RESUMO
The distribution of dryland trees and their density, cover, size, mass and carbon content are not well known at sub-continental to continental scales1-14. This information is important for ecological protection, carbon accounting, climate mitigation and restoration efforts of dryland ecosystems15-18. We assessed more than 9.9 billion trees derived from more than 300,000 satellite images, covering semi-arid sub-Saharan Africa north of the Equator. We attributed wood, foliage and root carbon to every tree in the 0-1,000 mm year-1 rainfall zone by coupling field data19, machine learning20-22, satellite data and high-performance computing. Average carbon stocks of individual trees ranged from 0.54 Mg C ha-1 and 63 kg C tree-1 in the arid zone to 3.7 Mg C ha-1 and 98 kg tree-1 in the sub-humid zone. Overall, we estimated the total carbon for our study area to be 0.84 (±19.8%) Pg C. Comparisons with 14 previous TRENDY numerical simulation studies23 for our area found that the density and carbon stocks of scattered trees have been underestimated by three models and overestimated by 11 models, respectively. This benchmarking can help understand the carbon cycle and address concerns about land degradation24-29. We make available a linked database of wood mass, foliage mass, root mass and carbon stock of each tree for scientists, policymakers, dryland-restoration practitioners and farmers, who can use it to estimate farmland tree carbon stocks from tablets or laptops.
Assuntos
Carbono , Clima Desértico , Ecossistema , Árvores , Carbono/análise , Carbono/metabolismo , Árvores/anatomia & histologia , Árvores/química , Árvores/metabolismo , Dessecação , Imagens de Satélites , África Subsaariana , Aprendizado de Máquina , Madeira/análise , Raízes de Plantas , Agricultura , Recuperação e Remediação Ambiental , Bases de Dados Factuais , Biomassa , ComputadoresRESUMO
Design of hardware based on biological principles of neuronal computation and plasticity in the brain is a leading approach to realizing energy- and sample-efficient AI and learning machines. An important factor in selection of the hardware building blocks is the identification of candidate materials with physical properties suitable to emulate the large dynamic ranges and varied timescales of neuronal signaling. Previous work has shown that the all-or-none spiking behavior of neurons can be mimicked by threshold switches utilizing material phase transitions. Here, we demonstrate that devices based on a prototypical metal-insulator-transition material, vanadium dioxide (VO2), can be dynamically controlled to access a continuum of intermediate resistance states. Furthermore, the timescale of their intrinsic relaxation can be configured to match a range of biologically relevant timescales from milliseconds to seconds. We exploit these device properties to emulate three aspects of neuronal analog computation: fast (~1 ms) spiking in a neuronal soma compartment, slow (~100 ms) spiking in a dendritic compartment, and ultraslow (~1 s) biochemical signaling involved in temporal credit assignment for a recently discovered biological mechanism of one-shot learning. Simulations show that an artificial neural network using properties of VO2 devices to control an agent navigating a spatial environment can learn an efficient path to a reward in up to fourfold fewer trials than standard methods. The phase relaxations described in our study may be engineered in a variety of materials and can be controlled by thermal, electrical, or optical stimuli, suggesting further opportunities to emulate biological learning in neuromorphic hardware.
Assuntos
Aprendizagem , Redes Neurais de Computação , Computadores , Encéfalo/fisiologia , Neurônios/fisiologiaRESUMO
Artificial intelligence (AI) for facial diagnostics is increasingly used in the genetics clinic to evaluate patients with potential genetic conditions. Current approaches focus on one type of AI called Deep Learning (DL). While DL- based facial diagnostic platforms have a high accuracy rate for many conditions, less is understood about how this technology assesses and classifies (categorizes) images, and how this compares to humans. To compare human and computer attention, we performed eye-tracking analyses of geneticist clinicians (n = 22) and non-clinicians (n = 22) who viewed images of people with 10 different genetic conditions, as well as images of unaffected individuals. We calculated the Intersection-over-Union (IoU) and Kullback-Leibler divergence (KL) to compare the visual attentions of the two participant groups, and then the clinician group against the saliency maps of our deep learning classifier. We found that human visual attention differs greatly from DL model's saliency results. Averaging over all the test images, IoU and KL metric for the successful (accurate) clinician visual attentions versus the saliency maps were 0.15 and 11.15, respectively. Individuals also tend to have a specific pattern of image inspection, and clinicians demonstrate different visual attention patterns than non-clinicians (IoU and KL of clinicians versus non-clinicians were 0.47 and 2.73, respectively). This study shows that humans (at different levels of expertise) and a computer vision model examine images differently. Understanding these differences can improve the design and use of AI tools, and lead to more meaningful interactions between clinicians and AI technologies.
