Deep Learning Techniques to Characterize the <i>RPS28P7</i> Pseudogene and the <i>Metazoa</i>-<i>SRP</i> Gene as Drug Potential Targets in Pancreatic Cancer Patients
The molecular explanation about why some pancreatic cancer (PaCa) patients die early and others die later is poorly understood. This study aimed to discover potential novel markers and drug targets that could be useful to stratify and extend expected survival in prospective early-death patients. We...
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2024-02-01
|
Series: | Biomedicines |
Subjects: | |
Online Access: | https://www.mdpi.com/2227-9059/12/2/395 |
_version_ | 1797298860712787968 |
---|---|
author | Iván Salgado Ernesto Prado Montes de Oca Isaac Chairez Luis Figueroa-Yáñez Alejandro Pereira-Santana Andrés Rivera Chávez Jesús Bernardino Velázquez-Fernandez Teresa Alvarado Parra Adriana Vallejo |
author_facet | Iván Salgado Ernesto Prado Montes de Oca Isaac Chairez Luis Figueroa-Yáñez Alejandro Pereira-Santana Andrés Rivera Chávez Jesús Bernardino Velázquez-Fernandez Teresa Alvarado Parra Adriana Vallejo |
author_sort | Iván Salgado |
collection | DOAJ |
description | The molecular explanation about why some pancreatic cancer (PaCa) patients die early and others die later is poorly understood. This study aimed to discover potential novel markers and drug targets that could be useful to stratify and extend expected survival in prospective early-death patients. We deployed a deep learning algorithm and analyzed the gene copy number, gene expression, and protein expression data of death versus alive PaCa patients from the GDC cohort. The genes with higher relative amplification (copy number <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>></mo><mn>4</mn></mrow></semantics></math></inline-formula> times in the dead compared with the alive group) were <i>EWSR1</i>, <i>FLT3</i>, <i>GPC3</i>, <i>HIF1A</i>, <i>HLF</i>, and <i>MEN1</i>. The most highly up-regulated genes (>8.5-fold change) in the death group were <i>RPL30</i>, <i>RPL37</i>, <i>RPS28P7</i>, <i>RPS11</i>, <i>Metazoa</i>_<i>SRP</i>, <i>CAPNS1</i>, <i>FN1</i>, <i>H3</i>−<i>3B</i>, <i>LCN2</i>, and <i>OAZ1</i>. None of their corresponding proteins were up or down-regulated in the death group. The mRNA of the <i>RPS28P7</i> pseudogene could act as ceRNA sponging the miRNA that was originally directed to the parental gene <i>RPS28</i>. We propose <i>RPS28P7</i> mRNA as the most druggable target that can be modulated with small molecules or the RNA technology approach. These markers could be added as criteria to patient stratification in future PaCa drug trials, but further validation in the target populations is encouraged. |
first_indexed | 2024-03-07T22:41:10Z |
format | Article |
id | doaj.art-f6d4631064cb465cbf1af89543056293 |
institution | Directory Open Access Journal |
issn | 2227-9059 |
language | English |
last_indexed | 2024-03-07T22:41:10Z |
publishDate | 2024-02-01 |
publisher | MDPI AG |
record_format | Article |
series | Biomedicines |
