Deep Learning in Molecular Recognition

Molecular recognition, the non-covalent interaction between multiple molecules, plays critical roles in many natural biological systems such as those between DNA-protein, RNA-ribosome, enzyme-substrate, receptor-ligand, and antigen-antibody. Many of the detailed molecular basis remains to be explored.

In addition, molecular recognition elements can also be synthesized with rigorous designing to fulfill various engineering needs, including artificial molecular recognition platforms, self-assembly proteins, and therapeutic drug delivery systems.

On the other hand, inspired by and to resemble the biological brains, deep learning techniques have been adapted in handling a variety of biological relevant challenges involving high dimensionality and highly nonlinear functions. For example, the deep learning system Alphafold2 has been demonstrated to have the ability to predict protein structures with impressive accuracy.

This “Deep Learning in Molecular Recognition” Research Topic of Frontiers in Molecular Biosciences aims to bring together works to discuss the latest developments and challenges on elucidating molecular recognition employing deep learning techniques, with a focus on applications such as drug discovery, protein-protein interaction prediction, and structural biology.

Through this collaboration, we aim to advance the state of the art in deep learning for molecular recognition and lay the groundwork for future breakthroughs in this rapidly advancing field.

As topic editors of this research topic, we would like to invite you to contribute relevant papers, including reviews, mini-reviews, research articles, methods, and perspectives.

Areas to be covered in this Research Topic include, but are not limited to, the following themes:

• Protein Complex Assembly;

• Protein-protein interaction (PPI) prediction;

• Binding free energy calculation;

• Enzyme-substrate recognition;

• Synthetic binding proteins (SBP) design;

• Monoclonal antibody design;

• Computer-aided drug design (CADD);

• Drug-drug interaction (DDI) prediction.