Assuntos
Inteligência Artificial , Computadores , Humanos , Simulação por ComputadorRESUMO
Computer vision refers to the theory and implementation of artificial systems that extract information from images to understand their content. Although computers are widely used by cell biologists for visualization and measurement, interpretation of image content, i.e., the selection of events worth observing and the definition of what they mean in terms of cellular mechanisms, is mostly left to human intuition. This Essay attempts to outline roles computer vision may play and should play in image-based studies of cellular life.
Assuntos
Técnicas Citológicas/métodos , Processamento de Imagem Assistida por Computador/métodos , Automação , Computadores , Humanos , Armazenamento e Recuperação da Informação , Neutrófilos/citologiaRESUMO
BACKGROUND & AIMS: Endoscopic assessment of ulcerative colitis (UC) typically reports only the maximum severity observed. Computer vision methods may better quantify mucosal injury detail, which varies among patients. METHODS: Endoscopic video from the UNIFI clinical trial (A Study to Evaluate the Safety and Efficacy of Ustekinumab Induction and Maintenance Therapy in Participants With Moderately to Severely Active Ulcerative Colitis) comparing ustekinumab and placebo for UC were processed in a computer vision analysis that spatially mapped Mayo Endoscopic Score (MES) to generate the Cumulative Disease Score (CDS). CDS was compared with the MES for differentiating ustekinumab vs placebo treatment response and agreement with symptomatic remission at week 44. Statistical power, effect, and estimated sample sizes for detecting endoscopic differences between treatments were calculated using both CDS and MES measures. Endoscopic video from a separate phase 2 clinical trial replication cohort was performed for validation of CDS performance. RESULTS: Among 748 induction and 348 maintenance patients, CDS was lower in ustekinumab vs placebo users at week 8 (141.9 vs 184.3; P < .0001) and week 44 (78.2 vs 151.5; P < .0001). CDS was correlated with the MES (P < .0001) and all clinical components of the partial Mayo score (P < .0001). Stratification by pretreatment CDS revealed ustekinumab was more effective than placebo (P < .0001) with increasing effect in severe vs mild disease (-85.0 vs -55.4; P < .0001). Compared with the MES, CDS was more sensitive to change, requiring 50% fewer participants to demonstrate endoscopic differences between ustekinumab and placebo (Hedges' g = 0.743 vs 0.460). CDS performance in the JAK-UC replication cohort was similar to UNIFI. CONCLUSIONS: As an automated and quantitative measure of global endoscopic disease severity, the CDS offers artificial intelligence enhancement of traditional MES capability to better evaluate UC in clinical trials and potentially practice.
Assuntos
Colite Ulcerativa , Humanos , Inteligência Artificial , Colite Ulcerativa/diagnóstico , Colite Ulcerativa/tratamento farmacológico , Colonoscopia/métodos , Computadores , Indução de Remissão , Índice de Gravidade de Doença , Ustekinumab/efeitos adversosRESUMO
ColabFold offers accelerated prediction of protein structures and complexes by combining the fast homology search of MMseqs2 with AlphaFold2 or RoseTTAFold. ColabFold's 40-60-fold faster search and optimized model utilization enables prediction of close to 1,000 structures per day on a server with one graphics processing unit. Coupled with Google Colaboratory, ColabFold becomes a free and accessible platform for protein folding. ColabFold is open-source software available at https://github.com/sokrypton/ColabFold and its novel environmental databases are available at https://colabfold.mmseqs.com .
