Learning Based Methods for Code Runtime Complexity Prediction

Sikka, Jagriti; Satya, Kushal; Kumar, Yaman; Uppal, Shagun; Shah, Rajiv Ratn; Zimmermann, Roger

doi:10.1007/978-3-030-45439-5_21

Cited by 12 publications

(5 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…No significant difference in percent error was observed between the total number of base pairs computed by all RNA folding algorithms, with the largest discernible difference between Vsfold5 and Vienna (Adjusted P value = 0.9989). This agrees with current studies, as the challenge biotechnicians face instead lies within predictions in O(N3) and O(N4) time and space where N is the sequence length (using big O notation) [50]. While certain algorithms can reduce higher-ordered structures to O(N3), thereby reducing computational complexity, a growing minimal N value correlates with more possible making the algorithm less accurate [21].…”

Section: Assessment Of Percent Error Of In Total Base Pairs and Knott...supporting

confidence: 86%

Exploring the Accuracy of ab Initio Prediction Methods for Viral Pseudoknotted RNA Structures

Medeiros,

Pearl,

Carboni

et al. 2024

Preprint

View full text Add to dashboard Cite

The prediction of tertiary RNA structures is significant to the field of medicine (e.g. mRNA vaccines, genome editing), and the exploration of viral transcripts. Though many RNA folding software exist, few studies have condensed their locus of attention solely to viral pseudoknotted RNA. These regulatory pseudoknots play a role in genome replication, gene expression, and protein synthesis. This study explores five RNA folding engines that compute either the minimum free energy (MFE) or the maximum expected accuracy (MEA). These folding engines were tested against 26 experimentally derived short pseudoknotted sequences (20-150nt) using metrics that are commonly applied to software prediction accuracy (e.g. F1 scoring, PPV). This paper reports higher accuracy RNA prediction engines (pKiss) when compared to previous iterations of the software, and when compared to older folding engines. They show that MEA folding software does not always outperform MFE folding software in prediction accuracy when assessed with metrics such as percent error, sensitivity, PPV, and F1 scoring when applied to viral pseudoknotted RNA. Moreover, the results suggest that thermodynamic model parameters will not ensure accuracy if auxiliary parameters such as Mg2+ binding, dangling end options, and H-type penalties are not applied. The observations reported in this paper highlight the quality between different ab initio prediction methods while enforcing the idea that a better understanding of intracellular thermodynamics is necessary for a more efficacious screening of RNAs.

show abstract

Section: Assessment Of Percent Error Of In Total Base Pairs and Knott...supporting

confidence: 86%

Exploring the Accuracy of ab Initio Prediction Methods for Viral Pseudoknotted RNA Structures

Medeiros,

Pearl,

Carboni

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

Section: Assessment Of Percent Error Of In Total Base Pairs and Knott...supporting

confidence: 86%

Exploring the accuracy of ab initio prediction methods for viral pseudoknotted RNA structures

Medeiros,

Pearl,

Carboni

et al. 2024

Preprint

View full text Add to dashboard Cite

The prediction of tertiary RNA structures is significant to the field of medicine (e.g. mRNA vaccines, genome editing), and the exploration of viral transcripts. Though many RNA folding software exist, few studies have condensed their locus of attention solely to viral pseudoknotted RNA. These regulatory pseudoknots play a role in genome replication, gene expression, and protein synthesis. This study explores five RNA folding engines that compute either the minimum free energy (MFE) or the maximum expected accuracy (MEA). These folding engines were tested against 26 experimentally derived short pseudoknotted sequences (20-150nt) using metrics that are commonly applied to software prediction accuracy (e.g. F1 scoring, PPV). This paper reports higher accuracy RNA prediction engines, such as pKiss, when compared to previous iterations of the software, and when compared to older folding engines. They show that MEA folding software does not always outperform MFE folding software in prediction accuracy when assessed with metrics such as percent error, sensitivity, PPV, and F1 scoring when applied to viral pseudoknotted RNA. Moreover, the results suggest that thermodynamic model parameters will not ensure accuracy if auxiliary parameters such as Mg2+ binding, dangling end options, and H-type penalties are not applied. The observations reported in this paper highlight the quality between different ab initio prediction methods while enforcing the idea that a better understanding of intracellular thermodynamics is necessary for a more efficacious screening of RNAs.

show abstract

“…Sikka et al [25] investigate the use of machine learning to automatically predict the code runtime complexity class (e.g., O(n 2 )) of short programs. To this end, they collected 933 Java implementations of various algorithms from a competitive programming platform and annotated each with the corresponding complexity class (i.e., one of O(1), O(log n), O(n), O(n log n), O(n 2 )).…”

Section: Code Runtime Complexity Classificationmentioning

confidence: 99%

“…Sentiment Classification [3], [18], [19] Informative App Review Detection [20] App Review Classification [21], [27] Self-Admitted Technical Debt Detection [22] Comment Classification [23] Code-Comment Coherence Prediction [24] Linguistic Smell Detection [2] Code Runtime Complexity Classification [25] Code Readability Prediction [26] Outcome…”

Section: Fine-tuning and Testingmentioning

confidence: 99%

Making the most of small Software Engineering datasets with modern machine learning

Prenner¹,

Robbes²

2021

Preprint

View full text Add to dashboard Cite

This paper provides a starting point for Software Engineering (SE) researchers and practitioners faced with the problem of training machine learning models on small datasets. Due to the high costs associated with labeling data, in Software Engineering, there exist many small (< 1 000 samples) and medium-sized (< 100 000 samples) datasets. While deep learning has set the state of the art in many machine learning tasks, it is only recently that it has proven effective on small-sized datasets, primarily thanks to pre-training, a semi-supervised learning technique that leverages abundant unlabelled data alongside scarce labelled data. In this work, we evaluate pre-trained Transformer models on a selection of 13 smaller datasets from the SE literature, covering both, source code and natural language. Our results suggest that pre-trained Transformers are competitive and in some cases superior to previous models, especially for tasks involving natural language; whereas for source code tasks, in particular for very small datasets, traditional machine learning methods often has the edge. In addition, we experiment with several techniques that ought to aid training on small datasets, including active learning, data augmentation, soft labels, self-training and intermediate-task fine-tuning, and issue recommendations on when they are effective. We also release all the data, scripts, and most importantly pre-trained models for the community to reuse on their own datasets.

show abstract

Learning Based Methods for Code Runtime Complexity Prediction

Cited by 12 publications

References 12 publications

Exploring the Accuracy of ab Initio Prediction Methods for Viral Pseudoknotted RNA Structures

Exploring the Accuracy of ab Initio Prediction Methods for Viral Pseudoknotted RNA Structures

Exploring the accuracy of ab initio prediction methods for viral pseudoknotted RNA structures

Making the most of small Software Engineering datasets with modern machine learning

Contact Info

Product

Resources

About