Related Experiment Video
Updated: Aug 6, 2026
12:00
A Practical Guide to Phylogenetics for Nonexperts
Published on: February 5, 2014
A deep learning-based score to evaluate multiple sequence alignments
Nimrod Serok1, Ksenia Polonsky1, Haim Ashkenazy2
1The Shmunis School of Biomedicine and Cancer Research, George S. Wise Faculty of Life Sciences, Tel Aviv University, Tel Aviv 69978, Israel.
Molecular Biology and Evolution
|July 21, 2026
Summary
The sum-of-pairs (SoP) score used in multiple sequence alignment (MSA) often fails to identify the most accurate alignments. Deep learning models developed in this study significantly improve alignment accuracy and phylogenetic inference.
Area of Science:
- Genomics
- Bioinformatics
- Computational Biology
Background:
- Multiple sequence alignment (MSA) is crucial for molecular evolution and comparative genomics.
- Current MSA methods often optimize the sum-of-pairs (SoP) score, which may not reflect true alignment accuracy.
Purpose of the Study:
- To evaluate the performance of the SoP score in reflecting alignment accuracy.
- To develop novel deep learning-based scoring functions for improved MSA accuracy.
- To enhance the reliability of downstream phylogenetic inference.
Main Methods:
- Evaluation of SoP score using simulated and empirical benchmark alignments.
- Development of a deep learning regression model (Model 1) to predict MSA accuracy.
- Development of a deep learning ranking model (Model 2) to select the best MSA from alternatives.
Main Results:
- The SoP score often does not identify the most accurate MSA.
- Model 1 shows a stronger correlation with alignment accuracy than the SoP score.
- Model 2 outperforms SoP, Model 1, and existing alignment programs in identifying top-ranking MSAs.
- Using the proposed method for MSA selection improves phylogenetic reconstruction accuracy.
Conclusions:
- The SoP score is an inadequate objective function for accurate MSA.
- Deep learning-based scoring functions offer a significant improvement for MSA accuracy.
- The developed models enhance the reliability of phylogenetic inference by improving MSA quality.
Related Concept Videos
02:54Evolutionary Relationships through Genome Comparisons
Genome comparison is one of the excellent ways to interpret the evolutionary relationships between organisms. The basic principle of genome comparison is that if two species share a common feature, it is likely encoded by the DNA sequence conserved between both species. The advent of genome sequencing technologies in the late 20th century enabled scientists to understand the concept of conservation of domains between species and helped them to deduce evolutionary relationships across diverse...
03:21RNA-seq
RNA sequencing, or RNA-Seq, is a high-throughput sequencing technology used to study the transcriptome of a cell. Transcriptomics helps to interpret the functional elements of a genome and identify the molecular constituents of an organism. Additionally, it also helps in understanding the development of an organism and the occurrence of diseases.
Before the discovery of RNA-seq, microarray-based methods and Sanger sequencing were used for transcriptome analysis. However, while microarray-based...
Before the discovery of RNA-seq, microarray-based methods and Sanger sequencing were used for transcriptome analysis. However, while microarray-based...