RESUMO
We describe the operation and improvement of AlphaFold, the system that was entered by the team AlphaFold2 to the "human" category in the 14th Critical Assessment of Protein Structure Prediction (CASP14). The AlphaFold system entered in CASP14 is entirely different to the one entered in CASP13. It used a novel end-to-end deep neural network trained to produce protein structures from amino acid sequence, multiple sequence alignments, and homologous proteins. In the assessors' ranking by summed z scores (>2.0), AlphaFold scored 244.0 compared to 90.8 by the next best group. The predictions made by AlphaFold had a median domain GDT_TS of 92.4; this is the first time that this level of average accuracy has been achieved during CASP, especially on the more difficult Free Modeling targets, and represents a significant improvement in the state of the art in protein structure prediction. We reported how AlphaFold was run as a human team during CASP14 and improved such that it now achieves an equivalent level of performance without intervention, opening the door to highly accurate large-scale structure prediction.
Assuntos
Modelos Moleculares , Redes Neurais de Computação , Dobramento de Proteína , Proteínas , Software , Sequência de Aminoácidos , Biologia Computacional , Aprendizado Profundo , Conformação Proteica , Proteínas/química , Proteínas/metabolismo , Análise de Sequência de ProteínaRESUMO
BACKGROUND: Over half a million individuals are diagnosed with head and neck cancer each year globally. Radiotherapy is an important curative treatment for this disease, but it requires manual time to delineate radiosensitive organs at risk. This planning process can delay treatment while also introducing interoperator variability, resulting in downstream radiation dose differences. Although auto-segmentation algorithms offer a potentially time-saving solution, the challenges in defining, quantifying, and achieving expert performance remain. OBJECTIVE: Adopting a deep learning approach, we aim to demonstrate a 3D U-Net architecture that achieves expert-level performance in delineating 21 distinct head and neck organs at risk commonly segmented in clinical practice. METHODS: The model was trained on a data set of 663 deidentified computed tomography scans acquired in routine clinical practice and with both segmentations taken from clinical practice and segmentations created by experienced radiographers as part of this research, all in accordance with consensus organ at risk definitions. RESULTS: We demonstrated the model's clinical applicability by assessing its performance on a test set of 21 computed tomography scans from clinical practice, each with 21 organs at risk segmented by 2 independent experts. We also introduced surface Dice similarity coefficient, a new metric for the comparison of organ delineation, to quantify the deviation between organ at risk surface contours rather than volumes, better reflecting the clinical task of correcting errors in automated organ segmentations. The model's generalizability was then demonstrated on 2 distinct open-source data sets, reflecting different centers and countries to model training. CONCLUSIONS: Deep learning is an effective and clinically applicable technique for the segmentation of the head and neck anatomy for radiotherapy. With appropriate validation studies and regulatory approvals, this system could improve the efficiency, consistency, and safety of radiotherapy pathways.
Assuntos
Aprendizado Profundo , Neoplasias de Cabeça e Pescoço , Algoritmos , Neoplasias de Cabeça e Pescoço/diagnóstico por imagem , Neoplasias de Cabeça e Pescoço/radioterapia , Humanos , Tomografia Computadorizada por Raios XRESUMO
Proteins are essential to life, and understanding their structure can facilitate a mechanistic understanding of their function. Through an enormous experimental effort1-4, the structures of around 100,000 unique proteins have been determined5, but this represents a small fraction of the billions of known protein sequences6,7. Structural coverage is bottlenecked by the months to years of painstaking effort required to determine a single protein structure. Accurate computational approaches are needed to address this gap and to enable large-scale structural bioinformatics. Predicting the three-dimensional structure that a protein will adopt based solely on its amino acid sequence-the structure prediction component of the 'protein folding problem'8-has been an important open research problem for more than 50 years9. Despite recent progress10-14, existing methods fall far short of atomic accuracy, especially when no homologous structure is available. Here we provide the first computational method that can regularly predict protein structures with atomic accuracy even in cases in which no similar structure is known. We validated an entirely redesigned version of our neural network-based model, AlphaFold, in the challenging 14th Critical Assessment of protein Structure Prediction (CASP14)15, demonstrating accuracy competitive with experimental structures in a majority of cases and greatly outperforming other methods. Underpinning the latest version of AlphaFold is a novel machine learning approach that incorporates physical and biological knowledge about protein structure, leveraging multi-sequence alignments, into the design of the deep learning algorithm.
