This Perspective explores the application of machine learning toward improved diagnosis and treatment. We outline a vision for how machine learning can transform three broad areas of biomedicine: ...clinical diagnostics, precision treatments, and health monitoring, where the goal is to maintain health through a range of diseases and the normal aging process. For each area, early instances of successful machine learning applications are discussed, as well as opportunities and challenges for machine learning. When these challenges are met, machine learning promises a future of rigorous, outcomes-based medicine with detection, diagnosis, and treatment strategies that are continuously adapted to individual and environmental differences.
Goecks et al. provide an ambitious vision of how machine learning could impact healthcare, outlining the progress and challenges of applying machine learning approaches to clinical diagnostics, precision therapeutics, and health monitoring.
A handful of tumor-derived cell lines form the mainstay of cancer therapeutic development, yielding drugs with an impact typically measured as months to disease progression. To develop more effective ...breast cancer therapeutics and more readily understand their clinical impact, we constructed a functional metabolic portrait of 46 independently derived breast cell lines. Our analysis of glutamine uptake and dependence identified a subset of triple-negative samples that are glutamine auxotrophs. Ambient glutamine indirectly supports environmental cystine acquisition via the xCT antiporter, which is expressed on one-third of triple-negative tumors in vivo. xCT inhibition with the clinically approved anti-inflammatory sulfasalazine decreases tumor growth, revealing a therapeutic target in breast tumors of poorest prognosis and a lead compound for rapid, effective drug development.
•Most breast tumors survive glutamine restriction, limiting its therapeutic use•A subset of triple-negative breast tumors are true glutamine auxotrophs•Conventional biomarkers of glutamine reliance do not identify true auxotrophs•Triple-negative tumors require cystine import via the xCT transporter
Compared with normal cells, tumor cells have undergone an array of genetic and epigenetic alterations. Often, these changes underlie cancer development, progression, and drug resistance, so the ...utility of model systems rests on their ability to recapitulate the genomic aberrations observed in primary tumors. Tumor-derived cell lines have long been used to study the underlying biologic processes in cancer, as well as screening platforms for discovering and evaluating the efficacy of anticancer therapeutics. Multiple -omic measurements across more than a thousand cancer cell lines have been produced following advances in high-throughput technologies and multigroup collaborative projects. These data complement the large, international cancer genomic sequencing efforts to characterize patient tumors, such as The Cancer Genome Atlas (TCGA) and International Cancer Genome Consortium (ICGC). Given the scope and scale of data that have been generated, researchers are now in a position to evaluate the similarities and differences that exist in genomic features between cell lines and patient samples. As pharmacogenomics models, cell lines offer the advantages of being easily grown, relatively inexpensive, and amenable to high-throughput testing of therapeutic agents. Data generated from cell lines can then be used to link cellular drug response to genomic features, where the ultimate goal is to build predictive signatures of patient outcome. This review highlights the recent work that has compared -omic profiles of cell lines with primary tumors, and discusses the advantages and disadvantages of cancer cell lines as pharmacogenomic models of anticancer therapies.
The Future of Conservation survey, launched in March 2017, has proposed a framework to help with interpreting the array of ethical stances underpinning the motivations for biological conservation. In ...this article we highlight what is missing in this debate to date. Our overall aim is to explore what an acceptance of ecocentric ethics would mean for how conservation is practised and how its policies are developed. We start by discussing the shortcomings of the survey and present a more convincing and accurate categorization of the conservation debate. Conceiving the future of conservation as nothing less than an attempt to preserve abundant life on earth, we illustrate the strategic and ethical advantage of ecocentric over anthropocentric approaches to conservation. After examining key areas of the current debate we endorse and defend the Nature Needs Half and bio-proportionality proposals. These proposals show how the acceptance of an ecocentric framework would aid both practices and policies aimed at promoting successful conservation. We conclude that these proposals bring a radically different and more effective approach to conservation than anthropocentric approaches, even though the latter purport to be pragmatic.
