The prosperity of computer vision (CV) and natural language procession (NLP) has spurred the development deep learning in many other domains. advancement machine provides us with an alternative option besides computationally expensive density functional theories (DFT). Kernel method graph neural networks have been widely studied as two mainstream methods for property prediction. promising achie...

We analyze the use, advantages, and drawbacks of graph kernels in chemoin-formatics, including a comparison of kernel-based approaches with other methodology, as well as examples of applications. Kernel-based machine learning [1], now widely applied in chemoinformatics, delivers state-of-the-art performance [2] in tasks like classification and regression. Molecular graph kernels [3] are a recen...

Improving drug discovery efficiency is a core and long-standing challenge in discovery. For this purpose, many graph learning methods have been developed to search potential candidates with fast speed low cost. In fact, the pursuit of high prediction performance on limited number datasets has crystallized their architectures hyperparameters, making them lose advantage repurposing new data gener...

Double Pushout graph transformation naturally facilitates the modelling of chemical reactions: labelled undirected graphs model molecules and direct derivations model chemical reactions. However, the most straightforward modelling approach ignores the relative placement of atoms and their neighbours in space. Stereoisomers of chemical compounds thus cannot be distinguished, even though their ch...

Graph theory plays an important role for modelling and designing chemical structures complex networks. Chemical graph is commonly used to analyse comprehend networks, as well their features. In theory, a structure can be represented by vertices edges where denote atoms molecular bonds. The concept of resolvability parameters G= (V, E) relatively new advanced field in which the complete built so...

For a (molecular) graph, the first Zagreb index M1 is equal to the sum of squares of the vertex degrees, and the second Zagreb index M2 is equal to the sum of products of degrees of pairs of adjacent vertices. In this paper, we study the Zagreb indices of n-vertex connected graphs with k cut vertices, the upper bound for M1and M2-values of n-vertex connected graphs with k cut vertices are deter...

Recently, a new molecular graph matrix, Harary matrix, was defined in honor of Professor Frank Harary, and new graph invariants (local and global) based on it were also defined and researched, Harary index is one of these invariants. The Harary matrix can be used to derive a variant of the Balaban index, Harary index was also successfully tested in several structure-property relationships, so i...