dd><dd> Hits both forms. Hits orthophosphoric acid and polyphosphoric acid anhydrides. Doesn't hit monophosphoric acid anhydride esters (in
|
| 1113 |
+
cluding acidic mono- & di- esters) but will hit some polyphosphoric acid anhydride esters (mono- esters on pyrophosphoric acid and longe
|
| 1114 |
+
r, di- esters on linear triphosphoric acid and longer). Hits acid and conjugate base.
|
| 1115 |
+
|
| 1116 |
+
<p></p></dd><dt> Sulfonic Acid. High specificity.
|
| 1117 |
+
</dt><dd> [$([#16X4](=[OX1])(=[OX1])([#6])[OX2H,OX1H0-]),$([#16X4+2]([OX1-])([OX1-])([#6])[OX2H,OX1H0-])]
|
| 1118 |
+
</dd><dd> Only hits carbo- sulfonic acids (Won't hit herteroatom-substituted molecules). Hits acid and conjugate base. Hits Both Depiction Fo
|
| 1119 |
+
rms. Hits Arene sulfonic acids.
|
| 1120 |
+
|
| 1121 |
+
<p></p></dd><dt> Acyl Halide
|
| 1122 |
+
</dt><dd> [CX3](=[OX1])[F,Cl,Br,I]
|
| 1123 |
+
</dd><dd> (acid halide, -oyl halide)<p></p></dd></dl><br>
|
| 1124 |
+
|
| 1125 |
+
|
| 1126 |
+
<a name="CHARGE"></a><h2>Charge </h2>
|
| 1127 |
+
|
| 1128 |
+
<dl>
|
| 1129 |
+
<p></p><dt> Anionic divalent Nitrogen
|
| 1130 |
+
</dt><dd> [NX2-]
|
| 1131 |
+
|
| 1132 |
+
<p></p></dd><dt> Oxenium Oxygen
|
| 1133 |
+
</dt><dd> [OX2H+]=*
|
| 1134 |
+
|
| 1135 |
+
<p></p></dd><dt> Oxonium Oxygen
|
| 1136 |
+
</dt><dd> [OX3H2+]
|
| 1137 |
+
|
| 1138 |
+
<p></p></dd><dt> Carbocation
|
| 1139 |
+
</dt><dd> [#6+]
|
| 1140 |
+
|
| 1141 |
+
<p></p></dd><dt> sp2 cationic carbon.
|
| 1142 |
+
</dt><dd> [$([cX2+](:*):*)]
|
| 1143 |
+
</dd><dd> Aromatic cationic sp2 carbon with a free electron in a non-bonding sp2 hybrid orbital
|
| 1144 |
+
|
| 1145 |
+
<p></p></dd><dt> Azide ion.
|
| 1146 |
+
</dt><dd> [$([NX1-]=[NX2+]=[NX1-]),$([NX1]#[NX2+]-[NX1-2])]
|
| 1147 |
+
</dd><dd> Hits N in azide ion
|
| 1148 |
+
|
| 1149 |
+
<p></p></dd><dt> Zwitterion High Specificity
|
| 1150 |
+
</dt><dd> [+1]~*~*~[-1]
|
| 1151 |
+
</dd><dd> +1 charged atom separated by any 3 bonds from a -1 charged atom.
|
| 1152 |
+
|
| 1153 |
+
<p></p></dd><dt> Zwitterion Low Specificity, Crude
|
| 1154 |
+
</dt><dd>[$([!-0!-1!-2!-3!-4]~*~[!+0!+1!+2!+3!+4]),$([!-0!-1!-2!-3!-4]~*~*~[!+0!+1!+2!+3!+4]),$([!-0!-1!-2!-3!-4]~*~*~*~[!+0!+1!+2!+3!+4]),$([!-0!-1!-2!-3!-4]~*~*~*~*~[!+0!+1!+2!+3!+4]),$([!-0!-1!-2!-3!-4]~*~*~*~*~*~[!+0!+1!+2!+3!+4]),$([!-0!-1!-2!-3!-4]~*~*~*~*~*~*~[!+0!+1!+2!+3!+4]),$([!-0!-1!-2!-3!-4]~*~*~*~*~*~*~*~[!+0!+1!+2!+3!+4]),$([!-0!-1!-2!-3!-4]~*~*~*~*~*~*~*~*~[!+0!+1!+2!+3!+4]),$([!-0!-1!-2!-3!-4]~*~*~*~*~*~*~*~*~*~[!+0!+1!+2!+3!+4])]
|
| 1155 |
+
</dd><dd> Variously charged moieties separated by up to ten bonds.
