ProFeatX

Amino Acid Composition (AAC), size=20

Dipeptide Composition (DPC), size=400

Tripeptide Composition (TPC), size=8000

Composition of K-Spaced Amino Acid Pairs (CKSAAP), vector size = 2400

All sequences must be longer than the gap value.

Max. gap [0, 20]

Dipeptide Deviation from Expected Mean (DDE), vector size = 400

Enhanced Amino Acid Composition (EAAC), vector size = (sequence length - 4) * 20
All sequences must be the same length and longer than the window value. Your sequences will be cropped to the length of the shortest sequence of your input.

Window size [1, 20]

Amino Acid Pair Antigenicity Scale (AAPAS), vector size = 400

Composition Moment Vector (CMV), vector size = 20

Grouped Amino Acid Composition (GAAC), vector size = 5

Enhanced Grouped Amino Acid Composition (EGAAC), vector size = (sequence length - 4) * 5

All sequences must be the same length and longer than the window value. Your sequences will be cropped to the length of the shortest sequence of your input.

Window size [1, 1000]

Composition of K-Spaced Amino Acid Group Pairs (CKSAAGP), vector size = 150

All sequences must be longer than the lag value.

Max. gap [0, 100]

Grouped Dipeptide Composition (GDPC), vector size = 25

Grouped Tripeptide Composition (GTPC), vector size = 125

Encoding Based on Grouped Weight (EBGW), vector size = 60

n [1, 1000]

Quasi-Sequence-Order (QSO), vector size = 100

All sequences must be longer than the lag value.

Lag [1, 1000]

Weight (0, 1)

Sequence-Order-Coupling Number (SOCN), vector size = 60

All sequences must be longer than the lag value.

Lag [1, 1000]

CTDC, vector size = 42

CTDT, vector size = 42

CTDD, vector size = 210

Conjoint Triad (CT), vector size = 343

All sequences must be longer than 2.

k-Spaced Conjoint Triad (KSCT), vector size = 646

All sequences must be longer than 2 * (k + 1).

k [1, 20]

Pseudo-Amino Acid Composition (PAAC), vector size = 50

All sequences must be longer than the lag value.

Lag [1, 1000]

Weight (0, 1)

Amphiphilic Pseudo-Amino Acid Composition (APAAC), vector size = 80

All sequences must be longer than the lag value.

Lag [1, 1000]

Weight (0, 1)

Binary, vector size = sequence length * 20

All sequences must be the same length. Your sequences will be cropped to the length of the shortest sequence of your input.

Taylor's Venn Diagram (TVD), vector size = sequence length

All sequences must be the same length. Your sequences will be cropped to the length of the shortest sequence of your input.

Pseudo k-Tuple Reduced Amino Acid Composition (PseKRAAC), vector size = 4

K-Tuple

Type

Reduced Amino Acid Cluster Type

Subtype

Gap [0, 9]

Lambda [1, 9]

PSSM, vector size = 20 * sequence length

All sequences must be the same length. Your sequences will be cropped to the length of the shortest sequence of your input.

Zip file with .pssm files (max. 10MB).

More info If no .zip file is provided, we will generate the .pssm files for 20 sequences at most. The .zip file should contain a single file per sequence. .pssm files are generated with PSI-BLAST.

No file chosen

PSSM Amino Acid Composition (PSSMAAC), vector size = 400

Zip file with .pssm files (max. 10MB)

More info If no .zip file is provided, we will generate the .pssm files for 20 sequences at most. The .zip file should contain a single file per sequence. .pssm files are generated with PSI-BLAST.

No file chosen

Bigram PSSM (BiPSSM), vector size = 400

All sequences length must be equal or greater than n + 1.

n [1, 30]

Zip file with .pssm files (max. 10MB)

More info If no .zip file is provided, we will generate the .pssm files for 20 sequences at most. The .zip file should contain a single file per sequence. .pssm files are generated with PSI-BLAST.

No file chosen

PSSM Autocovariance (PSSMAC), vector size = 400

All sequences length must be equal or greater than n + 1.

n [1, 30]

Zip file with .pssm files (max. 10MB)

More info If no .zip file is provided, we will generate the .pssm files for 20 sequences at most. The .zip file should contain a single file per sequence. .pssm files are generated with PSI-BLAST.

No file chosen

Pseudo-PSSM (PPSSM), vector size = 40

All sequences length must be equal or greater than n + 1.

n [1, 30]

Zip file with .pssm files (max. 10MB)

More info If no .zip file is provided, we will generate the .pssm files for 20 sequences at most. The .zip file should contain a single file per sequence. .pssm files are generated with PSI-BLAST.

No file chosen

Disorder, vector size = sequence length

All sequences must be the same length. Your sequences will be cropped to the length of the shortest sequence of your input.

Zip file with .csv files (max. 10MB)

More info If no .zip file is provided, we will generate the .csv files for 20 sequences at most. The .zip file should contain a single file per sequence. .csv files are generated with flDPnn.

No file chosen

Disorder Content (DisorderC), vector size = 2

Zip file with .csv files (max. 10MB)

More info If no .zip file is provided, we will generate the .csv files for 20 sequences at most. The .zip file should contain a single file per sequence. .csv files are generated with flDPnn.

No file chosen

Disorder Binary (DisorderB), vector size = 2 * sequence length

All sequences must be the same length. Your sequences will be cropped to the length of the shortest sequence of your input.

Zip file with .csv files (max. 10MB)

More info If no .zip file is provided, we will generate the .csv files for 20 sequences at most. The .zip file should contain a single file per sequence. .csv files are generated with flDPnn.

