Evaluating explorative prediction power of machine learning algorithms for materials discovery using k-fold forward cross-validation

Z Xiong, Y Cui, Z Liu, Y Zhao, M Hu, J Hu - Computational Materials …, 2020 - Elsevier
predictor should achieve high exploration accuracy. On the other hand, predictors that cannot
predict … then split into three sets – first 10%, middle 80%, and last 10%. The middle set is …

UFold: fast and accurate RNA secondary structure prediction with deep learning

L Fu, Y Cao, J Wu, Q Peng, Q Nie… - Nucleic acids research, 2022 - academic.oup.com
… over time, reaching a performance ceiling of about 80% (32). It … HIT 80 to remove any
sequences that have similarity over 80% … UFold can achieve a similar performance on …

RNA secondary structure prediction using an ensemble of two-dimensional deep neural networks and transfer learning

J Singh, J Hanson, K Paliwal, Y Zhou - Nature communications, 2019 - nature.com
Obtaining functional clues for noncoding RNAs requires accurate base-pairing or
secondary-structure prediction… sequences with annotated secondary structure from bpRNA 34 at …

RNA secondary structure prediction using deep learning with thermodynamic integration

K Sato, M Akiyama, Y Sakakibara - Nature communications, 2021 - nature.com
secondary structure prediction from single sequences, and our method, which is able to achieve
high accuracy … EST 44 , with a cutoff threshold of 80%, and discarded sequences whose …

[HTML][HTML] Highly accurate protein structure prediction with AlphaFold

…, M Figurnov, O Ronneberger, K Tunyasuvunakool… - nature, 2021 - nature.com
accurate end-to-end structure prediction, a new equivariant attention architecture, use of
intermediate losses to achieve iterative refinement of predictions… fewer than 80 amino acids had …

Improving prediction of protein secondary structure, backbone angles, solvent accessibility and contact numbers by using predicted contact maps and an ensemble of …

J Hanson, K Paliwal, T Litfin, Y Yang, Y Zhou - Bioinformatics, 2019 - academic.oup.com
… to achieving high performance for the accuracy of predicting … model, we performed 10-fold
Cross Validation (CV) on our … the 10 folds) against Model 0’s performance on the Validation

Predicting protein structural classes for low-similarity sequences by evaluating different features

XJ Zhu, CQ Feng, HY Lai, W Chen, L Hao - Knowledge-Based Systems, 2019 - Elsevier
… through grid search with 10-fold cross validation in the LibSVM … that the maximum accuracy
was achieved by combining … feature for protein structural class prediction. Comparative …

Easy and accurate protein structure prediction using ColabFold

G Kim, S Lee, E Levy Karin, H Kim, Y Moriwaki… - Nature …, 2024 - nature.com
… made significant strides toward achieving this goal. AlphaFold2 … capable of producing protein
structure predictions nearly … In addition, through 16 iterations, a total of 80 predicted protein

Combination of Support Vector Machine and K-Fold cross validation to predict compressive strength of concrete in marine environment

H Ling, C Qian, W Kang, C Liang, H Chen - Construction and Building …, 2019 - Elsevier
… built to compare the prediction precision with SVM model. … In the dataset, 80 groups of data
were employed as the … and lower the difficulty of obtaining wanted papers, the parameter of …

Short-Term Photovoltaic Power Output Prediction Based on k-Fold Cross-Validation and an Ensemble Model

R Zhu, W Guo, X Gong - Energies, 2019 - mdpi.com
… The k-fold cross-validation method can effectively improve the … can achieve higher prediction
accuracy than a single model. … selected 80% of the samples as the training set and 10% of …