rdkit version and warning

[sonjaleo]

Because of the RDKit version 2020.03.3 used in KinFragLib, a warning is showing up
<frozen importlib._bootstrap>:219: RuntimeWarning: to-Python converter for boost::shared_ptr<RDKit::FilterCatalogEntry const> already registered; second conversion method ignored.
When updating RDKit to the current version, this warning disappears.
Actually, when updating RDKit, there occurs another problem with the pandas DataFrames in notebooks/custom_kinfraglib/1_1_custom_filters_unwanted_substructures.ipynb

I also found this warning in

• https://projects.volkamerlab.org/teachopencadd/talktorials/T003_compound_unwanted_substructures.html
• https://colab.research.google.com/github/DarkMatterAI/mrl/blob/master/nbs/tutorials/tutorials.generative_models.vae.ipynb

[dominiquesydow]

Actually, when updating RDKit, there occurs another problem with the pandas DataFrames in notebooks/custom_kinfraglib/1_1_custom_filters_unwanted_substructures.ipynb

What kind of problem occurs in this case?

[sonjaleo]

Actually, when updating RDKit, there occurs another problem with the pandas DataFrames in notebooks/custom_kinfraglib/1_1_custom_filters_unwanted_substructures.ipynb

What kind of problem occurs in this case?

It cannot display any pandas DataFrames anymore.
I can check later what kind of error message is shown when trying to access a DataFrame.

[sonjaleo]

After doing it again and checking the web again, I found that you already had that problem in TeachOpenCadd
https://githubmemory.com/repo/volkamerlab/teachopencadd/issues/131

`---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
~/.local/lib/python3.8/site-packages/IPython/core/formatters.py in call(self, obj)
700 type_pprinters=self.type_printers,
701 deferred_pprinters=self.deferred_printers)
--> 702 printer.pretty(obj)
703 printer.flush()
704 return stream.getvalue()

~/.local/lib/python3.8/site-packages/IPython/lib/pretty.py in pretty(self, obj)
392 if cls is not object
393 and callable(cls.dict.get('repr')):
--> 394 return _repr_pprint(obj, self, cycle)
395
396 return _default_pprint(obj, self, cycle)

~/.local/lib/python3.8/site-packages/IPython/lib/pretty.py in repr_pprint(obj, p, cycle)
698 """A pprint that just redirects to the normal repr function."""
699 # Find newlines and replace them with p.break()
--> 700 output = repr(obj)
701 lines = output.splitlines()
702 with p.group():

~/anaconda3/envs/kinfraglib/lib/python3.8/site-packages/pandas/core/frame.py in repr(self)
993 else:
994 width = None
--> 995 self.to_string(
996 buf=buf,
997 max_rows=max_rows,

~/anaconda3/envs/kinfraglib/lib/python3.8/site-packages/pandas/core/frame.py in to_string(self, buf, columns, col_space, header, index, na_rep, formatters, float_format, sparsify, index_names, justify, max_rows, min_rows, max_cols, show_dimensions, decimal, line_width, max_colwidth, encoding)
1129 decimal=decimal,
1130 )
-> 1131 return fmt.DataFrameRenderer(formatter).to_string(
1132 buf=buf,
1133 encoding=encoding,

~/anaconda3/envs/kinfraglib/lib/python3.8/site-packages/pandas/io/formats/format.py in to_string(self, buf, encoding, line_width)
1051
1052 string_formatter = StringFormatter(self.fmt, line_width=line_width)
-> 1053 string = string_formatter.to_string()
1054 return save_to_buffer(string, buf=buf, encoding=encoding)
1055

~/anaconda3/envs/kinfraglib/lib/python3.8/site-packages/pandas/io/formats/string.py in to_string(self)
23
24 def to_string(self) -> str:
---> 25 text = self._get_string_representation()
26 if self.fmt.should_show_dimensions:
27 text = "".join([text, self.fmt.dimensions_info])

~/anaconda3/envs/kinfraglib/lib/python3.8/site-packages/pandas/io/formats/string.py in _get_string_representation(self)
38 return self._empty_info_line
39
---> 40 strcols = self._get_strcols()
41
42 if self.line_width is None:

~/anaconda3/envs/kinfraglib/lib/python3.8/site-packages/pandas/io/formats/string.py in _get_strcols(self)
29
30 def _get_strcols(self) -> list[list[str]]:
---> 31 strcols = self.fmt.get_strcols()
32 if self.fmt.is_truncated:
33 strcols = self._insert_dot_separators(strcols)

