Small molecule probes are instrumental in the discovery and validation of novel therapeutic targets. However, high-affinity ligands are unavailable for a vast majority of potentially druggable proteins. Many of those orphan (i.e., ligandless) proteins are involved in cellular signaling, protein-protein interactions or transcription machinery and have critical roles in disease. Conventional computational strategies, such as QSAR or structure-based design, are often suboptimal for such hard-to-target proteins. Here, we present FRASE-bot, a new artificial intelligence (AI)-based tool to assemble ligands for orphan proteins from fragments directly in their putative binding sites. FRASE-bot exploits the previously developed concept of FRAgments in Structural Environments (FRASE). We successfully used FRASE-based design to develop potent in vivo antitumor agents. However, the published FRASE-based approach has a critical limitation: it only allows to exploit PDB/SAR information within a given protein family, hence precluding the ligand discovery for the majority of novel targets of interest belonging to understudied families. In contrast, FRASE-bot allows exploiting the full body of 3D structural and SAR data to assemble a ligand in the binding site of any orphan protein. It makes use of convolutional neural networks (ConvNet) to (i) locate potential FRASE sites in the protein of interest, (ii) calculate fitness scores for all potential FRASEs, and (iii) assess contributions of all respective fragments to the binding affinity in the context of a ligand. Technical details of the method, as well as preliminary benchmark studies will be discussed.

AI-driven 3D design for orphan targets from big PDB/SAR data

Macromolecular Chemistry: The Second Century

[Author Benefits](https://scimeetings.acs.org/?utm_source=pubs_content_marketing&utm_medium=website&utm_campaign=0320_MCF_NPI_Launch_Spring_Homepage&ref=pubs_content_marketing)

[How to use SciMeetings](https://storage.googleapis.com/dl.morressier.com/acs/SciMeetings-ACSSpring2020-HowToGuide_M3020-Final.pdf)

[Frequently Asked Questions](https://storage.googleapis.com/dl.morressier.com/acs/SciMtng_ACSNMSp2020_FAQ_M3120_Final.pdf)

ACS Spring 2020 National Meeting & Expo

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.