spelling | doaj.art-f6d4631064cb465cbf1af895430562932024-02-23T15:08:42ZengMDPI AGBiomedicines2227-90592024-02-0112239510.3390/biomedicines12020395Deep Learning Techniques to Characterize the <i>RPS28P7</i> Pseudogene and the <i>Metazoa</i>-<i>SRP</i> Gene as Drug Potential Targets in Pancreatic Cancer PatientsIván Salgado0Ernesto Prado Montes de Oca1Isaac Chairez2Luis Figueroa-Yáñez3Alejandro Pereira-Santana4Andrés Rivera Chávez5Jesús Bernardino Velázquez-Fernandez6Teresa Alvarado Parra7Adriana Vallejo8Medical Robotics and Biosignals Laboratory, Centro de Innovación y Desarrollo Tecnológico en Cómputo, Instituto Politécnico Nacional (IPN), Mexico City 07700, MexicoRegulatory SNPs Laboratory, Personalized Medicine National Laboratory (LAMPER), Guadalajara Unit, Medical and Pharmaceutical Biotechnology Department, Research Center in Technology and Design Assistance of Jalisco State (CIATEJ), National Council of Science and Technology (CONACYT), Guadalajara 44270, Jalisco, MexicoTecnologico de Monterrey, Institute of Advanced Materials for Sustainable Manufacturing, Monterrey 64849, Jalisco, MexicoIndustrial Biotechnology Unit, Center for Research and Assistance in Technology and Design of the State of Jalisco, A.C. (CIATEJ), Guadalajara 44270, Jalisco, MexicoIndustrial Biotechnology Unit, Center for Research and Assistance in Technology and Design of the State of Jalisco, A.C. (CIATEJ), Guadalajara 44270, Jalisco, MexicoRegulatory SNPs Laboratory, Personalized Medicine National Laboratory (LAMPER), Guadalajara Unit, Medical and Pharmaceutical Biotechnology Department, Research Center in Technology and Design Assistance of Jalisco State (CIATEJ), National Council of Science and Technology (CONACYT), Guadalajara 44270, Jalisco, MexicoConsejo Nacional de Ciencia y Tecnología (CONACYT), Av. Insurgentes sur 1582, Alcaldía Benito Juárez, Mexico City 03940, MexicoRegulatory SNPs Laboratory, Personalized Medicine National Laboratory (LAMPER), Guadalajara Unit, Medical and Pharmaceutical Biotechnology Department, Research Center in Technology and Design Assistance of Jalisco State (CIATEJ), National Council of Science and Technology (CONACYT), Guadalajara 44270, Jalisco, MexicoUnidad de Biotecnología Médica y Farmacéutica, CONACYT-Centro de Investigación y Asistencia en Tecnologia y Diseño del Estado de Jalisco AC, Av. Normalistas 800, Colinas de la Normal, Guadalajara 44270, Jalisco, MexicoThe molecular explanation about why some pancreatic cancer (PaCa) patients die early and others die later is poorly understood. This study aimed to discover potential novel markers and drug targets that could be useful to stratify and extend expected survival in prospective early-death patients. We deployed a deep learning algorithm and analyzed the gene copy number, gene expression, and protein expression data of death versus alive PaCa patients from the GDC cohort. The genes with higher relative amplification (copy number <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>></mo><mn>4</mn></mrow></semantics></math></inline-formula> times in the dead compared with the alive group) were <i>EWSR1</i>, <i>FLT3</i>, <i>GPC3</i>, <i>HIF1A</i>, <i>HLF</i>, and <i>MEN1</i>. The most highly up-regulated genes (>8.5-fold change) in the death group were <i>RPL30</i>, <i>RPL37</i>, <i>RPS28P7</i>, <i>RPS11</i>, <i>Metazoa</i>_<i>SRP</i>, <i>CAPNS1</i>, <i>FN1</i>, <i>H3</i>−<i>3B</i>, <i>LCN2</i>, and <i>OAZ1</i>. None of their corresponding proteins were up or down-regulated in the death group. The mRNA of the <i>RPS28P7</i> pseudogene could act as ceRNA sponging the miRNA that was originally directed to the parental gene <i>RPS28</i>. We propose <i>RPS28P7</i> mRNA as the most druggable target that can be modulated with small molecules or the RNA technology approach. These markers could be added as criteria to patient stratification in future PaCa drug trials, but further validation in the target populations is encouraged.https://www.mdpi.com/2227-9059/12/2/395deep learningpancreatic cancerlethalitybiomarkersgene copy numbergene expression |
