Data-driven crop growth simulation on time-varying generated images using multi-conditional generative adversarial networks.

BACKGROUND: Image-based crop growth modeling can substantially contribute to precision agriculture by revealing spatial crop development over time, which allows an early and location-specific estimation of relevant future plant traits, such as leaf area or biomass. A prerequisite for realistic and sharp crop image generation is the integration of multiple growth-influencing conditions in a model, such as an image of an initial growth stage, the associated growth time, and further information about the field treatment. While image-based models provide more flexibility for crop growth modeling than process-based models, there is still a significant research gap in the comprehensive integration of various growth-influencing conditions. Further exploration and investigation are needed to address this gap. METHODS: We present a two-stage framework consisting first of an image generation model and second of a growth estimation model, independently trained. The image generation model is a conditional Wasserstein generative adversarial network (CWGAN). In the generator of this model, conditional batch normalization (CBN) is used to integrate conditions of different types along with the input image. This allows the model to generate time-varying artificial images dependent on multiple influencing factors. These images are used by the second part of the framework for plant phenotyping by deriving plant-specific traits and comparing them with those of non-artificial (real) reference images. In addition, image quality is evaluated using multi-scale structural similarity (MS-SSIM), learned perceptual image patch similarity (LPIPS), and Fréchet inception distance (FID). During inference, the framework allows image generation for any combination of conditions used in training; we call this generation data-driven crop growth simulation. RESULTS: Experiments are performed on three datasets of different complexity. These datasets include the laboratory plant Arabidopsis thaliana (Arabidopsis) and crops grown under real field conditions, namely cauliflower (GrowliFlower) and crop mixtures consisting of faba bean and spring wheat (MixedCrop). In all cases, the framework allows realistic, sharp image generations with a slight loss of quality from short-term to long-term predictions. For MixedCrop grown under varying treatments (different cultivars, sowing densities), the results show that adding these treatment information increases the generation quality and phenotyping accuracy measured by the estimated biomass. Simulations of varying growth-influencing conditions performed with the trained framework provide valuable insights into how such factors relate to crop appearances, which is particularly useful in complex, less explored crop mixture systems. Further results show that adding process-based simulated biomass as a condition increases the accuracy of the derived phenotypic traits from the predicted images. This demonstrates the potential of our framework to serve as an interface between a data-driven and a process-based crop growth model. CONCLUSION: The realistic generation and simulation  of future plant appearances is adequately feasible by multi-conditional CWGAN. The presented framework complements process-based models and overcomes their limitations, such as the reliance on assumptions and the low exact field-localization specificity, by realistic visualizations of the spatial crop development that directly lead to a high explainability of the model predictions.

Statin-induced Mitochondrial Priming Sensitizes Multiple Myeloma Cells to BCL2 and MCL-1 Inhibitors.

The BCL2 inhibitor venetoclax promotes apoptosis in blood cancer cells and is approved for treatment of chronic lymphocytic leukemia and acute myeloid leukemia. However, multiple myeloma cells are frequently more dependent on MCL-1 for survival, conferring resistance to venetoclax. Here we report that mevalonate pathway inhibition with statins can overcome resistance to venetoclax in multiple myeloma cell lines and primary cells. In addition, statins sensitize to apoptosis induced by MCL-1 inhibitor, S63845. In retrospective analysis of venetoclax clinical studies in multiple myeloma, background statin use was associated with a significantly enhanced rate of stringent complete response and absence of progressive disease. Statins sensitize multiple myeloma cells to venetoclax by upregulating two proapoptotic proteins: PUMA via a p53-independent mechanism and NOXA via the integrated stress response. These findings provide rationale for prospective testing of statins with venetoclax regimens in multiple myeloma. SIGNIFICANCE: BH3 mimetics including venetoclax hold promise for treatment of multiple myeloma but rational combinations are needed to broaden efficacy. This study presents mechanistic and clinical data to support addition of pitavastatin to venetoclax regimens in myeloma. The results open a new avenue for repurposing statins in blood cancer.

The road less traveled: activating an oncogenic kinase.

Elevated phosphoinositide 3-kinase (PI3K) activity in human tumors has prompted widespread efforts to develop chemical PI3K inhibitors for oncology indications. In an innovative new study, Gong et al. report the discovery of a highly selective activator of the PI3Kα isoform, with promising activity in assays of nerve regrowth and cardioprotection from ischemia-reperfusion injury (IRI).

The WW domain of IQGAP1 binds directly to the p110α catalytic subunit of PI 3-kinase.

IQGAP1 is a multi-domain cancer-associated protein that serves as a scaffold protein for multiple signaling pathways. Numerous binding partners have been found for the calponin homology, IQ and GAP-related domains in IQGAP1. Identification of a binding partner for its WW domain has proven elusive, however, even though a cell-penetrating peptide derived from this domain has marked anti-tumor activity. Here, using in vitro binding assays with human proteins and co-precipitation from human cells, we show that the WW domain of human IQGAP1 binds directly to the p110α catalytic subunit of phosphoinositide 3-kinase (PI3K). In contrast, the WW domain does not bind to ERK1/2, MEK1/2, or the p85α regulatory subunit of PI3K when p85α is expressed alone. However, the WW domain is able to bind to the p110α/p85α heterodimer when both subunits are co-expressed, as well as to the mutationally activated p110α/p65α heterodimer. We present a model of the structure of the IQGAP1 WW domain, and experimentally identify key residues in the hydrophobic core and beta strands of the WW domain that are required for binding to p110α. These findings contribute to a more precise understanding of IQGAP1-mediated scaffolding, and of how IQGAP1-derived therapeutic peptides might inhibit tumorigenesis.