Structural Protein Sequences

Sequence and meta data for various protein structures

@kaggle.shahir_protein_data_set

Table List

2 tables(50.85 MB)

Pdb Data No Dups

@kaggle.shahir_protein_data_set.pdb_data_no_dups

7.13 MB
141401 rows
14 columns

structureid StructureId	classification Classification	experimentaltechnique ExperimentalTechnique	macromoleculetype MacromoleculeType	residuecount ResidueCount	resolution Resolution	structuremolecularweight StructureMolecularWeight	crystallizationmethod CrystallizationMethod	crystallizationtempk CrystallizationTempK	densitymatthews DensityMatthews	densitypercentsol DensityPercentSol	pdbxdetails PdbxDetails	phvalue PhValue	publicationyear PublicationYear
100D	DNA-RNA HYBRID	X-RAY DIFFRACTION	DNA/RNA Hybrid	20	1.9	6360.3	VAPOR DIFFUSION, HANGING DROP		1.78	30.89	pH 7.00, VAPOR DIFFUSION, HANGING DROP	7	1994
101D	DNA	X-RAY DIFFRACTION	DNA	24	2.25	7939.35	nan		2	38.45	nan		1995
101M	OXYGEN TRANSPORT	X-RAY DIFFRACTION	Protein	154	2.07	18112.8	nan		3.09	60.2	3.0 M AMMONIUM SULFATE, 20 MM TRIS, 1MM EDTA, PH 9.0	9	1999
102D	DNA	X-RAY DIFFRACTION	DNA	24	2.2	7637.17	VAPOR DIFFUSION, SITTING DROP	277	2.28	46.06	pH 7.00, VAPOR DIFFUSION, SITTING DROP, temperature 277.00K	7	1995
102L	HYDROLASE(O-GLYCOSYL)	X-RAY DIFFRACTION	Protein	165	1.74	18926.61	nan		2.75	55.28	nan		1993
102M	OXYGEN TRANSPORT	X-RAY DIFFRACTION	Protein	154	1.84	18010.64	nan		3.09	60.2	3.0 M AMMONIUM SULFATE, 20 MM TRIS, 1MM EDTA, PH 9.0	9	1999
103D	DNA	SOLUTION NMR	DNA	24		7502.93	nan				nan		1994
103L	HYDROLASE(O-GLYCOSYL)	X-RAY DIFFRACTION	Protein	167	1.9	19092.72	nan		2.7	54.46	nan		1993
103M	OXYGEN TRANSPORT	X-RAY DIFFRACTION	Protein	154	2.07	18093.78	nan		3.09	60.3	3.0 M AMMONIUM SULFATE, 20 MM TRIS, 1MM EDTA, PH 9.0	9	1999
104D	DNA-RNA HYBRID	SOLUTION NMR	DNA/RNA Hybrid	24		7454.78	nan				nan		1995


CREATE TABLE pdb_data_no_dups (
  "structureid" VARCHAR,
  "classification" VARCHAR,
  "experimentaltechnique" VARCHAR,
  "macromoleculetype" VARCHAR,
  "residuecount" BIGINT,
  "resolution" DOUBLE,
  "structuremolecularweight" DOUBLE,
  "crystallizationmethod" VARCHAR,
  "crystallizationtempk" DOUBLE,
  "densitymatthews" DOUBLE,
  "densitypercentsol" DOUBLE,
  "pdbxdetails" VARCHAR,
  "phvalue" DOUBLE,
  "publicationyear" DOUBLE
);