Sequence assignment validation in cryo-EM models with checkMySequence

The availability of new AI-based protein structure prediction tools radically changed the way cryo-EM maps are interpreted, but it has not eliminated the challenges of map interpretation faced by a microscopist. Models will continue to be locally rebuilt and refined using interactive tools. This inevitably results in occasional errors, among which register-shifts remain one of the most difficult to identify and correct. Here we introduce checkMySequence; a fast, fully automated and parameter-free method for detecting register-shifts in protein models built into cryo-EM maps. We show that the method can assist model building in cases where poorer map resolution hinders visual interpretation. We also show that checkMySequence could have helped avoid a widely discussed sequence register error in a model of SARS-CoV-2 RNA-dependent RNA polymerase that was originally detected thanks to a visual residue-by-residue inspection by members of the structural biology community.

Mapping Deforestation in Cerrado Based on Hybrid Deep Learning Architecture and Medium Spatial Resolution Satellite Time Series

Cerrado is the second largest biome in Brazil, covering about 2 million km2. This biome has experienced land use and land cover changes at high rates due to agricultural expansion so that more than 50% of its natural vegetation has already been removed. Therefore, it is crucial to provide technology capable of controlling and monitoring the Cerrado vegetation suppression in order to undertake the environmental conservation policies. Within this context, this work aims to develop a new methodology to detect deforestation in Cerrado through the combination of two Deep Learning (DL) architectures, Long Short-Term Memory (LSTM) and U-Net, and using Landsat and Sentinel image time series. In our proposed method, the LSTM evaluates the time series in relation to the time axis to create a deforestation probability map, which is spatially analyzed by the U-Net algorithm alongside the terrain slope to produce final deforestation maps. The method was applied in two different study areas, which better represent the main deforestation patterns present in Cerrado. The resultant deforestation maps based on cost-free Sentinel-2 images achieved high accuracy metrics, peaking at an overall accuracy of 99.81%±0.21 and F1-Score of 0.8795±0.1180. In addition, the proposed method showed strong potential to automate the PRODES project, which provides the official Cerrado yearly deforestation maps based on visual interpretation.

Assessing the distribution of total Fe, Cu, and Zn in tropical peat at an oil palm plantation and their relationship with several environmental factors

Extensive utilization of fragile tropical peatlands ecosystem encourages a better understanding of spatiotemporal micronutrients distribution. The distribution of total Fe, Cu, and Zn in peat and their relationship with environmental factors were studied under oil palm plantation, Pangkalan Pisang, Koto Gasib, Riau, Indonesia. Peat samples were taken compositely inside the block using a combination of six factors, including a) the oil palm age (<6, 6-15, >15 years old), b) the peat thickness (< 3 and >3 m), c) season (rainy and dry), d) the distances from the secondary canal (10, 25, 50, 75, 100, and 150 m), e) the distances from an oil palm tree (1, 2, 3, and 4 m), and f) the depth of sample collection (0-20, 20-40, and 40-70 cm from the peat surface). Total Fe, Cu, and Zn were determined by the wet digestion method. These micronutrients observed in this study possessed high variability; however, they were within the expected range in tropical peatland. The entire micronutrients were statistically different by oil palm age, peat thickness, and distance from canal. Meanwhile, total Cu and Zn were also significantly different at each season. The oil palm age, peat thickness, and distance from the canal were the common factors controlling total Fe, Cu, and Zn in peat significantly. Moreover, total Cu and Zn were also dictated by season, distance from the oil palm tree, and depth of sample collection. Based on visual interpretation in PCA (principal component analysis), all micronutrients were categorized into two groups, separated by 2 m distance from the oil palm tree and 20 cm depth from the soil surface. Our study also highlights the dominance of the dilution over the enrichment process in peat, which requires further research to formulate micronutrients fertilization, especially for an extended cultivation time.

