The iPPI-DB initiative: A Community-centered database of Protein-Protein Interaction modulators

Multi-level bioinformatics resources support drug target discovery of protein-protein interactions

Drug discovery often begins with a new target. Protein-protein interactions (PPIs) are crucial to multitudinous cellular processes and offer a promising avenue for drug-target discovery. PPIs are characterized by multi-level complexity: at the protein level, interaction networks can be used to identify potential targets, whereas at the residue level, the details of the interactions of individual PPIs can be used to examine a target's druggability. Much great progress has been made in target discovery through multi-level PPI-related computational approaches, but these resources have not been fully discussed. Here, we systematically survey bioinformatics tools for identifying and assessing potential drug targets, examining their characteristics, limitations and applications. This work will aid the integration of the broader protein-to-network context with the analysis of detailed binding mechanisms to support the discovery of drug targets.

PPII-AEAT: Prediction of protein-protein interaction inhibitors based on autoencoders with adversarial training

Protein-protein interactions (PPIs) have shown increasing potential as novel drug targets. The design and development of small molecule inhibitors targeting specific PPIs are crucial for the prevention and treatment of related diseases. Accordingly, effective computational methods are highly desired to meet the emerging need for the large-scale accurate prediction of PPI inhibitors. However, existing machine learning models rely heavily on the manual screening of features and lack generalizability. Here, we propose a new PPI inhibitor prediction method based on autoencoders with adversarial training (named PPII-AEAT) that can adaptively learn molecule representation to cope with different PPI targets. First, Extended-connectivity fingerprints and Mordred descriptors are employed to extract the primary features of small molecular compounds. Then, an autoencoder architecture is trained in three phases to learn high-level representations and predict inhibitory scores. We evaluate PPII-AEAT on nine PPI targets and two different tasks, including the PPI inhibitor identification task and inhibitory potency prediction task. The experimental results show that our proposed PPII-AEAT outperforms state-of-the-art methods.

A Multimodal Deep Learning Framework for Predicting PPI-Modulator Interactions

Protein-protein interactions (PPIs) are essential for various biological processes and diseases. However, most existing computational methods for identifying PPI modulators require either target structure or reference modulators, which restricts their applicability to novel PPI targets. To address this challenge, we propose MultiPPIMI, a sequence-based deep learning framework that predicts the interaction between any given PPI target and modulator. MultiPPIMI integrates multimodal representations of PPI targets and modulators and uses a bilinear attention network to capture intermolecular interactions. Experimental results on our curated benchmark data set show that MultiPPIMI achieves an average AUROC of 0.837 in three cold-start scenarios and an AUROC of 0.994 in the random-split scenario. Furthermore, the case study shows that MultiPPIMI can assist molecular docking simulations in screening inhibitors of Keap1/Nrf2 PPI interactions. We believe that the proposed method provides a promising way to screen PPI-targeted modulators.

Generating Potential Protein-Protein Interaction Inhibitor Molecules Based on Physicochemical Properties

Protein-protein interactions (PPIs) are associated with various diseases; hence, they are important targets in drug discovery. However, the physicochemical empirical properties of PPI-targeted drugs are distinct from those of conventional small molecule oral pharmaceuticals, which adhere to the "rule of five (RO5)". Therefore, developing PPI-targeted drugs using conventional methods, such as molecular generation models, is challenging. In this study, we propose a molecular generation model based on deep reinforcement learning that is specialized for the production of PPI inhibitors. By introducing a scoring function that can represent the properties of PPI inhibitors, we successfully generated potential PPI inhibitor compounds. These newly constructed virtual compounds possess the desired properties for PPI inhibitors, and they show similarity to commercially available PPI libraries. The virtual compounds are freely available as a virtual library.

Using a stacked ensemble learning framework to predict modulators of protein-protein interactions

Identifying small molecule protein-protein interaction modulators (PPIMs) is a highly promising and meaningful research direction for drug discovery, cancer treatment, and other fields. In this study, we developed a stacking ensemble computational framework, SELPPI, based on a genetic algorithm and tree-based machine learning method for effectively predicting new modulators targeting protein-protein interactions. More specifically, extremely randomized trees (ExtraTrees), adaptive boosting (AdaBoost), random forest (RF), cascade forest, light gradient boosting machine (LightGBM), and extreme gradient boosting (XGBoost) were used as basic learners. Seven types of chemical descriptors were taken as the input characteristic parameters. Primary predictions were obtained with each basic learner-descriptor pair. Then, the 6 methods mentioned above were used as meta learners and trained on the primary prediction in turn. The most efficient method was utilized as the meta learner. Finally, the genetic algorithm was used to select the optimal primary prediction output as the input of the meta learner for secondary prediction to obtain the final result. We systematically evaluated our model on the pdCSM-PPI datasets. To our knowledge, our model outperformed all existing models, which demonstrates its great power.