•Explaining competing ethical underpinnings for nature conservation•Critical discussion of the Future of Conservation survey•Compelling categorization of ecocentric approaches versus anthropocentric approaches•Highlighting the importance of the Nature Needs Half framework
Large-scale analysis of cellular response to anticancer drugs typically focuses on variation in potency (half-maximum inhibitory concentration, (IC50)), assuming that it is the most important ...difference between effective and ineffective drugs or sensitive and resistant cells. We took a multiparametric approach involving analysis of the slope of the dose-response curve, the area under the curve and the maximum effect (Emax). We found that some of these parameters vary systematically with cell line and others with drug class. For cell-cycle inhibitors, Emax often but not always correlated with cell proliferation rate. For drugs targeting the Akt/PI3K/mTOR pathway, dose-response curves were unusually shallow. Classical pharmacology has no ready explanation for this phenomenon, but single-cell analysis showed that it correlated with significant and heritable cell-to-cell variability in the extent of target inhibition. We conclude that parameters other than potency should be considered in the comparative analysis of drug response, particularly at clinically relevant concentrations near and above the IC50.
Cancer cells have diverse biological capabilities that are conferred by numerous genetic aberrations and epigenetic modifications. Today's powerful technologies are enabling these changes to the ...genome to be catalogued in detail. Tomorrow is likely to bring a complete atlas of the reversible and irreversible alterations that occur in individual cancers. The challenge now is to work out which molecular abnormalities contribute to cancer and which are simply 'noise' at the genomic and epigenomic levels. Distinguishing between these will aid in understanding how the aberrations in a cancer cell collaborate to drive pathophysiology. Past successes in converting information from genomic discoveries into clinical tools provide valuable lessons to guide the translation of emerging insights from the genome into clinical end points that can affect the practice of cancer medicine.
The identification of the molecular drivers of cancer by sequencing is the backbone of precision medicine and the basis of personalized therapy; however, biopsies of primary tumors provide only a ...snapshot of the evolution of the disease and may miss potential therapeutic targets, especially in the metastatic setting. A liquid biopsy, in the form of cell-free DNA (cfDNA) sequencing, has the potential to capture the inter- and intra-tumoral heterogeneity present in metastatic disease, and, through serial blood draws, track the evolution of the tumor genome. In order to determine the clinical utility of cfDNA sequencing we performed whole-exome sequencing on cfDNA and tumor DNA from two patients with metastatic disease; only minor modifications to our sequencing and analysis pipelines were required for sequencing and mutation calling of cfDNA. The first patient had metastatic sarcoma and 47 of 48 mutations present in the primary tumor were also found in the cell-free DNA. The second patient had metastatic breast cancer and sequencing identified an ESR1 mutation in the cfDNA and metastatic site, but not in the primary tumor. This likely explains tumor progression on Anastrozole. Significant heterogeneity between the primary and metastatic tumors, with cfDNA reflecting the metastases, suggested separation from the primary lesion early in tumor evolution. This is best illustrated by an activating PIK3CA mutation (H1047R) which was clonal in the primary tumor, but completely absent from either the metastasis or cfDNA. Here we show that cfDNA sequencing supplies clinically actionable information with minimal risks compared to metastatic biopsies. This study demonstrates the utility of whole-exome sequencing of cell-free DNA from patients with metastatic disease. cfDNA sequencing identified an ESR1 mutation, potentially explaining a patient's resistance to aromatase inhibition, and gave insight into how metastatic lesions differ from the primary tumor.
Rat sarcoma (Ras) GTPases regulate cell proliferation and survival through effector pathways including Raf-MAPK, and are the most frequently mutated genes in human cancer. Although it is well ...established that Ras activity requires binding to both GTP and the membrane, details of how Ras operates on the cell membrane to activate its effectors remain elusive. Efforts to target mutant Ras in human cancers to therapeutic benefit have also been largely unsuccessful. Here we show that Ras-GTP forms dimers to activate MAPK. We used quantitative photoactivated localization microscopy (PALM) to analyze the nanoscale spatial organization of PAmCherry1-tagged KRas 4B (hereafter referred to KRas) on the cell membrane under various signaling conditions. We found that at endogenous expression levels KRas forms dimers, and KRas ᴳ¹²ᴰ, a mutant that constitutively binds GTP, activates MAPK. Overexpression of KRas leads to formation of higher order Ras nanoclusters. Conversely, at lower expression levels, KRas ᴳ¹²ᴰ is monomeric and activates MAPK only when artificially dimerized. Moreover, dimerization and signaling of KRas are both dependent on an intact CAAX (C, cysteine; A, aliphatic; X, any amino acid) motif that is also known to mediate membrane localization. These results reveal a new, dimerization-dependent signaling mechanism of Ras, and suggest Ras dimers as a potential therapeutic target in mutant Ras-driven tumors.
