Key Points

  • Unsupervised consensus clustering put together patients with similar morphology or mutations into 5 morphologic and 8 genetic profiles.

  • Machine-learning techniques interrogated morphologic feature interdependencies and potential associations with mutations and survival.

Abstract

Morphologic interpretation is the standard in diagnosing myelodysplastic syndrome (MDS), but it has limitations, such as varying reliability in pathologic evaluation and lack of integration with genetic data. Somatic events shape morphologic features, but the complexity of morphologic and genetic changes makes clear associations challenging. This article interrogates novel clinical subtypes of MDS using a machine-learning technique devised to identify patterns of cooccurrence among morphologic features and genomic events. We sequenced 1079 MDS patients and analyzed bone marrow morphologic alterations and other clinical features. A total of 1929 somatic mutations were identified. Five distinct morphologic profiles with unique clinical characteristics were defined. Seventy-seven percent of higher-risk patients clustered in profile 1. All lower-risk (LR) patients clustered into the remaining 4 profiles: profile 2 was characterized by pancytopenia, profile 3 by monocytosis, profile 4 by elevated megakaryocytes, and profile 5 by erythroid dysplasia. These profiles could also separate patients with different prognoses. LR MDS patients were classified into 8 genetic signatures (eg, signature A had TET2 mutations, signature B had both TET2 and SRSF2 mutations, and signature G had SF3B1 mutations), demonstrating association with specific morphologic profiles. Six morphologic profiles/genetic signature associations were confirmed in a separate analysis of an independent cohort. Our study demonstrates that nonrandom or even pathognomonic relationships between morphology and genotype to define clinical features can be identified. This is the first comprehensive implementation of machine-learning algorithms to elucidate potential intrinsic interdependencies among genetic lesions, morphologies, and clinical prognostic in attributes of MDS.

