Search

Summary: A major challenge in cancer treatment is predicting clinical response to anti-cancer drugs on a personalized basis. Using a pharmacogenomics database of 1,001 cancer cell lines, we trained deep neural networks for prediction of drug response and assessed their performance on multiple clinical cohorts. We demonstrate that deep neural networks outperform the current state in machine learning frameworks. We provide a proof of concept for the use of deep neural network-based frameworks to aid precision oncology strategies. : Sakellaropoulos et al. designed a machine learning workflow to predict drug response and survival of cancer patients. All pipelines are trained on a large panel of cancer cell lines and tested in clinical cohorts. DNN outperforms other machine learning algorithms by capturing pathways that link gene expression with drug response. Keywords: drug response prediction, precision medicine, machine learning, deep neural networks, DNN

ARID2 is the most recurrently mutated SWI/SNF complex member in melanoma; however, its tumor-suppressive mechanisms in the context of the chromatin landscape remain to be elucidated. Here, we model ARID2 deficiency in melanoma cells, which results in defective PBAF complex assembly with a concomitant genomic redistribution of the BAF complex. Upon ARID2 depletion, a subset of PBAF and shared BAF-PBAF-occupied regions displays diminished chromatin accessibility and associated gene expression, while BAF-occupied enhancers gain chromatin accessibility and expression of genes linked to the process of invasion. As a function of altered accessibility, the genomic occupancy of melanoma-relevant transcription factors is affected and significantly correlates with the observed transcriptional changes. We further demonstrate that ARID2-deficient cells acquire the ability to colonize distal organs in multiple animal models. Taken together, our results reveal a role for ARID2 in mediating BAF and PBAF subcomplex chromatin dynamics with consequences for melanoma metastasis.

Although B-cell acute lymphoblastic leukemia (B-ALL) is the most common malignancy in children and while highly curable, it remains a leading cause of cancer-related mortality. The outgrowth of tumor subclones carrying mutations in genes responsible for resistance to therapy has led to a Darwinian model of clonal selection. Previous work has indicated that alterations in the epigenome might contribute to clonal selection, yet the extent to which the chromatin state is altered under the selective pressures of therapy is unknown. To address this, we performed chromatin immunoprecipitation, gene expression analysis, and enhanced reduced representation bisulfite sequencing on a cohort of paired diagnosis and relapse samples from individual patients who all but one relapsed within 36 months of initial diagnosis. The chromatin state at diagnosis varied widely among patients, while the majority of peaks remained stable between diagnosis and relapse. Yet a significant fraction was either lost or newly gained, with some patients showing few differences and others showing massive changes of the epigenetic state. Evolution of the epigenome was associated with pathways previously linked to therapy resistance as well as novel candidate pathways through alterations in pyrimidine biosynthesis and downregulation of polycomb repressive complex 2 targets. Three novel, relapse-specific superenhancers were shared by a majority of patients including one associated with S100A8, the top upregulated gene seen at relapse in childhood B-ALL. Overall, our results support a role of the epigenome in clonal evolution and uncover new candidate pathways associated with relapse. Significance: This study suggests a major role for epigenetic mechanisms in driving clonal evolution in B-ALL and identifies novel pathways associated with drug resistance.

Lack of cellular differentiation is a hallmark of many human cancers, including acute myeloid leukemia (AML). Strategies to overcome such a differentiation blockade are an approach for treating AML. To identify targets for differentiation-based therapies, we applied an integrated cell surface-based CRISPR platform to assess genes involved in maintaining the undifferentiated state of leukemia cells. Here we identify the RNA-binding protein ZFP36L2 as a critical regulator of AML maintenance and differentiation. Mechanistically, ZFP36L2 interacts with the 3' untranslated region of key myeloid maturation genes, including the ZFP36 paralogs, to promote their mRNA degradation and suppress terminal myeloid cell differentiation. Genetic inhibition of ZFP36L2 restores the mRNA stability of these targeted transcripts and ultimately triggers myeloid differentiation in leukemia cells. Epigenome profiling of several individuals with primary AML revealed enhancer modules near ZFP36L2 that associated with distinct AML cell states, establishing a coordinated epigenetic and post-transcriptional mechanism that shapes leukemic differentiation.

