NMJ-Analyser: high-throughput morphological screening of neuromuscular junctions identifies subtle changes in mouse neuromuscular disease models

AbstractThe neuromuscular junction (NMJ) is the peripheral synapse formed between a motor neuron axon terminal and a muscle fibre. NMJs are thought to be the primary site of peripheral pathology in many neuromuscular diseases, but innervation/denervation status is often assessed qualitatively with poor systematic criteria across studies, and separately from 3D morphological structure. Here, we describe the development of ‘NMJ-Analyser’, to comprehensively screen the morphology of NMJs and their corresponding innervation status automatically. NMJ-Analyser generates 29 biologically relevant features to quantitatively define healthy and aberrant neuromuscular synapses and applies machine learning to diagnose NMJ degeneration. We validated this framework in longitudinal analyses of wildtype mice, as well as in four different neuromuscular disease models: three for amyotrophic lateral sclerosis (ALS) and one for peripheral neuropathy. We showed that structural changes at the NMJ initially occur in the nerve terminal of mutant TDP43 and FUS ALS models. Using a machine learning algorithm, healthy and aberrant neuromuscular synapses are identified with 95% accuracy, with 88% sensitivity and 97% specificity. Our results validate NMJ-Analyser as a robust platform for systematic and structural screening of NMJs, and pave the way for transferrable, and cross-comparison and high-throughput studies in neuromuscular diseases.

Download Full-text

Design of English text-to-speech conversion algorithm based on machine learning

Journal of Intelligent & Fuzzy Systems ◽

10.3233/jifs-189238 ◽

2020 ◽

pp. 1-12

Author(s):

Li Dongmei

Keyword(s):

Machine Learning ◽

Speech Synthesis ◽

Feature Recognition ◽

Learning Algorithm ◽

Morphological Structure ◽

English Text ◽

Text To Speech ◽

Part Of Speech ◽

Modern Computer ◽

Conversion Algorithm

English text-to-speech conversion is the key content of modern computer technology research. Its difficulty is that there are large errors in the conversion process of text-to-speech feature recognition, and it is difficult to apply the English text-to-speech conversion algorithm to the system. In order to improve the efficiency of the English text-to-speech conversion, based on the machine learning algorithm, after the original voice waveform is labeled with the pitch, this article modifies the rhythm through PSOLA, and uses the C4.5 algorithm to train a decision tree for judging pronunciation of polyphones. In order to evaluate the performance of pronunciation discrimination method based on part-of-speech rules and HMM-based prosody hierarchy prediction in speech synthesis systems, this study constructed a system model. In addition, the waveform stitching method and PSOLA are used to synthesize the sound. For words whose main stress cannot be discriminated by morphological structure, label learning can be done by machine learning methods. Finally, this study evaluates and analyzes the performance of the algorithm through control experiments. The results show that the algorithm proposed in this paper has good performance and has a certain practical effect.

Download Full-text

A machine learning algorithm for high throughput identification of FTIR spectra: Application on microplastics collected in the Mediterranean Sea

Chemosphere ◽

10.1016/j.chemosphere.2019.05.113 ◽

2019 ◽

Vol 234 ◽

pp. 242-251 ◽

Cited By ~ 14

Author(s):

Mikaël Kedzierski ◽

Mathilde Falcou-Préfol ◽

Marie Emmanuelle Kerros ◽

Maryvonne Henry ◽

Maria Luiza Pedrotti ◽

...

Keyword(s):

Machine Learning ◽

Mediterranean Sea ◽

High Throughput ◽

Learning Algorithm ◽

Ftir Spectra ◽

Machine Learning Algorithm ◽

The Mediterranean

Download Full-text

La Risonanza Magnetica muscolare nelle malattie neuromuscolari

Rivista di Neuroradiologia ◽

10.1177/197140090301600333 ◽

2003 ◽

Vol 16 (3) ◽

pp. 503-510

Author(s):

A. Pichiecchio ◽

C. Cini ◽

M.G. Egitto ◽

A. Berardinelli ◽

E. Mercuri ◽

...

Keyword(s):

Magnetic Resonance ◽

Characteristic Feature ◽

Neuromuscular Disease ◽

Structural Changes ◽

Neuromuscular Diseases ◽

Risonanza Magnetica ◽

Muscle Involvement ◽

Mr Scanning

We describe the main magnetic resonance features of neuromuscular diseases based on a series of 345 patients undergoing muscle MR scans. The study aimed to establish the use of this method in the diagnosis of neuromuscular disease, namely its ability to distinguish neurogenic forms from primary myopathy by analysing the location, extension and distribution of structural changes. A selective muscle involvement was encountered in some myogenic diseases and can be considered a characteristic feature of different diseases and hence an important aid in diagnosis. We propose that MR scanning be included among the instrumental tests required in the diagnosis of neuromuscular disease.

Download Full-text

Iterative Experimental Design Based on Active Machine Learning Reduces the Experimental Burden Associated with Reaction Screening

10.26434/chemrxiv.12465299 ◽

2020 ◽

Author(s):

Natalie Eyke ◽

William H. Green ◽

Klavs F. Jensen

Keyword(s):

Machine Learning ◽

High Throughput ◽

Learning Algorithm ◽

Quality Data ◽

Experiment Planning ◽

Planning Tool ◽

High Quality Data ◽

Test Set ◽

Screening Experiments ◽

Selection Of

High-throughput reaction screening has emerged as a useful means of rapidly identifying the influence of key reaction variables on reaction outcomes. We show that active machine learning can further this objective by eliminating dependence on complete screens through iterative selection of maximally informative experiments from the subset of all possible experiments in the domain. To demonstrate our approach, we conduct retrospective analyses of the preexisting results of high-throughput reaction screening experiments. We compare the test set errors of models trained on actively-selected reactions to models trained on reactions selected at random from the same domain. We find that the degree to which models trained on actively-selected data outperform models trained on randomly-selected data depends on the domain being modeled, with it being possible to achieve very low test set errors when the dataset is heavily skewed in favor of low- or zero-yielding reactions. Our results confirm that the active learning algorithm is a useful experiment planning tool that can change the reaction screening paradigm, by allowing discovery and process chemists to focus their reaction screening efforts on the generation of a small amount of high-quality data.

