State of the art prediction of HIV-1 protease cleavage sites

Rögnvaldsson, Thorsteinn; You, Liwen; Garwicz, Daniel

doi:10.1093/bioinformatics/btu810

Cited by 48 publications

(67 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently (March 2015), a paper entitled "State of the art prediction of HIV-1 protease cleavage sites," by R€ ognvaldsson, You and Garwicz, was published in the journal Bioinformatics, which purports that, in the context of increased data availability, the "state of the art" for this problem is achieved using an LSVM and orthogonal encoding, which outperforms a number of direct physicochemical encodings combined with an SVM using a (nonlinear) radial basis function kernel (RSVM). 25 The good performance for orthogonal encoding combined with linear classifiers on this problem has been corroborated by a number of sources.…”

Section: Literature Reviewmentioning

confidence: 85%

“…8,25 For this reason, the {746, 1625, Schilling} data sets were used for training the classifiers and the Impens dataset used to evaluate the classifiers. The Impens data set was selected for generating the performance measures as it has not been used in the definition or evaluation of any of the physicochemical encodings we wish to evaluate, removing the possibility of a resubstitution error.…”

Section: Resultsmentioning

confidence: 99%

“…Additionally, a benchmark has been published for this experiment using the current state of the art approach. 25 …”

Section: Resultsmentioning

confidence: 99%

“…36 Although G€ ok and € Ozcerit found the use of OETMAP encoding to offer an improvement over orthogonal encoding, later evaluations by R€ ognvaldsson et al on a larger dataset found it to in fact be inferior to orthogonal encoding. 25 Later work by G€ ok further evaluated the use of physicochemical properties. 37 Each of the 544 physicochemical properties in the AAindex was evaluated individually using an encoding where the non-zero values in an orthogonal encoding are replaced by the corresponding value from the scale.…”

Section: Literature Reviewmentioning

confidence: 99%

“…51 Additionally, previous wet lab research has suggested that HIV-1 protease specificity depends on the conformation of the substrate, rather than the recognition of specific amino acids. 20 Orthogonal encoding, as was employed in the recently published state of the art for detecting HIV-1 protease cleavage points in a peptide, 25 can be considered only an indirect encoding of such properties of the amino acids from which the learning algorithm must derive its own interpretation and estimates of values. However, it is not apparent if there is currently sufficient available training data (and of sufficient quality) to allow the learning algorithms to infer these properties optimally from an orthogonal encoding.…”

Section: Literature Reviewmentioning

confidence: 99%

See 4 more Smart Citations

The importance of physicochemical characteristics and nonlinear classifiers in determining HIV-1 protease specificity

Manning

Walsh

2016

Bioengineered

View full text Add to dashboard Cite

This paper reviews recent research relating to the application of bioinformatics approaches to determining HIV-1 protease specificity, outlines outstanding issues, and presents a new approach to addressing these issues. Leading machine learning theory for the problem currently suggests that the direct encoding of the physicochemical properties of the amino acid substrates is not required for optimal performance. A number of amino acid encoding approaches which incorporate potentially relevant physicochemical properties of the substrate are identified, and are evaluated using a nonlinear task decomposition based neuroevolution algorithm. The results are evaluated, and compared against a recent benchmark set on a nonlinear classifier using only amino acid sequence and identity information. Ensembles of these nonlinear classifiers using the physicochemical properties of the substrate are demonstrated to consistently outperform the recently published state-of-the-art linear support vector machine based approach in out-of-sample evaluations.

show abstract

Section: Literature Reviewmentioning

confidence: 85%

Section: Resultsmentioning

confidence: 99%

“…Additionally, a benchmark has been published for this experiment using the current state of the art approach. 25 …”

Section: Resultsmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

See 3 more Smart Citations

The importance of physicochemical characteristics and nonlinear classifiers in determining HIV-1 protease specificity

Manning

Walsh

2016

Bioengineered

View full text Add to dashboard Cite

show abstract

Potentiation of Drug Toxicity through Virus Latency Reversal Promotes Preferential Elimination of HIV Infected Cells

Tung

Hayn

Riber

et al. 2022

Advanced Therapeutics

View full text Add to dashboard Cite

Eliminating latently infected cells is a highly challenging, indispensable step toward the cure for HIV/AIDS. Hypothesis put forward herein is that the unique HIV protease cut site (Phe‐Pro) can be reconstructed using a potent inhibitor of tubulin polymerization, monomethyl auristatin F (MMAF), which features Phe at its C‐terminus. This presents opportunities to design prodrugs that are specifically activated by the HIV protease. To this end, a series of MMAF derivatives is synthesized and evaluated in cell culture using latently HIV‐infected cells. The cytotoxicity of compounds is indeed enhanced upon latency reversal by up to 11‐fold. As a result, in a mixed cell population, nanomolar concentrations of the lead compounds depletes predominantly the HIV‐infected cells and in doing so markedly enriches the pool of the uninfected cells. Affinity of the lead compounds to the viral protease is validated computationally and experimentally but despite expectations, the mechanism of action of the synthesized toxins is shown to be independent from the enzymatic activity of the HIV protease.

show abstract

A combined cheminformatic and bioinformatic approach to address the proteolytic stability challenge in peptide‐based drug discovery

et al. 2015

View full text Add to dashboard Cite

We have created models to predict cleavage sites for several human proteases including caspase-1, caspase-3, caspase-6, caspase-7, cathepsin B, cathepsin D, cathepsin G, cathepsin K, cathepsin L, elastase-2, granzyme A, granzyme B, matrix metallopeptidase-2 (MMP2), MMP7, MMP9, thrombin, and trypsin-1. Rather than representing the sequence pattern around the potential cleavage site through a series of flags with each flag representing one of the 20 standard amino acids, we first represent each amino acid by its calculated properties. For these calculated properties, we use validated cheminformatic descriptors, such as molecular weight, logP, and polar surface area, of the individual amino acids. Finally, the cleavage site-specific descriptors are calculated through various combinations of the individual amino acid descriptors for the residues surrounding the cleavage site. Some of these combinations do not take into account the location of the residue, as long as it is in a prescribed neighborhood of the potential cleavage site, whereas others are sensitive to the precise order of the residues in the sequence. The key advantage of this approach is that it allows one to perform meaningful calculations with nonstandard amino acids for which little or no data exists. Finally, using both docking and molecular dynamics simulations, we examine the potential for and limitations of protease crystal structures to impact the design of proteolytically stable peptides.

show abstract

State of the art prediction of HIV-1 protease cleavage sites

Abstract: thorsteinn.rognvaldsson@hh.se.

Cited by 48 publications

References 35 publications

The importance of physicochemical characteristics and nonlinear classifiers in determining HIV-1 protease specificity

The importance of physicochemical characteristics and nonlinear classifiers in determining HIV-1 protease specificity

Potentiation of Drug Toxicity through Virus Latency Reversal Promotes Preferential Elimination of HIV Infected Cells

A combined cheminformatic and bioinformatic approach to address the proteolytic stability challenge in peptide‐based drug discovery

Contact Info

Product

Resources

About