|
| 1156 |
+
|
| 1157 |
+
<p></p></dd><dt> Zwitterion Low Specificity
|
| 1158 |
+
</dt><dd> ([!-0!-1!-2!-3!-4].[!+0!+1!+2!+3!+4])
|
| 1159 |
+
</dd><dd> Variously charged moieties that are within the same molecule but not-necessarily connected. Uses component-level grouping.<p></p></dd></dl>
|
| 1160 |
+
<br>
|
| 1161 |
+
|
| 1162 |
+
|
| 1163 |
+
<a name="H_BOND"></a><h2> H-bond Donors & Acceptors</h2>
|
| 1164 |
+
|
| 1165 |
+
<dl>
|
| 1166 |
+
<p></p><dt> Hydrogen-bond acceptor
|
| 1167 |
+
</dt><dd> [#6,#7;R0]=[#8]
|
| 1168 |
+
</dd><dd> Only hits carbonyl and nitroso. Matches a 2-atom pattern consisting of a carbon or nitrogen not in a ring, double bonded to an oxyge
|
| 1169 |
+
n.
|
| 1170 |
+
|
| 1171 |
+
<p></p></dd><dt> Hydrogen-bond acceptor
|
| 1172 |
+
</dt><dd> [!$([#6,F,Cl,Br,I,o,s,nX3,#7v5,#15v5,#16v4,#16v6,*+1,*+2,*+3])]
|
| 1173 |
+
</dd><dd> A H-bond acceptor is a heteroatom with no positive charge, note that negatively charged oxygen or sulphur are included. Excluded are
|
| 1174 |
+
halogens, including F, heteroaromatic oxygen, sulphur and pyrrole N. Higher oxidation levels of N,P,S are excluded. Note P(III) is currentl
|
| 1175 |
+
y included. Zeneca's work would imply that (O=S=O) shoud also be excluded.
|
| 1176 |
+
|
| 1177 |
+
<p></p></dd><dt> Hydrogen-bond donor.
|
| 1178 |
+
</dt><dd> [!$([#6,H0,-,-2,-3])]
|
| 1179 |
+
</dd><dd> A H-bond donor is a non-negatively charged heteroatom with at least one H
|
| 1180 |
+
|
| 1181 |
+
<p></p></dd><dt> Hydrogen-bond donor.
|
| 1182 |
+
</dt><dd> [!H0;#7,#8,#9]
|
| 1183 |
+
</dd><dd> Must have an N-H bond, an O-H bond, or a F-H bond
|
| 1184 |
+
|
| 1185 |
+
<p></p></dd><dt> Possible intramolecular H-bond
|
| 1186 |
+
</dt><dd> [O,N;!H0]-*~*-*=[$([C,N;R0]=O)]
|
| 1187 |
+
</dd><dd> Note that the overall SMARTS consists of five atoms. The fifth atom is defined by a "recursive SMARTS", where "$()" encloses a valid
|
| 1188 |
+
nested SMARTS and acts syntactically like an atom-primitive in the overall SMARTS. Multiple nesting is allowed.<p></p></dd></dl><br>
|
| 1189 |
+
|
| 1190 |
+
<a name="RAD"></a><h2>Radicals </h2>
|
| 1191 |
+
|
| 1192 |
+
<dl>
|
| 1193 |
+
<p></p><dt> Carbon Free-Radical
|
| 1194 |
+
</dt><dd> [#6;X3v3+0]
|
| 1195 |
+
</dd><dd> Hits a neutral carbon with three single bonds.