REFERENCES

1.
Vardiman
JW
,
Thiele
J
,
Arber
DA
, et al
.
The 2008 revision of the World Health Organization (WHO) classification of myeloid neoplasms and acute leukemia: rationale and important changes
.
Blood
.
2009
;
114
(
5
):
937
-
951
.
2.
Arber
DA
,
Orazi
A
,
Hasserjian
R
, et al
.
The 2016 revision to the World Health Organization classification of myeloid neoplasms and acute leukemia [published correction appears in Blood. 2016;128(3):462-463]
.
Blood
.
2016
;
127
(
20
):
2391
-
2405
.
3.
Stephenson
J
,
Mufti
GJ
,
Yoshida
Y
.
Myelodysplastic syndromes: from morphology to molecular biology. Part II. The molecular genetics of myelodysplasia
.
Int J Hematol
.
1993
;
57
(
2
):
99
-
112
.
4.
Cazzola
M
,
Della Porta
MG
,
Travaglino
E
,
Malcovati
L
.
Classification and prognostic evaluation of myelodysplastic syndromes
.
Semin Oncol
.
2011
;
38
(
5
):
627
-
634
.
5.
Greenberg
P
,
Cox
C
,
LeBeau
MM
, et al
.
International scoring system for evaluating prognosis in myelodysplastic syndromes
.
Blood
.
1997
;
89
(
6
):
2079
-
2088
.
6.
Zhang
L
,
Stablein
DM
,
Epling-Burnette
P
, et al
.
Diagnosis of myelodysplastic syndromes and related conditions: rates of discordance between local and central review in the NHLBI MDS Natural History Study [abstract]
.
Blood
.
2018
;
132
(
suppl 1
):
4370
.
7.
Nagata
Y
,
Maciejewski
JP
.
The functional mechanisms of mutations in myelodysplastic syndrome
.
Leukemia
.
2019
;
33
(
12
):
2779
-
2794
.
8.
Broséus
J
,
Alpermann
T
,
Wulfert
M
, et al;
MPN and MPNr-EuroNet (COST Action BM0902)
.
Age, JAK2(V617F) and SF3B1 mutations are the main predicting factors for survival in refractory anaemia with ring sideroblasts and marked thrombocytosis
.
Leukemia
.
2013
;
27
(
9
):
1826
-
1831
.
9.
De Rocco
D
,
Zieger
B
,
Platokouki
H
, et al
.
MYH9-related disease: five novel mutations expanding the spectrum of causative mutations and confirming genotype/phenotype correlations
.
Eur J Med Genet
.
2013
;
56
(
1
):
7
-
12
.
10.
Pfeilstöcker
M
,
Tuechler
H
,
Sanz
G
, et al
.
Time-dependent changes in mortality and transformation risk in MDS
.
Blood
.
2016
;
128
(
7
):
902
-
910
.
11.
Makishima
H
,
Yoshida
K
,
Nguyen
N
, et al
.
Somatic SETBP1 mutations in myeloid malignancies
.
Nat Genet
.
2013
;
45
(
8
):
942
-
946
.
12.
Makishima
H
,
Yoshizato
T
,
Yoshida
K
, et al
.
Dynamics of clonal evolution in myelodysplastic syndromes
.
Nat Genet
.
2017
;
49
(
2
):
204
-
212
.
13.
Hirsch
CM
,
Przychodzen
BP
,
Radivoyevitch
T
, et al
.
Molecular features of early onset adult myelodysplastic syndrome
.
Haematologica
.
2017
;
102
(
6
):
1028
-
1034
.
14.
Haferlach
T
,
Nagata
Y
,
Grossmann
V
, et al
.
Landscape of genetic lesions in 944 patients with myelodysplastic syndromes
.
Leukemia
.
2014
;
28
(
2
):
241
-
247
.
15.
Wang
K
,
Li
M
,
Hakonarson
H
.
ANNOVAR: functional annotation of genetic variants from high-throughput sequencing data
.
Nucleic Acids Res
.
2010
;
38
(
16
):
e164
.
16.
Sherry
ST
,
Ward
MH
,
Kholodov
M
, et al
.
dbSNP: the NCBI database of genetic variation
.
Nucleic Acids Res
.
2001
;
29
(
1
):
308
-
311
.
17.
Auton
A
,
Brooks
LD
,
Durbin
RM
, et al;
1000 Genomes Project Consortium
.
A global reference for human genetic variation
.
Nature
.
2015
;
526
(
7571
):
68
-
74
.
18.
Lek
M
,
Karczewski
KJ
,
Minikel
EV
, et al;
Exome Aggregation Consortium
.
Analysis of protein-coding genetic variation in 60,706 humans
.
Nature
.
2016
;
536
(
7616
):
285
-
291
.
19.
Nagata
Y
,
Makishima
H
,
Kerr
CM
, et al
.
Invariant patterns of clonal succession determine specific clinical features of myelodysplastic syndromes
.
Nat Commun
.
