Harnessing the evolutionary information on oxygen binding proteins through Support Vector Machines based modules

Ion-pumping microbial rhodopsin protein classification by machine learning approach

BACKGROUND

Rhodopsin is a seven-transmembrane protein covalently linked with retinal chromophore that absorbs photons for energy conversion and intracellular signaling in eukaryotes, bacteria, and archaea. Haloarchaeal rhodopsins are Type-I microbial rhodopsin that elicits various light-driven functions like proton pumping, chloride pumping and Phototaxis behaviour. The industrial application of Ion-pumping Haloarchaeal rhodopsins is limited by the lack of full-length rhodopsin sequence-based classifications, which play an important role in Ion-pumping activity. The well-studied Haloarchaeal rhodopsin is a proton-pumping bacteriorhodopsin that shows promising applications in optogenetics, biosensitized solar cells, security ink, data storage, artificial retinal implant and biohydrogen generation. As a result, a low-cost computational approach is required to identify Ion-pumping Haloarchaeal rhodopsin sequences and its subtype.

RESULTS

This study uses a support vector machine (SVM) technique to identify these ion-pumping Haloarchaeal rhodopsin proteins. The haloarchaeal ion pumping rhodopsins viz., bacteriorhodopsin, halorhodopsin, xanthorhodopsin, sensoryrhodopsin and marine prokaryotic Ion-pumping rhodopsins like actinorhodopsin, proteorhodopsin have been utilized to develop the methods that accurately identified the ion pumping haloarchaeal and other type I microbial rhodopsins. We achieved overall maximum accuracy of 97.78%, 97.84% and 97.60%, respectively, for amino acid composition, dipeptide composition and hybrid approach on tenfold cross validation using SVM. Predictive models for each class of rhodopsin performed equally well on an independent data set. In addition to this, similar results were achieved using another machine learning technique namely random forest. Simultaneously predictive models performed equally well during five-fold cross validation. Apart from this study, we also tested the own, blank, BLAST dataset and annotated whole-genome rhodopsin sequences of PWS haloarchaeal isolates in the developed methods. The developed web server ( https://bioinfo.imtech.res.in/servers/rhodopred ) can identify the Ion Pumping Haloarchaeal rhodopsin proteins and their subtypes. We expect this web tool would be useful for rhodopsin researchers.

CONCLUSION

The overall performance of the developed method results show that it accurately identifies the Ionpumping Haloarchaeal rhodopsin and their subtypes using known and unknown microbial rhodopsin sequences. We expect that this study would be useful for optogenetics, molecular biologists and rhodopsin researchers.

Computational method for aromatase-related proteins using machine learning approach

Human aromatase enzyme is a microsomal cytochrome P450 and catalyzes aromatization of androgens into estrogens during steroidogenesis. For breast cancer therapy, third-generation aromatase inhibitors (AIs) have proven to be effective; however patients acquire resistance to current AIs. Thus there is a need to predict aromatase-related proteins to develop efficacious AIs. A machine learning method was established to identify aromatase-related proteins using a five-fold cross validation technique. In this study, different SVM approach-based models were built using the following approaches like amino acid, dipeptide composition, hybrid and evolutionary profiles in the form of position-specific scoring matrix (PSSM); with maximum accuracy of 87.42%, 84.05%, 85.12%, and 92.02% respectively. Based on the primary sequence, the developed method is highly accurate to predict the aromatase-related proteins. Prediction scores graphs were developed using the known dataset to check the performance of the method. Based on the approach described above, a webserver for predicting aromatase-related proteins from primary sequence data was developed and implemented at https://bioinfo.imtech.res.in/servers/muthu/aromatase/home.html. We hope that the developed method will be useful for aromatase protein related research.

PeNGaRoo, a combined gradient boosting and ensemble learning framework for predicting non-classical secreted proteins

MOTIVATION

Gram-positive bacteria have developed secretion systems to transport proteins across their cell wall, a process that plays an important role during host infection. These secretion mechanisms have also been harnessed for therapeutic purposes in many biotechnology applications. Accordingly, the identification of features that select a protein for efficient secretion from these microorganisms has become an important task. Among all the secreted proteins, 'non-classical' secreted proteins are difficult to identify as they lack discernable signal peptide sequences and can make use of diverse secretion pathways. Currently, several computational methods have been developed to facilitate the discovery of such non-classical secreted proteins; however, the existing methods are based on either simulated or limited experimental datasets. In addition, they often employ basic features to train the models in a simple and coarse-grained manner. The availability of more experimentally validated datasets, advanced feature engineering techniques and novel machine learning approaches creates new opportunities for the development of improved predictors of 'non-classical' secreted proteins from sequence data.

RESULTS

In this work, we first constructed a high-quality dataset of experimentally verified 'non-classical' secreted proteins, which we then used to create benchmark datasets. Using these benchmark datasets, we comprehensively analyzed a wide range of features and assessed their individual performance. Subsequently, we developed a two-layer Light Gradient Boosting Machine (LightGBM) ensemble model that integrates several single feature-based models into an overall prediction framework. At this stage, LightGBM, a gradient boosting machine, was used as a machine learning approach and the necessary parameter optimization was performed by a particle swarm optimization strategy. All single feature-based LightGBM models were then integrated into a unified ensemble model to further improve the predictive performance. Consequently, the final ensemble model achieved a superior performance with an accuracy of 0.900, an F-value of 0.903, Matthew's correlation coefficient of 0.803 and an area under the curve value of 0.963, and outperforming previous state-of-the-art predictors on the independent test. Based on our proposed optimal ensemble model, we further developed an accessible online predictor, PeNGaRoo, to serve users' demands. We believe this online web server, together with our proposed methodology, will expedite the discovery of non-classically secreted effector proteins in Gram-positive bacteria and further inspire the development of next-generation predictors.

AVAILABILITY AND IMPLEMENTATION

http://pengaroo.erc.monash.edu/.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.