Several models of long short-term memory (LSTM) neural networks were constructed. Each model was trained on the complete mouse genome to predict the exon–intron structure of a gene. The performance of the neural networks was compared using a test sample and experimental sequencing data obtained using rat brain cell cultures after treatment with spicing inhibitors.

中文翻译：

---

用于预测基因外显子-内含子结构的长短期记忆神经网络

构建了多个长短期记忆 (LSTM) 神经网络模型。每个模型都在完整的小鼠基因组上进行训练，以预测基因的外显子 - 内含子结构。神经网络的性能使用测试样本和使用加香料抑制剂处理后的大鼠脑细胞培养物获得的实验测序数据进行比较。