BioSeq-Analysis2.0: an updated platform for analyzing DNA, RNA, and protein sequences at sequence level and residue level based on machine learning approaches

| Home | Server | Tutorial | Document | Download | Citation | Contact us |

---

DNA-Analysis2.0:

RNA-Analysis2.0:

Protein-Analysis2.0

AminoAcid_Residue

Mode(?)	---------------------------- ** Residue-Level ** ---------------------------- One-hot One-hot(6-bit) Binary(5-bit) AESNN3 Position-specific-2 PP SS-Residue SASA-Residue PAM250 BLOSUM62 PSSM PSFM CS-Residue ---------------------------- ** Sequence-Level ** ---------------------------- AAC GAAC MAC GAC NMBAC PAAC CTDC CTDD CTDT SOCNumber QSOrder ZSCALE TPC GTPC CKSAAP CKSAAGP SSEB Kmer DR Distance Pair AC CC ACC PDT PC-PseAAC SC-PseAAC PC-PseAAC-General SC-PseAAC-General Top-n-gram PDT-Profile DT AC-PSSM CC-PSSM ACC-PSSM SS SASA CS PSSM-RT PSSM-DT (?)
Feature selection(?)	mutual information chi-square
Dimensions(?)	2000 1000 500 400 300 200 100 50
Window size(?)
Type of problem(?)	Binary classification Multiclass classification
Number of labels(?)	2 3 4 5 6
Machine learning algorithm(?)	Support Vector Machine Random Forest Conditional Random Field
Parameter optimization(?)	No Yes
C(cost)(?)	2⁻¹ 2⁰ 2¹ 2² 2³ 2⁴ 2⁵ 2⁶ 2⁷ From: 2⁻¹ 2⁰ 2¹ To: 2⁵ 2⁷
g(gamma)(?)	2⁻⁷ 2⁻⁶ 2⁻⁵ 2⁻⁴ 2⁻³ 2⁻² 2⁻¹ 2⁰ 2¹ 2² 2³ From: 2⁻⁷ 2⁻⁵ 2⁻³ To: 2⁻¹ 2⁰ 2³
n_estimators(?)	50 100 200 300 400 500 From: 100 200 300 To: 400 500 600
neighbors(?)	3 5 7 9 11 13 From: 3 5 7 To: 11 13 15
Performance measure for parameter optimization(?)	ACC MCC AUC
Sampling(?)	None Under sampling
Cross validation(?)	5-fold cross validation Independent dataset test
Input the independent dataset in FASTA format (?): (minimum 5 sequences for each submission) or upload a file in FASTA format (?): Labels of independent dataset (?):
Input your e-mail(optional)(?)
Sequence Input:Input protein sequences in FASTA format(?): (5-100 sequences for each submission) or upload a file in FASTA format(?):
Label Input:Input protein sequences label in FASTA format(?): (each protein residue must be aligned with one label) or upload a file in FASTA format(?):

Please wait.........