Modeling disease progression in Multiple Myeloma with Hopfield networks and single-cell RNA-seq

Sergii Domanskyi; Alex Hakansson; Giovanni Paternostro; Carlo Piermarocchi

doi:10.1109/bibm47256.2019.8983325

Modeling disease progression in Multiple Myeloma with Hopfield networks and single-cell RNA-seq

Proceedings (IEEE Int Conf Bioinformatics Biomed). 2019 Nov:2019:2129-2136. doi: 10.1109/bibm47256.2019.8983325. Epub 2020 Feb 6.

Authors

Sergii Domanskyi¹, Alex Hakansson², Giovanni Paternostro³, Carlo Piermarocchi¹

Affiliations

¹ Michigan State University, East Lansing, MI, USA.
² Salgomed, Inc., Del Mar, CA, USA.
³ SBP Medical Discovery Institute, La Jolla, CA, USA.

Abstract

Associative memories in Hopfield's neural networks are mapped to gene expression pattern to model different paths of disease progression towards Multiple Myeloma (MM). The model is built using single cell RNA-seq data from bone marrow aspirates of MM patients as well as patients diagnosed with Monoclonal Gammopathy of Undetermined Significance (MGUS) and Smoldering Multiple Myeloma (SMM), two medical conditions that often progress to full MM.

Results: We identify different clusters of MGUS, SMM, and MM cells, map them to Hopfield associative memory patterns, and model the dynamics of transition between the different patterns. The model is then used to identify genes that are differentialy expressed across different MM stages and whose simultaneous inhibition is associated to a delayed disease progression.

Keywords: cancer disease progression; neural networks; single cell sequencing data.

Grants and funding

R01 GM122085/GM/NIGMS NIH HHS/United States