Methods for a Rapid and Automated Description of Proteins

Guo, Zhanyong; Cremer, Dieter

doi:10.1002/9781119148739.ch7

Cited by 3 publications

(5 citation statements)

References 165 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although there is no right way of selecting a space curve to represent the protein backbone, by choosing the one selected for Melodia, we can have consistent results in our applications, assuring the reproducibility of Machine Learning experiments. References Røgen and Bohr (2002) and Guo and Cremer (2016) scrutinize the impact on the differential geometry by the choice of representation for the curve. In particular, reference Guo and Cremer (2016) clarifies the reason for choosing the cubic spline as the most satisfactory representation.…”

Section: Methodsmentioning

confidence: 99%

“…References Røgen and Bohr (2002) and Guo and Cremer (2016) scrutinize the impact on the differential geometry by the choice of representation for the curve. In particular, reference Guo and Cremer (2016) clarifies the reason for choosing the cubic spline as the most satisfactory representation.…”

Section: Methodsmentioning

confidence: 99%

“…All Melodia features are documented in Notebook tutorials ( Supplementary Appendix ), covering examples ranging from primary usage to more advanced structural analysis. An extensive study regarding this methodology can be found in Guo and Cremer (2016) .…”

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Melodia: a Python library for protein structure analysis

Montalvão,

Pitt,

Pinheiro

et al. 2024

Bioinformatics

View full text Add to dashboard Cite

Summary Analysing protein structure similarities is an important step in protein engineering and drug discovery. Methodologies that are more advanced than simple RMSD are available but often require extensive mathematical or computational knowledge for implementation. Grouping and optimising such tools in an efficient open-source library increases accessibility and encourages the adoption of more advanced metrics. Melodia is a Python library with a complete set of components devised for describing, comparing and analysing the shape of protein structures using differential geometry of three-dimensional curves and knot theory. It can generate robust geometric descriptors for thousands of shapes in just a few minutes. Those descriptors are more sensitive to structural feature variation than RMSD deviation. Melodia also incorporates sequence structural annotation and three-dimensional visualisations. Availability and implementation Melodia is an open-source Python library freely available on https://github.com/rwmontalvao/Melodia_py, along with interactive Jupyter Notebook tutorials. Supplementary information Supplementary data are available at Bioinformatics online.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Melodia: a Python library for protein structure analysis

Montalvão,

Pitt,

Pinheiro

et al. 2024

Bioinformatics

View full text Add to dashboard Cite

show abstract

“…However, these classifications often conflict with each other [ 46 ]. A more promising approach to determine protein fold based on secondary structure has been introduced by Ranganathan et al [ 35 ] and Guo and Cremer [ 47 ] coined Automated Protein Structure Analysis (APSA). The original idea behind APSA is based on the Unified Reaction Valley Approach (URVA) developed by Kraka et al [ 48 ], where a reaction path is characterized by its arc length, curvature, and torsion.…”

Section: Methods and Rationalementioning

confidence: 99%

“…The scalar curvature

is expressed as a function of arc length s

and the scalar torsion

where

is the norm and

is the vector triple product. A protein can then be represented by considering the curvature and torsion at the anchor points (locations of CA) forming a 1D vector with twice the the number of amino acids [ 35 , 47 ]. We limit the number of protein chains to 6 and the number of amino acids per chain as 1500 to have consistent input size.…”

Section: Methods and Rationalementioning

confidence: 99%

SSnet: A Deep Learning Approach for Protein-Ligand Interaction Prediction

Verma

Trozzi

et al. 2021

IJMS

View full text Add to dashboard Cite

Computational prediction of Protein-Ligand Interaction (PLI) is an important step in the modern drug discovery pipeline as it mitigates the cost, time, and resources required to screen novel therapeutics. Deep Neural Networks (DNN) have recently shown excellent performance in PLI prediction. However, the performance is highly dependent on protein and ligand features utilized for the DNN model. Moreover, in current models, the deciphering of how protein features determine the underlying principles that govern PLI is not trivial. In this work, we developed a DNN framework named SSnet that utilizes secondary structure information of proteins extracted as the curvature and torsion of the protein backbone to predict PLI. We demonstrate the performance of SSnet by comparing against a variety of currently popular machine and non-Machine Learning (ML) models using various metrics. We visualize the intermediate layers of SSnet to show a potential latent space for proteins, in particular to extract structural elements in a protein that the model finds influential for ligand binding, which is one of the key features of SSnet. We observed in our study that SSnet learns information about locations in a protein where a ligand can bind, including binding sites, allosteric sites and cryptic sites, regardless of the conformation used. We further observed that SSnet is not biased to any specific molecular interaction and extracts the protein fold information critical for PLI prediction. Our work forms an important gateway to the general exploration of secondary structure-based Deep Learning (DL), which is not just confined to protein-ligand interactions, and as such will have a large impact on protein research, while being readily accessible for de novo drug designers as a standalone package.

show abstract

Dieter Cremer's contribution to the field of theoretical chemistry

Kraka

Cremer²

2019

Int J of Quantum Chemistry

View full text Add to dashboard Cite

This legacy article reviews the contributions of Dieter Cremer (1944‐2017) to the field of theoretical chemistry, highlighting his major accomplishments in method development and applied quantum chemistry, which has led to many advances in the field. His work reflects an extraordinary breadth and deep understanding of theory, which is needed to solve complex chemical problems. His passion for science has inspired many colleagues in the past and will do so in the future.

show abstract

Methods for a Rapid and Automated Description of Proteins

Cited by 3 publications

References 165 publications

Melodia: a Python library for protein structure analysis

Melodia: a Python library for protein structure analysis

SSnet: A Deep Learning Approach for Protein-Ligand Interaction Prediction

Dieter Cremer's contribution to the field of theoretical chemistry

Contact Info

Product

Resources

About