Using Proteomics Data to Identify Personalized Treatments in Multiple Myeloma: A Machine Learning Approach
This paper describes a machine learning (ML) decision support system to provide a list of chemotherapeutics that individual multiple myeloma (MM) patients are sensitive/resistant to, based on their proteomic profile. The methodology used in this study involved understanding the parameter space and s...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-10-01
|
Series: | International Journal of Molecular Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/1422-0067/24/21/15570 |
_version_ | 1797631902535909376 |
---|---|
author | Angeliki Katsenou Roisin O’Farrell Paul Dowling Caroline A. Heckman Peter O’Gorman Despina Bazou |
author_facet | Angeliki Katsenou Roisin O’Farrell Paul Dowling Caroline A. Heckman Peter O’Gorman Despina Bazou |
author_sort | Angeliki Katsenou |
collection | DOAJ |
description | This paper describes a machine learning (ML) decision support system to provide a list of chemotherapeutics that individual multiple myeloma (MM) patients are sensitive/resistant to, based on their proteomic profile. The methodology used in this study involved understanding the parameter space and selecting the dominant features (proteomics data), identifying patterns of proteomic profiles and their association to the recommended treatments, and defining the decision support system of personalized treatment as a classification problem. During the data analysis, we compared several ML algorithms, such as linear regression, Random Forest, and support vector machines, to classify patients as sensitive/resistant to therapeutics. A further analysis examined data-balancing techniques that emerged due to the small cohort size. The results suggest that utilizing proteomics data is a promising approach for identifying effective treatment options for patients with MM (reaching on average an accuracy of 81%). Although this pilot study was limited by the small patient cohort (39 patients), which restricted the training and validation of the explored ML solutions to identify complex associations between proteins, it holds great promise for developing personalized anti-MM treatments using ML approaches. |
first_indexed | 2024-03-11T11:29:17Z |
format | Article |
id | doaj.art-fbc7b00ee8da43d1baf80ba2aff8b41b |
institution | Directory Open Access Journal |
issn | 1661-6596 1422-0067 |
language | English |
last_indexed | 2024-03-11T11:29:17Z |
publishDate | 2023-10-01 |
publisher | MDPI AG |
record_format | Article |
series | International Journal of Molecular Sciences |
spelling | doaj.art-fbc7b00ee8da43d1baf80ba2aff8b41b2023-11-10T15:04:28ZengMDPI AGInternational Journal of Molecular Sciences1661-65961422-00672023-10-0124211557010.3390/ijms242115570Using Proteomics Data to Identify Personalized Treatments in Multiple Myeloma: A Machine Learning ApproachAngeliki Katsenou0Roisin O’Farrell1Paul Dowling2Caroline A. Heckman3Peter O’Gorman4Despina Bazou5Department of Electronics and Electrical Engineering, Trinity College Dublin, D02 PN40 Dublin, IrelandDepartment of Electronics and Electrical Engineering, Trinity College Dublin, D02 PN40 Dublin, IrelandDepartment of Biology, Maynooth University, W23 F2K8 Kildare, IrelandInstitute for Molecular Medicine Finland-FIMM, HiLIFE-Helsinki Institute of Life Science, iCAN Digital Precision Cancer Medicine Flagship, University of Helsinki, 00290 Helsinki, FinlandDepartment of Haematology, Mater Misericordiae University Hospital, D07 R2WY Dublin, IrelandSchool of Medicine, University College Dublin, D04 V1W8 Dublin, IrelandThis paper describes a machine learning (ML) decision support system to provide a list of chemotherapeutics that individual multiple myeloma (MM) patients are sensitive/resistant to, based on their proteomic profile. The methodology used in this study involved understanding the parameter space and selecting the dominant features (proteomics data), identifying patterns of proteomic profiles and their association to the recommended treatments, and defining the decision support system of personalized treatment as a classification problem. During the data analysis, we compared several ML algorithms, such as linear regression, Random Forest, and support vector machines, to classify patients as sensitive/resistant to therapeutics. A further analysis examined data-balancing techniques that emerged due to the small cohort size. The results suggest that utilizing proteomics data is a promising approach for identifying effective treatment options for patients with MM (reaching on average an accuracy of 81%). Although this pilot study was limited by the small patient cohort (39 patients), which restricted the training and validation of the explored ML solutions to identify complex associations between proteins, it holds great promise for developing personalized anti-MM treatments using ML approaches.https://www.mdpi.com/1422-0067/24/21/15570multiple myelomaproteomicsdrug sensitivity scoremachine learning |
spellingShingle | Angeliki Katsenou Roisin O’Farrell Paul Dowling Caroline A. Heckman Peter O’Gorman Despina Bazou Using Proteomics Data to Identify Personalized Treatments in Multiple Myeloma: A Machine Learning Approach International Journal of Molecular Sciences multiple myeloma proteomics drug sensitivity score machine learning |
title | Using Proteomics Data to Identify Personalized Treatments in Multiple Myeloma: A Machine Learning Approach |
title_full | Using Proteomics Data to Identify Personalized Treatments in Multiple Myeloma: A Machine Learning Approach |
title_fullStr | Using Proteomics Data to Identify Personalized Treatments in Multiple Myeloma: A Machine Learning Approach |
title_full_unstemmed | Using Proteomics Data to Identify Personalized Treatments in Multiple Myeloma: A Machine Learning Approach |
title_short | Using Proteomics Data to Identify Personalized Treatments in Multiple Myeloma: A Machine Learning Approach |
title_sort | using proteomics data to identify personalized treatments in multiple myeloma a machine learning approach |
topic | multiple myeloma proteomics drug sensitivity score machine learning |
url | https://www.mdpi.com/1422-0067/24/21/15570 |
work_keys_str_mv | AT angelikikatsenou usingproteomicsdatatoidentifypersonalizedtreatmentsinmultiplemyelomaamachinelearningapproach AT roisinofarrell usingproteomicsdatatoidentifypersonalizedtreatmentsinmultiplemyelomaamachinelearningapproach AT pauldowling usingproteomicsdatatoidentifypersonalizedtreatmentsinmultiplemyelomaamachinelearningapproach AT carolineaheckman usingproteomicsdatatoidentifypersonalizedtreatmentsinmultiplemyelomaamachinelearningapproach AT peterogorman usingproteomicsdatatoidentifypersonalizedtreatmentsinmultiplemyelomaamachinelearningapproach AT despinabazou usingproteomicsdatatoidentifypersonalizedtreatmentsinmultiplemyelomaamachinelearningapproach |