|
| 1196 |
+
|
| 1197 |
+
<p></p></dd><dt> Nitrogen Free-Radical
|
| 1198 |
+
</dt><dd> [#7;X2v4+0]
|
| 1199 |
+
</dd><dd> Hits a neutral nitrogen with two single bonds or with a single and a triple bond. <p></p></dd></dl><br>
|
| 1200 |
+
|
| 1201 |
+
|
| 1202 |
+
<a name="BREAK"></a>
|
| 1203 |
+
<h2>
|
| 1204 |
+
6. Breakdown of Complex SMARTS
|
| 1205 |
+
</h2><br><br>
|
| 1206 |
+
|
| 1207 |
+
|
| 1208 |
+
<table border="" cols="2" width="750" nosave=""><tbody><tr>
|
| 1209 |
+
<td align="center"><a href="#AM_AC"> Amino Acid </a></td>
|
| 1210 |
+
<td align="center"><a href="#ES_AM"> Ester or Amide </a></td>
|
| 1211 |
+
<!--th><!--a href="#"> <!--/a></td>
|
| 1212 |
+
</table><br><br>
|
| 1213 |
+
|
| 1214 |
+
|
| 1215 |
+
<a NAME="AM_AC"><h2>Amino Acid </h2></a>
|
| 1216 |
+
|
| 1217 |
+
<b>[$([$([NX3H,NX4H2+]),$([NX3](C)(C)(C))]1[CX4H]([CH2][CH2][CH2]1)[CX3](=[OX1])[OX2H,OX1-,N]),$([$([NX3H2,NX4H3+]),$([NX3H](C)(C))][CX4H2][CX3](=[OX1])[OX2H,OX1-,N]),$([$([NX3H2,NX4H3+]),$([NX3H](C)(C))][CX4H]([*])[CX3](=[OX1])[OX2H,OX1-,N])]</b>
|
| 1218 |
+
|
| 1219 |
+
i<pre>
|
| 1220 |
+
[$( Proline
|
| 1221 |
+
[ N:
|
| 1222 |
+
$([ terminal
|
| 1223 |
+
NX3H neutral
|
| 1224 |
+
, or
|
| 1225 |
+
NX4H2+]) + charged
|
| 1226 |
+
, or
|
| 1227 |
+
$([NX3](C)(C)(C))]1 internal
|
| 1228 |
+
[CX4H] C: alpha
|
| 1229 |
+
([CH2][CH2][CH2]1) pro side chain
|
| 1230 |
+
[CX3] C: of COOH
|
| 1231 |
+
(=[OX1]) O: =O of COOH
|
| 1232 |
+
[OX2H,OX1-,N] O: term COOH (neutral or -) or intern
|
| 1233 |
+
), OR
|
| 1234 |
+
$( Glycine
|
| 1235 |
+
[ N:
|
| 1236 |
+
$([ terminal
|
| 1237 |
+
NX3H2 neutral
|
| 1238 |
+
, or
|
| 1239 |
+
NX4H3+]) + charged
|
| 1240 |
+
, or
|
| 1241 |
+
$([NX3H](C)(C)) internal
|
| 1242 |
+
[CX4H2] C: alpha (w/ H side chain)
|
| 1243 |
+
[CX3] C: of COOH
|
| 1244 |
+
(=[OX1]) O: =O of COOH
|
| 1245 |
+
[OX2H,OX1-,N] O: term COOH (neutral or -) or intern
|
| 1246 |
+
), OR
|
| 1247 |
+
$( Other amino acid
|
| 1248 |
+
[ N:
|
| 1249 |
+
$([ terminal
|
| 1250 |
+
NX3H2 neutral
|
| 1251 |
+
, or
|
| 1252 |
+
NX4H3+]) + charged
|
| 1253 |
+
, or
|
| 1254 |
+
$([NX3H](C)(C))] internal
|
| 1255 |
+
[CX4H] C: alpha
|
| 1256 |
+
([*]) any side chain
|
| 1257 |
+
[CX3] C: of COOH
|
| 1258 |
+
(=[OX1]) O: =O of COOH
|
| 1259 |
+
[OX2H,OX1-,N] O: term COOH (neutral or -) or intern
|
| 1260 |
+
)]
|
| 1261 |
+
</pre>
|
| 1262 |
+
|
| 1263 |
+
<br><br>
|
| 1264 |
+
<a NAME="ES_AM"><h2> Ester or Amide </h2></a>
|
| 1265 |
+
|
| 1266 |
+
|
| 1267 |
+
<b>[#6][CX3](=O)[$([OX2H0]([#6])[#6]),$([#7])] </b>
|
| 1268 |
+
<pre>
|
| 1269 |
+
[#6] An atom that is a carbon
|
| 1270 |
+
[CX3] Connected to an atom that is a three-connected carbon
|
| 1271 |
+
(=O) Which is double bonded to an oxygen
|
| 1272 |
+
[ Connected to an atom
|
| 1273 |
+
$( That is in an environment where
|
| 1274 |
+
[OX2H0] An atom that is a two-connected oxygen, without hydrogens
|
| 1275 |
+
([#6])[#6]) Is connected to two carbons, one of them being the carbonyl C
|
| 1276 |
+
, Or
|
| 1277 |
+
$( That is in an environment where
|
| 1278 |
+
[#7] An atom is a nitrogen.