Fragment-based drug discovery supports drugging 'undruggable' protein-protein interactions

Protein-protein interactions (PPIs) have important roles in various cellular processes, but are commonly described as 'undruggable' therapeutic targets due to their large, flat, featureless interfaces. Fragment-based drug discovery (FBDD) has achieved great success in modulating PPIs, with more than ten compounds in clinical trials. Here, we highlight the progress of FBDD in modulating PPIs for therapeutic development. Targeting hot spots that have essential roles in both fragment binding and PPIs provides a shortcut for the development of PPI modulators via FBDD. We highlight successful cases of cracking the 'undruggable' problems of PPIs using fragment-based approaches. We also introduce new technologies and future trends. Thus, we hope that this review will provide useful guidance for drug discovery targeting PPIs.

Explore drug-like space with deep generative models

The process of design/discovery of drugs involves the identification and design of novel molecules that have the desired properties and bind well to a given disease-relevant target. One of the main challenges to effectively identify potential drug candidates is to explore the vast drug-like chemical space to find novel chemical structures with desired physicochemical properties and biological characteristics. Moreover, the chemical space of currently available molecular libraries is only a small fraction of the total possible drug-like chemical space. Deep molecular generative models have received much attention and provide an alternative approach to the design and discovery of molecules. To efficiently explore the drug-like space, we first constructed the drug-like dataset and then performed the generative design of drug-like molecules using a Conditional Randomized Transformer approach with the molecular access system (MACCS) fingerprint as a condition and compared it with previously published molecular generative models. The results show that the deep molecular generative model explores the wider drug-like chemical space. The generated drug-like molecules share the chemical space with known drugs, and the drug-like space captured by the combination of quantitative estimation of drug-likeness (QED) and quantitative estimate of protein-protein interaction targeting drug-likeness (QEPPI) can cover a larger drug-like space. Finally, we show the potential application of the model in design of inhibitors of MDM2-p53 protein-protein interaction. Our results demonstrate the potential application of deep molecular generative models for guided exploration in drug-like chemical space and molecular design.

Predicting the Likelihood of Molecules to Act as Modulators of Protein-Protein Interactions

Targeting protein-protein interactions (PPIs) by small molecule modulators (iPPIs) is an attractive strategy for drug therapy, and some iPPIs have already been introduced into the clinic. Blocking PPIs is however considered to be a more difficult task than inhibiting enzymes or antagonizing receptor activity. In this paper, we examine whether it is possible to predict the likelihood of molecules to act as iPPIs. Using our in-house iterative stochastic elimination (ISE) algorithm, we constructed two classification models that successfully distinguish between iPPIs from the iPPI-DB database and decoy molecules from either the Enamine HTS collection (ISE 1) or the ZINC database (ISE 2). External test sets of iPPIs taken from the TIMBAL database and decoys from Enamine HTS or ZINC were screened by the models: the area under the curve for the receiver operating characteristic curve was 0.85-0.89, and the Enrichment Factor increased from an initial 1 to as much as 66 for ISE 1 and 57 for ISE 2. Screening of the Enamine HTS and ZINC data sets through both models results in a library of ∼1.3 million molecules that pass either one of the models. This library is enriched with iPPI candidates that are structurally different from known iPPIs, and thus, it is useful for target-specific screenings and should accelerate the discovery of iPPI drug candidates. The entire library is available in Table S6.

