Genetic program activity delineates risk, relapse, and therapy responsiveness in multiple myeloma

Improved classification of soil As contamination at continental scale: Resolving class imbalances using machine learning approach

The identification of arsenic (As)-contaminated areas is an important prerequisite for soil management and reclamation. Although previous studies have attempted to identify soil As contamination via machine learning (ML) methods combined with soil spectroscopy, they have ignored the rarity of As-contaminated soil samples, leading to an imbalanced learning problem. A novel ML framework was thus designed herein to solve the imbalance issue in identifying soil As contamination from soil visible and near-infrared spectra. Spectral preprocessing, imbalanced dataset resampling, and model comparisons were combined in the ML framework, and the optimal combination was selected based on the recall. In addition, Bayesian optimization was used to tune the model hyperparameters. The optimized model achieved recall, area under the curve, and balanced accuracy values of 0.83, 0.88, and 0.79, respectively, on the testing set. The recall was further improved to 0.87 with the threshold adjustment, indicating the model's excellent performance and generalization capability in classifying As-contaminated soil samples. The optimal model was applied to a global soil spectral dataset to predict areas at a high risk of soil As contamination on a global scale. The ML framework established in this study represents a milestone in the classification of soil As contamination and can serve as a valuable reference for contamination management in soil science.

Gene regulatory network topology governs resistance and treatment escape in glioma stem-like cells

Poor prognosis and drug resistance in glioblastoma (GBM) can result from cellular heterogeneity and treatment-induced shifts in phenotypic states of tumor cells, including dedifferentiation into glioma stem-like cells (GSCs). This rare tumorigenic cell subpopulation resists temozolomide, undergoes proneural-to-mesenchymal transition (PMT) to evade therapy, and drives recurrence. Through inference of transcriptional regulatory networks (TRNs) of patient-derived GSCs (PD-GSCs) at single-cell resolution, we demonstrate how the topology of transcription factor interaction networks drives distinct trajectories of cell-state transitions in PD-GSCs resistant or susceptible to cytotoxic drug treatment. By experimentally testing predictions based on TRN simulations, we show that drug treatment drives surviving PD-GSCs along a trajectory of intermediate states, exposing vulnerability to potentiated killing by siRNA or a second drug targeting treatment-induced transcriptional programs governing nongenetic cell plasticity. Our findings demonstrate an approach to uncover TRN topology and use it to rationally predict combinatorial treatments that disrupt acquired resistance in GBM.

An atlas of causal and mechanistic drivers of interpatient heterogeneity in glioma

Grade IV glioma, formerly known as glioblastoma multiforme (GBM) is the most aggressive and lethal type of brain tumor, and its treatment remains challenging in part due to extensive interpatient heterogeneity in disease driving mechanisms and lack of prognostic and predictive biomarkers. Using mechanistic inference of node-edge relationship (MINER), we have analyzed multiomics profiles from 516 patients and constructed an atlas of causal and mechanistic drivers of interpatient heterogeneity in GBM (gbmMINER). The atlas has delineated how 30 driver mutations act in a combinatorial scheme to causally influence a network of regulators (306 transcription factors and 73 miRNAs) of 179 transcriptional "programs", influencing disease progression in patients across 23 disease states. Through extensive testing on independent patient cohorts, we share evidence that a machine learning model trained on activity profiles of programs within gbmMINER significantly augments risk stratification, identifying patients who are super-responders to standard of care and those that would benefit from 2 nd line treatments. In addition to providing mechanistic hypotheses regarding disease prognosis, the activity of programs containing targets of 2 nd line treatments accurately predicted efficacy of 28 drugs in killing glioma stem-like cells from 43 patients. Our findings demonstrate that interpatient heterogeneity manifests from differential activities of transcriptional programs, providing actionable strategies for mechanistically characterizing GBM from a systems perspective and developing better prognostic and predictive biomarkers for personalized medicine.

The Urgent Need for Precision Medicine in Cancer and Its Microenvironment: The Paradigmatic Case of Multiple Myeloma

Precision medicine is particularly relevant for cancer and microenvironment deconvolution for therapeutic purposes in hematological and non-hematological malignancies [...].

A single-cell based precision medicine approach using glioblastoma patient-specific models

Glioblastoma (GBM) is a heterogeneous tumor made up of cell states that evolve over time. Here, we modeled tumor evolutionary trajectories during standard-of-care treatment using multi-omic single-cell analysis of a primary tumor sample, corresponding mouse xenografts subjected to standard of care therapy, and recurrent tumor at autopsy. We mined the multi-omic data with single-cell SYstems Genetics Network AnaLysis (scSYGNAL) to identify a network of 52 regulators that mediate treatment-induced shifts in xenograft tumor-cell states that were also reflected in recurrence. By integrating scSYGNAL-derived regulatory network information with transcription factor accessibility deviations derived from single-cell ATAC-seq data, we developed consensus networks that modulate cell state transitions across subpopulations of primary and recurrent tumor cells. Finally, by matching targeted therapies to active regulatory networks underlying tumor evolutionary trajectories, we provide a framework for applying single-cell-based precision medicine approaches to an individual patient in a concurrent, adjuvant, or recurrent setting.

Insights into high-risk multiple myeloma from an analysis of the role of PHF19 in cancer

Despite  improvements in outcome, 15-25% of newly diagnosed multiple myeloma (MM) patients have treatment resistant high-risk (HR) disease with a poor survival. The lack of a genetic basis for HR has focused attention on the role played by epigenetic changes. Aberrant expression and somatic mutations affecting genes involved in the regulation of tri-methylation of the lysine (K) 27 on histone 3 H3 (H3K27me3) are common in cancer. H3K27me3 is catalyzed by EZH2, the catalytic subunit of the Polycomb Repressive Complex 2 (PRC2). The deregulation of H3K27me3 has been shown to be involved in oncogenic transformation and tumor progression in a variety of hematological malignancies including MM. Recently we have shown that aberrant overexpression of the PRC2 subunit PHD Finger Protein 19 (PHF19) is the most significant overall contributor to HR status further focusing attention on the role played by epigenetic change in MM. By modulating both the PRC2/EZH2 catalytic activity and recruitment, PHF19 regulates the expression of key genes involved in cell growth and differentiation. Here we review the expression, regulation and function of PHF19 both in normal and the pathological contexts of solid cancers and MM. We present evidence that strongly implicates PHF19 in the regulation of genes important in cell cycle and the genetic stability of MM cells making it highly relevant to HR MM behavior. A detailed understanding of the normal and pathological functions of PHF19 will allow us to design therapeutic strategies able to target aggressive subsets of MM.