Inverse pharmacology: Approaches and tools for introducing druggability into engineered proteins

Abstract

A major feature of twenty-first century medical research is the development of therapeutic strategies that use 'biologics' (large molecules, usually engineered proteins) and living cells instead of, or as well as, the small molecules that were the basis of pharmacology in earlier eras. The high power of these techniques can bring correspondingly high risk, and therefore the need for the potential for external control. One way of exerting control on therapeutic proteins is to make them responsive to small molecules; in a clinical context, these small molecules themselves have to be safe. Conventional pharmacology has resulted in thousands of small molecules licensed for use in humans, and detailed structural data on their binding to their protein targets. In principle, these data can be used to facilitate the engineering of drug-responsive modules, taken from natural proteins, into synthetic proteins. This has been done for some years (for example, Cre-ERT2) but usually in a painstaking manner. Recently, we have developed the bioinformatic tool SynPharm to facilitate the design of drug-responsive proteins. In this review, we outline the history of the field, the design and use of the Synpharm tool, and describe our own experiences in engineering druggability into the Cpf1 effector of CRISPR gene editing.

Keywords: CRISPR; Cpf1; Drug; Gene editing; Pharmaceutical; Protein engineering; Structure-function; Synthetic biology.

Fig. 1

Examples of drug binding sites formed by amino acids spaced widely in a protein, or those in a relatively defined segment. (a) Shows the structure of human ecto-5′-nucleotidase binding to the drug, αβmethylene-ADP. From the first amino acid involved in the binding to the last, the drug-binding segment includes 469 of the protein's 533 amino acids, and the binding pocket is clearly dependent on the way the whole protein folds to locate these amino acids in space. This would not be a promising candidate as a ‘module’ that could be included in engineered proteins. (b) Shows the human CB1 receptor complexed with the drug AM11452. Here the drug-binding segment constitutes only 120 of the protein's 472 amino acids, and the drug-binding site is on the edge of the protein, much less dependent on the protein's overall structure. This is therefore a more promising candidate to be a transferrable module. Note that the plots on the right of the figure show only the drug-binding segment, not the whole protein. These images come from the SynPHARM web tool described in the text.

Fig. 2

some classic modes of drug action, and their potential for use in engineered systems. (a) Depicts classical agonism, in which a drug (in this case pilocarpine) mimics the action of a natural ligand (in this case, acetylcholine, Ach) on a receptor (in this case, the M3 muscarinic acetylcholine receptor). (b) Depicts antagonism, in which a drug (in this case, atropine, a competitive neutral antagonist) inhibits the action of the natural ligand on the same M3 receptor. It should be noted that other, more subtle, drug actions exist but they are beyond the scope of this article. (c,d) Depict schemes in which a drug displaces a target from a protein, to which it is otherwise bound and sequestered, in a way that prevents the target interacting with its effector, either a cytoplasmic molecule (c) or the genome (d). Because the schemes in (c,d) rely only on modulating a target's binding to a membrane protein or chaperone, their action is relatively independent of the global structure of the target, so might be transferrable to a chimaeric protein. The DNA graphic in (c,d) is from US Department of Energy and is public domain (source: https://commons.wikimedia.org/wiki/File:Dna-split.png).

Fig. 3

Screenshots from the SynPHARM tool. (a) Shows a small part of a complete table of targets, ordered by ‘proportional length’ of the drug-binding segment compared to the whole molecule. (b,c,d) Depict data on the CaS receptor at the top of the table (viewed by clicking on its index number); (b) Shows a rotatable 3D model, with the drug-binding element coloured, (c) shows positions of drug-interacting amino acids within this segment, and (d) depicts in colour the inter-residue distances in the whole protein. White gaps represent absence of reliable data.

Fig. 4

Design of druggable Cpf1. (a) Shows the ligand-binding segment of the human estrogen receptor α, binding tamoxifen; (b) shows the ligand-binding segment of the human progesterone receptor, binding progesterone; (c) depicts the structure of Acidaminococcus Cpf1 (PDB entry 5B43, Cpf1 binding to DNA): the position between amino acids 584 and 585, chosen for insertion of the ER-LBD and PR-LBD, is arrowed. (d) Shows the hydroxytamoxifen-dependence of the engineered Cpf1, in an assay in which Cpf1 activity disrupts a repressor and allows expression of a fluorescent reporter: this graph is from Dominguez-Monedero et al., 2018, edited to remove bars referring to other experiments.