Assuntos
Dobramento de Proteína , Software , Computadores , Bases de Dados Factuais , ProteínasRESUMO
MOTIVATION: Protein structure comparison is pivotal for deriving homological relationships, elucidating protein functions, and understanding evolutionary developments. The burgeoning field of in-silico protein structure prediction now yields billions of models with near-experimental accuracy, necessitating sophisticated tools for discerning structural similarities among proteins, particularly when sequence similarity is limited. RESULTS: In this article, we have developed the align distance matrix with scale (ADAMS) pipeline, which synergizes the distance matrix alignment method with the scale-invariant feature transform algorithm, streamlining protein structure comparison on a proteomic scale. Utilizing a computer vision-centric strategy for contrasting disparate distance matrices, ADAMS adeptly alleviates challenges associated with proteins characterized by a high degree of structural flexibility. Our findings indicate that ADAMS achieves a level of performance and accuracy on par with Foldseek, while maintaining similar speed. Crucially, ADAMS overcomes certain limitations of Foldseek in handling structurally flexible proteins, establishing it as an efficacious tool for in-depth protein structure analysis with heightened accuracy. AVAILABILITY: ADAMS can be download and used as a python package from Python Package Index (PyPI): adams · PyPI. Source code and other materials are available from young55775/ADAMS-developing (github.com). An online server is available: Bseek Search Server (cryonet.ai).
Assuntos
Algoritmos , Proteômica , Software , Proteínas/química , ComputadoresRESUMO
MOTIVATION: Missing values are commonly observed in metabolomics data from mass spectrometry. Imputing them is crucial because it assures data completeness, increases the statistical power of analyses, prevents inaccurate results, and improves the quality of exploratory analysis, statistical modeling, and machine learning. Numerous Missing Value Imputation Algorithms (MVIAs) employ heuristics or statistical models to replace missing information with estimates. In the context of metabolomics data, we identified 52 MVIAs implemented across 70 R functions. Nevertheless, the usage of those 52 established methods poses challenges due to package dependency issues, lack of documentation, and their instability. RESULTS: Our R package, 'imputomics', provides a convenient wrapper around 41 (plus random imputation as a baseline model) out of 52 MVIAs in the form of a command-line tool and a web application. In addition, we propose a novel functionality for selecting MVIAs recommended for metabolomics data with the best performance or execution time. AVAILABILITY AND IMPLEMENTATION: 'imputomics' is freely available as an R package (github.com/BioGenies/imputomics) and a Shiny web application (biogenies.info/imputomics-ws). The documentation is available at biogenies.info/imputomics.
Assuntos
Metabolômica , Software , Metabolômica/métodos , Algoritmos , Computadores , Espectrometria de Massas/métodosRESUMO
MOTIVATION: Seeding is a rate-limiting stage in sequence alignment for next-generation sequencing reads. The existing optimization algorithms typically utilize hardware and machine-learning techniques to accelerate seeding. However, an efficient solution provided by professional next-generation sequencing compressors has been largely overlooked by far. In addition to achieving remarkable compression ratios by reordering reads, these compressors provide valuable insights for downstream alignment that reveal the repetitive computations accounting for more than 50% of seeding procedure in commonly used short read aligner BWA-MEM at typical sequencing coverage. Nevertheless, the exploited redundancy information is not fully realized or utilized. RESULTS: In this study, we present a compressive seeding algorithm, named CompSeed, to fill the gap. CompSeed, in collaboration with the existing reordering-based compression tools, finishes the BWA-MEM seeding process in about half the time by caching all intermediate seeding results in compact trie structures to directly answer repetitive inquiries that frequently cause random memory accesses. Furthermore, CompSeed demonstrates better performance as sequencing coverage increases, as it focuses solely on the small informative portion of sequencing reads after compression. The innovative strategy highlights the promising potential of integrating sequence compression and alignment to tackle the ever-growing volume of sequencing data. AVAILABILITY AND IMPLEMENTATION: CompSeed is available at https://github.com/i-xiaohu/CompSeed.
Assuntos
Compressão de Dados , Software , Análise de Sequência de DNA/métodos , Algoritmos , Compressão de Dados/métodos , Computadores , Sequenciamento de Nucleotídeos em Larga Escala/métodosRESUMO
Guided by brain-like 'spiking' computational frameworks, neuromorphic computing-brain-inspired computing for machine intelligence-promises to realize artificial intelligence while reducing the energy requirements of computing platforms. This interdisciplinary field began with the implementation of silicon circuits for biological neural routines, but has evolved to encompass the hardware implementation of algorithms with spike-based encoding and event-driven representations. Here we provide an overview of the developments in neuromorphic computing for both algorithms and hardware and highlight the fundamentals of learning and hardware frameworks. We discuss the main challenges and the future prospects of neuromorphic computing, with emphasis on algorithm-hardware codesign.