|
| 1279 |
+
)]
|
| 1280 |
+
</pre>
|
| 1281 |
+
<br><br>
|
| 1282 |
+
<a NAME="EXMPL"></a>
|
| 1283 |
+
<H2>
|
| 1284 |
+
7. Interesting Example SMARTS
|
| 1285 |
+
</H2>
|
| 1286 |
+
|
| 1287 |
+
<dl>
|
| 1288 |
+
<p><dt> Oxygen double bonded to aliphatic carbon or nitrogen, single bonded to an aromatic ring, with a
|
| 1289 |
+
halogen in meta position
|
| 1290 |
+
<dd> [#8]=[C,N]-aaa[F,Cl,Br,I]
|
| 1291 |
+
|
| 1292 |
+
<p><dt> Aliphatic carbon attached to oxygen with any bond
|
| 1293 |
+
<dd> C~O
|
| 1294 |
+
|
| 1295 |
+
<p><dt> Oxygen or nitrogen, with at least one hydrogen attached and not in a ring
|
| 1296 |
+
<dd> [O,N;!H0;R0]
|
| 1297 |
+
|
| 1298 |
+
<p><dt> Oxygen double bonded to aliphatic carbon or nitrogen
|
| 1299 |
+
<dd> [#8]=[C,N] or O=[C,N]
|
| 1300 |
+
|
| 1301 |
+
<p><dt> Aliphatic atom single-bonded to any carbon which isn't a trifluromethyl carbon
|
| 1302 |
+
<dd> A[#6;!$(C(F)(F)F)]
|
| 1303 |
+
|
| 1304 |
+
<p><dt> PCB
|
| 1305 |
+
<dd> [$(c:cCl),$(c:c:cCl),$(c:c:c:cCl)]-[$(c:cCl),$(c:c:cCl),$(c:c:c:cCl)]
|
| 1306 |
+
<dd> Polychlorinated Biphenyls. Overall SMARTS is atom-bond-atom. Note that ":" is explicit aromatic bond, and "-" is explicit single bo
|
| 1307 |
+
nd. On each side of the single bond, we use three nested SMARTS to represent
|
| 1308 |
+
the ortho, meta, and para position.
|
| 1309 |
+
|
| 1310 |
+
<p><dt> Imidazolium Nitrogen
|
| 1311 |
+
<dd> [nX3r5+]:c:n
|
| 1312 |
+
|
| 1313 |
+
<p><dt> 1-methyl-2-hydroxy benzene with either a Cl or H at the 5 position.
|
| 1314 |
+
<dd> [c;$([*Cl]),$([*H1])]1ccc(O)c(C)c1 or Cc1:c(O):c:c:[$(cCl),$([cH])]:c1
|
| 1315 |
+
<dd> The "H" primitive in SMARTS means "total number
|
| 1316 |
+
of attached hydrogens", i.e., [C] will match C in [CH4] methane, [CH3]
|
| 1317 |
+
methyl, [CH2] methylene, etc., [CH3] will only match methyl. This is similar
|
| 1318 |
+
to the use of "H" in SMILES to specify hydrogen count. The default value
|
| 1319 |
+
for the SMARTS "H" primitive is 1 (same as SMILES, e.g., [CH2]=[CH]-[OH]
|
| 1320 |
+
same as CC=O). This H-specification value includes all attached hydrogens:
|
| 1321 |
+
implicit and explicit (e.g., isotopic [2H]).
|
| 1322 |
+
|
| 1323 |
+
<p><dt> Nonstandard atom groups.
|
| 1324 |
+
<dd> [!#1;!#2;!#3;!#5;!#6;!#7;!#8;!#9;!#11;!#12;!#15;!#16;!#17;!#19;!#20;!#35;!#53]</p></dl><br>
|
| 1325 |
+
<h2>More Information</h2>
|
| 1326 |
+
<A HREF="/dayhtml/doc/theory/theory.smarts.html">Theory Manual</A><br>
|
| 1327 |
+
<A HREF="/dayhtml_tutorials/languages/smarts/smarts_practice.html">SMARTS Practice</A><br>
|
| 1328 |
+
</td>
|
| 1329 |
+
</tr>
|
| 1330 |
+
<tr>
|
| 1331 |
+
<td><iframe src="/iframes/footer.html" name="iframe3" width="350" height="200"
|
| 1332 |
+
scrolling="no" frameborder="0"></iframe></td>
|
| 1333 |
+
</tr>
|
| 1334 |
+
</table>
|
| 1335 |
+
</body>
|
| 1336 |
+
</html>
|
| 1337 |
+
|
| 1338 |
+
--></tr></tbody></table></td>
|