A drug discovery platform to identify compounds that inhibit EGFR triple mutants

Saraon, Punit; Snider, Jamie; Kalaidzidis, Yannis; Wybenga‐Groot, Leanne E.; Weiss, Konstantin; Rai, Ankit; Radulovich, Nikolina; Drecun, Luka; Vučković, Nika; Vučetić, Adriana; Wong, Victoria; Thériault, Brigitte L.; Pham, Nhu-An; Park, Jin H.; Datti, Alessandro; Wang, Jenny; Pathmanathan, Shivanthy; Aboualizadeh, Farzaneh; Lyakisheva, Anna; Yao, Zhong; Wang, Yuhui; Joseph, Babu; Aman, Ahmed; Moran, Michael F.; Prakesch, Michaël; Poda, Gennady; Marcellus, Richard; Uehling, David; Samaržija, Miroslav; Jakopović, Marko; Tsao, Ming‐Sound; Shepherd, Frances A.; Sacher, Adrian G.; Leighl, Natasha B.; Akhmanova, Anna; Al‐awar, Rima; Zerial, Marino; Štagljar, Igor

doi:10.1038/s41589-020-0484-2

Cited by 31 publications

(25 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, many binary PPI assays can generate highly quantitative scores. For example, such assays have been previously used to determine relative binding affinities or to assess the effects of mutations and drugs on specific PPIs 19,39,40 . Here, we demonstrate that the quantitative readouts of two versatile PPI assays, LuTHy and mN2H, can be used to systematically detect protein interactions within distinct multiprotein complexes, and confidently differentiate direct PPIs from indirect associations.…”

Section: Discussionmentioning

confidence: 99%

A quantitative mapping approach to identify direct interactions within complexomes

Trepte

Secker

Choi

et al. 2021

Preprint

View full text Add to dashboard Cite

Complementary methods are required to fully characterize all protein complexes, or the complexome, of a cell. Affinity purification coupled to mass-spectrometry (AP-MS) can identify the composition of complexes at proteome-scale. However, information on direct contacts between subunits is often lacking. In contrast, solving the 3D structure of protein complexes can provide this information, but structural biology techniques are not yet scalable for systematic, proteome-wide efforts. Here, we optimally combine two orthogonal high-throughput binary interaction assays, LuTHy and N2H, and demonstrate that their quantitative readouts can be used to differentiate direct interactions from indirect associations within multiprotein complexes. We also show that LuTHy allows accurate distance measurements between proteins in live cells and apply these findings to study the impact of the polyglutamine expansion mutation on the structurally unresolved N-terminal domain of Huntingtin. Thus, we present a new framework based on quantitative interaction assays to complement structural biology and AP-MS techniques, which should help to provide first-approximation contact maps of multiprotein complexes at proteome-scale.Graphical Abstract

show abstract

Section: Discussionmentioning

confidence: 99%

A quantitative mapping approach to identify direct interactions within complexomes

Trepte

Secker

Choi

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…As a result of remarkable performance in such applications as computer visionand speech synthesis, deep learning has become widely used in bioinformatics as well as in quantitative structure-activity relationship (QSAR) studies in drug discovery [1], making use of efficient data representations using non-linear transformations that smooth the learning process of embedded hidden patterns. A small number of studies adopted deep neural networks (DNN) for predicting DTI binary class employing various inputs of proteins and drugs.…”

Section: A Research Motivationmentioning

confidence: 99%

“…One of the preliminary stages of drug discovery is the determination of innovative candidate drug compounds that interact with particular target proteins. Through in vivo and in vitro studies, several high-throughput experiments have been conducted to identify the novel compounds with the anticipated interactive characteristics [1]. However, expensive costs and chronological order requirements make it impracticable to scan immense volumes of targets and mixtures.…”

Section: Introductionmentioning

confidence: 99%

DeepH-DTA: Deep Learning for Predicting Drug-Target Interactions: A Case Study of COVID-19 Drug Repurposing

et al. 2020

View full text Add to dashboard Cite

The rapid spread of novel coronavirus pneumonia (COVID-19) has led to a dramatically increased mortality rate worldwide. Despite many efforts, the rapid development of an effective vaccine for this novel virus will take considerable time and relies on the identification of drug-target (DT) interactions utilizing commercially available medication to identify potential inhibitors. Motivated by this, we propose a new framework, called DeepH-DTA, for predicting DT binding affinities for heterogeneous drugs. We propose a heterogeneous graph attention (HGAT) model to learn topological information of compound molecules and bidirectional ConvLSTM layers for modeling spatio-sequential information in simplified molecular-input line-entry system (SMILES) sequences of drug data. For protein sequences, we propose a squeezed-excited dense convolutional network for learning hidden representations within amino acid sequences; while utilizing advanced embedding techniques for encoding both kinds of input sequences. The performance of DeepH-DTA is evaluated through extensive experiments against cutting-edge approaches utilising two public datasets (Davis, and KIBA) which comprise eclectic samples of the kinase protein family and the pertinent inhibitors. DeepH-DTA attains the highest Concordance Index (CI) of 0.924 and 0.927 and also achieved a mean square error (MSE) of 0.195 and 0.111 on the Davis and KIBA datasets respectively. Moreover, a study using FDA-approved drugs from the Drug Bank database is performed using DeepH-DTA to predict the affinity scores of drugs against SARS-CoV-2 amino acid sequences, and the results show that that the model can predict some of the SARS-Cov-2 inhibitors that have been recently approved in many clinical studies.

show abstract

“…Recently, a new drug discovery platform, MaMTH-DS [97] , was used to identify interactions between membrane proteins and how they change in response to a specific mutation or following the induction of specific stimulus, such as a hormone, agonist, or phosphorylation event [98] , with potential usefulness in studying dynamic interactome changes in proteins involved in cell signaling, and how these pathways are affected in NPDs. Since more than one gene may contribute to NPD phenotypes, CRISPR-based genetic screens can be applied to reveal functional relationships between genes in coordinating a phenotype [99] .…”

Section: Network-based Multiomics To Explore Mt Alterations In Ipscs mentioning

confidence: 99%

Mitochondria under the spotlight: On the implications of mitochondrial dysfunction and its connectivity to neuropsychiatric disorders

Zilocchi

Broderick

Phanse

et al. 2020

Computational and Structural Biotechnology Journal

View full text Add to dashboard Cite

show abstract

A drug discovery platform to identify compounds that inhibit EGFR triple mutants

Cited by 31 publications

References 41 publications

A quantitative mapping approach to identify direct interactions within complexomes

A quantitative mapping approach to identify direct interactions within complexomes

DeepH-DTA: Deep Learning for Predicting Drug-Target Interactions: A Case Study of COVID-19 Drug Repurposing

Mitochondria under the spotlight: On the implications of mitochondrial dysfunction and its connectivity to neuropsychiatric disorders

Contact Info

Product

Resources

About