This Month in Bioinformatics- Research Updates of February 2021

5 mins read
Monthly Research Updates- February 2021

We summarize the research done in bioinformatics in the month of February.

1. A new deep-learning approach to predict miRNA targets

A new hybrid deep-learning approach is developed for predicting miRNA targets known as miTAR [1]. It predicts miRNA targets with high accuracy. This approach includes convolutional neural networks and recurrent neural networks. These both methods help in learning special features and discern sequential features respectively. This model is capable of fitting different input datasets [1]. miTAR is a user-friendly tool, available on Github.

For more details, read here.

2. A new gene predictor for distinct metagenomic data complexities

A new gene finder is developed namely, geneRFinder to predict genes in distinct metagenomic data complexities [2]. It is an ORF extraction-based tool that can identify intergenic regions and coding sequences in metagenomic data. geneRFinder is available on Gitlab and The authors have also provided benchmark data for gene prediction, which is available at

For more details, read here.

3. A new algorithm to detect rigid domains in proteins

A new graph-based algorithm is proposed for finding out rigid domains in proteins based on which a new web server is developed by the authors [3]. This is known as the “Detection of rigid domains in proteins”. It integrates graph-clustering algorithm and Viterbi algorithm. The web server is available at The code is written in Python and is available on Github.

For more details, read here.

4. A New Tool to Align Highly Variable Regions in HIV Sequences

A new tool called NGlyAlign is developed to build and align the highly variable regions in HIV sequences [4]. It is an automated library building tool that allows easy alignment of highly variable HIV envelope regions. It is an open-source tool and is freely available at This method is easily applicable to large sequences and other highly variable glycoproteins including the Hepatitis C virus.

For more details, read here.

5. A new machine learning method to predict human dicer cleavage sites

A new predictor namely, ReCGBM, is developed for human dicer cleavage sites [5]. This predictor is based on a gradient-boosting method that uses weak-prediction models to predict cleavage sites. The authors have used lightGBM as a framework of the gradient boosting machine method of machine learning [5]. The source code is available on Github.

For more details, read here.

6. A New Software providing Filters for Next-Generation Sequencing

Wardell et al., [6] have developed a new software called FiNGS. It provides high-precision data. This software filters somatic variants. It is a user-friendly tool that allows users to customize filters and thresholds. Users can also implement their own filtering strategies. FiNGS is platform-independent, easy to install, and written in Python3. It can be downloaded via Bioconda, PyPi, or as a docker image. The source code is available on Github.

For more details, read here.


  1. Gu, T., Zhao, X., Barbazuk, W. B., & Lee, J. H. (2020). miTAR: a hybrid deep learning-based approach for predicting miRNA targets. bioRxiv.
  2. Silva, R., Padovani, K., Góes, F., & Alves, R. (2020). geneRFinder: gene finding in distinct metagenomic data complexities. BioRxiv.
  3. Dang, T. K. L., Nguyen, T., Habeck, M., Gültas, M., & Waack, S. (2021). A graph-based algorithm for detecting rigid domains in protein structures. BMC bioinformatics22(1), 1-19.
  4. Akand, E. H., & Murray, J. M. (2021). NGlyAlign: an automated library building tool to align highly divergent HIV envelope sequences. BMC bioinformatics22(1), 1-14.
  5. Liu, P., Song, J., Lin, C. Y., & Akutsu, T. (2021). ReCGBM: a gradient boosting-based method for predicting human dicer cleavage sites. BMC bioinformatics22(1), 1-17.
  6. Wardell, C.P., Ashby, C. & Bauer, M.A. (2021). FiNGS: high quality somatic mutations using filters for next generation sequencing. BMC Bioinformatics 22, 77.

Leave a Reply

Blind docking vs site-specific docking
Previous Story

Blind Docking vs Site-specific Docking

programming in php
Next Story

How to execute Unix/shell commands in PHP?

Latest from Bioinformatics Research Updates

0 $0.00