scholarly journals Augmented base pairing networks encode RNA-small molecule binding preferences

2020 ◽  
Vol 48 (14) ◽  
pp. 7690-7699
Author(s):  
Carlos Oliver ◽  
Vincent Mallet ◽  
Roman Sarrazin Gendron ◽  
Vladimir Reinharz ◽  
William L Hamilton ◽  
...  
Keyword(s):  
Drug Discovery ◽  
Structure Function ◽  
Small Molecule ◽  
Rna Structure ◽  
Rna Binding ◽  
Binding Specificity ◽  
Representation Learning ◽  
Learning Task ◽  
Graph Representation ◽  
Base Pairing

Abstract RNA-small molecule binding is a key regulatory mechanism which can stabilize 3D structures and activate molecular functions. The discovery of RNA-targeting compounds is thus a current topic of interest for novel therapies. Our work is a first attempt at bringing the scalability and generalization abilities of machine learning methods to the problem of RNA drug discovery, as well as a step towards understanding the interactions which drive binding specificity. Our tool, RNAmigos, builds and encodes a network representation of RNA structures to predict likely ligands for novel binding sites. We subject ligand predictions to virtual screening and show that we are able to place the true ligand in the 71st–73rd percentile in two decoy libraries, showing a significant improvement over several baselines, and a state of the art method. Furthermore, we observe that augmenting structural networks with non-canonical base pairing data is the only representation able to uncover a significant signal, suggesting that such interactions are a necessary source of binding specificity. We also find that pre-training with an auxiliary graph representation learning task significantly boosts performance of ligand prediction. This finding can serve as a general principle for RNA structure-function prediction when data is scarce. RNAmigos shows that RNA binding data contains structural patterns with potential for drug discovery, and provides methodological insights for possible applications to other structure-function learning tasks. The source code, data and a Web server are freely available at http://rnamigos.cs.mcgill.ca.

scholarly journals Augmented base pairing networks encode RNA-small molecule binding preferences

2019 ◽  
Author(s):  
Carlos Oliver ◽  
Vincent Mallet ◽  
Roman Sarrazin Gendron ◽  
Vladimir Reinharz ◽  
William L. Hamilton ◽  
...  
Keyword(s):  
Drug Discovery ◽  
Small Molecule ◽  
Binding Sites ◽  
Rna Binding ◽  
Graph Representation ◽  
Learning Approaches ◽  
Base Pairing ◽  
Binding Prediction ◽  
Structural Patterns ◽  
Small Molecule Ligands

AbstractMotivationThe binding of small molecules to RNAs is an important mechanism which can stabilize 3D structures or activate key molecular functions. To date, computational and experimental efforts toward small molecule binding prediction have primarily focused on protein targets. Considering that a very large portion of the genome is transcribed into non-coding RNAs but only few regions are translated into proteins, successful annotations of RNA elements targeted by small-molecule would likely uncover a vast repertoire of biological pathways and possibly lead to new therapeutic avenues.ResultsOur work is a first attempt at bringing machine learning approaches to the problem of RNA drug discovery. RNAmigos takes advantage of the unique structural properties of RNA to predict small molecule ligands for unseen binding sites. A key feature of our model is an efficient representation of binding sites as augmented base pairing networks (ABPNs) aimed at encoding important structural patterns. We subject our ligand predictions to two virtual screen settings and show that we are able to rank the known ligand on average in the 73rd percentile, showing a significant improvement over several baselines. Furthermore, we observe that graphs which are augmented with non-Watson Crick (a.k.a non-canonical) base pairs are the only representation which is able to retrieve a significant signal, suggesting that non-canonical interactions are an necessary source of binding specificity in RNAs. We also find that an auxiliary graph representation task significantly boosts performance by providing efficient structural embeddings to the low data setting of ligand prediction. RNAmigos shows that RNA binding data contains structural patterns with potential for drug discovery, and provides methodological insights which can be applied to other structure-function learning tasks.AvailabilityCode and data is freely available at http://csb.cs.mcgill.ca/[email protected]

scholarly journals Systematic analysis of the interactions driving small molecule–RNA recognition

2020 ◽  
Vol 11 (7) ◽  
pp. 802-813 ◽  
Author(s):  
G. Padroni ◽  
N. N. Patwardhan ◽  
M. Schapira ◽  
A. E. Hargrove
Keyword(s):  
Drug Discovery ◽  
Small Molecules ◽  
Small Molecule ◽  
Rna Binding ◽  
Rna Recognition ◽  
Systematic Analysis

This study underscores privileged interactions for RNA binding small molecules, an emerging focus in drug discovery.

