Learned Indexing in Proteins: Extended Work on Substituting
Complex Distance Calculations with Embedding and Clustering
Techniques

V 2022

Learned Indexing in Proteins: Extended Work on Substituting Complex Distance Calculations with Embedding and Clustering Techniques

OĽHA, Jaroslav, Terézia SLANINÁKOVÁ, Martin GENDIAR, Matej ANTOL, Vlastislav DOHNAL et. al.

Basic information

Original name

Learned Indexing in Proteins: Extended Work on Substituting Complex Distance Calculations with Embedding and Clustering Techniques

Authors

OĽHA, Jaroslav, Terézia SLANINÁKOVÁ, Martin GENDIAR, Matej ANTOL and Vlastislav DOHNAL

Edition

2022

Publisher

arXiv

Other information

Language

English

Type of outcome

Výzkumná zpráva

Country of publisher

United States of America

Confidentiality degree

není předmětem státního či obchodního tajemství

References:

URL

Organization unit

Faculty of Informatics

DOI

http://dx.doi.org/10.48550/ARXIV.2208.08910

Keywords in English

Protein database;Embedding non-vector data;Learned metric index;Similarity search;Machine learning for indexing

Abstract

V originále

Despite the constant evolution of similarity searching research, it continues to face the same challenges stemming from the complexity of the data, such as the curse of dimensionality and computationally expensive distance functions. Various machine learning techniques have proven capable of replacing elaborate mathematical models with combinations of simple linear functions, often gaining speed and simplicity at the cost of formal guarantees of accuracy and correctness of querying. The authors explore the potential of this research trend by presenting a lightweight solution for the complex problem of 3D protein structure search. The solution consists of three steps -- (i) transformation of 3D protein structural information into very compact vectors, (ii) use of a probabilistic model to group these vectors and respond to queries by returning a given number of similar objects, and (iii) a final filtering step which applies basic vector distance functions to refine the result.

Links

EF16_019/0000822, research and development project

Name: Centrum excelence pro kyberkriminalitu, kyberbezpečnost a ochranu kritických informačních infrastruktur

LM2018131, research and development project

Name: Česká národní infrastruktura pro biologická data (Acronym: ELIXIR-CZ)

Investor: Ministry of Education, Youth and Sports of the CR, Czech National Infrastructure for Biological Data

LM2018140, research and development project

Name: e-Infrastruktura CZ (Acronym: e-INFRA CZ)

Investor: Ministry of Education, Youth and Sports of the CR

MUNI/A/1195/2021, interní kód MU

Name: Aplikovaný výzkum v oblastech vyhledávání, analýz a vizualizací rozsáhlých dat, zpracování přirozeného jazyka a aplikované umělé inteligence

Investor: Masaryk University

Citovat

OĽHA, Jaroslav, Terézia SLANINÁKOVÁ, Martin GENDIAR, Matej ANTOL and Vlastislav DOHNAL. Learned Indexing in Proteins: Extended Work on Substituting Complex Distance Calculations with Embedding and Clustering Techniques. arXiv, 2022. Available from: https://dx.doi.org/10.48550/ARXIV.2208.08910.

@misc{2212035,
   author = {Oľha, Jaroslav and Slanináková, Terézia and Gendiar, Martin and Antol, Matej and Dohnal, Vlastislav},
   doi = {http://dx.doi.org/10.48550/ARXIV.2208.08910},
   keywords = {Protein database;Embedding non-vector data;Learned metric index;Similarity search;Machine learning for indexing},
   language = {eng},
   publisher = {arXiv},
   title = {Learned Indexing in Proteins: Extended Work on Substituting Complex Distance Calculations with Embedding and Clustering Techniques},
   url = {https://arxiv.org/abs/2208.08910},
   year = {2022}
}

TY  - GEN
ID  - 2212035
AU  - Oľha, Jaroslav - Slanináková, Terézia - Gendiar, Martin - Antol, Matej - Dohnal, Vlastislav
PY  - 2022
TI  - Learned Indexing in Proteins: Extended Work on Substituting Complex Distance Calculations with Embedding and Clustering Techniques
PB  - arXiv
KW  - Protein database;Embedding non-vector data;Learned metric index;Similarity search;Machine learning for indexing
UR  - https://arxiv.org/abs/2208.08910
N2  - Despite the constant evolution of similarity searching research, it continues to face the same challenges stemming from the complexity of the data, such as the curse of dimensionality and computationally expensive distance functions. Various machine learning techniques have proven capable of replacing elaborate mathematical models with combinations of simple linear functions, often gaining speed and simplicity at the cost of formal guarantees of accuracy and correctness of querying. The authors explore the potential of this research trend by presenting a lightweight solution for the complex problem of 3D protein structure search. The solution consists of three steps -- (i) transformation of 3D protein structural information into very compact vectors, (ii) use of a probabilistic model to group these vectors and respond to queries by returning a given number of similar objects, and (iii) a final filtering step which applies basic vector distance functions to refine the result.
ER  -

OĽHA, Jaroslav, Terézia SLANINÁKOVÁ, Martin GENDIAR, Matej ANTOL and Vlastislav DOHNAL. \textit{Learned Indexing in Proteins: Extended Work on Substituting Complex Distance Calculations with Embedding and Clustering Techniques}. arXiv, 2022. Available from: https://dx.doi.org/10.48550/ARXIV.2208.08910.

Detailed Information on Publication Record