Search for: All records

SUMMARY The metabolism of tetrahydrofolate (H₄PteGlu_n)‐bound one‐carbon (C₁) units (C₁metabolism) is multifaceted and required for plant growth, but it is unclear what of many possible synthesis pathways provide C₁units in specific organelles and tissues. One possible source of C₁units is via formate‐tetrahydrofolate ligase, which catalyzes the reversible ATP‐driven production of 10‐formyltetrahydrofolate (10‐formyl‐H₄PteGlu_n) from formate and tetrahydrofolate (H₄PteGlu_n). Here, we report biochemical and functional characterization of the enzyme fromArabidopsis thaliana(AtFTHFL). We show that the recombinant AtFTHFL has lowerK_mandk_catvalues with pentaglutamyl tetrahydrofolate (H₄PteGlu₅) as compared to monoglutamyl tetrahydrofolate (H₄PteGlu₁), resulting in virtually identical catalytic efficiencies for the two substrates. Stable transformation ofArabidopsisplants with the EGFP‐tagged AtFTHFL, followed with fluorescence microscopy, demonstrated cytosolic signal. Two independent T‐DNA insertion lines with impaired AtFTHFL function had shorter roots compared to the wild type plants, demonstrating the importance of this enzyme for root growth. Overexpressing AtFTHFL led to the accumulation of H₄PteGlu_n + 5,10‐methylene‐H₄PteGlu_nand serine, accompanied with the depletion of formate and glycolate, in roots of the transgenicArabidopsisplants. This metabolic adjustment supports the hypothesis that AtFTHFL feeds the cytosolic C₁network in roots with C₁units originating from glycolate, and that these units are then used mainly for biosynthesis of serine, and not as much for the biosynthesis of 5‐methyl‐H₄PteGlu_n, methionine, andS‐adenosylmethionine. This finding has implications for any future attempts to engineer one‐carbon unit‐requiring products through manipulation of the one‐carbon metabolic network in non‐photosynthetic organs. 

When dealing with data from distinct locations, machine learning algorithms tend to demonstrate an implicit preference of some locations over the others, which constitutes biases that sabotage the spatial fairness of the algorithm. This unfairness can easily introduce biases in subsequent decision-making given broad adoptions of learning-based solutions in practice. However, locational biases in AI are largely understudied. To mitigate biases over locations, we propose a locational meta-referee (Meta-Ref) to oversee the few-shot meta-training and meta-testing of a deep neural network. Meta-Ref dynamically adjusts the learning rates for training samples of given locations to advocate a fair performance across locations, through an explicit consideration of locational biases and the characteristics of input data. We present a three-phase training framework to learn both a meta-learning-based predictor and an integrated Meta-Ref that governs the fairness of the model. Once trained with a distribution of spatial tasks, Meta-Ref is applied to samples from new spatial tasks (i.e., regions outside the training area) to promote fairness during the fine-tune step. We carried out experiments with two case studies on crop monitoring and transportation safety, which show Meta-Ref can improve locational fairness while keeping the overall prediction quality at a similar level. 

Cloud masking is both a fundamental and a critical task in the vast majority of Earth observation problems across social sectors, including agriculture, energy, water, etc. The sheer volume of satellite imagery to be processed has fast-climbed to a scale (e.g., >10 PBs/year) that is prohibitive for manual processing. Meanwhile, generating reliable cloud masks and image composite is increasingly challenging due to the continued distribution-shifts in the imagery collected by existing sensors and the ever-growing variety of sensors and platforms. Moreover, labeled samples are scarce and geographically limited compared to the needs in real large-scale applications. In related work, traditional remote sensing methods are often physics-based and rely on special spectral signatures from multi- or hyper-spectral bands, which are often not available in data collected by many -- and especially more recent -- high-resolution platforms. Machine learning and deep learning based methods, on the other hand, often require large volumes of up-to-date training data to be reliable and generalizable over space. We propose an autonomous image composition and masking (Auto-CM) framework to learn to solve the fundamental tasks in a label-free manner, by leveraging different dynamics of events in both geographic domains and time-series. Our experiments show that Auto-CM outperforms existing methods on a wide-range of data with different satellite platforms, geographic regions and bands. 

Estimating human mobility responses to the large-scale spreading of the COVID-19 pandemic is crucial, since its significance guides policymakers to give Non-pharmaceutical Interventions, such as closure or reopening of businesses. It is challenging to model due to complex social contexts and limited training data. Recently, we proposed a conditional generative adversarial network (COVID-GAN) to estimate human mobility response under a set of social and policy conditions integrated from multiple data sources. Although COVID-GAN achieves a good average estimation accuracy under real-world conditions, it produces higher errors in certain regions due to the presence of spatial heterogeneity and outliers. To address these issues, in this article, we extend our prior work by introducing a new spatio-temporal deep generative model, namely, COVID-GAN+. COVID-GAN+ deals with the spatial heterogeneity issue by introducing a new spatial feature layer that utilizes the local Moran statistic to model the spatial heterogeneity strength in the data. In addition, we redesign the training objective to learn the estimated mobility changes from historical average levels to mitigate the effects of spatial outliers. We perform comprehensive evaluations using urban mobility data derived from cell phone records and census data. Results show that COVID-GAN+ can better approximate real-world human mobility responses than prior methods, including COVID-GAN.