CNN-KCL: Automatic myocarditis diagnosis using convolutional neural network combined with k-means clustering

<abstract> <p>Myocarditis is the form of an inflammation of the middle layer of the heart wall which is caused by a viral infection and can affect the heart muscle and its electrical system. It has remained one of the most challenging diagnoses in cardiology. Myocardial is the prime cause of unexpected death in approximately 20% of adults less than 40 years of age. Cardiac MRI (CMR) has been considered a noninvasive and golden standard diagnostic tool for suspected myocarditis and plays an indispensable role in diagnosing various cardiac diseases. However, the performance of CMR depends heavily on the clinical presentation and features such as chest pain, arrhythmia, and heart failure. Besides, other imaging factors like artifacts, technical errors, pulse sequence, acquisition parameters, contrast agent dose, and more importantly qualitatively visual interpretation can affect the result of the diagnosis. This paper introduces a new deep learning-based model called Convolutional Neural Network-Clustering (CNN-KCL) to diagnose Myocarditis. In this study, we used 47 subjects with a total number of 98,898 images to diagnose myocarditis disease. Our results demonstrate that the proposed method achieves an accuracy of 97.41% based on 10 fold-cross validation technique with 4 clusters for diagnosis of Myocarditis. To the best of our knowledge, this research is the first to use deep learning algorithms for the diagnosis of myocarditis.</p> </abstract>

Demarcation of Groundwater Potential Zones Using Geospatial Technology in Edappadi Block, Salem District, Tamil Nadu, India

Groundwater is one of the world's most valuable resources, which contributes 85% of drinking water supplies. It is imperative to explore ground-water zone for the utilization to the people. Edappadi block in Salem District, Tamil Nadu, is rocky terrain largely depends on groundwater for drinking and irrigation. One of the most useful tools for locating ground water potential zones is remote sensing and geographic information system (GIS). Different types of thematic maps, such as lithology, geomorphology, drainage density, slope, lineament, and land use/land cover, can be easily created by visual interpretation of IRS-1C, LISS-III data and maps are prepared using GIS. The water potential zones are determined using a rank and weightage approach. In order to demarcate the water potential zones, the vector overlay method is used. Lithology is given more weight than geomorphology, followed by lineament density, lineament frequency, lineament intersection, slope and land use/land cover. Based on the overall results, the potential zone of groundwater in the research region is divided into five groups: Excellent, Very Good, Good, Moderate, and Poor.

Visual Interpretation of Brain Hypometabolisms Related to Neurological Long COVID: A French Multicentric Experience

This multicenter study aims to provide a qualitative and consensual description of brain 18F-FDG PET images in patients with suspected neurological long COVID, regarding the previously reported pattern involving olfactory bulbs and other limbic/paralimbic regions, as well as the brainstem and cerebellum.Methods: From the beginning of August 2021 to the end of October 2021, brain 18F-FDG PET exams of patients referred for suspected neurological long COVID with positive reverse transcription polymerase chain reaction (RT-PCR) and/or serology for the SARS-CoV-2 infection were retrospectively reviewed in three French Nuclear Medicine departments. Experimented nuclear physicians from each department had to classify according to the same visual interpretation analysis brain 18F-FDG PET scans as being normal, mildly to moderate (incomplete or moderately hypometabolic), or severely affected within the previously reported long COVID hypometabolic pattern. Results: On the 143 brain 18F-FDG PET performed during this period 3 months, 53% of scans were visually interpreted as normal, 31% as mildly to moderate and 16% as severely affected according to the COVID hypometabolic pattern. Importantly, this specific hypometabolic pattern is reported as identical in the three Nuclear Medicine departments. Typical illustrative examples are provided to help nuclear physicians in the interpretation of long COVID pattern.Conclusion: The proposed PET metabolic pattern is easily identified at visual interpretation in clinical routine in part of patients with suspicion of neurological long COVID, requiring special consideration for fronto-basal paramedian regions, the brainstem and cerebellum.

Visualizing Berio’s Sinfonia: Choreographing Animation for Indeterminate Narratives

In 1968, a year of massive political and cultural upheaval, Luciano Berio composed a score that would shape his legacy. Entitled Sinfonia, which literally means sounding together, the symphony was sparked by the assassination of Martin Luther King. Heralded as “the ultimate pre-postmodernist musical palimpsest” (Service, 2012). Sinfonia reverberates with the political assassinations and massive protests punctuated by police repression that marked 1968. In late 2019, I was offered an animated projection commission with a primary voice in choosing a piece for live symphonic performance/projection. After some researching, I found Berio’s Sinfonia. It had what I was looking for - a “contemporary” piece, it resisted illustration, linear narrative and 19th century romanticism while eschewing the rigid formality of serialism. Instead, it embraced two core Modernist principles – fragmentation and use of the archive. Berio quoted/sampled disparate chunks of literature, music, and events of 1968 in the service of the political and the poetic to discover unity in the heterogeneous. His score seemed ripe for visual interpretation - and exposition - with animation as the prime driver. Following Berio’s lead, I chose visual sampling as my entre and turned to Google. By animating in and out of iconic (and lesser known) images in the orb of 1968, I created a commensurate puzzle piece that mirrored the suggested avant-garde intent I found in Sinfonia – “Where now? Who now? When now?” (Beckett, 1965, p. 291).

