NoAS-DS : Neural optimal architecture search for detection of diverse DNA signals
Copyright © 2021 Elsevier Ltd. All rights reserved..
Neural network architectures are high-performing variable models that can solve many learning tasks. Designing architectures manually require substantial time and also prior knowledge and expertise to develop a high-accuracy model. Most of the architecture search methods are developed over the task of image classification resulting in the building of complex architectures intended for large data inputs such as images. Motivated by the applications of DNA computing in Neural Architecture Search (NAS), we propose NoAS-DS which is specifically built for the architecture search of sequence-based classification tasks. Furthermore, NoAS-DS is applied to the task of predicting binding sites. Unlike other methods that implement only Convolution layers, NoAS-DS, specifically combines Convolution and LSTM layers that helps in the process of automatic architecture building. This hybrid approach helped in achieving high accuracy results on TFBS and RBP datasets which outperformed other models in TF-DNA binding prediction tasks. The best architectures generated by the proposed model can be applied to other DNA datasets of similar nature using transfer learning technique that demonstrates its generalization capability. This greatly reduces the effort required to build new architectures for other prediction tasks.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2022 |
---|---|
Erschienen: |
2022 |
Enthalten in: |
Zur Gesamtaufnahme - volume:147 |
---|---|
Enthalten in: |
Neural networks : the official journal of the International Neural Network Society - 147(2022) vom: 01. März, Seite 63-71 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Sivangi, Kaushik Bhargav [VerfasserIn] |
---|
Links: |
---|
Themen: |
9007-49-2 |
---|
Anmerkungen: |
Date Completed 01.02.2022 Date Revised 01.02.2022 published: Print-Electronic Citation Status MEDLINE |
---|
doi: |
10.1016/j.neunet.2021.12.009 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM335149227 |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM335149227 | ||
003 | DE-627 | ||
005 | 20231225225213.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231225s2022 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1016/j.neunet.2021.12.009 |2 doi | |
028 | 5 | 2 | |a pubmed24n1117.xml |
035 | |a (DE-627)NLM335149227 | ||
035 | |a (NLM)34979461 | ||
035 | |a (PII)S0893-6080(21)00482-2 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Sivangi, Kaushik Bhargav |e verfasserin |4 aut | |
245 | 1 | 0 | |a NoAS-DS |b Neural optimal architecture search for detection of diverse DNA signals |
264 | 1 | |c 2022 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Completed 01.02.2022 | ||
500 | |a Date Revised 01.02.2022 | ||
500 | |a published: Print-Electronic | ||
500 | |a Citation Status MEDLINE | ||
520 | |a Copyright © 2021 Elsevier Ltd. All rights reserved. | ||
520 | |a Neural network architectures are high-performing variable models that can solve many learning tasks. Designing architectures manually require substantial time and also prior knowledge and expertise to develop a high-accuracy model. Most of the architecture search methods are developed over the task of image classification resulting in the building of complex architectures intended for large data inputs such as images. Motivated by the applications of DNA computing in Neural Architecture Search (NAS), we propose NoAS-DS which is specifically built for the architecture search of sequence-based classification tasks. Furthermore, NoAS-DS is applied to the task of predicting binding sites. Unlike other methods that implement only Convolution layers, NoAS-DS, specifically combines Convolution and LSTM layers that helps in the process of automatic architecture building. This hybrid approach helped in achieving high accuracy results on TFBS and RBP datasets which outperformed other models in TF-DNA binding prediction tasks. The best architectures generated by the proposed model can be applied to other DNA datasets of similar nature using transfer learning technique that demonstrates its generalization capability. This greatly reduces the effort required to build new architectures for other prediction tasks | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a Binding sites | |
650 | 4 | |a LSTM | |
650 | 4 | |a Neural architecture search | |
650 | 4 | |a RBP | |
650 | 4 | |a TFBS | |
650 | 7 | |a DNA |2 NLM | |
650 | 7 | |a 9007-49-2 |2 NLM | |
700 | 1 | |a Dasari, Chandra Mohan |e verfasserin |4 aut | |
700 | 1 | |a Amilpur, Santhosh |e verfasserin |4 aut | |
700 | 1 | |a Bhukya, Raju |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Neural networks : the official journal of the International Neural Network Society |d 1996 |g 147(2022) vom: 01. März, Seite 63-71 |w (DE-627)NLM087746824 |x 1879-2782 |7 nnns |
773 | 1 | 8 | |g volume:147 |g year:2022 |g day:01 |g month:03 |g pages:63-71 |
856 | 4 | 0 | |u http://dx.doi.org/10.1016/j.neunet.2021.12.009 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 147 |j 2022 |b 01 |c 03 |h 63-71 |