Cargando…

Predicting Bone Metastasis Using Gene Expression-Based Machine Learning Models

Bone is the most common site of distant metastasis from malignant tumors, with the highest prevalence observed in breast and prostate cancers. Such bone metastases (BM) cause many painful skeletal-related events, such as severe bone pain, pathological fractures, spinal cord compression, and hypercal...

Descripción completa

Detalles Bibliográficos
Autores principales: Albaradei, Somayah, Uludag, Mahmut, Thafar, Maha A., Gojobori, Takashi, Essack, Magbubah, Gao, Xin
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8631472/
https://www.ncbi.nlm.nih.gov/pubmed/34858485
http://dx.doi.org/10.3389/fgene.2021.771092
_version_ 1784607568413327360
author Albaradei, Somayah
Uludag, Mahmut
Thafar, Maha A.
Gojobori, Takashi
Essack, Magbubah
Gao, Xin
author_facet Albaradei, Somayah
Uludag, Mahmut
Thafar, Maha A.
Gojobori, Takashi
Essack, Magbubah
Gao, Xin
author_sort Albaradei, Somayah
collection PubMed
description Bone is the most common site of distant metastasis from malignant tumors, with the highest prevalence observed in breast and prostate cancers. Such bone metastases (BM) cause many painful skeletal-related events, such as severe bone pain, pathological fractures, spinal cord compression, and hypercalcemia, with adverse effects on life quality. Many bone-targeting agents developed based on the current understanding of BM onset’s molecular mechanisms dull these adverse effects. However, only a few studies investigated potential predictors of high risk for developing BM, despite such knowledge being critical for early interventions to prevent or delay BM. This work proposes a computational network-based pipeline that incorporates a ML/DL component to predict BM development. Based on the proposed pipeline we constructed several machine learning models. The deep neural network (DNN) model exhibited the highest prediction accuracy (AUC of 92.11%) using the top 34 featured genes ranked by betweenness centrality scores. We further used an entirely separate, “external” TCGA dataset to evaluate the robustness of this DNN model and achieved sensitivity of 85%, specificity of 80%, positive predictive value of 78.10%, negative predictive value of 80%, and AUC of 85.78%. The result shows the models’ way of learning allowed it to zoom in on the featured genes that provide the added benefit of the model displaying generic capabilities, that is, to predict BM for samples from different primary sites. Furthermore, existing experimental evidence provides confidence that about 50% of the 34 hub genes have BM-related functionality, which suggests that these common genetic markers provide vital insight about BM drivers. These findings may prompt the transformation of such a method into an artificial intelligence (AI) diagnostic tool and direct us towards mechanisms that underlie metastasis to bone events.
format Online
Article
Text
id pubmed-8631472
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-86314722021-12-01 Predicting Bone Metastasis Using Gene Expression-Based Machine Learning Models Albaradei, Somayah Uludag, Mahmut Thafar, Maha A. Gojobori, Takashi Essack, Magbubah Gao, Xin Front Genet Genetics Bone is the most common site of distant metastasis from malignant tumors, with the highest prevalence observed in breast and prostate cancers. Such bone metastases (BM) cause many painful skeletal-related events, such as severe bone pain, pathological fractures, spinal cord compression, and hypercalcemia, with adverse effects on life quality. Many bone-targeting agents developed based on the current understanding of BM onset’s molecular mechanisms dull these adverse effects. However, only a few studies investigated potential predictors of high risk for developing BM, despite such knowledge being critical for early interventions to prevent or delay BM. This work proposes a computational network-based pipeline that incorporates a ML/DL component to predict BM development. Based on the proposed pipeline we constructed several machine learning models. The deep neural network (DNN) model exhibited the highest prediction accuracy (AUC of 92.11%) using the top 34 featured genes ranked by betweenness centrality scores. We further used an entirely separate, “external” TCGA dataset to evaluate the robustness of this DNN model and achieved sensitivity of 85%, specificity of 80%, positive predictive value of 78.10%, negative predictive value of 80%, and AUC of 85.78%. The result shows the models’ way of learning allowed it to zoom in on the featured genes that provide the added benefit of the model displaying generic capabilities, that is, to predict BM for samples from different primary sites. Furthermore, existing experimental evidence provides confidence that about 50% of the 34 hub genes have BM-related functionality, which suggests that these common genetic markers provide vital insight about BM drivers. These findings may prompt the transformation of such a method into an artificial intelligence (AI) diagnostic tool and direct us towards mechanisms that underlie metastasis to bone events. Frontiers Media S.A. 2021-11-10 /pmc/articles/PMC8631472/ /pubmed/34858485 http://dx.doi.org/10.3389/fgene.2021.771092 Text en Copyright © 2021 Albaradei, Uludag, Thafar, Gojobori, Essack and Gao. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Genetics
Albaradei, Somayah
Uludag, Mahmut
Thafar, Maha A.
Gojobori, Takashi
Essack, Magbubah
Gao, Xin
Predicting Bone Metastasis Using Gene Expression-Based Machine Learning Models
title Predicting Bone Metastasis Using Gene Expression-Based Machine Learning Models
title_full Predicting Bone Metastasis Using Gene Expression-Based Machine Learning Models
title_fullStr Predicting Bone Metastasis Using Gene Expression-Based Machine Learning Models
title_full_unstemmed Predicting Bone Metastasis Using Gene Expression-Based Machine Learning Models
title_short Predicting Bone Metastasis Using Gene Expression-Based Machine Learning Models
title_sort predicting bone metastasis using gene expression-based machine learning models
topic Genetics
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8631472/
https://www.ncbi.nlm.nih.gov/pubmed/34858485
http://dx.doi.org/10.3389/fgene.2021.771092
work_keys_str_mv AT albaradeisomayah predictingbonemetastasisusinggeneexpressionbasedmachinelearningmodels
AT uludagmahmut predictingbonemetastasisusinggeneexpressionbasedmachinelearningmodels
AT thafarmahaa predictingbonemetastasisusinggeneexpressionbasedmachinelearningmodels
AT gojoboritakashi predictingbonemetastasisusinggeneexpressionbasedmachinelearningmodels
AT essackmagbubah predictingbonemetastasisusinggeneexpressionbasedmachinelearningmodels
AT gaoxin predictingbonemetastasisusinggeneexpressionbasedmachinelearningmodels