1 - 50 of 126 results


A tool for the analysis of subcellular proteomics data, based on the use of standardized lists of subcellular markers. MetaMass analyzed data from 11 studies using MetaMass, mapping the subcellular location of 5,970 proteins. Our analysis revealed large variations in the performance of subcellular fractionation protocols as well as systematic biases in protein annotation databases. The Excel and R versions of MetaMass should enhance transparency and reproducibility in subcellular proteomics.


An extension of the PSORT II program for protein subcellular location prediction. WoLF PSORT converts protein amino acid sequences into numerical localization features; based on sorting signals, amino acid composition and functional motifs such as DNA-binding motifs. After conversion, a simple k-nearest neighbor classifier is used for prediction. Using html, the evidence for each prediction is shown in two ways: (i) a list of proteins of known localization with the most similar localization features to the query, and (ii) tables with detailed information about individual localization features. WoLF PSORT not only provides subcellular localization prediction with competitive accuracy, but also provides detailed information relevant to protein localization to help users to form their own hypotheses.


Allows mitochondrial pre-sequence and cleavage site prediction. MitoFates is a prediction method that formulates pre-sequence prediction as a binary classification problem, employing a standard support vector machine (SVM) classifier. The software MitoFates predicts the position of cleavage sites with an error rate of 29%. Its prediction was applied to the human proteome, providing candidate lists of pre-sequence containing proteins, protein isoforms with differential localization, and potentially disease related mitochondrial proteins.

FUEL-mLoc / Feature-Unified Prediction and Explanation of multi-Localization of cellular proteins in multiple organisms

Interprets the prediction decisions by unified features, which are more clear, self-evident and structured. FUEL-mLoc is a web-server which not only predicts single- and multi-label proteins from almost all of the common organisms, but also provides interpretable information to explain why the prediction decisions are made. Compared to existing interpretable web-servers, FUEL-mLoc uses unified feature information for more clear, self-evident and structured interpretation. Besides, FUEL-mLoc performs better than other subcellular-localization predictors.


Predicts five classes of subcellular localization of proteins in eukaryotes: secretory pathway, cytoplasm, nucleus, mitochondrion and chloroplast. BaCelLo is a method for subcellular localization prediction that adopts a balancing procedure by assuming a uniform a priori probability for the classes. This software distinguishes between animal and fungal organisms. It can be used for large scale analysis of whole genomes to produce an estimate and annotation of the protein content in each subcellular compartment.

MSLVP / Multiple Subcellular Localization of Viral Proteins

Predicts the subcellular location (SCL) of multiplex viral proteins. MSLVP is based on a support vector machine (SVM) method that employs new data set of experimentally verified sequences. It was tested thank to 10-fold cross validation using “one-versus-other” and “one-versus-one” classification approach employing viral proteins at 90% and 30% sequence identity. The tool allows to annotate subcellular localization of viral proteins with higher accuracy.


Determines nine sub-cellular localizations. SubCons employs a Random Forest (RF) classifier to combine four predictors. It can generate Position-Specific Scoring Matrixes (PSSMs) and offers users the option to submit entire proteomes. This tool is helpful to understand the localization of a protein, in particular as it scales to complete genomes. It provides state of the art predictions, a confidence score rates the reliability of a prediction in order to evaluate the reliability of the prediction.


Predicts protein sub-chloroplastic localization, based on targeting signal detection and membrane protein information. SChloro is based on the recognition of sequence signals that define target specificity (chloroplast and thylakoid targeting signals) as well as on the prediction of the potential type of interaction with chloroplast membranes (single-pass, multi-pass and peripheral interaction). SChloro significantly outperforms the available state-of-the-art methods, both in single and multi-label settings.


A protein subcellular localization prediction pipeline aiming to deal with the small sample size learning and multi-location proteins annotation problems. Five semi-supervised algorithms that can make use of lower-quality data were integrated, and a new multi-label classification approach by incorporating the correlations among different organelles in cells was proposed. The organelle correlations were modeled by the Bayesian network, and the topology of the correlation graph was used to guide the order of binary classifiers training in the multi-label classification to reflect the label dependence relationship.


Provides predictor for predicting plant protein subcellular localization. iLoc-Plant is a classifier that predicts the subcellular localization of both singleplex and multiplex plant proteins. This method is particularly helpful for the vast majority of experimental scientists, who wish get the desired results without the need to understand the detailed mathematics. It is also natural and effective in dealing with proteins having both single and multiple subcellular locations.