2019
;
10
(
1
):
5386
.
20.
Wilkerson
MD
,
Hayes
DN
.
ConsensusClusterPlus: a class discovery tool with confidence assessments and item tracking
.
Bioinformatics
.
2010
;
26
(
12
):
1572
-
1573
.
21.
Ma
J
,
Stingo
FC
,
Hobbs
BP
.
Bayesian predictive modeling for genomic based personalized treatment selection
.
Biometrics
.
2016
;
72
(
2
):
575
-
583
.
22.
Ma
J
,
Hobbs
BP
,
Stingo
FC
.
Integrating genomic signatures for treatment selection with Bayesian predictive failure time models
.
Stat Methods Med Res
.
2018
;
27
(
7
):
2093
-
2113
.
23.
Ma
J
,
Stingo
FC
,
Hobbs
BP
.
Bayesian personalized treatment selection strategies that integrate predictive with prognostic determinants
.
Biom J
.
2019
;
61
(
4
):
902
-
917
.
24.
Newman
ME
,
Girvan
M
.
Finding and evaluating community structure in networks
.
Phys Rev E Stat Nonlin Soft Matter Phys
.
2004
;
69
(
2 Pt 2
):
026113
.
25.
Reichardt
J
,
Bornholdt
S
.
Statistical mechanics of community detection
.
Phys Rev E Stat Nonlin Soft Matter Phys
.
2006
;
74
(
1 Pt 2
):
016110
.
26.
Csardi
G
,
Nepusz
T
.
The igraph software package for complex network research
.
InterJournal Complex Syst
.
2006
;
1695
:
1695
.
27.
Kuhn
M
.
Building predictive models in R using the caret package
.
J Stat Softw
.
2008
;
28
(
5
):
28.
Ishwaran
H
,
Kogalur
UB
.
Consistency of random survival forests
.
Stat Probab Lett
.
2010
;
80
(
13-14
):
1056
-
1064
.
29.
Benjamini
Y
,
Hochberg
Y
.
Controlling the false discovery rate: a practical and powerful approach to multiple testing
.
J R Stat Soc B
.
1995
;
57
(
1
):
289
-
300
.
30.
Kanagal-Shamanna
R
,
Bueso-Ramos
CE
,
Barkoh
B
, et al
.
Myeloid neoplasms with isolated isochromosome 17q represent a clinicopathologic entity associated with myelodysplastic/myeloproliferative features, a high risk of leukemic transformation, and wild-type TP53
.
Cancer
.
2012
;
118
(
11
):
2879
-
2888
.
31.
Ohyashiki
K
,
Aota
Y
,
Akahane
D
, et al
.
The JAK2 V617F tyrosine kinase mutation in myelodysplastic syndromes (MDS) developing myelofibrosis indicates the myeloproliferative nature in a subset of MDS patients
.
Leukemia
.
2005
;
19
(
12
):
2359
-
2360
.
32.
Inoue
D
,
Bradley
RK
,
Abdel-Wahab
O
.
Spliceosomal gene mutations in myelodysplasia: molecular links to clonal abnormalities of hematopoiesis
.
Genes Dev
.
2016
;
30
(
9
):
989
-
1001
.
33.
Meggendorfer
M
,
Roller
A
,
Haferlach
T
, et al
.
SRSF2 mutations in 275 cases with chronic myelomonocytic leukemia (CMML)
.
Blood
.
2012
;
120
(
15
):
3080
-
3088
.
34.
Zhang
MY
,
Churpek
JE
,
Keel
SB
, et al
.
Germline ETV6 mutations in familial thrombocytopenia and hematologic malignancy
.
Nat Genet
.
2015
;
47
(
2
):
180
-
185
.
35.
Stengel
A
,
Kern
W
,
Haferlach
T
,
Meggendorfer
M
,
Fasan
A
,
Haferlach
C
.
The impact of TP53 mutations and TP53 deletions on survival varies between AML, ALL, MDS and CLL: an analysis of 3307 cases
.
Leukemia
.
2017
;
31
(
3
):
705
-
711
.
36.
Papaemmanuil
E
,
Gerstung
M
,
Malcovati
L
, et al;
Chronic Myeloid Disorders Working Group of the International Cancer Genome Consortium
.
Clinical and biological implications of driver mutations in myelodysplastic syndromes
.
Blood
.
2013
;
122
(
22
):
3616
-
3627
.
37.
Klampfl
T
,
Gisslinger
H
,
Harutyunyan
AS
, et al
.
Somatic mutations of calreticulin in myeloproliferative neoplasms
.
N Engl J Med
.
2013
;
369
(
25
):
2379
-
2390
.
38.
Polprasert
C
,
Schulze
I
,
Sekeres
MA
, et al
.
Inherited and somatic defects in DDX41 in myeloid neoplasms
.
Cancer Cell
.
2015
;
27
(
5
):
658
-
670
.
You do not currently have access to this content.

Sign in via your Institution

Sign In