Deep Learning of Protein Structural Classes: Any Evidence for an ‘Urfold’?

Jaiswal, Menuka; Saleem, Saad; Kweon, Yonghyeon; Draizen, Eli J.; Veretnik, Stella; Mura, Cameron; Bourne, Philip E.

doi:10.1109/sieds49339.2020.9106642

Cited by 5 publications

(3 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our -based dataset (), each atom is attributed with the following seven groups of features, which are one-hot (Boolean) encoded: (i) Atom Type (, , , , , ); (ii) Residue Type (, , , , , , , , , , , , , , , , , , , , ); (iii) Secondary Structure (, , ); (iv) Hydrophobic (or not); (v) Electronegative (or not); (vi) Positively-charged (or not); and (vii) Solvent-exposed (or not). For all of the DeepUrfold final production models reported here, the “residue type” feature was omitted because it was found to be uninformative, at least for this type of representation (see Supp Info §3 and Supp Figs S4-5); interestingly, this finding about the dispensability of a residue-type feature was presaged in early work on this project (e.g., the receiver operating characteristic (ROC) curves in Fig 2 of ref [66]).…”

Section: Resultsmentioning

confidence: 99%

Deep Generative Models of Protein Structure Uncover Distant Relationships Across a Continuous Fold Space

Draizen

Veretnik

Mura

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Unresolved questions about the discrete/continuous dichotomy of protein fold space permeate structural and evolutionary biology. From protein structure comparison and classification to evolutionary analyses and function prediction, our views of fold space implicitly rest upon many assumptions that impact how we analyze, interpret and come to understand biological systems. Discrete views of fold space categorize similar folds into separate groups; unfortunately, such a ‘binning’ process inherently fails to capture many remote relationships. While hierarchical databases such as CATH, SCOP, and ECOD represent major steps forward in protein classification, we believe that a scalable, objective and conceptually flexible method that is less reliant upon assumptions and heuristics could enable a more systematic and thorough exploration of fold space and evolutionary-distant relationships. Here, we develop a structure-guided, comparative analysis of proteins, leveraging embeddings derived from deep generative models, which represent a highly-compressed, lower-dimensional space of a given protein and its sequence, structure and biophysical properties. Building upon a recent ‘Urfold’ model of protein structure, the deep generative approach developed here, termed ‘DeepUrfold’, suggests a new, mostly-continuous view of fold space—a view that extends beyond simple 3D structural/geometric similarity, towards the realm of integrated sequence↔structure↔function properties. We find that such an approach can quantitatively represent and detect evolutionarily-remote relationships that are not captured by existing methods.

show abstract

Section: Resultsmentioning

confidence: 99%

Deep Generative Models of Protein Structure Uncover Distant Relationships Across a Continuous Fold Space

Draizen

Veretnik

Mura

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…More recently, various ML methods have been applied to learn the statistical laws between feature descriptors of protein sequences in a training dataset and their corresponding structural classes, and to build a probabilistic model for classification purposes, as can been seen in a recent review on protein function prediction [38]. In the following, we focus on the very recent applications of ML methods in the prediction of PSC, which include artificial neural networks [15,22], support vector machine [23,26,50,77], K-nearest neighbor [16,17,46], random forest [4], logistic regression [78,79], and deep learning [80][81][82][83][84]. Table 3 provides a list of machine learning algorithms and their recent variants used as classification models in the prediction of proteins structural classes.…”

Section: Classification Modelsmentioning

confidence: 99%

Recent Advances in the Prediction of Protein Structural Classes: Feature Descriptors and Machine Learning Algorithms

Zhu

Davari

2021

Crystals

View full text Add to dashboard Cite

In the postgenomic age, rapid growth in the number of sequence-known proteins has been accompanied by much slower growth in the number of structure-known proteins (as a result of experimental limitations), and a widening gap between the two is evident. Because protein function is linked to protein structure, successful prediction of protein structure is of significant importance in protein function identification. Foreknowledge of protein structural class can help improve protein structure prediction with significant medical and pharmaceutical implications. Thus, a fast, suitable, reliable, and reasonable computational method for protein structural class prediction has become pivotal in bioinformatics. Here, we review recent efforts in protein structural class prediction from protein sequence, with particular attention paid to new feature descriptors, which extract information from protein sequence, and the use of machine learning algorithms in both feature selection and the construction of new classification models. These new feature descriptors include amino acid composition, sequence order, physicochemical properties, multiprofile Bayes, and secondary structure-based features. Machine learning methods, such as artificial neural networks (ANNs), support vector machine (SVM), K-nearest neighbor (KNN), random forest, deep learning, and examples of their application are discussed in detail. We also present our view on possible future directions, challenges, and opportunities for the applications of machine learning algorithms for prediction of protein structural classes.

show abstract

“…While all of the possible features are contained in the Prop3D-20sf dataset and undoubtedly will be somewhat correlated, it is possible for one to select only certain subsets of features of interest. We also create subsets of the Boolean features that we have found to be minimally correlated [46], and those can be selected, for example, in training deep neural networks.…”

Section: Introductionmentioning

confidence: 99%

Prop3D: A Flexible, Python-based Platform for Machine Learning with Protein Structural Properties and Biophysical Data

Draizen

Murillo

Readey

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Machine learning (ML) has a rich history in structural bioinformatics, and modern approaches, such as deep learning, are revolutionizing our knowledge of the subtle relationships between biomolecular sequence, structure, function, dynamics and evolution. As with any advance that rests upon statistical learning approaches, the recent progress in biomolecular sciences is enabled by the availability of vast volumes of sufficiently-variable data. To be of utility, such datasets must be well-structured, machine-readable, intelligible and manipulable. These and related requirements pose challenges that become especially acute at the computational scales typical in ML. Furthermore, in structural bioinformatics such data generally relate to protein three-dimensional (3D) structures, which are inherently far more complex than sequence-based data. A significant and recurring challenge concerns the creation of large, high-quality, openly-accessible datasets that can be used for specific training and benchmarking tasks in ML pipelines for predictive modeling projects, along with reproducible splits for training and testing. Here, we report Prop3D, a protein biophysical and evolutionary featurization and data-processing pipeline that we have developed and deployed—both in the cloud and on local HPC resources—in order to systematically and reproducibly create comprehensive datasets, using the Highly Scalable Data Service (HSDS). Prop3D and its associated 'Prop3D-20sf' dataset can be of broader utility, as a community-wide resource, for other structure-related workflows, particularly for tasks that arise at the intersection of deep learning and classical structural bioinformatics.

show abstract

Deep Learning of Protein Structural Classes: Any Evidence for an ‘Urfold’?

Cited by 5 publications

References 36 publications

Deep Generative Models of Protein Structure Uncover Distant Relationships Across a Continuous Fold Space

Deep Generative Models of Protein Structure Uncover Distant Relationships Across a Continuous Fold Space

Recent Advances in the Prediction of Protein Structural Classes: Feature Descriptors and Machine Learning Algorithms

Prop3D: A Flexible, Python-based Platform for Machine Learning with Protein Structural Properties and Biophysical Data

Contact Info

Product

Resources

About