Seq2Feature: a comprehensive web-based feature extraction tool

Nikam, Rahul; Gromiha, M. Michael

doi:10.1093/bioinformatics/btz432

Cited by 24 publications

(14 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several important descriptors of sequences include, but are not limited to: the GC-content, bendability [42], flexibility [3] and free energy [16]. Recently, Nikam et al published Seq2Feature, an online tool that can extract up to 252 protein and 41 DNA sequence-based descriptors [27].…”

Section: Related Workmentioning

confidence: 99%

Novel transformer networks for improved sequence labeling in genomics

Clauwaert

Waegeman

2019

Preprint

View full text Add to dashboard Cite

In genomics, a wide range of machine learning methods is used to annotate biological sequences w.r.t. interesting positions such as transcription start sites, translation initiation sites, methylation sites, splice sites, promotor start sites, etc. In recent years, this area has been dominated by convolutional neural networks, which typically outperform older methods as a result of automated scanning for influential sequence motifs. As an alternative, we introduce in this paper transformer architectures for whole-genome sequence labeling tasks. We show that those architectures, which have been recently introduced for natural language processing, allow for a fast processing of long DNA sequences. We optimize existing networks and define a new way to calculate attention, resulting in state-of-the-art performances. To demonstrate this, we evaluate our transformer model architecture on several sequence labeling tasks, and find it to outperform specialized models for the annotation of transcription start sites, translation initiation sites and 4mC methylation in E. coli. In addition, the use of the full genome for model training and evaluation results in unbiased performance metrics, facilitating future benchmarking.

show abstract

Section: Related Workmentioning

confidence: 99%

Novel transformer networks for improved sequence labeling in genomics

Clauwaert

Waegeman

2019

Preprint

View full text Add to dashboard Cite

show abstract

“…A tool named "FastFeatGen" for parallel feature extraction from Genome sequences was developed by Md.Khaledur Rahman [5]. This is used to predict the DNA N 6 Methyladenine sites in Prokaryotes and Eukaryotes. A comprehensive web based tool named "Seq2Feature" was developed by Rahul Nikam et.…”

Section: Related Work For Feature Extractionmentioning

confidence: 99%

“…A comprehensive web based tool named "Seq2Feature" was developed by Rahul Nikam et. al [6] which computes features include physicochemical, energetic, conformational properties of DNA. This tool extracts features efficiently from protein and DNA sequences.…”

Section: Related Work For Feature Extractionmentioning

confidence: 99%

A Novel Feature Extraction from Genome Sequences For Taxonomic Classification Of Living Organisms

Muthulakshmi¹

2021

TURCOMAT

View full text Add to dashboard Cite

Genome sequencing aids in understanding the nature, characteristics, habitat and evolutionary history of all living organisms. Apart from sequencing, the more important task is to correctly place the sequenced genome in the taxonomy. Generally, the taxonomic classification of the living organisms is done by observing their morphological, behavioral, genetic and biochemical characteristics. Among them, taxonomic classification using genetic observation is more accurate scientifically as the Genome sequence analysis exploits the complete characteristics of the organism. In this paper, we developed a novel Frequency based Feature Extraction Technique (FFET) which extracts 120 features and helps to analyze the genome sequence of the organism and to classify them in the taxonomy accordingly. We performed a kingdom level taxonomic classification using the proposed FFET. The proposed FFET extracts features based on storage, frequency of nucleotide bases, pattern arrangement and amino acid composition of genome sequences. The feature extraction technique is applied to 150 samples of genome sequences of various organisms which were downloaded from National Centre for Biotechnology and Information (NCBI) database. The extracted features are classified using various Machine learning and Deep learning classifiers. From the results, it is evident that FFET performs well for classification with Convolutional Neural Network (CNN) classifier with an accuracy of 96.73 %.

show abstract

“…Properties of interest derived from the nucleotide sequence, such as bendability [39], flexibility [3] and free energy [15] have furthermore shown importance in determining TSSs. Seq2Feature, an online tool that has been published this year, has defined as many as 41 DNA sequence-based descriptors, highlighting the ongoing interest in retrieving interpretable features from the nucleotide sequence [21].…”

Section: Introductionmentioning

confidence: 99%

Explainable Transformer Models for Functional Genomics in Prokaryotes

Clauwaert

Menschaert

Waegeman

2020

Preprint

View full text Add to dashboard Cite

The annotation of transcription start sites with computational methods is an important and unsolved problem in genomics. In recent years, several novel experimental methodologies -named Cappable-seq, SMRT-Cappable-seq and SEnd-seq -have been introduced for the detection of transcription start sites and applied on E. coli. In this study, a comparison is made between these new methodologies and the curated transcription start site data set featured by RegulonDB. The analysis between these data sets is facilitated using deep learning techniques that cover both unsupervised and supervised learning, where we expand upon a framework that allows for interpretable deep learning in genomics. This study finds annotations of recent techniques to surpass the quality of annotations provided by Reg-ulonDB. Analysis of the transformer network trained for the detection of TSS in E. coli reveals its attention scores to pinpoint important promoter regions previously discussed in literature. Additionally, findings support the occurrence of a complex interaction between sense and antisense output probabilities, prevalent on key positions for interference of the transcription process.

show abstract

Seq2Feature: a comprehensive web-based feature extraction tool

Cited by 24 publications

References 7 publications

Novel transformer networks for improved sequence labeling in genomics

Novel transformer networks for improved sequence labeling in genomics

A Novel Feature Extraction from Genome Sequences For Taxonomic Classification Of Living Organisms

Explainable Transformer Models for Functional Genomics in Prokaryotes

Contact Info

Product

Resources

About