STRUCTURAL CLASSIFICATION OF PROTEINS USING IMAGE BASED MACHINE LEARNING

Classification of proteins is an important area of research that enables better grouping of proteins either by their function, evolutionary similarities or in their structural makeup. Structural classification is the area of research that this thesis focuses on. We use visualizations of proteins to build a machine learning class prediction model, that successfully classifies proteins using the Structural Classification of Proteins (SCOP) framework. SCOP is a well-researched classification with many approaches using a representation of a proteins secondary structure in a linear chain of structures. This thesis uses a novel approach of rendering a three dimensional visualization of the protein itself and then applying image based machine learning to determine a protein’s SCOP classification. The resulting convolutional neural network (CNN) method has achieved average accuracies in the range 78-87% on the 25PDB dataset, which is better than or equal to the existing methods.

STRUCTURAL CLASSIFICATION OF PROTEINS USING IMAGE BASED MACHINE LEARNING

Classification of proteins is an important area of research that enables better grouping of proteins either by their function, evolutionary similarities or in their structural makeup. Structural classification is the area of research that this thesis focuses on. We use visualizations of proteins to build a machine learning class prediction model, that successfully classifies proteins using the Structural Classification of Proteins (SCOP) framework. SCOP is a well-researched classification with many approaches using a representation of a proteins secondary structure in a linear chain of structures. This thesis uses a novel approach of rendering a three dimensional visualization of the protein itself and then applying image based machine learning to determine a protein’s SCOP classification. The resulting convolutional neural network (CNN) method has achieved average accuracies in the range 78-87% on the 25PDB dataset, which is better than or equal to the existing methods.

Molecular mechanisms of fat deposition: <i>IL-6</i> is a hub gene in fat lipolysis, comparing thin-tailed with fat-tailed sheep breeds

Tail fat content affects meat quality and varies significantly among different breeds of sheep. Ghezel (fat-tailed) and Zel (thin-tailed) are two important Iranian local sheep breeds with different patterns of fat storage. The current study presents the transcriptome characterization of tail fat using RNA sequencing in order to get a better comprehension of the molecular mechanism of lipid storage in the two mentioned sheep breeds. Seven (Zel = 4 and Ghezel = 3) 7-month-old male lambs were used for this experiment. The results of sequencing were analyzed with bioinformatics methods, including differentially expressed genes (DEGs) identification, functional enrichment analysis, structural classification of proteins, protein–protein interaction (PPI) and network and module analyses. Some of the DEGs, such as LIPG, SAA1, SOCS3, HIF-1α, and especially IL-6, had a close association with lipid metabolism. Furthermore, functional enrichment analysis revealed pathways associated with fat deposition, including “fatty acid metabolism”, “fatty acid biosynthesis” and “HIF-1 signaling pathway”. The structural classification of proteins showed that major down-regulated DEGs in the Zel (thin-tailed) breed were classified under transporter class and that most of them belonged to the solute carrier transporter (SLC) families. In addition, DEGs under the transcription factor class with an important role in lipolysis were up-regulated in the Zel (thin-tailed) breed. Also, network analysis revealed that IL-6 and JUNB were hub genes for up-regulated PPI networks, and HMGCS1, VPS35 and VPS26A were hub genes for down-regulated PPI networks. Among the up-regulated DEGs, the IL-6 gene seems to play an important role in lipolysis of tail fat in thin-tailed sheep breeds via various pathways such as tumor necrosis factor (TNF) signaling and mitogen-activated protein kinase (MAPK) signaling pathways. Due to the probable role of the IL-6 gene in fat lipolysis and also due to the strong interaction of IL-6 with the other up-regulated DEGs, it seems that IL-6 accelerates the degradation of lipids in tail fat cells.

SMI-BLAST: a novel supervised search framework based on PSI-BLAST for protein remote homology detection

Motivation As one of the most important and widely used mainstream iterative search tool for protein sequence search, an accurate Position-Specific Scoring Matrix (PSSM) is the key of PSI-BLAST. However, PSSMs containing non-homologous information obviously reduce the performance of PSI-BLAST for protein remote homology. Results To further study this problem, we summarize three types of Incorrectly Selected Homology (ISH) errors in PSSMs. A new search tool Supervised-Manner-based Iterative BLAST (SMI-BLAST) is proposed based on PSI-BLAST for solving these errors. SMI-BLAST obviously outperforms PSI-BLAST on the Structural Classification of Proteins-extended (SCOPe) dataset. Compared with PSI-BLAST on the ISH error subsets of SCOPe dataset, SMI-BLAST detects 1.6–2.87 folds more remote homologous sequences, and outperforms PSI-BLAST by 35.66% in terms of ROC1 scores. Furthermore, this framework is applied to JackHMMER, DELTA-BLAST and PSI-BLASTexB, and their performance is further improved. Availability and implementation User-friendly webservers for SMI-BLAST, JackHMMER, DELTA-BLAST and PSI-BLASTexB are established at http://bliulab.net/SMI-BLAST/, by which the users can easily get the results without the need to go through the mathematical details. Supplementary information Supplementary data are available at Bioinformatics online.

The SCOP database in 2020: expanded classification of representative family and superfamily domains of known protein structures

The Structural Classification of Proteins (SCOP) database is a classification of protein domains organised according to their evolutionary and structural relationships. We report a major effort to increase the coverage of structural data, aiming to provide classification of almost all domain superfamilies with representatives in the PDB. We have also improved the database schema, provided a new API and modernised the web interface. This is by far the most significant update in coverage since SCOP 1.75 and builds on the advances in schema from the SCOP 2 prototype. The database is accessible from http://scop.mrc-lmb.cam.ac.uk.

Lessons from making the Structural Classification of Proteins (SCOP) and their implications for protein structure modelling

The Structural Classification of Proteins (SCOP) database has facilitated the development of many tools and algorithms and it has been successfully used in protein structure prediction and large-scale genome annotations. During the development of SCOP, numerous exceptions were found to topological rules, along with complex evolutionary scenarios and peculiarities in proteins including the ability to fold into alternative structures. This article reviews cases of structural variations observed for individual proteins and among groups of homologues, knowledge of which is essential for protein structure modelling.