<scp>ALLO</scp>: A tool to discriminate and prioritize allosteric pockets

Akbar, Rahmad; Helms, Volkhard

doi:10.1111/cbdd.13161

Cited by 19 publications

(14 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Paratope-epitope prediction is a task known in the structural bioinformatics field as binding site prediction and is typically formulated as the problem of finding the set of residues (or patches) on the protein surface likely to interact with other proteins (Akbar and Helms, 2018;Akbar et al, 2017;Hwang et al, 2016;Jordan et al, 2012;Northey et al, 2018;Porollo and Meller, 2007). This problem can be formalized as a binary classification task in which a model is trained to discriminate binders from nonbinders at residue or sequence level.…”

Section: Predictability and Learnability Of The Paratope-epitope Interfacementioning

confidence: 99%

A compact vocabulary of paratope-epitope interactions enables predictability of antibody-antigen binding

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Predictability and Learnability Of The Paratope-epitope Interfacementioning

confidence: 99%

A compact vocabulary of paratope-epitope interactions enables predictability of antibody-antigen binding

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…First, as our models make predictions at the residue‐level, having a larger set of residues in the test dataset is a more important consideration than the number of proteins. A number of existing methods identify pockets and then, rank them based on their propensity of being active or allosteric binding pockets . Because proteins have fewer pockets than residues, these methods have been tested on datasets having diverse numbers of proteins.…”

Section: Discussionmentioning

confidence: 99%

“…A number of existing methods identify pockets and then, rank them based on their propensity of being active or allosteric binding pockets. 18,25,26,[60][61][62] Because proteins have fewer pockets than residues, these methods have been tested on datasets having diverse numbers of proteins. On the contrary, our models consider the total number of residues in the allosteric and active site test data sets where we have 167 allosteric, 6607 nonallosteric, 180 active site, and 4344 nonactive site residues.…”

Section: Discussionmentioning

confidence: 99%

Coupling dynamics and evolutionary information with structure to identify protein regulatory and functional binding sites

2019

View full text Add to dashboard Cite

Binding sites in proteins can be either specifically functional binding sites (active sites) that bind specific substrates with high affinity or regulatory binding sites (allosteric sites), that modulate the activity of functional binding sites through effector molecules. Owing to their significance in determining protein function, the identification of protein functional and regulatory binding sites is widely acknowledged as an important biological problem. In this work, we present a novel binding site prediction method, Active and Regulatory site Prediction (AR‐Pred), which supplements protein geometry, evolutionary, and physicochemical features with information about protein dynamics to predict putative active and allosteric site residues. As the intrinsic dynamics of globular proteins plays an essential role in controlling binding events, we find it to be an important feature for the identification of protein binding sites. We train and validate our predictive models on multiple balanced training and validation sets with random forest machine learning and obtain an ensemble of discrete models for each prediction type. Our models for active site prediction yield a median area under the curve (AUC) of 91% and Matthews correlation coefficient (MCC) of 0.68, whereas the less well‐defined allosteric sites are predicted at a lower level with a median AUC of 80% and MCC of 0.48. When tested on an independent set of proteins, our models for active site prediction show comparable performance to two existing methods and gains compared to two others, while the allosteric site models show gains when tested against three existing prediction methods. AR‐Pred is available as a free downloadable package at https://github.com/sambitmishra0628/AR-PRED_source.

show abstract

“…143 A plethora of computational methodologies and tools have recently utilized the wealth of available structural data and the predictive power of machine learning, often in combination with the aforementioned techniques, for predicting putative allosteric sites, allosteric signaling pathways, allosteric hotspots, and cryptic sites. [144][145][146][147][148][149][150][151][152][153][154][155][156] The allosteric database ASD v3.0 28 and the allosteric benchmark ASBench 157 have been extensively used for the training and testing of many developed tools for allosteric pocket detection. Tools such as Allosite 145 or Cryptosite 148 utilize pocket detection methods in conjunction with ASD to train machine learning algorithms, for example, SVD, 145,148 or Random Forests 147,155,156 to predict allosteric sites.…”

Section: Methodsmentioning

confidence: 99%

Rational design of allosteric modulators: Challenges and successes

Chatzigoulas

Cournia

2021

WIREs Comput Mol Sci

View full text Add to dashboard Cite

Recent advances in structural biology and computational techniques have revealed allosteric mechanisms for an abundance of targets leading to the establishment of rational design of allosteric modulators as a new avenue for drug discovery. Considering that allostery is an intrinsic property of the protein conformational ensemble, allosteric drug design has the potential to develop into an innovative approach to modulate the dysregulation of therapeutic targets that are considered to be undruggable at their orthosteric site, explore strategic design opportunities to tackle new chemical space, or develop mutant-specific therapies to target mutations occurring far from the enzyme active site. Traditionally, allosteric drug discovery has been performed through high-throughput screening or through serendipitous discoveries; however, recent developments in structure-based and ligand-based methods have led to exciting advancements of designing bioactive allosteric ligands rationally. In this review article, we highlight the advantages and disadvantages of allosteric modulators and present structure-based and ligand-based drug design methodologies for the identification of allosteric binding sites and allosteric modulators. We also illustrate representative studies for allosteric modulators design for proteins belonging to a wide range of protein families, also considering irreversible binding with covalent allosteric modulators. Additionally, we analyze challenges and successes in the rational design of allosteric inhibitors and activators. Finally, we present the future of rational allosteric ligand design with newly built computational tools that we expect to be applied in future studies, concluding to theoretical and practical guidelines for allosteric ligand design strategies and identify knowledge gaps that need to be addressed to improve efficiency in allosteric drug design.

show abstract

ALLO: A tool to discriminate and prioritize allosteric pockets

Cited by 19 publications

References 26 publications

A compact vocabulary of paratope-epitope interactions enables predictability of antibody-antigen binding

A compact vocabulary of paratope-epitope interactions enables predictability of antibody-antigen binding

Coupling dynamics and evolutionary information with structure to identify protein regulatory and functional binding sites

Rational design of allosteric modulators: Challenges and successes

Contact Info

Product

Resources

About