No file chosen

Secondary Structure Elements Binary (SSEB), vector size = 3 * sequence length

All sequences must be the same length. Your sequences will be cropped to the length of the shortest sequence of your input.

Zip file with .ss2, .spd33 or .spXout files (max. 10MB)

More info If no .zip file is provided, we will generate the .ss2 files for 20 sequences at most. The .zip file should contain a single file per sequence. .ss2 files are generated with PSIPRED, .spXout files are generated with SPINE-X, and .spd33 files are generated with SPIDER3.

No file chosen

Secondary Structure Elements Content (SSEC), vector size = 3

Zip file with .ss2, .spd33 or .spXout files (max. 10MB)

More info If no .zip file is provided, we will generate the .ss2 files for 20 sequences at most. The .zip file should contain a single file per sequence. .ss2 files are generated with PSIPRED, .spXout files are generated with SPINE-X, and .spd33 files are generated with SPIDER3.

No file chosen

Secondary Structure Probabilities Bigram (SSPB), vector size = 400

All sequences length must be equal or greater than n + 1.

n [1, 30]

Zip file with .ss2, .spd33 or .spXout files (max. 10MB)

More info If no .zip file is provided, we will generate the .ss2 files for 20 sequences at most. The .zip file should contain a single file per sequence. .ss2 files are generated with PSIPRED, .spXout files are generated with SPINE-X, and .spd33 files are generated with SPIDER3.

No file chosen

Secondary Structure Probabilities Autocovariance (SSPAC), vector size = 3

All sequences length must be equal or greater than n + 1.

n [1, 30]

Zip file with .ss2, .spd33 or .spXout files (max. 10MB)

More info If no .zip file is provided, we will generate the .ss2 files for 20 sequences at most. The .zip file should contain a single file per sequence. .ss2 files are generated with PSIPRED, .spXout files are generated with SPINE-X, and .spd33 files are generated with SPIDER3.

No file chosen

Torsion Angle (TA), vector size = 2 * sequence length

All sequences must be the same length. Your sequences will be cropped to the length of the shortest sequence of your input.

Zip file with .spXout or .spd33 files (max. 10MB)

More info A .zip file is mandatory. The .zip file should contain a single .spXout or .spd33 file per sequence. .spXout files are generated with SPINE-X and .spd33 files are generated with SPIDER3.

No file chosen

Torsion Angle Composition (TAC), vector size = 4

Zip file with .spXout or .spd33 files (max. 10MB)

More info A .zip file is mandatory. The .zip file should contain a single .spXout or .spd33 file per sequence. .spXout files are generated with SPINE-X and .spd33 files are generated with SPIDER3.

No file chosen

Torsion Angle Bigram (TAB), vector size = 400

All sequences length must be equal or greater than n + 1.

n [1, 30]

Zip file with .spXout or .spd33 files (max. 10MB)

More info A .zip file is mandatory. The .zip file should contain a single .spXout or .spd33 file per sequence. .spXout files are generated with SPINE-X and .spd33 files are generated with SPIDER3.

No file chosen

Torsion Angle Autocovariance (TAAC), vector size = 400

All sequences length must be equal or greater than n + 1.

n [1, 30]

Zip file with .spXout or .spd33 files (max. 10MB)

More info If no .zip file is provided, we will generate the .pssm files for 20 sequences at most. The .zip file should contain a single file per sequence. .pssm files are generated with PSI-BLAST.

No file chosen

Accessible Surface Area (ASA), vector size = sequence length

All sequences must be the same length. Your sequences will be cropped to the length of the shortest sequence of your input.

Zip file with .spXout or .spd33 files (max. 10MB)

More info A .zip file is mandatory. The .zip file should contain a single .spXout or .spd33 file per sequence. .spXout files are generated with SPINE-X and .spd33 files are generated with SPIDER3.

No file chosen

k-Nearest Neighbors - Peptide (KNNpeptide), vector size = 30 * number of classes

All sequences must be the same length. Your sequences will be cropped to the length of the shortest sequence of your input.

k [1, 100]

Training FASTA file (max. 10MB)
No file chosen

Labels file (max. 10MB) Example
No file chosen

k-Nearest Neighbors - Protein (KNNprotein), vector size = 30 * number of classes

k [1, 100]

Training FASTA file (max. 10MB)
No file chosen

Labels file (max. 10MB) Example
No file chosen

Amino Acid Index (AAI), vector size = sequence length * 531 All sequences must be the same length. Your sequences will be cropped to the length of the shortest sequence of your input.

BLOSUM62, vector size = sequence length * 20 All sequences must be the same length. Your sequences will be cropped to the length of the shortest sequence of your input.

Z-Scale (ZS), vector size = sequence length * 5
All sequences must be the same length. Your sequences will be cropped to the length of the shortest sequence of your input.

FASTA SEQUENCES

SET A

SET B

FASTA SEQUENCES

SET A

SET B

Amino acid composition-based descriptors

Grouped amino acid composition-based descriptors

Quasi-Sequence-Order-based descriptors

Autocorrelation-based descriptors

Composition/Transition/Distribution-based descriptors

Conjoint Triad-based descriptors

Pseudo-Amino Acid Composition-based descriptors

Binary-based descriptors

Pseudo k-Tuple Reduced Amino Acid Composition

PSSM-based descriptors (max. 20 sequences overall if generated)

Disorder-based descriptors (max. 20 sequences overall if generated)

Secondary structure-based descriptors (max. 20 sequences overall if generated)

Torsion angle-based and accessible surface area descriptors

k-Nearest Neighbors-based descriptors

Other descriptors