HECTAR / HEterokont subCellular TARgeting

Predicts the subcellular localisation of heterokont proteins with high accuracy. HECTAR is a statistical prediction method designed to assign proteins to five different categories of subcellular targeting: Signal peptides, type II signal anchors, chloroplast transit peptides, mitochondrion transit peptides and proteins which do not possess any N-terminal target peptide. This method is based on a hierarchical architecture which implements the divide and conquer approach to identify the different possible target peptides one at a time.


Organelle-specific proteomic studies have started to delineate its various subproteomes, but sequence-based prediction software is necessary to assign proteins subcellular localizations at whole genome scale. Unfortunately, existing tools are oriented toward land plants and tend to mispredict the localization of nuclear-encoded algal proteins, predicting many chloroplast proteins as mitochondrion targeted. PredAlgo predicts intracellular localization of those proteins to one of three intracellular compartments in green algae: the mitochondrion, the chloroplast, and the secretory pathway.

AtSubP / Arabidopsis Subcellular localization Predictor

Localizes gene products at the subcellular level will substantially advance Arabidopsis gene annotation. AtSubP is based on the combinatorial presence of diverse protein features, such as its amino acid composition, sequence-order effects, terminal information, Position-Specific Scoring Matrix, and similarity search-based Position-Specific Iterated-Basic Local Alignment Search Tool information. AtSubP outperformed all the existing tools currently being used for Arabidopsis proteome annotation.


Predicts the subcellular localization of eukaryotic proteins. DeepLoc is a well assembled protein collection with reliable subcellular localization information. This online resource can differentiate between 10 different localizations: Nucleus, Cytoplasm, Extracellular, Mitochondrion, Cell membrane, Endoplasmic reticulum, Chloroplast, Golgi apparatus, Lysosome/Vacuole and Peroxisome. This model outperforms current state-of-the-art algorithms, even those relying on homology information.

REALoc / Reliable and Effective methods to Assist predicting human protein subcellular Localization

Predicts human protein subcellular localization. REALoc is a highly accurate system that can predict localization to the cell membrane, cytoplasm, endoplasmic reticulum/Golgi, mitochondrion, nucleus, and extracellular. It also uses the absolute true success rate (ATSR) to represent the protein prediction score, which avoids under- and over-prediction. It can be divided into two kinds of relationship layers, one-to-one and many-to-many.


Two sparse and interpretable multi-label predictors, namely mLASSO and mEN for large-scale predictions of both single- and multi-location proteins. Given a query protein, its feature vector is constructed by exploiting the gene ontology (GO) frequency information in the ProSeq-GO database. By using the one-vs-rest LASSO and EN classifiers, 87 and 429 out of 8,000+ GO terms are selected, respectively. Based on these selected essential GO terms, the interpretability is analyzed for both algorithms.

PLPD / Protein Localization Predictor based on D-SVDD

Predicts protein localization. PLPD can detect the likelihood of specific localization for a protein by using the Density-induced Support Vector Data Description (D-SVDD). D-SVDD is extended for this algorithm to run the prediction of protein subcellular localization. It utilizes three measurements for the assessment and to refine the protein localization predictor. PLPD approach is complimentary to other method such as the nearest neighbor or the discriminate covariant method.

cmeAnalysis / clathrin-mediated endocytosis analysis

Allows quantification of clathrin-coated pit dynamics from fluorescence time-lapse data. cmeAnalysis provides functionalities including: (1) sensitive detection, (2) tracking (based on u-track), (3) master/slave detection for multi-channel data, (4) intensity-based classification of coated structures, and (5) lifetime analysis. It also contains a graphical user interface (GUI) for inspection of analysis results from individual movies.


Predicts the amino acid sequence-based human protein subcellular location to cover human subcellular localizations. The sequences are represented by multi-view complementary features, i.e., context vocabulary annotation-based gene ontology (GO) terms, peptide-based functional domains, and residue-based statistical features. The major updates include: i) taking into consideration feature correlation and the hierarchical structure of GO terms; ii) extracting residue features from different segments of N and C-terminals; and iii) use of the latest versions of gene ontology, conserved domain database and SWISS-PROT database. Hum-mPLoc is designed to predict subcellular localization of human proteins.


A multi-label predictor based on penalized logistic regression and adaptive decisions for predicting both single- and multi-location proteins. Specifically, for each query protein, mPLR-Loc exploits the information from the Gene Ontology (GO) database by using its accession number (AC) or the ACs of its homologs obtained via BLAST. The frequencies of GO occurrences are used to construct feature vectors, which are then classified by an adaptive decision-based multi-label penalized logistic regression classifier. In addition to being able to rapidly and accurately predict subcellular localization of single- and multi-label proteins, mPLR-Loc can also provide probabilistic confidence scores for the prediction decisions.