scholarly journals Protein Structural Alignments From Sequence

2020 ◽  
Author(s):  
James T. Morton ◽  
Charlie E. M. Strauss ◽  
Robert Blackwell ◽  
Daniel Berenberg ◽  
Vladimir Gligorijevic ◽  
...  
Keyword(s):  
Sequence Alignment ◽  
Sequence Similarity ◽  
Language Model ◽  
Language Models ◽  
Evolutionary Analysis ◽  
Homology Detection ◽  
Remote Homology ◽  
Alignment Algorithms ◽  
Modern Molecular Biology ◽  
Gpu Architectures

AbstractComputing sequence similarity is a fundamental task in biology, with alignment forming the basis for the annotation of genes and genomes and providing the core data structures for evolutionary analysis. Standard approaches are a mainstay of modern molecular biology and rely on variations of edit distance to obtain explicit alignments between pairs of biological sequences. However, sequence alignment algorithms struggle with remote homology tasks and cannot identify similarities between many pairs of proteins with similar structures and likely homology. Recent work suggests that using machine learning language models can improve remote homology detection. To this end, we introduce DeepBLAST, that obtains explicit alignments from residue embeddings learned from a protein language model integrated into an end-to-end differentiable alignment framework. This approach can be accelerated on the GPU architectures and outperforms conventional sequence alignment techniques in terms of both speed and accuracy when identifying structurally similar proteins.

scholarly journals SHsearch - a method for fast remote homology detection

2018 ◽  
Author(s):  
Mohamed Baddar
Keyword(s):  
Markov Models ◽  
Sequence Similarity ◽  
Protein Homology ◽  
Homology Detection ◽  
Remote Homology ◽  
Sensitivity Loss ◽  
Computationally Intensive ◽  
Profile Hmm ◽  
Programming Algorithms ◽  
Remote Homology Detection

Remote homology detection is the problem of detecting homology in cases of low sequence similarity. It is a hard computational problem with no approach that works well in all cases. Methods based on profile hidden Markov models (HMM) often exhibit relatively higher sensitivity for detecting remote homologies than commonly used approaches. However, calculating similarity scores in profile HMM methods is computationally intensive as they use dynamic programming algorithms. In this paper we introduce SHsearch: a new method for remote protein homology detection. Our method is implemented as a modification of HHsearch: a remote protein homology detection method based on comparing two profile HMMs. The motivation for modification was to reduce the run time of HHsearch significantly with minimal sensitivity loss. SHsearch focuses on comparing the important submodels of the query and database HMMs instead of comparing the complete models. Hence, SHsearch achieves a significant speedup over HHsearch with minimal loss in sensitivity. On SCOP 1.63, SHsearch achieved 88X speedup with 8.2% loss in sensitivity with respect to HHsearch at error rate of 10%, which deemed to be an acceptable tradeoff.

scholarly journals SHsearch: a method for fast remote homology detection

2018 ◽  
Author(s):  
Mohamed Baddar
Keyword(s):  
Markov Models ◽  
Sequence Similarity ◽  
Protein Homology ◽  
Homology Detection ◽  
Remote Homology ◽  
Sensitivity Loss ◽  
Computationally Intensive ◽  
Profile Hmm ◽  
Programming Algorithms ◽  
Remote Homology Detection

Remote homology detection is the problem of detecting homology in cases of low sequence similarity. It is a hard computational problem with no approach that works well in all cases. Methods based on profile hidden Markov models (HMM) often exhibit relatively higher sensitivity for detecting remote homologies than commonly used approaches. However, calculating similarity scores in profile HMM methods is computationally intensive as they use dynamic programming algorithms. In this paper we introduce SHsearch: a new method for remote protein homology detection. Our method is implemented as a modification of HHsearch: a remote protein homology detection method based on comparing two profile HMMs. The motivation for modification was to reduce the run time of HHsearch significantly with minimal sensitivity loss. SHsearch focuses on comparing the important submodels of the query and database HMMs instead of comparing the complete models. Hence, SHsearch achieves a significant speedup over HHsearch with minimal loss in sensitivity. On SCOP 1.63, SHsearch achieved 88X speedup with 8.2% loss in sensitivity with respect to HHsearch at error rate of 10%, which deemed to be an acceptable tradeoff.

scholarly journals Efficient Multiple Sequences Alignment Algorithm Generation via Components Assembly Under PAR Framework

2021 ◽  
Vol 11 ◽  
Author(s):  
Haipeng Shi ◽  
Haihe Shi ◽  
Shenghua Xu
Keyword(s):  
Sequence Alignment ◽  
Multiple Sequence Alignment ◽  
Sequence Similarity ◽  
Alignment Algorithm ◽  
Pairwise Sequence Alignment ◽  
Multiple Sequence ◽  
Sequence Alignment Algorithm ◽  
Alignment Algorithms ◽  
Sequence Similarity Analysis ◽  
High Level

As a key algorithm in bioinformatics, sequence alignment algorithm is widely used in sequence similarity analysis and genome sequence database search. Existing research focuses mainly on the specific steps of the algorithm or is for specific problems, lack of high-level abstract domain algorithm framework. Multiple sequence alignment algorithms are more complex, redundant, and difficult to understand, and it is not easy for users to select the appropriate algorithm; some computing errors may occur. Based on our constructed pairwise sequence alignment algorithm component library and the convenient software platform PAR, a few expansion domain components are developed for multiple sequence alignment application domain, and specific multiple sequence alignment algorithm can be designed, and its corresponding program, i.e., C++/Java/Python program, can be generated efficiently and thus enables the improvement of the development efficiency of complex algorithms, as well as accuracy of sequence alignment calculation. A star alignment algorithm is designed and generated to demonstrate the development process.

