Dataset Information

Predicting the multi-label protein subcellular localization through multi-information fusion and MLSI dimensionality reduction based on MLFE classifier.

ABSTRACT:

Motivation

Multi-label protein subcellular localization (SCL) is an indispensable way to study protein function. It can locate a certain protein (such as the human transmembrane protein that promotes the invasion of the SARS-CoV-2) or expression product at a specific location in a cell, which can provide a reference for clinical treatment of diseases such as COVID-19.

Results

The paper proposes a novel method named ML-locMLFE. First of all, six feature extraction methods are adopted to obtain protein effective information. These methods include pseudo amino acid composition (PseAAC), encoding based on grouped weight (EBGW), gene ontology (GO), multi-scale continuous and discontinuous (MCD), residue probing transformation (RPT) and evolutionary distance transformation (EDT). In the next part, we utilize the multi-label information latent semantic index (MLSI) method to avoid the interference of redundant information. In the end, multi-label learning with feature induced labeling information enrichment (MLFE) is adopted to predict the multi-label protein SCL. The Gram-positive bacteria dataset is chosen as a training set, while the Gram-negative bacteria dataset, virus dataset, newPlant dataset and SARS-CoV-2 dataset as the test sets. The overall actual accuracy (OAA) of the first four datasets is 99.23%, 93.82%, 93.24%, and 96.72% by the leave-one-out cross validation (LOOCV). It is worth mentioning that the OAA prediction result of our predictor on the SARS-CoV-2 dataset is 72.73%. The results indicate that the ML-locMLFE method has obvious advantages in predicting the SCL of multi-label protein, which provides new ideas for further research on the SCL of multi-label protein.

Availability and implementation

The source codes and data are publicly available at https://github.com/QUST-AIBBDRC/ML-locMLFE/.

Supplementary information

Supplementary data are available at Bioinformatics online.

SUBMITTER: Liu Y

PROVIDER: S-EPMC8690230 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Predicting protein subcellular localization is an important and difficult problem, particularly when query proteins may have the multiplex character, i.e., simultaneously exist at, or move between, two or more different subcellular location sites. Most of the existing protein subcellular location predictor can only be used to deal with the single-location or "singleplex" proteins. Actually, multiple-location or "multiplex" proteins should not be ignored because they usually posses some unique biological functions worthy of our special notice. By introducing the "multi-labeled learning" and "accumulation-layer scale", a new predictor, called iLoc-Euk, has been developed that can be used to deal with the systems containing both singleplex and multiplex proteins. As a demonstration, the jackknife cross-validation was performed with iLoc-Euk on a benchmark dataset of eukaryotic proteins classified into the following 22 location sites: (1) acrosome, (2) cell membrane, (3) cell wall, (4) centriole, (5) chloroplast, (6) cyanelle, (7) cytoplasm, (8) cytoskeleton, (9) endoplasmic reticulum, (10) endosome, (11) extracellular, (12) Golgi apparatus, (13) hydrogenosome, (14) lysosome, (15) melanosome, (16) microsome (17) mitochondrion, (18) nucleus, (19) peroxisome, (20) spindle pole body, (21) synapse, and (22) vacuole, where none of proteins included has ?25% pairwise sequence identity to any other in a same subset. The overall success rate thus obtained by iLoc-Euk was 79%, which is significantly higher than that by any of the existing predictors that also have the capacity to deal with such a complicated and stringent system. As a user-friendly web-server, iLoc-Euk is freely accessible to the public at the web-site http://icpr.jci.edu.cn/bioinfo/iLoc-Euk. It is anticipated that iLoc-Euk may become a useful bioinformatics tool for Molecular Cell Biology, Proteomics, System Biology, and Drug Development Also, its novel approach will further stimulate the development of predicting other protein attributes.

Project description:BackgroundEnzymes play an irreplaceable and important role in maintaining the lives of living organisms. The Enzyme Commission (EC) number of an enzyme indicates its essential functions. Correct identification of the first digit (family class) of the EC number for a given enzyme is a hot topic in the past twenty years. Several previous methods adopted functional domain composition to represent enzymes. However, it would lead to dimension disaster, thereby reducing the efficiency of the methods. On the other hand, most previous methods can only deal with enzymes belonging to one family class. In fact, several enzymes belong to two or more family classes.ResultsIn this study, a fast and efficient multi-label classifier, named PredictEFC, was designed. To construct this classifier, a novel feature extraction scheme was designed for processing functional domain information of enzymes, which counting the distribution of each functional domain entry across seven family classes in the training dataset. Based on this scheme, each training or test enzyme was encoded into a 7-dimenion vector by fusing its functional domain information and above statistical results. Random k-labelsets (RAKEL) was adopted to build the classifier, where random forest was selected as the base classification algorithm. The two tenfold cross-validation results on the training dataset shown that the accuracy of PredictEFC can reach 0.8493 and 0.8370. The independent test on two datasets indicated the accuracy values of 0.9118 and 0.8777.ConclusionThe performance of PredictEFC was slightly lower than the classifier directly using functional domain composition. However, its efficiency was sharply improved. The running time was less than one-tenth of the time of the classifier directly using functional domain composition. In additional, the utility of PredictEFC was superior to the classifiers using traditional dimensionality reduction methods and some previous methods, and this classifier can be transplanted for predicting enzyme family classes of other species. Finally, a web-server available at http://124.221.158.221/ was set up for easy usage.

Project description:BackgroundDiabetes mellitus characterized by hyperglycemia as a result of insufficient production of or reduced sensitivity to insulin poses a growing threat to the health of people. It is a heterogeneous disorder with multiple etiologies consisting of type 1 diabetes, type 2 diabetes, gestational diabetes and so on. Diabetes-associated protein/gene prediction is a key step to understand the cellular mechanisms related to diabetes mellitus. Compared with experimental methods, computational predictions of candidate proteins/genes are cheaper and more effortless. Protein-protein interaction (PPI) data produced by the high-throughput technology have been used to prioritize candidate disease genes/proteins. However, the false interactions in the PPI data seriously hurt computational methods performance. In order to address that particular question, new methods are developed to identify candidate disease genes/proteins via integrating biological data from other sources.ResultsIn this study, a new framework called PDMG is proposed to predict candidate disease genes/proteins. First, the weighted networks are building in terms of the combination of the subcellular localization information and PPI data. To form the weighted networks, the importance of each compartment is evaluated based on the number of interacted proteins in this compartment. This is because the very different roles played by different compartments in cell activities. Besides, some compartments are more important than others. Based on the evaluated compartments, the interactions between proteins are scored and the weighted PPI networks are constructed. Second, the known disease genes are extracted from OMIM database as the seed genes to expand disease-specific networks based on the weighted networks. Third, the weighted values between a protein and its neighbors in the disease-related networks are added together and the sum is as the score of the protein. Last but not least, the proteins are ranked based on descending order of their scores. The candidate proteins in the top are considered to be associated with the diseases and are potential disease-related proteins. Various types of data, such as type 2 diabetes-associated genes, subcellular localizations and protein interactions, are used to test PDMG method.ConclusionsThe results show that the proteins/genes functionally exerting a direct influence over diabetes are consistently placed at the head of the queue. PDMG expands and ranks 445 candidate proteins from the seed set including original 27 type 2 diabetes proteins. Out of the top 27 proteins, 14 proteins are the real type 2 diabetes proteins. The literature extracted from the PubMed database has proved that, out of 13 novel proteins, 8 proteins are associated with diabetes.