Protein Secondary Structure Casp12 Cb513 Ts115
dataset of casp12, cb513,ts115
@kaggle.tamzidhasan_protein_secondary_structure_casp12_cb513_ts115
dataset of casp12, cb513,ts115
@kaggle.tamzidhasan_protein_secondary_structure_casp12_cb513_ts115
Protein secondary structure can be calculated based on its atoms' 3D coordinates once the protein's 3D structure is solved using X-ray crystallography or NMR. The benchmark dataset casp13 , cb513 and ts115 is used in here . Every character in the secondary protein sequence is amino acid and described in below :
However, X-ray or NMR is expensive. Ideally, we would like to predict the secondary structure of a protein based on its primary sequence directly, which has had a long history.
The main dataset lists peptide sequences and their corresponding secondary structures.
Description of columns:
2. seq: the sequence of the peptide
3. sst3: the three-state (Q3) secondary structure
4. sst8: the eight-state (Q8) secondary structure
This is a secondary structure datasets with Eight states (H,B,E,G,I,T,S,C). There are 8679 Non-Redundant chains (25%) in training data set . Three state :[H=(G,H,I); E=(B,E); C=(T,S,C)]
The link of dataset - Protein Secondary Structure
CREATE TABLE test_secondary_structure_casp12 (
"seq" VARCHAR,
"sst3" VARCHAR,
"sst8" VARCHAR
);CREATE TABLE test_secondary_structure_cb513 (
"seq" VARCHAR,
"sst3" VARCHAR,
"sst8" VARCHAR
);CREATE TABLE test_secondary_structure_ts115 (
"seq" VARCHAR,
"sst3" VARCHAR,
"sst8" VARCHAR
);CREATE TABLE training_secondary_structure_train (
"seq" VARCHAR,
"sst3" VARCHAR,
"sst8" VARCHAR
);CREATE TABLE validation_secondary_structure_valid (
"seq" VARCHAR,
"sst3" VARCHAR,
"sst8" VARCHAR
);Anyone who has the link will be able to view this.