scholarly journals SHsearch: a method for fast remote homology detection

2018 ◽  
Author(s):  
Mohamed Baddar
Keyword(s):  
Markov Models ◽  
Sequence Similarity ◽  
Protein Homology ◽  
Homology Detection ◽  
Remote Homology ◽  
Sensitivity Loss ◽  
Computationally Intensive ◽  
Profile Hmm ◽  
Programming Algorithms ◽  
Remote Homology Detection

Remote homology detection is the problem of detecting homology in cases of low sequence similarity. It is a hard computational problem with no approach that works well in all cases. Methods based on profile hidden Markov models (HMM) often exhibit relatively higher sensitivity for detecting remote homologies than commonly used approaches. However, calculating similarity scores in profile HMM methods is computationally intensive as they use dynamic programming algorithms. In this paper we introduce SHsearch: a new method for remote protein homology detection. Our method is implemented as a modification of HHsearch: a remote protein homology detection method based on comparing two profile HMMs. The motivation for modification was to reduce the run time of HHsearch significantly with minimal sensitivity loss. SHsearch focuses on comparing the important submodels of the query and database HMMs instead of comparing the complete models. Hence, SHsearch achieves a significant speedup over HHsearch with minimal loss in sensitivity. On SCOP 1.63, SHsearch achieved 88X speedup with 8.2% loss in sensitivity with respect to HHsearch at error rate of 10%, which deemed to be an acceptable tradeoff.

SVM-BALSA: Remote homology detection based on Bayesian sequence alignment

2005 ◽  
Vol 29 (6) ◽  
pp. 440-443 ◽  
Author(s):  
Bobbie-Jo Webb-Robertson ◽  
Christopher Oehmen ◽  
Melissa Matzke
Keyword(s):  
Sequence Alignment ◽  
Homology Detection ◽  
Remote Homology ◽  
Remote Homology Detection

A Comprehensive Analysis of Sequence Alignment Algorithms for LongRead Sequencing

2016 ◽  
Vol 11 (3) ◽  
pp. 375-381
Author(s):  
Yu Zhang ◽  
Jian Tai He ◽  
Yangde Zhang ◽  
Ke Zuo
Keyword(s):  
Sequence Alignment ◽  
Comprehensive Analysis ◽  
Alignment Algorithms

INTEGRATION OF n-GRAM LANGUAGE MODELS IN MULTIPLE CLASSIFIER SYSTEMS FOR OFFLINE HANDWRITTEN TEXT LINE RECOGNITION

2008 ◽  
Vol 22 (07) ◽  
pp. 1301-1321 ◽  
Author(s):  
ROMAN BERTOLAMI ◽  
HORST BUNKE
Keyword(s):  
Language Model ◽  
Language Models ◽  
Combination Method ◽  
Text Line ◽  
Multiple Classifier Systems ◽  
Classifier Systems ◽  
Handwritten Text ◽  
Handwritten Text Recognition ◽  
Multiple Classifier ◽  
N Gram

Current multiple classifier systems for unconstrained handwritten text recognition do not provide a straightforward way to utilize language model information. In this paper, we describe a generic method to integrate a statistical n-gram language model into the combination of multiple offline handwritten text line recognizers. The proposed method first builds a word transition network and then rescores this network with an n-gram language model. Experimental evaluation conducted on a large dataset of offline handwritten text lines shows that the proposed approach improves the recognition accuracy over a reference system as well as over the original combination method that does not include a language model.

scholarly journals Automated Source Code Generation and Auto-Completion Using Deep Learning: Comparing and Discussing Current Language Model-Related Approaches

AI ◽  
2021 ◽  
Vol 2 (1) ◽  
pp. 1-16
Author(s):  
Juan Cruz-Benito ◽  
Sanjay Vishwakarma ◽  
Francisco Martin-Fernandez ◽  
Ismael Faro
Keyword(s):  
Deep Learning ◽  
Learning Community ◽  
Programming Languages ◽  
Language Processing ◽  
Code Generation ◽  
Language Model ◽  
Language Models ◽  
Stochastic Gradient Descent ◽  
Network Architectures ◽  
Learning Architectures

In recent years, the use of deep learning in language models has gained much attention. Some research projects claim that they can generate text that can be interpreted as human writing, enabling new possibilities in many application areas. Among the different areas related to language processing, one of the most notable in applying this type of modeling is programming languages. For years, the machine learning community has been researching this software engineering area, pursuing goals like applying different approaches to auto-complete, generate, fix, or evaluate code programmed by humans. Considering the increasing popularity of the deep learning-enabled language models approach, we found a lack of empirical papers that compare different deep learning architectures to create and use language models based on programming code. This paper compares different neural network architectures like Average Stochastic Gradient Descent (ASGD) Weight-Dropped LSTMs (AWD-LSTMs), AWD-Quasi-Recurrent Neural Networks (QRNNs), and Transformer while using transfer learning and different forms of tokenization to see how they behave in building language models using a Python dataset for code generation and filling mask tasks. Considering the results, we discuss each approach’s different strengths and weaknesses and what gaps we found to evaluate the language models or to apply them in a real programming context.

Sign in / Sign up

Export Citation Format

Share Document