CoGANPPIS: Coevolution-enhanced Global Attention Neural Network for Protein-Protein Interaction Site Prediction

Protein-protein interactions are essential in biochemical processes. Accurate prediction of the protein-protein interaction sites (PPIs) deepens our understanding of biological mechanism and is crucial for new drug design. However, conventional experimental methods for PPIs prediction are costly and time-consuming so that many computational approaches, especially ML-based methods, have been developed recently. Although these approaches have achieved gratifying results, there are still two limitations: (1) Most models have excavated some useful input features, but failed to take coevolutionary features into account, which could provide clues for inter-residue relationships; (2) The attention-based models only allocate attention weights for neighboring residues, instead of doing it globally, neglecting that some residues being far away from the target residues might also matter. We propose a coevolution-enhanced global attention neural network, a sequence-based deep learning model for PPIs prediction, called CoGANPPIS. It utilizes three layers in parallel for feature extraction: (1) Local-level representation aggregation layer, which aggregates the neighboring residues' features; (2) Global-level representation learning layer, which employs a novel coevolution-enhanced global attention mechanism to allocate attention weights to all the residues on the same protein sequences; (3) Coevolutionary information learning layer, which applies CNN & pooling to coevolutionary information to obtain the coevolutionary profile representation. Then, the three outputs are concatenated and passed into several fully connected layers for the final prediction. Application on two benchmark datasets demonstrated a state-of-the-art performance of our model. The source code is publicly available at https://github.com/Slam1423/CoGANPPIS_source_code.

A Multi-Task Learning Framework for Overcoming the Catastrophic Forgetting in Automatic Speech Recognition

Recently, data-driven based Automatic Speech Recognition (ASR) systems have achieved state-of-the-art results. And transfer learning is often used when those existing systems are adapted to the target domain, e.g., fine-tuning, retraining. However, in the processes, the system parameters may well deviate too much from the previously learned parameters. Thus, it is difficult for the system training process to learn knowledge from target domains meanwhile not forgetting knowledge from the previous learning process, which is called as catastrophic forgetting (CF). In this paper, we attempt to solve the CF problem with the lifelong learning and propose a novel multi-task learning (MTL) training framework for ASR. It considers reserving original knowledge and learning new knowledge as two independent tasks, respectively. On the one hand, we constrain the new parameters not to deviate too far from the original parameters and punish the new system when forgetting original knowledge. On the other hand, we force the new system to solve new knowledge quickly. Then, a MTL mechanism is employed to get the balance between the two tasks. We applied our method to an End2End ASR task and obtained the best performance in both target and original datasets.

Hard Sample Mining for the Improved Retraining of Automatic Speech Recognition

It is an effective way that improves the performance of the existing Automatic Speech Recognition (ASR) systems by retraining with more and more new training data in the target domain. Recently, Deep Neural Network (DNN) has become a successful model in the ASR field. In the training process of the DNN based methods, a back propagation of error between the transcription and the corresponding annotated text is used to update and optimize the parameters. Thus, the parameters are more influenced by the training samples with a big propagation error than the samples with a small one. In this paper, we define the samples with significant error as the hard samples and try to improve the performance of the ASR system by adding many of them. Unfortunately, the hard samples are sparse in the training data of the target domain, and manually label them is expensive. Therefore, we propose a hard samples mining method based on an enhanced deep multiple instance learning, which can find the hard samples from unlabeled training data by using a small subset of the dataset with manual labeling in the target domain. We applied our method to an End2End ASR task and obtained the best performance.