Fig. 3: Deep learning strategies used in competition.
From: Deep learning models for predicting RNA degradation via dual crowdsourcing
a, Public test versus private test performance of all teams in the Kaggle challenge. Black star: experimental error. Red star: DegScore baseline model13. Orange star: DegScore-XGB model using DegScore featurization with XGBoost. Purple star: baseline kernel used by many top-performing teams. b, Distance embedding used to represent nucleotide proximity to other nucleotides in secondary structure. c, Schematic of the single neural net (NN) architecture used by the first-placed solution. This solution combined two sets of features into a single NN architecture, which combined elements of classic recurrent neural networks and convolutional neural networks. d, Schematic of the full solution pipeline for the second-placed solution. This solution combined single-model neural networks, similar to the ones used for the first-placed solution, with more complex second- and third-level stacking using XGBoost25 as the higher level learner. Abbreviations in schematics: CNN: convolutional neural network, GRU: gated recurrent unit, GNN: graph neural network, LSTM: long short-term memory neural network, SN: signal-noise, XGB: XGBoost.