The NSD2 p.E1099K (EK) mutation is observed in 10% of acute lymphoblastic leukemia (ALL) samples with enrichment at relapse indicating a role in clonal evolution and drug resistance. To discover mechanisms that mediate clonal expansion, we engineered B-precursor ALL (B-ALL) cell lines (Reh, 697) to overexpress wildtype (WT) and EK NSD2, but observed no differences in proliferation, clonal growth, or chemosensitivity. To address whether NSD2 EK acts collaboratively with other pathways, we used short hairpin RNAs to knockdown expression of NSD2 in B-ALL cell lines heterozygous for NSD2 EK (RS4;11, RCH-ACV, SEM). Knockdown resulted in decreased proliferation in all lines, decreased clonal growth in RCH-ACV, and increased sensitivity to cytotoxic chemotherapeutic agents, although the pattern of drug sensitivity varied among cell lines implying that the oncogenic properties of NSD2 mutations are likely cell context specific and rely on cooperative pathways. Knockdown of both Type II and REIIBP EK isoforms had a greater impact than knockdown of Type II alone, suggesting that both SET containing EK isoforms contribute to phenotypic changes driving relapse. Furthermore, in vivo models using both cell lines and patient samples revealed dramatically enhanced proliferation of NSD2 EK compared with WT and reduced sensitivity to 6-mercaptopurine in the relapse sample relative to diagnosis. Finally, EK-mediated changes in chromatin state and transcriptional output differed dramatically among cell lines further supporting a cell context–specific role of NSD2 EK. These results demonstrate a unique role of NSD2 EK in mediating clonal fitness through pleiotropic mechanisms dependent on the genetic and epigenetic landscape. Implications: NSD2 EK mutation leads to drug resistance and a clonal advantage in childhood B-ALL.

Relapse-enriched somatic variants drive drug resistance in childhood acute lymphoblastic leukemia. We used digital droplet-based polymerase chain reaction to establish whether relapse-enriched mutations in emerging subclones could be detected in peripheral blood samples before frank relapse. Although limitations in sensitivity for some probes hindered detection of certain variants, we successfully detected variants in NT5C2 and PRPS1 at a fractional abundance of 0.005% to 0.3%, 41 to 116 days before relapse. As mutations in both these genes confer resistance to thiopurines, early detection protocols using peripheral blood could be implemented to preemptively alter maintenance therapy to extinguish resistant clones before overt relapse.

