handle the SKEMPI data

[code4luck]

hello, when i use python script/process_skempi.py --csv-path $SKEMPI_CSV_PATH --pdb-dir $SKEMPI_PDB_DIR --output-csv-path $PROCESSED_SKEMPI_CSV_PATH --output-pdb-dir $PROCESSED_SKEMPI_PDB_DIR --no-repair to handle the SKEMPI data(downlod from the SKEMPI[csv and PDBs]) its report ERROR: lack "#Pdb'" and "Mutation(s)_cleaned",?

[xianquzhe1]

你好，我也出现了上面的问题，请问解决掉了嘛

[TangHuihao]

Just add (in file process_skempi.py)
"aggr_data = aggr_data.reset_index()" line
between
"print(f"Fold {i}: {aggr_data.loc[pdbs].shape[0]} entries, {len(pdbs)} unique #Pdbs")" line 103
and "# convert format for subsequent processing" line 104.
it seems work for me for now.
the problem may because Multiindex of the dataframe.
but i still not sure this should be correct or not for the final results.

只需在(in file process_skempi.py)
“print(f"Fold {i}: {aggr_data.loc[pdbs].shape[0]} entries, {len(pdbs)} unique #Pdbs")"
和 "# convert format for subsequently processing" 行之间添加
“aggr_data = aggr_data.reset_index()”。

目前看来对我来说是可行的。
问题可能是因为数据框的多索引。
但我仍然不确定这对于最终结果是否正确。

[xianquzhe1]

感谢，我也已经解决掉了