HARIBOSS: a curated database of RNA-small molecules structures to aid rational drug design

MOTIVATION

RNA molecules are implicated in numerous fundamental biological processes and many human pathologies, such as cancer, neurodegenerative disorders, muscular diseases and bacterial infections. Modulating the mode of action of disease-implicated RNA molecules can lead to the discovery of new therapeutical agents and even address pathologies linked to 'undruggable' protein targets. This modulation can be achieved by direct targeting of RNA with small molecules. As of today, only a few RNA-targeting small molecules are used clinically. One of the main obstacles that have hampered the development of a rational drug design protocol to target RNA with small molecules is the lack of a comprehensive understanding of the molecular mechanisms at the basis of RNA-small molecule (RNA-SM) recognition.

RESULTS

Here, we present Harnessing RIBOnucleic acid-Small molecule Structures (HARIBOSS), a curated collection of RNA-SM structures determined by X-ray crystallography, nuclear magnetic resonance spectroscopy and cryo-electron microscopy. HARIBOSS facilitates the exploration of drug-like compounds known to bind RNA, the analysis of ligands and pockets properties and ultimately the development of in silico strategies to identify RNA-targeting small molecules.

AVAILABILITY AND IMPLEMENTATION

HARIBOSS can be explored via a web interface available at http://hariboss.pasteur.cloud.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

De novo molecular design with deep molecular generative models for PPI inhibitors

We construct a protein-protein interaction (PPI) targeted drug-likeness dataset and propose a deep molecular generative framework to generate novel drug-likeness molecules from the features of the seed compounds. This framework gains inspiration from published molecular generative models, uses the key features associated with PPI inhibitors as input and develops deep molecular generative models for de novo molecular design of PPI inhibitors. For the first time, quantitative estimation index for compounds targeting PPI was applied to the evaluation of the molecular generation model for de novo design of PPI-targeted compounds. Our results estimated that the generated molecules had better PPI-targeted drug-likeness and drug-likeness. Additionally, our model also exhibits comparable performance to other several state-of-the-art molecule generation models. The generated molecules share chemical space with iPPI-DB inhibitors as demonstrated by chemical space analysis. The peptide characterization-oriented design of PPI inhibitors and the ligand-based design of PPI inhibitors are explored. Finally, we recommend that this framework will be an important step forward for the de novo design of PPI-targeted therapeutics.

Identification of a Quinone Derivative as a YAP/TEAD Activity Modulator from a Repurposing Library

The transcriptional regulators YAP (Yes-associated protein) and TAZ (transcriptional co-activator with PDZ-binding motif) are the major downstream effectors in the Hippo pathway and are involved in cancer progression through modulation of the activity of TEAD (transcriptional enhanced associate domain) transcription factors. To exploit the advantages of drug repurposing in the search of new drugs, we developed a similar approach for the identification of new hits interfering with TEAD target gene expression. In our study, a 27-member in-house library was assembled, characterized, and screened for its cancer cell growth inhibition effect. In a secondary luciferase-based assay, only seven compounds confirmed their specific involvement in TEAD activity. IA5 bearing a p-quinoid structure reduced the cytoplasmic level of phosphorylated YAP and the YAP–TEAD complex transcriptional activity and reduced cancer cell growth. IA5 is a promising hit compound for TEAD activity modulator development.

Challenges in Discovering Drugs That Target the Protein-Protein Interactions of Disordered Proteins

Protein–protein interactions (PPIs) outnumber proteins and are crucial to many fundamental processes; in consequence, PPIs are associated with several pathological conditions including neurodegeneration and modulating them by drugs constitutes a potentially major class of therapy. Classically, however, the discovery of small molecules for use as drugs entails targeting individual proteins rather than targeting PPIs. This is largely because discovering small molecules to modulate PPIs has been seen as extremely challenging. Here, we review the difficulties and limitations of strategies to discover drugs that target PPIs directly or indirectly, taking as examples the disordered proteins involved in neurodegenerative diseases.

InDeep: 3D fully convolutional neural networks to assist in silico drug design on protein-protein interactions

MOTIVATION

Protein-protein interactions (PPIs) are key elements in numerous biological pathways and the subject of a growing number of drug discovery projects including against infectious diseases. Designing drugs on PPI targets remains a difficult task and requires extensive efforts to qualify a given interaction as an eligible target. To this end, besides the evident need to determine the role of PPIs in disease-associated pathways and their experimental characterization as therapeutics targets, prediction of their capacity to be bound by other protein partners or modulated by future drugs is of primary importance.