Assuntos
Inteligência Artificial/tendências , Computadores/tendências , Redes Neurais de Computação , Algoritmos , Modelos NeurológicosRESUMO
Software implementations of brain-inspired computing underlie many important computational tasks, from image processing to speech recognition, artificial intelligence and deep learning applications. Yet, unlike real neural tissue, traditional computing architectures physically separate the core computing functions of memory and processing, making fast, efficient and low-energy computing difficult to achieve. To overcome such limitations, an attractive alternative is to design hardware that mimics neurons and synapses. Such hardware, when connected in networks or neuromorphic systems, processes information in a way more analogous to brains. Here we present an all-optical version of such a neurosynaptic system, capable of supervised and unsupervised learning. We exploit wavelength division multiplexing techniques to implement a scalable circuit architecture for photonic neural networks, successfully demonstrating pattern recognition directly in the optical domain. Such photonic neurosynaptic networks promise access to the high speed and high bandwidth inherent to optical systems, thus enabling the direct processing of optical telecommunication and visual data.
Assuntos
Biomimética/métodos , Modelos Neurológicos , Redes Neurais de Computação , Reconhecimento Automatizado de Padrão/métodos , Fótons , Aprendizado de Máquina Supervisionado , Aprendizado de Máquina não Supervisionado , Potenciais de Ação , Sistemas Computacionais , Computadores , Rede Nervosa/citologia , Rede Nervosa/fisiologia , Neurônios/citologia , Neurônios/fisiologia , Sinapses/fisiologiaRESUMO
The debate on whether computer gaming enhances players' cognitive function is an ongoing and contentious issue. Aiming to delve into the potential impacts of computer gaming on the players' cognitive function, we embarked on a brain imaging-derived phenotypes (IDPs)-wide Mendelian randomization (MR) study, utilizing publicly available data from a European population. Our findings indicate that computer gaming has a positive impact on fluid intelligence (odds ratio [OR] = 6.264, P = 4.361 × 10-10, 95% confidence interval [CI] 3.520-11.147) and cognitive function (OR = 3.322, P = 0.002, 95% CI 1.563-7.062). Out of the 3062 brain IDPs analyzed, only one phenotype, IDP NET100 0378, was significantly influenced by computer gaming (OR = 4.697, P = 1.10 × 10-5, 95% CI 2.357-9.361). Further MR analysis suggested that alterations in the IDP NET100 0378 caused by computer gaming may be a potential factor affecting fluid intelligence (OR = 1.076, P = 0.041, 95% CI 1.003-1.153). Our MR study lends support to the notion that computer gaming can facilitate the development of players' fluid intelligence by enhancing the connectivity between the motor cortex in the resting-state brain and key regions such as the left dorsolateral prefrontal cortex and the language center.
Assuntos
Análise da Randomização Mendeliana , Jogos de Vídeo , Encéfalo/diagnóstico por imagem , Cognição , Computadores , Inteligência , Fenótipo , NeuroimagemRESUMO
ABC portal (http://abc.sklehabc.com) is a database and web portal containing 198 single-cell transcriptomic datasets of development, differentiation and disorder of blood/immune cells. All the datasets were re-annotated with a manually curated and unified single-cell reference, especially for the haematopoietic stem and progenitor cells. ABC portal provides web-based interactive analysis modules, especially a comprehensive cell-cell communication analysis and disease-related gene signature analysis. Importantly, ABC portal allows customized sample selection based on a combination of several metadata for downstream analysis and comparison analysis across datasets. ABC portal also allows users to select multiple cell types for analysis in the modules. Together, ABC portal provides an interactive interface of single-cell data exploration and re-analysis with customized analysis modules for the researchers and clinicians, and will facilitate understanding of haematopoiesis and blood/immune disorders.
Assuntos
Células Sanguíneas , Computadores , Bases de Dados Factuais , Perfilação da Expressão Gênica , TranscriptomaRESUMO
The CRISPR-Cas system is a highly adaptive and RNA-guided immune system found in bacteria and archaea, which has applications as a genome editing tool and is a valuable system for studying the co-evolutionary dynamics of bacteriophage interactions. Here introduces CRISPRimmunity, a new web server designed for Acr prediction, identification of novel class 2 CRISPR-Cas loci, and dissection of key CRISPR-associated molecular events. CRISPRimmunity is built on a suite of CRISPR-oriented databases providing a comprehensive co-evolutionary perspective of the CRISPR-Cas and anti-CRISPR systems. The platform achieved a high prediction accuracy of 0.997 for Acr prediction when tested on a dataset of 99 experimentally validated Acrs and 676 non-Acrs, outperforming other existing prediction tools. Some of the newly identified class 2 CRISPR-Cas loci using CRISPRimmunity have been experimentally validated for cleavage activity in vitro. CRISPRimmunity offers the catalogues of pre-identified CRISPR systems to browse and query, the collected resources or databases to download, a well-designed graphical interface, a detailed tutorial, multi-faceted information, and exportable results in machine-readable formats, making it easy to use and facilitating future experimental design and further data mining. The platform is available at http://www.microbiome-bigdata.com/CRISPRimmunity. Moreover, the source code for batch analysis are published on Github (https://github.com/HIT-ImmunologyLab/CRISPRimmunity).
