WoLF PSORT: protein localization predictor

P. Horton; K.-J. Park; T. Obayashi; N. Fujita; H. Harada; C.J. Adams-Collier; K. Nakai

doi:10.1093/nar/gkm259

DeepPred-SubMito: A Novel Submitochondrial Localization Predictor Based on Multi-Channel Convolutional Neural Network and Dataset Balancing Treatment

International Journal of Molecular Sciences ◽

10.3390/ijms21165710 ◽

2020 ◽

Vol 21 (16) ◽

pp. 5710

Author(s):

Xiao Wang ◽

Yinping Jin ◽

Qiuwen Zhang

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Cross Validation ◽

Protein Localization ◽

Mitochondrial Protein ◽

Intermembrane Space ◽

The Matrix ◽

Localization Predictor ◽

High Level ◽

Fold Cross Validation

Mitochondrial proteins are physiologically active in different compartments, and their abnormal location will trigger the pathogenesis of human mitochondrial pathologies. Correctly identifying submitochondrial locations can provide information for disease pathogenesis and drug design. A mitochondrion has four submitochondrial compartments, the matrix, the outer membrane, the inner membrane, and the intermembrane space, but various existing studies ignored the intermembrane space. The majority of researchers used traditional machine learning methods for predicting mitochondrial protein localization. Those predictors required expert-level knowledge of biology to be encoded as features rather than allowing the underlying predictor to extract features through a data-driven procedure. Besides, few researchers have considered the imbalance in datasets. In this paper, we propose a novel end-to-end predictor employing deep neural networks, DeepPred-SubMito, for protein submitochondrial location prediction. First, we utilize random over-sampling to decrease the influence caused by unbalanced datasets. Next, we train a multi-channel bilayer convolutional neural network for multiple subsequences to learn high-level features. Third, the prediction result is outputted through the fully connected layer. The performance of the predictor is measured by 10-fold cross-validation and 5-fold cross-validation on the SM424-18 dataset and the SubMitoPred dataset, respectively. Experimental results show that the predictor outperforms state-of-the-art predictors. In addition, the prediction of results in the M983 dataset also confirmed its effectiveness in predicting submitochondrial locations.

Download Full-text

Lighting a path: genetic studies pinpoint neurodevelopmental mechanisms in autism and related disorders

Dialogues in Clinical Neuroscience ◽

10.31887/10.31887/dcns.2012.14.3/mpescosolido ◽

2012 ◽

Vol 14 (3) ◽

pp. 239-252

Keyword(s):

Molecular Mechanisms ◽

Protein Localization ◽

Regulation Of Gene Expression ◽

Neuronal Cell ◽

Mrna Splicing ◽

Genetic Mutations ◽

Scaffolding Proteins ◽

Molecular Processes ◽

Genetic Studies ◽

Novel Treatments

In this review, we outline critical molecular processes that have been implicated by discovery of genetic mutations in autism. These mechanisms need to be mapped onto the neurodevelopment step(s) gone awry that may be associated with cause in autism. Molecular mechanisms include: (i) regulation of gene expression; (ii) pre-mRNA splicing; (iii) protein localization, translation, and turnover; (iv) synaptic transmission; (v) cell signaling; (vi) the functions of cytoskeletal and scaffolding proteins; and (vii) the function of neuronal cell adhesion molecules. While the molecular mechanisms appear broad, they may converge on only one of a few steps during neurodevelopment that perturbs the structure, function, and/or plasticity of neuronal circuitry. While there are many genetic mutations involved, novel treatments may need to target only one of few developmental mechanisms.

Download Full-text