PMID- 34320000
OWN - NLM
STAT- MEDLINE
DCOM- 20211104
LR  - 20211104
IS  - 1932-6203 (Electronic)
IS  - 1932-6203 (Linking)
VI  - 16
IP  - 7
DP  - 2021
TI  - Machine learning predicts treatment sensitivity in multiple myeloma based on 
      molecular and clinical information coupled with drug response.
PG  - e0254596
LID - 10.1371/journal.pone.0254596 [doi]
LID - e0254596
AB  - Providing treatment sensitivity stratification at the time of cancer diagnosis 
      allows better allocation of patients to alternative treatment options. Despite 
      many clinical and biological risk markers having been associated with variable 
      survival in cancer, assessing the interplay of these markers through Machine 
      Learning (ML) algorithms still remains to be fully explored. Here, we present a 
      Multi Learning Training approach (MuLT) combining supervised, unsupervised and 
      self-supervised learning algorithms, to examine the predictive value of 
      heterogeneous treatment outcomes for Multiple Myeloma (MM). We show that gene 
      expression values improve the treatment sensitivity prediction and recapitulates 
      genetic abnormalities detected by Fluorescence in situ hybridization (FISH) 
      testing. MuLT performance was assessed by cross-validation experiments, in which 
      it predicted treatment sensitivity with 68.70% of AUC. Finally, simulations 
      showed numerical evidences that in average 17.07% of patients could get better 
      response to a different treatment at the first line.
FAU - Venezian Povoa, Lucas
AU  - Venezian Povoa L
AUID- ORCID: 0000-0003-4002-4122
AD  - Aeronautics Institute of Technology (ITA), Bioengineering Lab, Sao Jose dos 
      Campos, Brazil.
AD  - Aeronautics Institute of Technology (ITA), Computer Science Division, Sao Jose 
      dos Campos, Brazil.
AD  - AC Camargo Cancer Center (ACCCC), International Research and Educational Center, 
      Sao Paulo, Brazil.
AD  - Federal Institute for Education, Science, and Technology of Sao Paulo (IFPS), 
      Jacarei, Brazil.
FAU - Ribeiro, Carlos Henrique Costa
AU  - Ribeiro CHC
AUID- ORCID: 0000-0002-5760-8426
AD  - Aeronautics Institute of Technology (ITA), Bioengineering Lab, Sao Jose dos 
      Campos, Brazil.
AD  - Aeronautics Institute of Technology (ITA), Computer Science Division, Sao Jose 
      dos Campos, Brazil.
FAU - Silva, Israel Tojal da
AU  - Silva ITD
AUID- ORCID: 0000-0002-4687-1499
AD  - AC Camargo Cancer Center (ACCCC), International Research and Educational Center, 
      Sao Paulo, Brazil.
LA  - eng
PT  - Journal Article
PT  - Research Support, Non-U.S. Gov't
DEP - 20210728
PL  - United States
TA  - PLoS One
JT  - PloS one
JID - 101285081
RN  - 0 (Antineoplastic Agents)
SB  - IM
MH  - Antineoplastic Agents/*therapeutic use
MH  - Area Under Curve
MH  - Gene Expression Regulation, Neoplastic
MH  - Humans
MH  - In Situ Hybridization, Fluorescence
MH  - *Machine Learning
MH  - Multiple Myeloma/*drug therapy/genetics/mortality
MH  - ROC Curve
MH  - Survival Rate
MH  - Treatment Outcome
PMC - PMC8318243
COIS- The authors declare no competing interests.
EDAT- 2021/07/29 06:00
MHDA- 2021/11/05 06:00
PMCR- 2021/07/28
CRDT- 2021/07/28 17:22
PHST- 2020/10/26 00:00 [received]
PHST- 2021/06/29 00:00 [accepted]
PHST- 2021/07/28 17:22 [entrez]
PHST- 2021/07/29 06:00 [pubmed]
PHST- 2021/11/05 06:00 [medline]
PHST- 2021/07/28 00:00 [pmc-release]
AID - PONE-D-20-33606 [pii]
AID - 10.1371/journal.pone.0254596 [doi]
PST - epublish
SO  - PLoS One. 2021 Jul 28;16(7):e0254596. doi: 10.1371/journal.pone.0254596. 
      eCollection 2021.