Assuntos
Sistemas CRISPR-Cas , Edição de Genes , Edição de Genes/métodos , Sistemas CRISPR-Cas/genética , Bactérias/genética , Archaea/genética , ComputadoresRESUMO
Proteins form complex interactions in the cellular environment to carry out their functions. They exhibit a wide range of binding modes depending on the cellular conditions, which result in a variety of ordered or disordered assemblies. To help rationalise the binding behavior of proteins, the FuzPred server predicts their sequence-based binding modes without specifying their binding partners. The binding mode defines whether the bound state is formed through a disorder-to-order transition resulting in a well-defined conformation, or through a disorder-to-disorder transition where the binding partners remain conformationally heterogeneous. To account for the context-dependent nature of the binding modes, the FuzPred method also estimates the multiplicity of binding modes, the likelihood of sampling multiple binding modes. Protein regions with a high multiplicity of binding modes may serve as regulatory sites or hot-spots for structural transitions in the assembly. To facilitate the interpretation of the predictions, protein regions with different interaction behaviors can be visualised on protein structures generated by AlphaFold. The FuzPred web server (https://fuzpred.bio.unipd.it) thus offers insights into the structural and dynamical changes of proteins upon interactions and contributes to development of structure-function relationships under a variety of cellular conditions.
Assuntos
Computadores , Proteínas , Conformação Proteica , Proteínas/química , Domínios Proteicos , SoftwareRESUMO
PlasMapper 3.0 is a web server that allows users to generate, edit, annotate and interactively visualize publication quality plasmid maps. Plasmid maps are used to plan, design, share and publish critical information about gene cloning experiments. PlasMapper 3.0 is the successor to PlasMapper 2.0 and offers many features found only in commercial plasmid mapping/editing packages. PlasMapper 3.0 allows users to paste or upload plasmid sequences as input or to upload existing plasmid maps from its large database of >2000 pre-annotated plasmids (PlasMapDB). This database can be searched by plasmid names, sequence features, restriction sites, preferred host organisms, and sequence length. PlasMapper 3.0 also supports the annotation of new or never-before-seen plasmids using its own feature database that contains common promoters, terminators, regulatory sequences, replication origins, selectable markers and other features found in most cloning plasmids. PlasMapper 3.0 has several interactive sequence editors/viewers that allow users to select and view plasmid regions, insert genes, modify restriction sites or perform codon optimization. The graphics for PlasMapper 3.0 have also been substantially upgraded. It now offers an interactive, full-color plasmid viewer/editor that allows users to zoom, rotate, re-color, linearize, circularize, edit annotated features and modify plasmid images or labels to improve the esthetic qualities of their plasmid map and textual displays. All the plasmid images and textual displays are downloadable in multiple formats. PlasMapper 3.0 is available online at https://plasmapper.ca.
Assuntos
Software , Interface Usuário-Computador , Plasmídeos/genética , Computadores , Sequência de Bases , InternetRESUMO
The Bioinformation and DNA Data Bank of Japan (DDBJ) Center (https://www.ddbj.nig.ac.jp) maintains database archives that cover a wide range of fields in life sciences. As a founding member of the International Nucleotide Sequence Database Collaboration (INSDC), our primary mission is to collect and distribute nucleotide sequence data, as well as their study and sample information, in collaboration with the National Center for Biotechnology Information in the United States and the European Bioinformatics Institute. In addition to INSDC resources, the Center operates databases for functional genomics (GEA: Genomic Expression Archive), metabolomics (MetaboBank), and human genetic and phenotypic data (JGA: Japanese Genotype-Phenotype Archive). These databases are built on the supercomputer of the National Institute of Genetics, whose remaining computational capacity is actively utilized by domestic researchers for large-scale biological data analyses. Here, we report our recent updates and the activities of our services.