Compound dataset and custom code for deep generative multi-target compound design

Structural feature-driven pattern analysis for multitarget modulator landscapes

MOTIVATION

Multitargeting features of small molecules have been of increasing interest in recent years. Polypharmacological drugs that address several therapeutic targets may provide greater therapeutic benefits for patients. Furthermore, multitarget compounds can be used to address proteins of the same (or similar) protein families for their exploration as potential pharmacological targets. In addition, the knowledge of multitargeting features is of major importance in the drug selection process; particularly in ultra-large virtual screening procedures to gain high-quality compound collections. However, large-scale multitarget modulator landscapes are almost non-existent.

RESULTS

We implemented a specific feature-driven computer-aided pattern analysis (C@PA) to extract molecular-structural features of inhibitors of the model protein family of ATP-binding cassette (ABC) transporters. New molecular-structural features have been identified that successfully expanded the known multitarget modulator landscape of pan-ABC transporter inhibitors. The prediction capability was biologically confirmed by the successful discovery of pan-ABC transporter inhibitors with a distinct inhibitory activity profile.

AVAILABILITY AND IMPLEMENTATION

The multitarget dataset is available on the PANABC web page (http://www.panabc.info) and its use is free of charge.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Binding mode analysis of ABCA7 for the prediction of novel Alzheimer's disease therapeutics

The adenosine-triphosphate-(ATP)-binding cassette (ABC) transporter ABCA7 is a genetic risk factor for Alzheimer's disease (AD). Defective ABCA7 promotes AD development and/or progression. Unfortunately, ABCA7 belongs to the group of 'under-studied' ABC transporters that cannot be addressed by small-molecules. However, such small-molecules would allow for the exploration of ABCA7 as pharmacological target for the development of new AD diagnostics and therapeutics. Pan-ABC transporter modulators inherit the potential to explore under-studied ABC transporters as novel pharmacological targets by potentially binding to the proposed 'multitarget binding site'. Using the recently reported cryogenic-electron microscopy (cryo-EM) structures of ABCA1 and ABCA4, a homology model of ABCA7 has been generated. A set of novel, diverse, and potent pan-ABC transporter inhibitors has been docked to this ABCA7 homology model for the discovery of the multitarget binding site. Subsequently, application of pharmacophore modelling identified the essential pharmacophore features of these compounds that may support the rational drug design of innovative diagnostics and therapeutics against AD.

Fine-tuning of a generative neural network for designing multi-target compounds

Exploring the origin of multi-target activity of small molecules and designing new multi-target compounds are highly topical issues in pharmaceutical research. We have investigated the ability of a generative neural network to create multi-target compounds. Data sets of experimentally confirmed multi-target, single-target, and consistently inactive compounds were extracted from public screening data considering positive and negative assay results. These data sets were used to fine-tune the REINVENT generative model via transfer learning to systematically recognize multi-target compounds, distinguish them from single-target or inactive compounds, and construct new multi-target compounds. During fine-tuning, the model showed a clear tendency to increasingly generate multi-target compounds and structural analogs. Our findings indicate that generative models can be adopted for de novo multi-target compound design.

Compound dataset and custom code for deep generative multi-target compound design

AIM

Generating a data and software infrastructure for evaluating multi-target compound (MT-CPD) design via deep generative modeling.

METHODOLOGY

The REINVENT 2.0 approach for generative modeling was extended for MT-CPD design and a large benchmark data set was curated.

EXEMPLARY RESULTS & DATA

Proof-of-concept for deep generative MT-CPD design was established. Custom code and the benchmark set comprising 2809 MT-CPDs, 61,928 single-target and 295,395 inactive compounds from biological screens are made freely available.

LIMITATIONS & NEXT STEPS

MT-CPD design via deep learning is still at its conceptual stages. It will be required to demonstrate experimental impact. The data and software we provide enable further investigation of MT-CPD design and generation of candidate molecules for experimental programs.