AngularQA: Protein Model Quality Assessment with LSTM Networks

Conover, Matthew; Staples, Max; Si, Dong; Ming, Sun; Cao, Renzhi

doi:10.1101/560995

Cited by 9 publications

(11 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ACC, MCC, SN, and SP values showed that SDM6A comprehensively outperformed i6mA-Pred and iDNA6mA by more than 3.1%–5.8%, 6.3%–11.8%, 0.5%–5.9%, and 5.9%, respectively (Table 3). It is generally assumed that DL methods perform better than do other ML-based algorithms, 32 which has been widely applied in protein structure and function prediction 33, 34, 35, 36, 37, 38, 39. However, SMD6A consistently outperformed the DL-based method, iDNA6mA, on both benchmark and independent datasets, further emphasizing that systematic selection of feature encodings and two-layer ensemble models are essential for improved prediction.…”

Section: Resultsmentioning

confidence: 99%

SDM6A: A Web-Based Integrative Machine-Learning Framework for Predicting 6mA Sites in the Rice Genome

Basith

Manavalan

Shin

et al. 2019

Molecular Therapy - Nucleic Acids

137

View full text Add to dashboard Cite

DNA N6-adenine methylation (6mA) is an epigenetic modification in prokaryotes and eukaryotes. Identifying 6mA sites in rice genome is important in rice epigenetics and breeding, but non-random distribution and biological functions of these sites remain unclear. Several machine-learning tools can identify 6mA sites but show limited prediction accuracy, which limits their usability in epigenetic research. Here, we developed a novel computational predictor, called the Sequence-based DNA N6-methyladenine predictor (SDM6A), which is a two-layer ensemble approach for identifying 6mA sites in the rice genome. Unlike existing methods, which are based on single models with basic features, SDM6A explores various features, and five encoding methods were identified as appropriate for this problem. Subsequently, an optimal feature set was identified from encodings, and corresponding models were developed individually using support vector machine and extremely randomized tree. First, all five single models were integrated via ensemble approach to define the class for each classifier. Second, two classifiers were integrated to generate a final prediction. SDM6A achieved robust performance on cross-validation and independent evaluation, with average accuracy and Matthews correlation coefficient (MCC) of 88.2% and 0.764, respectively. Corresponding metrics were 4.7%–11.0% and 2.3%–5.5% higher than those of existing methods, respectively. A user-friendly, publicly accessible web server (http://thegleelab.org/SDM6A) was implemented to predict novel putative 6mA sites in rice genome.

show abstract

Section: Resultsmentioning

confidence: 99%

SDM6A: A Web-Based Integrative Machine-Learning Framework for Predicting 6mA Sites in the Rice Genome

Basith

Manavalan

Shin

et al. 2019

Molecular Therapy - Nucleic Acids

137

View full text Add to dashboard Cite

show abstract

“…It shows that the predictions of MASS are significantly different to the predictions of QAcon, ProQ3, and SVMQA. We also evaluated our method using 57 targets in CASP13 experiment along with 16 methods participating in CASP13 including ModFOLD7 series [15], FaeNNz, ProQ4 [14], MESHI series, VoroMQA series [44], MULTICOM-NOVEL, Bhattacharya-SingQ, Bhattacharya-Server, PLU-AngularQA [45], and PLU-TopQA (methods having missing models or targets were excluded). The results are shown in Table 3 for stage 2 and Additional file 1: Table S8 for stage 1.…”

Section: Resultsmentioning

confidence: 99%

MASS: predict the global qualities of individual protein models using random forests and novel statistical potentials

Liu

Zheng

2020

BMC Bioinformatics

View full text Add to dashboard Cite

Background: Protein model quality assessment (QA) is an essential procedure in protein structure prediction. QA methods can predict the qualities of protein models and identify good models from decoys. Clustering-based methods need a certain number of models as input. However, if a pool of models are not available, methods that only need a single model as input are indispensable. Results: We developed MASS, a QA method to predict the global qualities of individual protein models using random forests and various novel energy functions. We designed six novel energy functions or statistical potentials that can capture the structural characteristics of a protein model, which can also be used in other protein-related bioinformatics research. MASS potentials demonstrated higher importance than the energy functions of RWplus, GOAP, DFIRE and Rosetta when the scores they generated are used as machine learning features. MASS outperforms almost all of the four CASP11 top-performing single-model methods for global quality assessment in terms of all of the four evaluation criteria officially used by CASP, which measure the abilities to assign relative and absolute scores, identify the best model from decoys, and distinguish between good and bad models. MASS has also achieved comparable performances with the leading QA methods in CASP12 and CASP13.

show abstract

“…Although the proposed predictor has shown an excellent performance over the other methods, there is still room for improvement. This includes exploration of other ML algorithms such as decision tree-based [31,32] and neural network-based algorithms [33,34,35] on the same dataset, incorporation of novel features and computational approach as implemented in References [36,37,38,39], and increasing the size of the training dataset based on the future experimental data. Furthermore, we implemented our proposed algorithm in the form of user-friendly web-server () for the wider research community to use.…”

Section: Discussionmentioning

confidence: 99%

mACPpred: A Support Vector Machine-Based Meta-Predictor for Identification of Anticancer Peptides

Boopathi

Subramaniyam

Malik

et al. 2019

IJMS

151

109

View full text Add to dashboard Cite

Anticancer peptides (ACPs) are promising therapeutic agents for targeting and killing cancer cells. The accurate prediction of ACPs from given peptide sequences remains as an open problem in the field of immunoinformatics. Recently, machine learning algorithms have emerged as a promising tool for helping experimental scientists predict ACPs. However, the performance of existing methods still needs to be improved. In this study, we present a novel approach for the accurate prediction of ACPs, which involves the following two steps: (i) We applied a two-step feature selection protocol on seven feature encodings that cover various aspects of sequence information (composition-based, physicochemical properties and profiles) and obtained their corresponding optimal feature-based models. The resultant predicted probabilities of ACPs were further utilized as feature vectors. (ii) The predicted probability feature vectors were in turn used as an input to support vector machine to develop the final prediction model called mACPpred. Cross-validation analysis showed that the proposed predictor performs significantly better than individual feature encodings. Furthermore, mACPpred significantly outperformed the existing methods compared in this study when objectively evaluated on an independent dataset.

show abstract

AngularQA: Protein Model Quality Assessment with LSTM Networks

Cited by 9 publications

References 27 publications

SDM6A: A Web-Based Integrative Machine-Learning Framework for Predicting 6mA Sites in the Rice Genome

SDM6A: A Web-Based Integrative Machine-Learning Framework for Predicting 6mA Sites in the Rice Genome

MASS: predict the global qualities of individual protein models using random forests and novel statistical potentials

mACPpred: A Support Vector Machine-Based Meta-Predictor for Identification of Anticancer Peptides

Contact Info

Product

Resources

About