Significance Rat sarcoma (Ras) proteins play central roles in both normal and oncogenic signaling. Mechanisms of how Ras interacts with its effectors on the cell membrane, however, are still poorly understood, significantly hampering efforts to target this molecule in human cancer. Here we have used quantitative superresolution fluorescence microscopy in combination with carefully engineered biological systems to show that Ras dimers drive oncogenic signaling through the Raf-MAPK pathway. Our study suggests a new, dimer model of Ras-Raf signaling and the potential value of Ras dimers as a therapeutic target.
Abstract
Immune checkpoint inhibitors (ICIs) targeting PD-L1 and PD-1 have improved survival in a subset of patients with advanced non-small cell lung cancer (NSCLC). However, only a minority of ...NSCLC patients respond to ICIs, highlighting the need for superior immunotherapy. Herein, we report on a nanoparticle-based immunotherapy termed ARAC (Antigen Release Agent and Checkpoint Inhibitor) designed to enhance the efficacy of PD-L1 inhibitor. ARAC is a nanoparticle co-delivering PLK1 inhibitor (volasertib) and PD-L1 antibody. PLK1 is a key mitotic kinase that is overexpressed in various cancers including NSCLC and drives cancer growth. Inhibition of PLK1 selectively kills cancer cells and upregulates PD-L1 expression in surviving cancer cells thereby providing opportunity for ARAC targeted delivery in a feedforward manner. ARAC reduces effective doses of volasertib and PD-L1 antibody by 5-fold in a metastatic lung tumor model (LLC-JSP) and the effect is mainly mediated by CD8+ T cells. ARAC also shows efficacy in another lung tumor model (KLN-205), which does not respond to CTLA-4 and PD-1 inhibitor combination. This study highlights a rational combination strategy to augment existing therapies by utilizing our nanoparticle platform that can load multiple cargo types at once.
Here, we describe a multiplexed immunohistochemical platform with computational image processing workflows, including image cytometry, enabling simultaneous evaluation of 12 biomarkers in one ...formalin-fixed paraffin-embedded tissue section. To validate this platform, we used tissue microarrays containing 38 archival head and neck squamous cell carcinomas and revealed differential immune profiles based on lymphoid and myeloid cell densities, correlating with human papilloma virus status and prognosis. Based on these results, we investigated 24 pancreatic ductal adenocarcinomas from patients who received neoadjuvant GVAX vaccination and revealed that response to therapy correlated with degree of mono-myelocytic cell density and percentages of CD8+ T cells expressing T cell exhaustion markers. These data highlight the utility of in situ immune monitoring for patient stratification and provide digital image processing pipelines to the community for examining immune complexity in precious tissue sections, where phenotype and tissue architecture are preserved to improve biomarker discovery and assessment.
Display omitted
•Multiplex IHC and computational image analysis phenotypes tumor-immune complexity•In situ leukocyte density correlates with subclassification and prognosis in HNSCC•Immune complexity stratifies response to vaccination therapy in PDAC•CD8+ T cell and PD-L1 status correlate with outcomes of vaccinated PDAC patients
Tsujikawa et al. develop a multiplex immunohistochemistry and image cytometry platform to reveal immune-based metrics for patient stratification and response monitoring. In HNSCC and PDAC, prognosis correlates with mono-myelocytic cell density. In PDAC, percentages of PD-1, Eomes, Ki67, and granzyme B in CD8+ T cells correlate with response to vaccine therapy.