Patient similarity network of newly diagnosed multiple myeloma identifies patient subgroups with distinct genetic features and clinical implications

Bhalla, Sherry; Melnekoff, David; Aleman, Adolfo; Leshchenko, Violetta V.; Restrepo, Paula; Onel, Kenan; Sawyer, Jeffrey R.; Madduri, Deepu; Richter, Joshua; Richard, Shambavi; Chari, Ajai; Cho, Hearn Jay; Dudley, Joel T.; Jagannath, Sundar; Laganà, Alessandro; Parekh, Samir

doi:10.1126/sciadv.abg9551

Cited by 58 publications

(46 citation statements)

References 83 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2,3 Recent analyses of large multiomics data from newly diagnosed patients with MM revealed a complex genomic landscape and the existence of multiple genetic subtypes with distinct and well-defined sets of co-occurring genetic alterations and transcriptomic features, which could stratify patients according to their risk of progression after first-line therapy and overall survival. 4,5 Broadly, chromosomal translocations involving the immunoglobulin locus on chromosome 14 and oncogenes such as NSD2, CCND1, and MAF and hyperdiploidy, a genetic abnormality defined by the presence of 3 copies of at least 2 oddnumbered chromosomes, are often the main initiating events. Additional recurrent alterations, including both single nucleotide variants and copy number changes, can then associate with translocations and hyperdiploidy following different patterns of co-occurrence and mutual exclusivity, further contributing to increased genomic complexity.…”

Section: Alessandro Lagan à | Icahn School Of Medicine At Mount Sinaimentioning

confidence: 99%

The genome of IMiD-refractory myeloma

Laganà

2023

Blood

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Alessandro Lagan à | Icahn School Of Medicine At Mount Sinaimentioning

confidence: 99%

The genome of IMiD-refractory myeloma

Laganà

2023

Blood

Self Cite

View full text Add to dashboard Cite

show abstract

“…Most of the research studies on patient similarity were rooted in cancer-related domains [ 18 , 22 , 41 ]. Glioblastoma multiforme (GBM), an aggressive adult brain tumor, was the focus of a previous study [ 18 ], in which mRNA expression, DNA methylation, and microRNA (miRNA) expression data were combined.…”

Section: Related Workmentioning

confidence: 99%

A Novel Patient Similarity Network (PSN) Framework Based on Multi-Model Deep Learning for Precision Medicine

Navaz

Kassabi

Serhani

2022

JPM

View full text Add to dashboard Cite

Precision medicine can be defined as the comparison of a new patient with existing patients that have similar characteristics and can be referred to as patient similarity. Several deep learning models have been used to build and apply patient similarity networks (PSNs). However, the challenges related to data heterogeneity and dimensionality make it difficult to use a single model to reduce data dimensionality and capture the features of diverse data types. In this paper, we propose a multi-model PSN that considers heterogeneous static and dynamic data. The combination of deep learning models and PSN allows ample clinical evidence and information extraction against which similar patients can be compared. We use the bidirectional encoder representations from transformers (BERT) to analyze the contextual data and generate word embedding, where semantic features are captured using a convolutional neural network (CNN). Dynamic data are analyzed using a long-short-term-memory (LSTM)-based autoencoder, which reduces data dimensionality and preserves the temporal features of the data. We propose a data fusion approach combining temporal and clinical narrative data to estimate patient similarity. The experiments we conducted proved that our model provides a higher classification accuracy in determining various patient health outcomes when compared with other traditional classification algorithms.

show abstract

“…Secondary events, including gain of 1q, del(17p), del(1p) and MYC translocations, accumulate along the disease course. Recently, large datasets and computational approaches have been used to refine the genomic classification of MM by accounting for numerous features, resulting in a granular view of the disease 7–9 . In the context of genetic risk stratification of newly diagnosed MM (NDMM), the IGH translocations t(4;14), t(14;16) and t(14;20) as well as del(17p), all established unfavorable markers, are usually analyzed using fluorescence in situ hybridization (FISH) 2,10,11 .…”

Section: Introductionmentioning

confidence: 99%

Amp(1q) and tetraploidy are commonly acquired chromosomal abnormalities in relapsed multiple myeloma

Locher

Jukic

Vogi

et al. 2022

European J of Haematology

View full text Add to dashboard Cite

Long-term disease control in multiple myeloma (MM) is typically an unmet medical need, and most patients experience multiple relapses. Fluorescence in situ hybridization (FISH) is the standard technique to detect chromosomal abnormalities (CAs), which are important to estimate the prognosis of MM and the allocation of risk adapted therapies. In advanced stages, the importance of CAs needs further investigation. From 148 MM patients, two or more paired samples, at least one of which was collected at relapse, were analyzed by FISH. Using targeted next-generation sequencing, we molecularly investigated samples harboring relapse-associated CAs.Sixty-one percent of the patients showed a change in the cytogenetic profile during the disease course, including 10% who acquired high-risk cytogenetics. Amp(1q) (≥4 copies of 1q21), driven by an additional increase in copy number in patients who already had 3 copies of 1q21, was the most common acquired CA with 16% affected patients. Tetraploidy, found in 10% of the samples collected at the last time-point, was unstable over the course of the disease and was associated with TP53 lesions.Our results indicate that cytogenetic progression is common in relapsed patients. The relatively high frequency of amp(1q) suggests an active role for this CA in disease progression.chromosome aberrations, multiple myeloma, recurrence, tetraploidy Novelty statementsWhat is the new aspect of your work?In a longitudinal multiple myeloma study, we examined the occurrence of chromosomal amplifications such as tetraploidy.

show abstract

Patient similarity network of newly diagnosed multiple myeloma identifies patient subgroups with distinct genetic features and clinical implications

Abstract: Integrative multiomics analysis of myeloma identifies 12 disease subtypes defined by specific patterns of genetic alterations.

Cited by 58 publications

References 83 publications

The genome of IMiD-refractory myeloma

The genome of IMiD-refractory myeloma

A Novel Patient Similarity Network (PSN) Framework Based on Multi-Model Deep Learning for Precision Medicine

Amp(1q) and tetraploidy are commonly acquired chromosomal abnormalities in relapsed multiple myeloma

Contact Info

Product

Resources

About