A Deep Learning Proteomic Scale Approach for Drug Design

Abstract

Computational approaches have accelerated novel therapeutic discovery in recent decades. The Computational Analysis of Novel Drug Opportunities (CANDO) platform for shotgun multi-target therapeutic discovery, repurposing, and design aims to improve their efficacy and safety by employing a holistic approach by computing interaction signatures between every drug/compound and a large library of non-redundant protein structures corresponding to the human proteome fold space. These signatures are compared and analyzed to determine if a given drug/compound is efficacious and safe for a given indication/disease. In this study, we used a deep learning based autoencoder to first reduce the dimensionality of CANDO computed drug-proteome interaction signatures. We then employed a reduced conditional variational autoencoder to generate novel drug-like compounds when given a target encoded "objective" signature. Using this model, we designed compounds to recreate the interaction signatures for twenty approved and experimental drugs and showed that 16/20 designed compounds are predicted to be significantly (p-value ≤ .05) more behaviorally similar relative to all corresponding controls, and 20/20 are predicted to be more behaviorally similar relative to a random control. We further observed that redesigns of objectives developed via rational drug design perform significantly better than those derived from natural sources (p-value ≤.05), suggesting that the model has learned an abstraction of rational drug design. We also show that designed compounds are structurally diverse and synthetically feasible when compared to their respective objective drugs despite consistently high predicted behavioral similarity. Finally, we generated new designs that enhance thirteen drugs/compounds associated with non-small cell lung cancer and anti-aging properties using their predicted proteomic interaction signatures. This work represents a significant step forward in automating holistic therapeutic design with machine learning, and subsequently offers a reduction in the time needed to generate novel, effective, and safe drug leads for any indication.

Multiscale Analysis and Validation of Effective Drug Combinations Targeting Driver Kras Mutations in Non-Small Cell Lung Cancer

“…Validation studies for the top candidates from our full drug/compound library are in progress to determine if other compounds synergize with available KRAS G12C inhibitors, or achieve inhibition alone. Novel designs based on mutant-specific inhibitors have also been synthesized and are also in the process of being validated [59]. The goal of this study is to develop sophisticated multiscale hybrid computational/experimental pipelines for precision drug discovery that are capable of rapidly generating safe and effective putative drug candidate leads, along with elucidating mechanistic details that may be used as a basis for further hypothesis generation.…”

Effective holistic characterization of small molecule effects using heterogeneous biological networks

“…Here we describe the use of the Computational Analysis of Novel Drug Opportunities (CANDO) platform for both drug indication as well as ADR prediction. CANDO is a shotgun multiscale drug repurposing, discovery, and design platform whose fundamental tenet or paradigm is to assess the biological or therapeutic potential of small molecule chemical compounds based on their interactions to higher scale entities such as proteins, proteomes, and pathways (Minie et al, 2014; Sethi et al, 2015; Chopra and Samudrala, 2016; Falls et al, 2019; Mangione and Samudrala, 2019; Schuler and Samudrala, 2019; Hudson and Samudrala, 2021; Mangione et al, 2020a; Chopra et al, 2016; Mangione et al, 2020b; Overhoff et al, 2021; Schuler et al, 2021; Moukheiber et al, 2022; Mangione et al, 2022; Bruggemann et al, 2022). Our hypotheses are that compound behavior is describable in terms of their interaction signatures, which are real value vectors representing interactions between a given compound and a library of proteins, pathways, cells, etc.…”

“…and that compounds with similar signatures will have similar effects in biological systems and therefore can be repurposed accordingly. Novel compounds may also be designed to mimic behaviors observed in desired interaction signatures (Overhoff et al, 2021). The current version (v3) of the platform features thousands of both human approved drugs and investigational compounds and the diseases for which they are indicated/associated, as well as tens of thousands of protein structures from multiple organisms, including Homo sapiens and SARS-CoV-2.…”