Feiyun Zhu

Seq2seq Fingerprint: An Unsupervised Deep Molecular Embedding for Drug Discovery

Many of todays drug discoveries require expertise knowledge and insanely expensive biological experiments for identifying the chemical molecular properties. However, despite the growing interests of using supervised machine learning algorithms to automatically identify those chemical molecular properties, there is little advancement of the performance and accuracy due to the limited amount of training data. In this paper, we propose a novel unsupervised molecular embedding method, providing a continuous feature vector for each molecule to perform further tasks, e.g., solubility classification. In the proposed method, a multi-layered Gated Recurrent Unit (GRU) network is used to map the input molecule into a continuous feature vector of fixed dimensionality, and then another deep GRU network is employed to decode the continuous vector back to the original molecule. As a result, the continuous encoding vector is expected to contain rigorous and enough information to recover the original molecule and predict its chemical properties. The proposed embedding method could utilize almost unlimited molecule data for the training phase. With sufficient information encoded in the vector, the proposed method is also robust and task-insensitive. The performance and robustness are confirmed and interpreted in our extensive experiments.

Deep Correlational Learning for Survival Prediction from Multi-modality Data

Technological advances have created a great opportunity to provide multi-view data for patients. However, due to the large discrepancy between different heterogeneous views, traditional survival models are unable to efficiently handle multiple modalities data as well as learn very complex interactions that can affect survival outcomes in various ways. In this paper, we develop a Deep Correlational Survival Model (DeepCorrSurv) for the integration of multi-view data. The proposed network consists of two sub-networks, view-specific and common sub-network. To remove the view discrepancy, the proposed DeepCorrSurv first explicitly maximizes the correlation among the views. Then it transfers feature hierarchies from view commonality and specifically fine-tunes on the survival regression task. Extensive experiments on real lung and brain tumor data sets demonstrated the effectiveness of the proposed DeepCorrSurv model using multiple modalities data across different tumor types.

WSISA: Making Survival Prediction from Whole Slide Histopathological Images

Image-based precision medicine techniques can be used to better treat cancer patients. However, the gigapixel resolution of Whole Slide Histopathological Images (WSIs) makes traditional survival models computationally impossible. These models usually adopt manually labeled discriminative patches from region of interests (ROIs) and are unable to directly learn discriminative patches from WSIs. We argue that only a small set of patches cannot fully represent the patients survival status due to the heterogeneity of tumor. Another challenge is that survival prediction usually comes with insufficient training patient samples. In this paper, we propose an effective Whole Slide Histopathological Images Survival Analysis framework (WSISA) to overcome above challenges. To exploit survival-discriminative patterns from WSIs, we first extract hundreds of patches from each WSI by adaptive sampling and then group these images into different clusters. Then we propose to train an aggregation model to make patient-level predictions based on cluster-level Deep Convolutional Survival (DeepConvSurv) prediction results. Different from existing state-of-the-arts image-based survival models which extract features using some patches from small regions of WSIs, the proposed framework can efficiently exploit and utilize all discriminative patterns in WSIs to predict patients survival status. To the best of our knowledge, this has not been shown before. We apply our method to the survival predictions of glioma and non-small-cell lung cancer using three datasets. Results demonstrate the proposed framework can significantly improve the prediction performance compared with the existing state-of-the-arts survival methods.

Cohesion-driven Online Actor-Critic Reinforcement Learning for mHealth Intervention

In the wake of the vast population of smart device users worldwide, mobile health (mHealth) technologies are hopeful to generate positive and wide influence on peoples health. They are able to provide flexible, affordable and portable health guides to devise users. Current online decision-making methods for mHealth assume that the users are completely heterogeneous. They share no information among users and learn a separate policy for each user. However, data for each user is very limited in size to support the separate online learning, leading to unstable policies that contain lots of variances. Besides, we find the truth that a user may be similar with some, but not all, users, and connected users tend to have similar behaviors. In this paper, we propose a network cohesion constrained (actor-critic) Reinforcement Learning (RL) method for mHealth. The goal is to explore how to share information among similar users to better convert the limited user information into sharper learned policies. To the best of our knowledge, this is the first online actor-critic RL for mHealth and first network cohesion constrained (actor-critic) RL method in all applications. The network cohesion is important to derive effective policies. We come up with a novel method to learn the network by using the warm start trajectory, which directly reflects the users property. The optimization of our model is difficult and very different from the general supervised learning due to the indirect observation of values. As a contribution, we propose two algorithms for the proposed online RLs. Apart from mHealth, the proposed methods can be easily applied or adapted to other health-related tasks. Extensive experiment results on the HeartSteps dataset demonstrates that in a variety of parameter settings, the proposed two methods obtain obvious improvements over the state-of-the-art methods.

