SMT-DTA: Improving Drug-Target Affinity Prediction with Semi-supervised Multi-task Training

  title={SMT-DTA: Improving Drug-Target Affinity Prediction with Semi-supervised Multi-task Training},
  author={Qizhi Pei and Lijun Wu and Jinhua Zhu and Yingce Xia and Shufang Xia and Tao Qin and Haiguang Liu and Tie-Yan Liu},
Drug-Target Affinity (DTA) prediction is an essential task for drug discovery and pharmaceutical research. Accurate predictions of DTA can greatly benefit the design of new drug. As wet experiments are costly and time consuming, the supervised data for DTA prediction is extremely limited. This seriously hinders the application of deep learning based methods, which require a large scale of supervised data. To address this challenge and improve the DTA prediction accuracy, we propose a framework… 

Figures and Tables from this paper



Interpretable Drug Target Prediction Using Deep Neural Representation

This work proposes an end-to-end neural network model that predicts DTIs directly from low level representations and provides biological interpretation using two-way attention mechanism.

DeepPurpose: a deep learning library for drug–target interaction prediction

DeepPurpose is presented, a comprehensive and easy-to-use DL library for DTI prediction, which supports training of customizedDTI prediction models by implementing 15 compound and protein encoders and over 50 neural architectures, along with providing many other useful features.

Computational-experimental approach to drug-target interaction mapping: A case study on kinase inhibitors

A systematic computational-experimental framework for the prediction and pre-clinical verification of drug-target interactions using a well-established kernel-based regression algorithm as the prediction model is introduced and demonstrated that the kernel- based modeling approach offers practical benefits for probing novel insights into the mode of action of investigational compounds, and for the identification of new target selectivities for drug repurposing applications.

DeepDTA: deep drug–target binding affinity prediction

A deep learning based model that uses only sequence information of both targets and drugs to predict DT interaction binding affinities is proposed, outperforming the KronRLS algorithm and SimBoost, a state‐of‐the‐art method for DT binding affinity prediction.

Machine Learning for Drug-Target Interaction Prediction

A hierarchical classification scheme is adopted and several representative methods of each category of drug-target interaction prediction are introduced, especially the recent state-of-the-art methods.

Self-Attention Based Molecule Representation for Predicting Drug-Target Interaction

A new molecule representation based on the self-attention mechanism is proposed, and a new DTI model using this molecule representation outperforms the state of the art by up to 4.9% points in terms of area under the precision-recall curve.

TransformerCPI: improving compound-protein interaction prediction by sequence-based deep learning with self-attention mechanism and label reversal experiments

New datasets specific for CPI prediction are constructed, a novel transformer neural network named TransformerCPI is proposed, and a more rigorous label reversal experiment is introduced to test whether a model learns true interaction features.

SimBoost: a read-across approach for predicting drug–target binding affinities using gradient boosting machines

A method is presented called SimBoost that predicts continuous (non-binary) values of binding affinities of compounds and proteins and thus incorporates the whole interaction spectrum from true negative to true positive interactions and outperform the previously reported models across the studied datasets.

DeepCDA: deep cross-domain compound-protein affinity prediction through LSTM and convolutional neural networks

The results show that the proposed method learns a more reliable model for the test domain in more challenging situations.

DeepAffinity: Interpretable Deep Learning of Compound-Protein Affinity through Unified Recurrent and Convolutional Neural Networks

Under novel representations of structurally-annotatedprotein sequences, a semi-supervised deep learning model that unifies recurrent and convolutional neural networks has been proposed to exploit both unlabeled and labeled data, for jointly encoding molecular representations and predicting affinities.