Related Experiment Video
Updated: Jan 28, 2026
09:40
Novel Sequence Discovery by Subtractive Genomics
Published on: January 25, 2019
9.1K
Probabilistic variable-length segmentation of protein sequences for discriminative motif discovery (DiMotif) and
Ehsaneddin Asgari1,2, Alice C McHardy2, Mohammad R K Mofrad3,4
1Molecular Cell Biomechanics Laboratory, Departments of Bioengineering and Mechanical Engineering, University of California, Berkeley, CA, 94720, USA.
Scientific Reports
|March 7, 2019
Summary
We introduce peptide-pair encoding (PPE), a novel method for segmenting protein sequences into variable-length sub-sequences. This approach enhances protein motif discovery and sequence embedding for machine learning applications in bioinformatics.
Area of Science:
- Bioinformatics
- Computational Biology
- Machine Learning
Background:
- Protein sequence analysis is crucial for understanding biological function.
- Existing methods for sequence segmentation and feature extraction have limitations.
- Subsequence-based approaches, inspired by natural language processing, offer new possibilities.
Purpose of the Study:
- To introduce peptide-pair encoding (PPE) as a general-purpose probabilistic segmentation method for protein sequences.
- To demonstrate the utility of PPE in protein motif discovery (DiMotif) and protein sequence embedding (ProtVecX).
- To provide a versatile representation for downstream machine learning tasks in protein bioinformatics.
Main Methods:
- Developed a modified byte-pair encoding (BPE) algorithm for probabilistic segmentation of protein sequences into variable-length sub-sequences (PPE).
- Implemented DiMotif, an alignment-free method for discriminative motif discovery using PPE.
- Extended k-mer based protein vector (ProtVec) embedding to variable-length sub-sequences using PPE, creating ProtVecX.
Main Results:
- DiMotif achieved high recall scores in discovering experimentally verified protein motifs and showed strong performance in classification tasks for integrins and biofilm formation.
- ProtVecX demonstrated marginal improvements over ProtVec in enzyme and toxin prediction tasks.
- Combined PPE-derived embeddings with raw amino acid k-mer features improved protein classification performance.
Conclusions:
- Peptide-pair encoding (PPE) provides a flexible and effective representation for protein sequences.
- PPE-based methods like DiMotif and ProtVecX offer valuable tools for motif discovery, sequence embedding, and various machine learning applications in protein bioinformatics.
- The PPE representation can enhance the performance of downstream machine learning tasks by capturing variable-length sub-sequence information.
Related Concept Videos
02:02Cis-regulatory Sequences
11.7K
Cis-regulatory sequences are short fragments of non-coding DNA that are present on the same chromosomes as the genes that they regulate. These fragments serve as binding sites for transcriptional regulators, proteins that are responsible for controlling gene transcription and differential gene expression across cell types in eukaryotes. Cis-regulatory sequences can be close to the gene of interest or thousands of bases away in the DNA sequence; however, those sequences that are further away are...
11.7K
02:02Cis-regulatory Sequences
4.1K
4.1K
01:57Sanger Sequencing
774.3K
DNA sequencing is a fundamental technique that is routinely used in the biological sciences. This method can be applied to a range of questions at different scales - from the sequencing of a cloned DNA fragment or the study of a mutation in a gene up to whole-genome sequencing. However, despite the widespread use of sequencing today, it was not until 1977 that Fredrick Sanger and his collaborators developed the chain-termination method to decode DNA sequences. It relies on the separation of a...
774.3K
03:00Next-generation Sequencing
98.4K
The first human genome sequencing project cost $2.7 billion and was declared complete in 2003, after 15 years of international cooperation and collaboration between several research teams and funding agencies. Today, with the advent of next-generation sequencing technologies, the cost and time of sequencing a human genome have dropped over 100 fold.
Next-Generation Sequencing Methods
Although all next-generation methods use different technologies, they all share a set of standard features....
Next-Generation Sequencing Methods
Although all next-generation methods use different technologies, they all share a set of standard features....
98.4K
01:05Maxam-Gilbert Sequencing
12.8K
In the same year as the discovery of the Sanger sequencing method, another group of scientists, Allan Maxam and Walter Gilbert, demonstrated their chemical-cleavage method for DNA sequencing. The Maxam-Gilbert method relies on using different chemicals that can cleave the DNA sequence at specific sites, the separation of resulting DNA fragments of variable size using electrophoresis, and deciphering the DNA sequence from the resulting gel bands.
Challenges of the Maxam-Gilbert Method
The...
Challenges of the Maxam-Gilbert Method
The...
12.8K
01:26Per-Unit Sequence Models
443
An ideal Y-Y transformer, grounded through neutral impedances, displays per-unit sequence networks akin to those of a single-phase ideal transformer when subjected to balanced positive- or negative-sequence currents. These currents do not produce neutral currents, and their associated voltage drops.
Zero-sequence currents, which are identical in magnitude and phase, generate a neutral current, resulting in voltage drops across the neutral impedance and the low-voltage winding. If the...
Zero-sequence currents, which are identical in magnitude and phase, generate a neutral current, resulting in voltage drops across the neutral impedance and the low-voltage winding. If the...
443