BCL::Contact–Low Confidence Fold Recognition Hits Boost Protein Contact Prediction and <i>De Novo</i> Structure Determination

Karakaş, Mert; Woetzel, Nils; Meiler, Jens

doi:10.1089/cmb.2009.0030

Cited by 5 publications

(6 citation statements)

References 67 publications

(85 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the context of CASP's assessment [56][57][58] for the advancement of methods of identifying 3D protein structures from their AA sequences, we observed that the template-based (3GA3_A) 3D FAM72A protein structure (with an overall Gfactor=−0.2) has a much reliable overall stereochemical and Binding interactions of FAM72A with Zn 2+ , Fe 3+ , and nucleic acid indicate that this protein may have a significant cellular function as a transcription factor, a finding that might be particularly interesting in view of FAM72A's role in cancer cell signaling [3] and may also interfere with enzymatic redox reactions [59][60][61].…”

Section: Discussionmentioning

confidence: 99%

Lead discovery and in silico 3D structure modeling of tumorigenic FAM72A (p17)

2014

View full text Add to dashboard Cite

FAM72A (p17) is a novel neuronal protein that has been linked to tumorigenic effects in non-neuronal tissue. Using state of the art in silico physicochemical analyses (e.g., I-TASSER, RaptorX, and Modeller), we determined the three-dimensional (3D) protein structure of FAM72A and further identified potential ligand-protein interactions. Our data indicate a Zn(2+)/Fe(3+)-containing 3D protein structure, based on a 3GA3_A model template, which potentially interacts with the organic molecule RSM ((2s)-2-(acetylamino)-N-methyl-4-[(R)-methylsulfinyl] butanamide). The discovery of RSM may serve as potential lead for further anti-FAM72A drug screening tests in the pharmaceutical industry because interference with FAM72A's activities via RSM-related molecules might be a novel option to influence the tumor suppressor protein p53 signaling pathways for the treatment of various types of cancers.

show abstract

Section: Discussionmentioning

confidence: 99%

Lead discovery and in silico 3D structure modeling of tumorigenic FAM72A (p17)

2014

View full text Add to dashboard Cite

show abstract

“…In the state-of-the-art of contact maps, some methods are trained in a balanced fashion with 50% positives and 50% negatives [29] or introducing a probability factor to reduce the training set [19], that looks for reducing the learning cycles. In our case, we don't reduce any positive instance from the training set because they are considering as restrictions.…”

Section: Training Of a Base Multiple Classifiermentioning

confidence: 99%

Tree-based Secondary Structure Interactions Predictor Method for Protein Contact Maps

Quintana-Zaez

Ruiz

Santiesteban-Toca

2018

CyS

View full text Add to dashboard Cite

Understanding the folding of proteins is one of the most interesting research field for the Bioinformatics. The contact maps constitute an intermediate step in the prediction of the 3D structure of the proteins and allow to represent folding patterns. Currently, the methods used to predict contact maps achieve low precision results, only about 25% of long-range (L/5) contacts are correctly predicted, and their knowledge base is not humanly interpretable. In this paper, we propose an easy implementation multiple classifier for contact maps, which is based on patterns of interaction between secondary structures and employed decision trees as base classifiers. This method is able to naturally reduce the level of imbalance between contact/non-contact classes. In addition, a set of interpretable rules are extracted as a complement to the prediction. The validation of method performance shows that an average of 45% of general contacts are correctly predicted. Moreover, a Z-score comparison of its longrange contacts predictions (L/5) with participant methods in CASP11 competition shows that it is competitive with the state-of-the-art methods.

show abstract

“…BCL::Contact [ 42 ] leverages sequence-based and physicochemical information. The physicochemical information comes from 32 different servers.…”

Section: Related Workmentioning

confidence: 99%

EPSILON-CP: using deep learning to combine information from multiple sources for protein contact prediction

2017

View full text Add to dashboard Cite

BackgroundAccurately predicted contacts allow to compute the 3D structure of a protein. Since the solution space of native residue-residue contact pairs is very large, it is necessary to leverage information to identify relevant regions of the solution space, i.e. correct contacts. Every additional source of information can contribute to narrowing down candidate regions. Therefore, recent methods combined evolutionary and sequence-based information as well as evolutionary and physicochemical information. We develop a new contact predictor (EPSILON-CP) that goes beyond current methods by combining evolutionary, physicochemical, and sequence-based information. The problems resulting from the increased dimensionality and complexity of the learning problem are combated with a careful feature analysis, which results in a drastically reduced feature set. The different information sources are combined using deep neural networks.ResultsOn 21 hard CASP11 FM targets, EPSILON-CP achieves a mean precision of 35.7% for top- L/10 predicted long-range contacts, which is 11% better than the CASP11 winning version of MetaPSICOV. The improvement on 1.5L is 17%. Furthermore, in this study we find that the amino acid composition, a commonly used feature, is rendered ineffective in the context of meta approaches. The size of the refined feature set decreased by 75%, enabling a significant increase in training data for machine learning, contributing significantly to the observed improvements.ConclusionsExploiting as much and diverse information as possible is key to accurate contact prediction. Simply merging the information introduces new challenges. Our study suggests that critical feature analysis can improve the performance of contact prediction methods that combine multiple information sources. EPSILON-CP is available as a webservice: http://compbio.robotics.tu-berlin.de/epsilon/ Electronic supplementary materialThe online version of this article (doi:10.1186/s12859-017-1713-x) contains supplementary material, which is available to authorized users.

show abstract

BCL::Contact–Low Confidence Fold Recognition Hits Boost Protein Contact Prediction and De Novo Structure Determination

Cited by 5 publications

References 67 publications

Lead discovery and in silico 3D structure modeling of tumorigenic FAM72A (p17)

Lead discovery and in silico 3D structure modeling of tumorigenic FAM72A (p17)

Tree-based Secondary Structure Interactions Predictor Method for Protein Contact Maps

EPSILON-CP: using deep learning to combine information from multiple sources for protein contact prediction

Contact Info

Product

Resources

About