spellingShingle | Iván Salgado Ernesto Prado Montes de Oca Isaac Chairez Luis Figueroa-Yáñez Alejandro Pereira-Santana Andrés Rivera Chávez Jesús Bernardino Velázquez-Fernandez Teresa Alvarado Parra Adriana Vallejo Deep Learning Techniques to Characterize the <i>RPS28P7</i> Pseudogene and the <i>Metazoa</i>-<i>SRP</i> Gene as Drug Potential Targets in Pancreatic Cancer Patients Biomedicines deep learning pancreatic cancer lethality biomarkers gene copy number gene expression |
title | Deep Learning Techniques to Characterize the <i>RPS28P7</i> Pseudogene and the <i>Metazoa</i>-<i>SRP</i> Gene as Drug Potential Targets in Pancreatic Cancer Patients |
title_full | Deep Learning Techniques to Characterize the <i>RPS28P7</i> Pseudogene and the <i>Metazoa</i>-<i>SRP</i> Gene as Drug Potential Targets in Pancreatic Cancer Patients |
title_fullStr | Deep Learning Techniques to Characterize the <i>RPS28P7</i> Pseudogene and the <i>Metazoa</i>-<i>SRP</i> Gene as Drug Potential Targets in Pancreatic Cancer Patients |
title_full_unstemmed | Deep Learning Techniques to Characterize the <i>RPS28P7</i> Pseudogene and the <i>Metazoa</i>-<i>SRP</i> Gene as Drug Potential Targets in Pancreatic Cancer Patients |
title_short | Deep Learning Techniques to Characterize the <i>RPS28P7</i> Pseudogene and the <i>Metazoa</i>-<i>SRP</i> Gene as Drug Potential Targets in Pancreatic Cancer Patients |
title_sort | deep learning techniques to characterize the i rps28p7 i pseudogene and the i metazoa i i srp i gene as drug potential targets in pancreatic cancer patients |
topic | deep learning pancreatic cancer lethality biomarkers gene copy number gene expression |
url | https://www.mdpi.com/2227-9059/12/2/395 |
work_keys_str_mv | AT ivansalgado deeplearningtechniquestocharacterizetheirps28p7ipseudogeneandtheimetazoaiisrpigeneasdrugpotentialtargetsinpancreaticcancerpatients AT ernestopradomontesdeoca deeplearningtechniquestocharacterizetheirps28p7ipseudogeneandtheimetazoaiisrpigeneasdrugpotentialtargetsinpancreaticcancerpatients AT isaacchairez deeplearningtechniquestocharacterizetheirps28p7ipseudogeneandtheimetazoaiisrpigeneasdrugpotentialtargetsinpancreaticcancerpatients AT luisfigueroayanez deeplearningtechniquestocharacterizetheirps28p7ipseudogeneandtheimetazoaiisrpigeneasdrugpotentialtargetsinpancreaticcancerpatients AT alejandropereirasantana deeplearningtechniquestocharacterizetheirps28p7ipseudogeneandtheimetazoaiisrpigeneasdrugpotentialtargetsinpancreaticcancerpatients AT andresriverachavez deeplearningtechniquestocharacterizetheirps28p7ipseudogeneandtheimetazoaiisrpigeneasdrugpotentialtargetsinpancreaticcancerpatients AT jesusbernardinovelazquezfernandez deeplearningtechniquestocharacterizetheirps28p7ipseudogeneandtheimetazoaiisrpigeneasdrugpotentialtargetsinpancreaticcancerpatients AT teresaalvaradoparra deeplearningtechniquestocharacterizetheirps28p7ipseudogeneandtheimetazoaiisrpigeneasdrugpotentialtargetsinpancreaticcancerpatients AT adrianavallejo deeplearningtechniquestocharacterizetheirps28p7ipseudogeneandtheimetazoaiisrpigeneasdrugpotentialtargetsinpancreaticcancerpatients |