RESULTS

We present InDeep, a tool for predicting functional binding sites within proteins that could either host protein epitopes or future drugs. Leveraging deep learning on a curated dataset of PPIs, this tool can proceed to enhanced functional binding site predictions either on experimental structures or along molecular dynamics trajectories. The benchmark of InDeep demonstrates that our tool outperforms state-of-the-art ligandable binding sites predictors when assessing PPI targets but also conventional targets. This offers new opportunities to assist drug design projects on PPIs by identifying pertinent binding pockets at or in the vicinity of PPI interfaces.

AVAILABILITY AND IMPLEMENTATION

The tool is available on GitLab at https://gitlab.pasteur.fr/InDeep/InDeep.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

pdCSM-PPI: Using Graph-Based Signatures to Identify Protein-Protein Interaction Inhibitors

Protein-protein interactions are promising sites for development of selective drugs; however, they have generally been viewed as challenging targets. Molecules targeting protein-protein interactions tend to be larger and more lipophilic than other drug-like molecules, mimicking the properties of interacting interfaces. Here, we propose a machine learning approach that uses a graph-based representation of small molecules to guide identification of inhibitors modulating protein-protein interactions, pdCSM-PPI. This approach was applied to 21 different PPI targets. We developed interaction-specific models that were able to accurately identify active compounds achieving MCC and F1 scores up to 1, and Pearson's correlations up to 0.87, outperforming previous approaches. Using insights from these individual models, we developed a generic protein-protein interaction modulator predictive model, which accurately predicted IC50 with a Pearson's correlation of 0.64 on a low redundancy blind test. Importantly, we were able to accurately identify active from inactive compounds, achieving an AUC of 0.77 and sensitivity and specificity of 76% and 78%, respectively. We believe pdCSM-PPI will be an important tool to help guide more efficient screening of new PPI inhibitors; it is freely available as an easy-to-use web server and API at http://biosig.unimelb.edu.au/pdcsm_ppi.

Analysis of physicochemical properties of protein-protein interaction modulators suggests stronger alignment with the "rule of five"

Despite the important roles played by protein-protein interactions (PPIs) in disease, they have been long considered as 'undruggable'. However, recent advances have suggested that PPIs are druggable but may not follow conventional rules of 'drug ability'. Here we explore which physicochemical parameters are essential for a PPI modulator to be a clinical drug by analysing the physicochemical properties of small-molecule PPI modulators in the market, in clinical trials, and published. Our analysis reveals that those compounds currently on the market have a larger range of values for most of the physicochemical parameters, whereas those in clinical trials fit much more stringently to standard drug-like parameters. This observation was particularly true for molecular weight, clog P and topological polar surface area, where aside from a few outliers, most of the compounds in clinical trials fit within standard drug-like parameters. This implies that the newer PPI modulators are more drug-like than those currently on the market, suggesting that designing new PPI-specific screening libraries should remain within standard drug-like parameters in order to obtain a clinical candidate. Taken together, our analysis has important implications for designing future drug discovery campaigns aimed at targeting PPIs.

Quantitative Estimate Index for Early-Stage Screening of Compounds Targeting Protein-Protein Interactions

Drug-likeness quantification is useful for screening drug candidates. Quantitative estimates of drug-likeness (QED) are commonly used to assess quantitative drug efficacy but are not suitable for screening compounds targeting protein-protein interactions (PPIs), which have recently gained attention. Therefore, we developed a quantitative estimate index for compounds targeting PPIs (QEPPI), specifically for early-stage screening of PPI-targeting compounds. QEPPI is an extension of the QED method for PPI-targeting drugs that models physicochemical properties based on the information available for drugs/compounds, specifically those reported to act on PPIs. FDA-approved drugs and compounds in iPPI-DB, which comprise PPI inhibitors and stabilizers, were evaluated using QEPPI. The results showed that QEPPI is more suitable than QED for early screening of PPI-targeting compounds. QEPPI was also considered an extended concept of the "Rule-of-Four" (RO4), a PPI inhibitor index. We evaluated the discriminatory performance of QEPPI and RO4 for datasets of PPI-target compounds and FDA-approved drugs using F-score and other indices. The F-scores of RO4 and QEPPI were 0.451 and 0.501, respectively. QEPPI showed better performance and enabled quantification of drug-likeness for early-stage PPI drug discovery. Hence, it can be used as an initial filter to efficiently screen PPI-targeting compounds.