Download Full-text

A High-Speed Screening Method by Combining a High-Throughput Method and a Machine-Learning Algorithm for Developing Novel Organic Electrolytes in Rechargeable Batteries

ECS Transactions ◽

10.1149/06802.0075ecst ◽

2015 ◽

Vol 68 (2) ◽

pp. 75-81 ◽

Cited By ~ 3

Author(s):

M.-S. Park ◽

Y.-S. Kang ◽

D. Im

Keyword(s):

Machine Learning ◽

High Throughput ◽

High Speed ◽

Learning Algorithm ◽

Screening Method ◽

Rechargeable Batteries ◽

Machine Learning Algorithm ◽

Organic Electrolytes ◽

High Throughput Method

Download Full-text

Efficient Prediction of Temperature-dependent Elastic and Mechanical Properties of 2D Materials

10.21203/rs.3.rs-902313/v1 ◽

2021 ◽

Author(s):

Chinedu Ekuma ◽

Z Liu ◽

Srihari Kastuar

Keyword(s):

Machine Learning ◽

Mechanical Properties ◽

High Throughput ◽

Learning Algorithm ◽

2D Materials ◽

Machine Learning Algorithm ◽

New Materials ◽

Temperature Dependent ◽

Efficient Prediction ◽

Properties Of Materials

Abstract An efficient automated toolkit for predicting the mechanical properties of materials can accelerate new materials design and discovery; this process often involves screening large configurational space in high-throughput calculations. Herein, we present the ElasTool toolkit for these applications. In particular, we use the ElasTool to study diversity of 2D materials and heterostructures, including their temperature-dependent mechanical properties and developed a machine learning algorithm for exploring predicted properties.

Download Full-text

Iterative Experimental Design Based on Active Machine Learning Reduces the Experimental Burden Associated with Reaction Screening

10.26434/chemrxiv.12465299.v1 ◽

2020 ◽

Author(s):

Natalie Eyke ◽

William H. Green ◽

Klavs F. Jensen

Keyword(s):

Machine Learning ◽

High Throughput ◽

Learning Algorithm ◽

Quality Data ◽

Experiment Planning ◽

Planning Tool ◽

High Quality Data ◽

Test Set ◽

Screening Experiments ◽

Selection Of

High-throughput reaction screening has emerged as a useful means of rapidly identifying the influence of key reaction variables on reaction outcomes. We show that active machine learning can further this objective by eliminating dependence on complete screens through iterative selection of maximally informative experiments from the subset of all possible experiments in the domain. To demonstrate our approach, we conduct retrospective analyses of the preexisting results of high-throughput reaction screening experiments. We compare the test set errors of models trained on actively-selected reactions to models trained on reactions selected at random from the same domain. We find that the degree to which models trained on actively-selected data outperform models trained on randomly-selected data depends on the domain being modeled, with it being possible to achieve very low test set errors when the dataset is heavily skewed in favor of low- or zero-yielding reactions. Our results confirm that the active learning algorithm is a useful experiment planning tool that can change the reaction screening paradigm, by allowing discovery and process chemists to focus their reaction screening efforts on the generation of a small amount of high-quality data.

Download Full-text

Machine Learning Algorithm to Predict Early Complications after Brain Tumor Surgery

10.1055/s-0038-1660728 ◽

2018 ◽

Author(s):

C.H.B. van Niftrik ◽

F. van der Wouden ◽

V. Staartjes ◽

J. Fierstra ◽

M. Stienen ◽

...

Keyword(s):

Machine Learning ◽

Brain Tumor ◽

Learning Algorithm ◽

Machine Learning Algorithm ◽

Tumor Surgery ◽

Early Complications ◽

Brain Tumor Surgery

Download Full-text

Intelligent system of English composition scoring model based on improved machine learning algorithm

Journal of Intelligent & Fuzzy Systems ◽

10.3233/jifs-189235 ◽

2020 ◽

pp. 1-11

Author(s):

Jie Liu ◽

Lin Lin ◽

Xiufang Liang

Keyword(s):

Machine Learning ◽

Evaluation System ◽

Intelligent System ◽

Learning Algorithm ◽

Learning Algorithms ◽

Machine Learning Algorithms ◽

Assessment System ◽

English Composition ◽

Region Extraction ◽

Constraint Model

The online English teaching system has certain requirements for the intelligent scoring system, and the most difficult stage of intelligent scoring in the English test is to score the English composition through the intelligent model. In order to improve the intelligence of English composition scoring, based on machine learning algorithms, this study combines intelligent image recognition technology to improve machine learning algorithms, and proposes an improved MSER-based character candidate region extraction algorithm and a convolutional neural network-based pseudo-character region filtering algorithm. In addition, in order to verify whether the algorithm model proposed in this paper meets the requirements of the group text, that is, to verify the feasibility of the algorithm, the performance of the model proposed in this study is analyzed through design experiments. Moreover, the basic conditions for composition scoring are input into the model as a constraint model. The research results show that the algorithm proposed in this paper has a certain practical effect, and it can be applied to the English assessment system and the online assessment system of the homework evaluation system algorithm system.

Download Full-text