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 with several simple yet effective strategies
in this work: (1) a multi-task training strategy, which takes the DTA
prediction and the masked language modeling (MLM) task on the paired
drug-target dataset; (2) a semi-supervised training method to empower the drug
and target representation learning by leveraging large-scale unpaired molecules
and proteins in training, which differs from previous pre-training and
fine-tuning methods that only utilize molecules or proteins in pre-training;
and (3) a cross-attention module to enhance the interaction between drug and
target representation. Extensive experiments are conducted on three real-world
benchmark datasets: BindingDB, DAVIS and KIBA. The results show that our
framework significantly outperforms existing methods and achieves
state-of-the-art performances, e.g., $0.712$ RMSE on BindingDB IC$_{50}$
measurement with more than $5\%$ improvement than previous best work. In
addition, case studies on specific drug-target binding activities, drug feature
visualizations, and real-world applications demonstrate the great potential of
our work. The code and data are released at this https URL

本文提出了一种基于深度学习的多任务训练、半监督学习和交叉注意力模块的方法，预测药物 - 靶标亲和性，有效地应用于药物设计和制造过程中，实验结果显示此方法具有较高的准确性和广泛的应用前景。

SMT-DTA: 半监督多任务训练提高药物 - 靶标亲和力预测

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

The Evidential regression network (ENet) estimates a continuous target and
its predictive uncertainty without costly Bayesian model averaging. However, it
is possible that the target is inaccurately predicted due to the gradient
shrinkage problem of the original loss function of the ENet, the negative log
marginal likelihood (NLL) loss. In this paper, the objective is to improve the
prediction accuracy of the ENet while maintaining its efficient uncertainty
estimation by resolving the gradient shrinkage problem. A multi-task learning
(MTL) framework, referred to as MT-ENet, is proposed to accomplish this aim. In
the MTL, we define the Lipschitz modified mean squared error (MSE) loss
function as another loss and add it to the existing NLL loss. The Lipschitz
modified MSE loss is designed to mitigate the gradient conflict with the NLL
loss by dynamically adjusting its Lipschitz constant. By doing so, the
Lipschitz MSE loss does not disturb the uncertainty estimation of the NLL loss.
The MT-ENet enhances the predictive accuracy of the ENet without losing
uncertainty estimation capability on the synthetic dataset and real-world
benchmarks, including drug-target affinity (DTA) regression. Furthermore, the
MT-ENet shows remarkable calibration and out-of-distribution detection
capability on the DTA benchmarks.

提出了一种多任务学习框架 MT-ENet，通过将 Lipschitz 修正均方误差（MSE）损失函数添加到负对数边缘似然 (NLL) 损失中，动态调整 Lipschitz 常数，以解决 Evidential regression network (ENet) 的梯度收缩问题，并提高其预测精度，同时保持其良好的不确定性估计能力，该方法在药物 - 靶标亲和力 (DTA) 回归等实际基准测试中表现出了出色的校准和超出分布检测能力。