科研速览 · Science Skim继续刷下去 · Keep skimming →
◆ Frontiers in artificial intelligence2026-01-01

A comparative evaluation of deep learning models for the classification of encoded splice-junction sequences.

Yogesh Kumar, Inderpreet Kaur, Nandini Modi, Priya Bhardwaj, Jaeyoung Choi, Muhammad Fazal Ijaz

一句话结论 · In one sentence

The highest held-out test accuracy (96.87%) was obtained with the Custom CNN from among the configurations that were saved. The MLP Mixer was the most highly accurate model during training (99.90%), but the model did not perform as well on the validation set (93.33%) or held-out test set (93.73%), suggesting some in-sample fitting. Model-capacity information, parameter-to-sample ratios, learning curves, class-wise metrics, and a targeted class-weighting comparison are reported. Class-weighting was performed during the training phase only, but class-weighting did not yield highest performance for the tested Custom CNN configuration. of the chosen Custom CNN configuration for the observed dataset.

原始摘要(英文原文)· Original abstract
INTRODUCTION: Computational classifiers can be benchmarked against public encoded splice-junction datasets, but the performance estimate will depend on the input representation, preprocessing pipeline, model set-up and evaluation design. METHODS: This study investigates the performance of 15 different Convolutional, Hybrid and Deep Learning architectures on a public encoded splice-junction dataset for 3-class classification. The results of the primary models were archived from one train/validation/held-out-test workflow and are presented as illustrative effects and not as statistically significant evidence of superiority. RESULTS: The highest held-out test accuracy (96.87%) was obtained with the Custom CNN from among the configurations that were saved. The MLP Mixer was the most highly accurate model during training (99.90%), but the model did not perform as well on the validation set (93.33%) or held-out test set (93.73%), suggesting some in-sample fitting. Model-capacity information, parameter-to-sample ratios, learning curves, class-wise metrics, and a targeted class-weighting comparison are reported. Class-weighting was performed during the training phase only, but class-weighting did not yield highest performance for the tested Custom CNN configuration. of the chosen Custom CNN configuration for the observed dataset. DISCUSSION: The conclusions are limited to the classification results that could be computed for the encoded benchmark dataset and the reported evaluation procedure. The results do not demonstrate a statistically significant superiority of the models in the sense of external generalization, clinical diagnostic validity, patient-based mutation detection, clinical utility or readiness for deployment. Leakage-free repeated evaluation, external datasets, stored sample predictions, statistically comparison of models' outputs, and clinically validated patient-level data would be needed for more general conclusions.
读原文 · Read the paper ↗

AI 追问PRO

登录后使用 AI 追问

讨论区

登录后参与讨论

相关论文 · Related

A comparative evaluation of deep learning models for the classification of encoded splice-junction sequences. — 科研速览 Science Skim