Assuntos
Redes Neurais de Computação , Conformação Proteica , Dobramento de Proteína , Proteínas/química , Sequência de Aminoácidos , Biologia Computacional/métodos , Biologia Computacional/normas , Bases de Dados de Proteínas , Aprendizado Profundo/normas , Modelos Moleculares , Reprodutibilidade dos Testes , Alinhamento de SequênciaRESUMO
Protein structures can provide invaluable information, both for reasoning about biological processes and for enabling interventions such as structure-based drug development or targeted mutagenesis. After decades of effort, 17% of the total residues in human protein sequences are covered by an experimentally determined structure1. Here we markedly expand the structural coverage of the proteome by applying the state-of-the-art machine learning method, AlphaFold2, at a scale that covers almost the entire human proteome (98.5% of human proteins). The resulting dataset covers 58% of residues with a confident prediction, of which a subset (36% of all residues) have very high confidence. We introduce several metrics developed by building on the AlphaFold model and use them to interpret the dataset, identifying strong multi-domain predictions as well as regions that are likely to be disordered. Finally, we provide some case studies to illustrate how high-quality predictions could be used to generate biological hypotheses. We are making our predictions freely available to the community and anticipate that routine large-scale and high-accuracy structure prediction will become an important tool that will allow new questions to be addressed from a structural perspective.
Assuntos
Biologia Computacional/normas , Aprendizado Profundo/normas , Modelos Moleculares , Conformação Proteica , Proteoma/química , Conjuntos de Dados como Assunto/normas , Diacilglicerol O-Aciltransferase/química , Glucose-6-Fosfatase/química , Humanos , Proteínas de Membrana/química , Dobramento de Proteína , Reprodutibilidade dos TestesRESUMO
The volume and complexity of diagnostic imaging is increasing at a pace faster than the availability of human expertise to interpret it. Artificial intelligence has shown great promise in classifying two-dimensional photographs of some common diseases and typically relies on databases of millions of annotated images. Until now, the challenge of reaching the performance of expert clinicians in a real-world clinical pathway with three-dimensional diagnostic scans has remained unsolved. Here, we apply a novel deep learning architecture to a clinically heterogeneous set of three-dimensional optical coherence tomography scans from patients referred to a major eye hospital. We demonstrate performance in making a referral recommendation that reaches or exceeds that of experts on a range of sight-threatening retinal diseases after training on only 14,884 scans. Moreover, we demonstrate that the tissue segmentations produced by our architecture act as a device-independent representation; referral accuracy is maintained when using tissue segmentations from a different type of device. Our work removes previous barriers to wider clinical use without prohibitive training data requirements across multiple pathologies in a real-world setting.
Assuntos
Aprendizado Profundo , Encaminhamento e Consulta , Doenças Retinianas/diagnóstico , Idoso , Tomada de Decisão Clínica , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Retina/diagnóstico por imagem , Retina/patologia , Doenças Retinianas/diagnóstico por imagem , Tomografia de Coerência ÓpticaRESUMO
Hybrid materials based on polyvinylpyrrolidone (PVP) with silver nanoparticles (AgNps) were synthesized applying two different strategies based on thermal or chemical reduction of silver ions to silver nanoparticles using PVP as a stabilizer. The formation of spherical silver nanoparticles with diameter ranging from 9 to 16 nm was confirmed by TEM analysis. UV-vis and FTIR spectroscopy were also applied to confirm the successful formation of AgNps. The antibacterial activity of the synthesized AgNPs/PVP against etalon strains of three different groups of bacteria-Staphylococcus aureus (S. aureus; gram-positive bacteria), Escherichia coli (E. coli; gram-negative bacteria), Pseudomonas aeruginosa (P. aeruginosa; non-ferment gram-negative bacteria), as well as against spores of Bacillus subtilis (B. subtilis) was studied. AgNps/PVP were tested for the presence of fungicidal activity against different yeasts and mold such as Candida albicans, Candida krusei, Candida tropicalis, Candida glabrata, and Aspergillus brasiliensis. The hybrid materials showed a strong antimicrobial effect against the tested bacterial and fungal strains and therefore have potential applications in biotechnology and biomedical science.
RESUMO
A very basic computational model is proposed to explain two puzzling findings in the time perception literature. First, spontaneous motor actions are preceded by up to 1-2 s of preparatory activity (Kornhuber and Deecke, 1965). Yet, subjects are only consciously aware of about a quarter of a second of motor preparation (Libet et al., 1983). Why are they not aware of the early part of preparation? Second, psychophysical findings (Spence et al., 2001) support the principle of attention prior entry (Titchener, 1908), which states that attended stimuli are perceived faster than unattended stimuli. However, electrophysiological studies reported no or little corresponding temporal difference between the neural signals for attended and unattended stimuli (McDonald et al., 2005; Vibell et al., 2007). We suggest that the key to understanding these puzzling findings is to think of onset detection in probabilistic terms. The two apparently paradoxical phenomena are naturally predicted by our signal detection theoretic model.