AI Medical Compendium Journal:
Chemical communications (Cambridge, England)

Showing 1 to 10 of 23 articles

Harnessing chemistry for plant-like machines: from soft robotics to energy harvesting in the phytosphere.

Chemical communications (Cambridge, England)
Nature, especially plants, can inspire scientists and engineers in the development of bioinspired machines able to adapt and interact with complex unstructured environments. Advances in manufacturing techniques, such as 3D printing, have expanded the...

Frontiers in nonviral delivery of small molecule and genetic drugs, driven by polymer chemistry and machine learning for materials informatics.

Chemical communications (Cambridge, England)
Materials informatics (MI) has immense potential to accelerate the pace of innovation and new product development in biotechnology. Close collaborations between skilled physical and life scientists with data scientists are being established in pursui...

Urine and serum metabolic profiling combined with machine learning for autoimmune disease discrimination and classification.

Chemical communications (Cambridge, England)
Precision diagnosis and classification of autoimmune diseases (ADs) is challenging due to the obscure symptoms and pathological causes. Biofluid metabolic analysis has the potential for disease screening, in which high throughput, rapid analysis and ...

Energy differences as descriptors for the correlation between and in nonfullerene organic photovoltaics.

Chemical communications (Cambridge, England)
ITIC-series nonfullerene organic photovoltaics (NF OPVs) have realized the simultaneous increases of the short-circuit current density () and open-circuit voltage (), called the positive correlation between and , which could improve the power conver...

Applying deep learning to iterative screening of medium-sized molecules for protein-protein interaction-targeted drug discovery.

Chemical communications (Cambridge, England)
We combined a library of medium-sized molecules with iterative screening using multiple machine learning algorithms that were ligand-based, which resulted in a large increase of the hit rate against a protein-protein interaction target. This was demo...

Intelligent convolution neural network-assisted SERS to realize highly accurate identification of six pathogenic .

Chemical communications (Cambridge, England)
Based on label-free SERS technology, the relationship between the Raman signals of pathogenic microorganisms and purine metabolites was analyzed in detail. A deep learning CNN model was successfully developed, achieving a high accuracy rate of 99.7%...

Unsupervised classification of voltammetric data beyond principal component analysis.

Chemical communications (Cambridge, England)
In this study, we evaluate different apoproaches to unsupervised classification of cyclic voltammetric data, including Principal Component Analysis (PCA), t-distributed Stochastic Neighbour Embedding (t-SNE), Uniform Manifold Approximation and Projec...

Contrastive representation learning of inorganic materials to overcome lack of training datasets.

Chemical communications (Cambridge, England)
Data representation forms a feature space where forms data distribution that is one of the key factors determining the prediction accuracy of machine learning (ML). In particular, the data representation is crucial to handle small and biased training...

Breath odor-based individual authentication by an artificial olfactory sensor system and machine learning.

Chemical communications (Cambridge, England)
Breath odor sensing-based individual authentication was conducted for the first time using an artificial olfactory sensor system. Using a 16-channel chemiresistive sensor array and machine learning, a mean accuracy of >97% was successfully achieved. ...

Sigma profiles in deep learning: towards a universal molecular descriptor.

Chemical communications (Cambridge, England)
This work showcases the remarkable ability of sigma profiles to function as molecular descriptors in deep learning. The sigma profiles of 1432 compounds are used to train convolutional neural networks that accurately correlate and predict a wide rang...