Quantitative Ranking of Ligand Binding Kinetics with a Multiscale Milestoning Simulation Approach

2018 ◽  
Author(s):  
Benjamin R. Jagger ◽  
Christoper T. Lee ◽  
Rommie Amaro
Keyword(s):  
Molecular Dynamics ◽  
Drug Discovery ◽  
Small Molecule ◽  
Brownian Dynamics ◽  
Model Simulation ◽  
Computational Cost ◽  
Lead Selection ◽  
Delta G ◽  
Dynamics Simulations

<p>The ranking of small molecule binders by their kinetic (kon and koff) and thermodynamic (delta G) properties can be a valuable metric for lead selection and optimization in a drug discovery campaign, as these quantities are often indicators of in vivo efficacy. Efficient and accurate predictions of these quantities can aid the in drug discovery effort, acting as a screening step. We have previously described a hybrid molecular dynamics, Brownian dynamics, and milestoning model, Simulation Enabled Estimation of Kinetic Rates (SEEKR), that can predict kon’s, koff’s, and G’s. Here we demonstrate the effectiveness of this approach for ranking a series of seven small molecule compounds for the model system, -cyclodextrin, based on predicted kon’s and koff’s. We compare our results using SEEKR to experimentally determined rates as well as rates calculated using long-timescale molecular dynamics simulations and show that SEEKR can effectively rank the compounds by koff and G with reduced computational cost. We also provide a discussion of convergence properties and sensitivities of calculations with SEEKR to establish “best practices” for its future use.</p>

Growing by Sharing - Story of Ryvu and Selvita

2020 ◽  
Vol 7 (1) ◽  
pp. 33-47
Author(s):  
Magdalena Marciniak
Keyword(s):  
Drug Discovery ◽  
Business Model ◽  
Small Molecule ◽  
Contract Research ◽  
Industrial Enterprises ◽  
Strong Position ◽  
Small Molecule Therapeutics

Ryvu Therapeutics and Selvita originated in 2007, a time when drug discovery in Poland was still not pursued by industrial enterprises. For many years, both entities operated one company and were known under a common name Selvita S.A., combining their efforts on both innovative small-molecule therapeutics for oncology and expertise in Contract Research Services (CRO). Following more than a decade of such a hybrid business model, Selvita established a strong position in the field of drug discovery and built trust among partners, clients, and investors globally. This encouraged the leaders of the company to separate the two divisions into fully autonomous units, which in fact, had already been operating quite independently and both were successful in diverse areas of drug discovery activities. At the beginning of October 2019, two new companies were established and both parts were given independence and more opportunities for growth. Discovery and development engine was named as Ryvu Therapeutics, and the CRO part of the company remained with the name Selvita. To reach this stage, both the divisions went through an interesting journey together, supporting and strengthening each other for the benefit of both.

Targeted Protein Degradation: "The Gold Rush is On!"

2020 ◽  
Vol 7 (1) ◽  
pp. 4-16
Author(s):  
Daria Kotlarek ◽  
Agata Pawlik ◽  
Maria Sagan ◽  
Marta Sowała ◽  
Alina Zawiślak-Architek ◽  
...  
Keyword(s):  
Drug Discovery ◽  
Protein Degradation ◽  
Small Molecule ◽  
Gold Rush ◽  
European Company ◽  
Drug Candidates ◽  
Protein Inhibition ◽  
Small Molecule Drug ◽  
Therapeutic Benefits ◽  
Talent Pool

Targeted Protein Degradation (TPD) is an emerging new modality of drug discovery that offers unprecedented therapeutic benefits over traditional protein inhibition. Most importantly, TPD unlocks the untapped pool of the proteome that to date has been considered undruggable. Captor Therapeutics (Captor) is the fourth global, and first European, company that develops small molecule drug candidates based on the principles of targeted protein degradation. Captor is located in Basel, Switzerland and Wroclaw, Poland and exploits the best opportunities of the two sites – experience and non-dilutive European grants, and talent pool, respectively. Through over $38 M of funding, Captor has been active in three areas of TPD: molecular glues, bi-specific degraders and direct degraders, ObteronsTM.

scholarly journals Hyperspectral Image Classification with Localized Graph Convolutional Filtering

2021 ◽  
Vol 13 (3) ◽  
pp. 526
Author(s):  
Shengliang Pu ◽  
Yuanfeng Wu ◽  
Xu Sun ◽  
Xiaotong Sun
Keyword(s):  
Hyperspectral Image ◽  
Principal Component ◽  
Representation Learning ◽  
Classification Performance ◽  
Hyperspectral Data ◽  
Spectral Graph Theory ◽  
Feature Reduction ◽  
Graph Representation ◽  
Novel Method ◽  
Local Graph

The nascent graph representation learning has shown superiority for resolving graph data. Compared to conventional convolutional neural networks, graph-based deep learning has the advantages of illustrating class boundaries and modeling feature relationships. Faced with hyperspectral image (HSI) classification, the priority problem might be how to convert hyperspectral data into irregular domains from regular grids. In this regard, we present a novel method that performs the localized graph convolutional filtering on HSIs based on spectral graph theory. First, we conducted principal component analysis (PCA) preprocessing to create localized hyperspectral data cubes with unsupervised feature reduction. These feature cubes combined with localized adjacent matrices were fed into the popular graph convolution network in a standard supervised learning paradigm. Finally, we succeeded in analyzing diversified land covers by considering local graph structure with graph convolutional filtering. Experiments on real hyperspectral datasets demonstrated that the presented method offers promising classification performance compared with other popular competitors.

Sign in / Sign up

Export Citation Format

Share Document