Highlights•Chemical graph theory and descriptors in drug discovery.•Chemical fingerprint
and similarity analysis.•Machine learning models for virtual screening.•Future challenges …

Highlights•GNN has attracted wide attention from the field of designing drug molecules.•The
applications of GNN in molecule scoring, molecule generation and optimization, and …

Quantitative structure–activity relationship modeling is one of the major computational tools
employed in medicinal chemistry. However, throughout its entire history it has drawn both …

Despite considerable progress in genome-and proteome-based high-throughput screening
methods and in rational drug design, the increase in approved drugs in the past decade did …

Research on the topological indices based on end-vertex degrees of edges has been
intensively rising recently. Randić index, one of the best-known topological indices in …

A philosophy for defining what constitutes a virtual high-throughput screen is discussed, and
the choices that influence decisions at each stage of the computational funnel are …

We report some properties especially lower and upper bounds in terms of other graph
invariants for the general sum-connectivity index which generalizes both the ordinary sum …

We present a novel connectivity index for (molecular) graphs, called sum-connectivity index
and give several basic properties for this index, especially lower and upper bounds in terms …

The harmonic index of a graph G is defined as the sum of the weights 2d (u)+ d (v) of all
edges uv of G, where d (u) denotes the degree of a vertex u in G. In this work, we present the …

Persistent homology is constrained to purely topological persistence, while multiscale
graphs account only for geometric information. This work introduces persistent spectral …