~/anaconda3/envs/kinfraglib/lib/python3.8/site-packages/pandas/io/formats/format.py in get_strcols(self)
538 Render a DataFrame to a list of columns (as lists of strings).
539 """
--> 540 strcols = self._get_strcols_without_index()
541
542 if self.index:

~/anaconda3/envs/kinfraglib/lib/python3.8/site-packages/pandas/io/formats/format.py in _get_strcols_without_index(self)
802 int(self.col_space.get(c, 0)), *(self.adj.len(x) for x in cheader)
803 )
--> 804 fmt_values = self.format_col(i)
805 fmt_values = _make_fixed_width(
806 fmt_values, self.justify, minimum=header_colwidth, adj=self.adj

~/anaconda3/envs/kinfraglib/lib/python3.8/site-packages/pandas/io/formats/format.py in format_col(self, i)
816 frame = self.tr_frame
817 formatter = self._get_formatter(i)
--> 818 return format_array(
819 frame.iloc[:, i]._values,
820 formatter,

~/anaconda3/envs/kinfraglib/lib/python3.8/site-packages/pandas/io/formats/format.py in format_array(values, formatter, float_format, na_rep, digits, space, justify, decimal, leading_space, quoting)
1238 )
1239
-> 1240 return fmt_obj.get_result()
1241
1242

~/anaconda3/envs/kinfraglib/lib/python3.8/site-packages/pandas/io/formats/format.py in get_result(self)
1269
1270 def get_result(self) -> list[str]:
-> 1271 fmt_values = self._format_strings()
1272 return _make_fixed_width(fmt_values, self.justify)
1273

~/anaconda3/envs/kinfraglib/lib/python3.8/site-packages/pandas/io/formats/format.py in _format_strings(self)
1332 for i, v in enumerate(vals):
1333 if not is_float_type[i] and leading_space:
-> 1334 fmt_values.append(f" {_format(v)}")
1335 elif is_float_type[i]:
1336 fmt_values.append(float_format(v))

~/anaconda3/envs/kinfraglib/lib/python3.8/site-packages/pandas/io/formats/format.py in _format(x)
1312 else:
1313 # object dtype
-> 1314 return str(formatter(x))
1315
1316 vals = extract_array(self.values, extract_numpy=True)

~/anaconda3/envs/kinfraglib/lib/python3.8/site-packages/pandas/io/formats/printing.py in pprint_thing(thing, _nest_lvl, escape_chars, default_escapes, quote_strings, max_seq_items)
231 result = f"'{as_escaped_string(thing)}'"
232 else:
--> 233 result = as_escaped_string(thing)
234
235 return result

~/anaconda3/envs/kinfraglib/lib/python3.8/site-packages/pandas/io/formats/printing.py in as_escaped_string(thing, escape_chars)
207 escape_chars = escape_chars or ()
208
--> 209 result = str(thing)
210 for c in escape_chars:
211 result = result.replace(c, translate[c])

~/anaconda3/envs/kinfraglib/lib/python3.8/site-packages/rdkit/Chem/PandasTools.py in PrintAsBase64PNGString(x, renderer)
381 return svg.toxml()
382 else:
--> 383 data = Draw._moltoimg(x, molSize, highlightAtoms, "", returnPNG=True, kekulize=True)
384 return '' % _get_image(
385 data)

~/anaconda3/envs/kinfraglib/lib/python3.8/site-packages/rdkit/Chem/Draw/init.py in _moltoimg(mol, sz, highlights, legend, returnPNG, drawOptions, **kwargs)
479 highlightBonds=bondHighlights)
480 else:
--> 481 d2d.DrawMolecule(mc, legend=legend or "", highlightAtoms=highlights or [])
482 d2d.FinishDrawing()
483 if returnPNG:

ValueError: bad query type1`

Did you found a solution for this by now?

[dominiquesydow]

Can you please provide a minimal example of your problem?

In the issue that you referenced, I think the problem was that some molecules could not be displayed in the grid image, while the rest of the molecules were just fine. We did not fix this; we simply decided to display only those molecules that were not problematic.

[sonjaleo]

Can you please provide a minimal example of your problem?

In the issue that you referenced, I think the problem was that some molecules could not be displayed in the grid image, while the rest of the molecules were just fine. We did not fix this; we simply decided to display only those molecules that were not problematic.

Just load the environment, update rdkit (I used the newest version 2021.09.2) and then run notebooks/custom_kinfraglib/1_1_custom_filters_unwanted_substructures.ipynb
After trying to display the Brenk structures, it crashes.

You are right, it does not seem to be a problem with only this one structure. I tried it after removing this structure, but the error is still there.