RSLpred-2.0 analysis

Predict the subcellular localization of rice proteins

Submit protein sequences, choose the required localization depth, and run the rice-specific prediction models.

Input: Protein FASTA
Limit: 10,000 records
Retention: 30 days

Step 1

Choose the input method

RSLpred2 accepts protein sequences from one source at a time.

Sequence type

Protein

Input method

Step 2

Add sequence data

FASTA sequence

Up to 10,000 sequences; each header must begin with >.

Working with a large dataset? Use the standalone RSLpred-2.0 package for local, scripted, and repeated analyses.

View standalone tool

Step 3

Choose the prediction level

Select prediction depth

Level I: Single vs Dual

Classifies query sequences into single or dual organelle localization

Level II: Single 10-Class

10 Organelles: Vacuole, Cytoplasm, Peroxisome, Golgi, ER, Membrane, etc.

Level III: Dual 6-Class

6 Organelle Pairs: Plastid & Mitochondria, Nucleus & Cytoplasm, etc.

Level IV: Membrane Topology

Classifies membrane proteins into Single-Pass or Multi-Pass

Select Model Strategy

Fast

DPCP Feature Vector. Fast speed.

Sensitive

TPC Feature Vector. Highest accuracy.

Step 4

Verify and submit

Your private results page opens automatically when processing is complete.

Publication

Please cite RSLpred2

Duhan, N., & Kaundal, R. (2025). RSLpred2: An Integrated Web Server for the Annotation of Rice Proteome Subcellular Localization Using Deep Learning. Rice, 18, 58.DOI: 10.1186/s12284-025-00767-7