Planar cell polarity (PCP) and neural tube defects (NTDs) are linked, with a subset of NTD patients found to harbor mutations in PCP genes, but there is limited data on whether these mutations disrupt PCP signaling in vivo. The core PCP gene Van Gogh (Vang), Vangl1/2 in mammals, is the most specific for PCP. We thus addressed potential causality of NTD-associated Vangl1/2 mutations, from either mouse or human patients, in Drosophila allowing intricate analysis of the PCP pathway. Introducing the respective mammalian mutations into Drosophila Vang revealed defective phenotypic and functional behaviors, with changes to Vang localization, post-translational modification, and mechanistic function, such as its ability to interact with PCP effectors. Our findings provide mechanistic insight into how different mammalian mutations contribute to developmental disorders and strengthen the link between PCP and NTD. Importantly, analyses of the human mutations revealed that each is a causative factor for the associated NTD., eLife digest As an embryo develops, its cells must work together to build mature tissues and organs. During the formation of the nervous system, for example, a sheet of cells destined to become the brain and spinal cord folds up into a tube spanning the length of the embryo. Normally, this tube – known as the ‘neural tube’ – zips up, and the cells that will eventually become skin and other surrounding tissues close in over it. If the neural tube does not close completely, different parts of the spinal cord or brain can remain unprotected. This can cause diseases called neural tube defects, such as spina bifida, which is characterized by holes in the backbone exposing the spinal cord and surrounding membranes. Patients with neural tube defects can have similar genetic mutations, for example, in the genes controlling a process called “planar cell polarity”, or PCP for short. Cells arranged in flat sheets use the PCP process to sense direction, and it is this process that allows structures, such as the scales on a fish or the hairs on a mouse, to all point in the same direction. PCP is also important in embryonic development: sheets of cells that can sense direction correctly can therefore move collectively to complete complex tasks (such as closing the neural tube). However, no-one knew whether the specific PCP gene mutations implicated in neural tube defects in humans actually affected the cells’ ability to sense direction, or indeed whether they were even involved in causing the diseases. Humphries et al. set out to find out more about these mutations using fruit flies as a model system. The fruit fly is widely used to study the genes and signals involved in direction sensing, especially PCP. Problems with PCP produce easily measurable changes in the wing and eye, showing what went wrong and how badly. Humphries et al. genetically engineered fruit flies to have the same mutations as human patients and revealed that these mutations did indeed alter cells’ ability to sense direction. These experiments also showed that each mutation did so in a different way, and with varying severity. This explained why the same mutations caused different levels of neural defects in mice (which are commonly used to study human diseases) and suggests that they might contribute to neural tube disorders in humans. These results show potential connections between neural tube defects and direction sensing in cells. In the future, this study and follow-up work could help researchers to understand what types of mutation have the most impact, which may eventually allow doctors to better predict who is most at risk of being affected by these conditions.

A major challenge in cancer treatment is predicting the clinical response to anti-cancer drugs on a personalized basis. The success of such a task largely depends on the ability to develop computational resources that integrate big "omic" data into effective drug-response models. Machine learning is both an expanding and an evolving computational field that holds promise to cover such needs. Here we provide a focused overview of: 1) the various supervised and unsupervised algorithms used specifically in drug response prediction applications, 2) the strategies employed to develop these algorithms into applicable models, 3) data resources that are fed into these frameworks and 4) pitfalls and challenges to maximize model performance. In this context we also describe a novel in silico screening process, based on Association Rule Mining, for identifying genes as candidate drivers of drug response and compare it with relevant data mining frameworks, for which we generated a web application freely available at: https://compbio.nyumc.org/drugs/. This pipeline explores with high efficiency large sample-spaces, while is able to detect low frequency events and evaluate statistical significance even in the multidimensional space, presenting the results in the form of easily interpretable rules. We conclude with future prospects and challenges of applying machine learning based drug response prediction in precision medicine.

The BCL2 family plays important roles in acute myeloid leukemia (AML). Venetoclax, a selective BCL2 inhibitor, has received FDA approval for the treatment of AML. However, drug resistance ensues after prolonged treatment, highlighting the need for a greater understanding of the underlying mechanisms. Using a genome-wide CRISPR/Cas9 screen in human AML, we identified genes whose inactivation sensitizes AML blasts to venetoclax. Genes involved in mitochondrial organization and function were significantly depleted throughout our screen, including the mitochondrial chaperonin CLPB. We demonstrated that CLPB is upregulated in human AML, it is further induced upon acquisition of venetoclax resistance, and its ablation sensitizes AML to venetoclax. Mechanistically, CLPB maintains the mitochondrial cristae structure via its interaction with the cristae-shaping protein OPA1, whereas its loss promotes apoptosis by inducing cristae remodeling and mitochondrial stress responses. Overall, our data suggest that targeting mitochondrial architecture may provide a promising approach to circumvent venetoclax resistance. Significance: A genome-wide CRISPR/Cas9 screen reveals genes involved in mitochondrial biological processes participate in the acquisition of venetoclax resistance. Loss of the mitochondrial protein CLPB leads to structural and functional defects of mitochondria, hence sensitizing AML cells to apoptosis. Targeting CLPB synergizes with venetoclax and the venetoclax/azacitidine combination in AML in a p53-independent manner. See related commentary by Savona and Rathmell, p. 831. This article is highlighted in the In This Issue feature, p. 813