Gardening Mt Vic

<p>Since Olmstead envisioned Central Park, New York, the study of gardening has slowly become the Staple of landscape historians. Gardening practices can engage the body with aesthetic experience through plants and materiality; landscape architects inform this process through expressive design intention and representations informed by conventions. When a creative drawing convention lacks sensitivity to how one reads the landscape, the intentions behind the expressions created by landscape architects become obscure or unclear. John Ward, a New Zealand Company secretary, stated that Wellington’s town belt was for “the beautiful appearance of the city to be secured.” (Cook, 1992) Over time, urban infrastructural developments have altered the boundaries of town belt parks; This was the case for Mount Victoria Park due to the 1930s development of Alexandra Road. Landscape architects recognise the significance of walking along the ridge of Mount Victoria because of its meaningful history; however, the large scale of the Mount Victoria Park means common planning practices cannot meaningfully engage with important opportunities for how its spatial compositions can dynamically affect the human experience. This is because landscape-planning tendencies typically utilise large-scale mapping to create utilitarian maintenance regimes that regiment spaces, rather than utilising landscape architectural principles in the forming of them. This design research investigation asks: how can landscape architecture establish a meaningful, human-scale experience of the garden at the scale of the large park? This study operates through design-led landscape architectural research. Site study of the Wellington Town Belt revealed that despite the scale of this site its variety of trails and open spaces for experiencing the site as a composed garden. This thesis argues that visual factors that enable composition focussed drawings to be meaningful can also be applied to the design of large-scale garden parks. Reflection on fieldwork was developed in design through crafted explorations of technique and convention resulting in a composition focussed drawing system. These designs were developed through a sensitivity to scale and drawing convention. The creative use of representation and site interpretation challenged utilitarian conceptions about the design of large-scale town belts to also include human-scale iterative visual interpretation. The results of these design experiments unified spaces and formed intense moments of beauty and meaning, during both movement and points of pause, resulting in a garden-like experience that expressed the particular beauty and unique attributes of Matairangi, Mt Victoria.</p>

Gardening Mt Vic

<p>Since Olmstead envisioned Central Park, New York, the study of gardening has slowly become the Staple of landscape historians. Gardening practices can engage the body with aesthetic experience through plants and materiality; landscape architects inform this process through expressive design intention and representations informed by conventions. When a creative drawing convention lacks sensitivity to how one reads the landscape, the intentions behind the expressions created by landscape architects become obscure or unclear. John Ward, a New Zealand Company secretary, stated that Wellington’s town belt was for “the beautiful appearance of the city to be secured.” (Cook, 1992) Over time, urban infrastructural developments have altered the boundaries of town belt parks; This was the case for Mount Victoria Park due to the 1930s development of Alexandra Road. Landscape architects recognise the significance of walking along the ridge of Mount Victoria because of its meaningful history; however, the large scale of the Mount Victoria Park means common planning practices cannot meaningfully engage with important opportunities for how its spatial compositions can dynamically affect the human experience. This is because landscape-planning tendencies typically utilise large-scale mapping to create utilitarian maintenance regimes that regiment spaces, rather than utilising landscape architectural principles in the forming of them. This design research investigation asks: how can landscape architecture establish a meaningful, human-scale experience of the garden at the scale of the large park? This study operates through design-led landscape architectural research. Site study of the Wellington Town Belt revealed that despite the scale of this site its variety of trails and open spaces for experiencing the site as a composed garden. This thesis argues that visual factors that enable composition focussed drawings to be meaningful can also be applied to the design of large-scale garden parks. Reflection on fieldwork was developed in design through crafted explorations of technique and convention resulting in a composition focussed drawing system. These designs were developed through a sensitivity to scale and drawing convention. The creative use of representation and site interpretation challenged utilitarian conceptions about the design of large-scale town belts to also include human-scale iterative visual interpretation. The results of these design experiments unified spaces and formed intense moments of beauty and meaning, during both movement and points of pause, resulting in a garden-like experience that expressed the particular beauty and unique attributes of Matairangi, Mt Victoria.</p>