Modeling transcriptomic age using knowledge-primed artificial neural networks
Abstract The development of ‘age clocks’, machine learning models predicting age from biological data, has been a major milestone in the search for reliable markers of biological age and has since become an invaluable tool in aging research. However, beyond their unquestionable utility, current cloc...
Guardado en:
| Autores principales: | , , , , , , , , , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
Nature Portfolio
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/777c395850e541569fc03b8d41e94be4 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:doaj.org-article:777c395850e541569fc03b8d41e94be4 |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:777c395850e541569fc03b8d41e94be42021-12-02T17:50:48ZModeling transcriptomic age using knowledge-primed artificial neural networks10.1038/s41514-021-00068-52056-3973https://doaj.org/article/777c395850e541569fc03b8d41e94be42021-06-01T00:00:00Zhttps://doi.org/10.1038/s41514-021-00068-5https://doaj.org/toc/2056-3973Abstract The development of ‘age clocks’, machine learning models predicting age from biological data, has been a major milestone in the search for reliable markers of biological age and has since become an invaluable tool in aging research. However, beyond their unquestionable utility, current clocks offer little insight into the molecular biological processes driving aging, and their inner workings often remain non-transparent. Here we propose a new type of age clock, one that couples predictivity with interpretability of the underlying biology, achieved through the incorporation of prior knowledge into the model design. The clock, an artificial neural network constructed according to well-described biological pathways, allows the prediction of age from gene expression data of skin tissue with high accuracy, while at the same time capturing and revealing aging states of the pathways driving the prediction. The model recapitulates known associations of aging gene knockdowns in simulation experiments and demonstrates its utility in deciphering the main pathways by which accelerated aging conditions such as Hutchinson–Gilford progeria syndrome, as well as pro-longevity interventions like caloric restriction, exert their effects.Nicholas HolzscheckCassandra FalckenhaynJörn SöhleBoris KristofRalf SiegnerAndré WernerJanka SchössowClemens JürgensHenry VölzkeHorst WenckMarc WinnefeldElke GrönnigerLars KaderaliNature PortfolioarticleGeriatricsRC952-954.6ENnpj Aging and Mechanisms of Disease, Vol 7, Iss 1, Pp 1-13 (2021) |
| institution |
DOAJ |
| collection |
DOAJ |
| language |
EN |
| topic |
Geriatrics RC952-954.6 |
| spellingShingle |
Geriatrics RC952-954.6 Nicholas Holzscheck Cassandra Falckenhayn Jörn Söhle Boris Kristof Ralf Siegner André Werner Janka Schössow Clemens Jürgens Henry Völzke Horst Wenck Marc Winnefeld Elke Grönniger Lars Kaderali Modeling transcriptomic age using knowledge-primed artificial neural networks |
| description |
Abstract The development of ‘age clocks’, machine learning models predicting age from biological data, has been a major milestone in the search for reliable markers of biological age and has since become an invaluable tool in aging research. However, beyond their unquestionable utility, current clocks offer little insight into the molecular biological processes driving aging, and their inner workings often remain non-transparent. Here we propose a new type of age clock, one that couples predictivity with interpretability of the underlying biology, achieved through the incorporation of prior knowledge into the model design. The clock, an artificial neural network constructed according to well-described biological pathways, allows the prediction of age from gene expression data of skin tissue with high accuracy, while at the same time capturing and revealing aging states of the pathways driving the prediction. The model recapitulates known associations of aging gene knockdowns in simulation experiments and demonstrates its utility in deciphering the main pathways by which accelerated aging conditions such as Hutchinson–Gilford progeria syndrome, as well as pro-longevity interventions like caloric restriction, exert their effects. |
| format |
article |
| author |
Nicholas Holzscheck Cassandra Falckenhayn Jörn Söhle Boris Kristof Ralf Siegner André Werner Janka Schössow Clemens Jürgens Henry Völzke Horst Wenck Marc Winnefeld Elke Grönniger Lars Kaderali |
| author_facet |
Nicholas Holzscheck Cassandra Falckenhayn Jörn Söhle Boris Kristof Ralf Siegner André Werner Janka Schössow Clemens Jürgens Henry Völzke Horst Wenck Marc Winnefeld Elke Grönniger Lars Kaderali |
| author_sort |
Nicholas Holzscheck |
| title |
Modeling transcriptomic age using knowledge-primed artificial neural networks |
| title_short |
Modeling transcriptomic age using knowledge-primed artificial neural networks |
| title_full |
Modeling transcriptomic age using knowledge-primed artificial neural networks |
| title_fullStr |
Modeling transcriptomic age using knowledge-primed artificial neural networks |
| title_full_unstemmed |
Modeling transcriptomic age using knowledge-primed artificial neural networks |
| title_sort |
modeling transcriptomic age using knowledge-primed artificial neural networks |
| publisher |
Nature Portfolio |
| publishDate |
2021 |
| url |
https://doaj.org/article/777c395850e541569fc03b8d41e94be4 |
| work_keys_str_mv |
AT nicholasholzscheck modelingtranscriptomicageusingknowledgeprimedartificialneuralnetworks AT cassandrafalckenhayn modelingtranscriptomicageusingknowledgeprimedartificialneuralnetworks AT jornsohle modelingtranscriptomicageusingknowledgeprimedartificialneuralnetworks AT boriskristof modelingtranscriptomicageusingknowledgeprimedartificialneuralnetworks AT ralfsiegner modelingtranscriptomicageusingknowledgeprimedartificialneuralnetworks AT andrewerner modelingtranscriptomicageusingknowledgeprimedartificialneuralnetworks AT jankaschossow modelingtranscriptomicageusingknowledgeprimedartificialneuralnetworks AT clemensjurgens modelingtranscriptomicageusingknowledgeprimedartificialneuralnetworks AT henryvolzke modelingtranscriptomicageusingknowledgeprimedartificialneuralnetworks AT horstwenck modelingtranscriptomicageusingknowledgeprimedartificialneuralnetworks AT marcwinnefeld modelingtranscriptomicageusingknowledgeprimedartificialneuralnetworks AT elkegronniger modelingtranscriptomicageusingknowledgeprimedartificialneuralnetworks AT larskaderali modelingtranscriptomicageusingknowledgeprimedartificialneuralnetworks |
| _version_ |
1718379292163833856 |