Group-Driven Reinforcement Learning for Personalized mHealth Intervention

Due to the popularity of smartphones and wearable devices nowadays, mobile health (mHealth) technologies are promising to bring positive and wide impacts on peoples health. State-of-the-art decision-making methods for mHealth rely on some ideal assumptions. Those methods either assume that the users are completely homogenous or completely heterogeneous. However, in reality, a user might be similar with some, but not all, users. In this paper, we propose a novel group-driven reinforcement learning method for the mHealth. We aim to understand how to share information among similar users to better convert the limited user information into sharper learned RL policies. Specifically, we employ the K-means clustering method to group users based on their trajectory information similarity and learn a shared RL policy for each group. Extensive experiment results have shown that our method can achieve clear gains over the state-of-the-art RL methods for mHealth.

Robust Actor-Critic Contextual Bandit for Mobile Health (mHealth) Interventions

We consider the actor-critic contextual bandit for the mobile health (mHealth) intervention. State-of-the-art decision-making algorithms generally ignore the outliers in the data-set. In this paper, we propose a novel robust contextual bandit method for the mHealth. It can achieve the conflicting goal of reducing the influence of outliers, while seeking for a similar solution compared with the state-of-the-art contextual bandit methods on the datasets without outliers. Such performance relies on two technologies: (1) the capped-L2 norm; (2) a reliable method to set the threshold hyper-parameter, which is inspired by one of the most fundamental techniques in the statistics. Although the model is non-convex and non-differentiable, we propose an effective reweighted algorithm and provide solid theoretical analyses. We prove that the proposed algorithm can sufficiently decrease the objective function value at each iteration and will converge after a finite number of iterations. Extensive experiment results on two datasets demonstrate that our method can achieve almost identical results compared with state-of-the-art contextual bandit methods on the dataset without outliers, and significantly outperform those state-of-the-art methods on the badly noised dataset with outliers in a variety of parameter settings.

Seq3seq Fingerprint: Towards End-to-end Semi-supervised Deep Drug Discovery

Observing the recent progress in Deep Learning, the employment of AI is surging to accelerate drug discovery and cut R&D costs in the last few years. However, the success of deep learning is attributed to large-scale clean high-quality labeled data, which is generally unavailable in drug discovery practices. In this paper, we address this issue by proposing an end-to-end deep learning framework in a semi-supervised learning fashion. That is said, the proposed deep learning approach can utilize both labeled and unlabeled data. While labeled data is of very limited availability, the amount of available unlabeled data is generally huge. The proposed framework, named as seq3seq fingerprint, automatically learns a strong representation of each molecule in an unsupervised way from a huge training data pool containing a mixture of both unlabeled and labeled molecules. In the meantime, the representation is also adjusted to further help predictive tasks, e.g., acidity, alkalinity or solubility classification. The entire framework is trained end-to-end and simultaneously learn the representation and inference results. Extensive experiments support the superiority of the proposed framework.

PRIM: An Efficient Preconditioning Iterative Reweighted Least Squares Method for Parallel Brain MRI Reconstruction

The most recent history of parallel Magnetic Resonance Imaging (pMRI) has in large part been devoted to finding ways to reduce acquisition time. While joint total variation (JTV) regularized model has been demonstrated as a powerful tool in increasing sampling speed for pMRI, however, the major bottleneck is the inefficiency of the optimization method. While all present state-of-the-art optimizations for the JTV model could only reach a sublinear convergence rate, in this paper, we squeeze the performance by proposing a linear-convergent optimization method for the JTV model. The proposed method is based on the Iterative Reweighted Least Squares algorithm. Due to the complexity of the tangled JTV objective, we design a novel preconditioner to further accelerate the proposed method. Extensive experiments demonstrate the superior performance of the proposed algorithm for pMRI regarding both accuracy and efficiency compared with state-of-the-art methods.

Robust Contextual Bandit via the Capped- ℓ _2 ℓ 2 Norm for Mobile Health Intervention.

This paper considers the actor-critic contextual bandit for the mobile health (mHealth) intervention. The state-of-the-art decision-making methods in the mHealth generally assume that the noise in the dynamic system follows the Gaussian distribution. Those methods use the least-square-based algorithm to estimate the expected reward, which is prone to the existence of outliers. To deal with the issue of outliers, we are the first to propose a novel robust actor-critic contextual bandit method for the mHealth intervention. In the critic updating, the capped-(ell _{2}) norm is used to measure the approximation error, which prevents outliers from dominating our objective. A set of weights could be achieved from the critic updating. Considering them gives a weighted objective for the actor updating. It provides the ineffective sample in the critic updating with zero weights for the actor updating. As a result, the robustness of both actor-critic updating is enhanced. There is a key parameter in the capped-(ell _{2}) norm. We provide a reliable method to properly set it by making use of one of the most fundamental definitions of outliers in statistics. Extensive experiment results demonstrate that our method can achieve almost identical results compared with the state-of-the-art methods on the dataset without outliers and dramatically outperform them on the datasets noised by outliers.

Seq3seq fingerprint: towards end-to-end semi-supervised deep drug discovery

Observing the recent progress in Deep Learning, the employment of AI is surging to accelerate drug discovery and cut R&D costs in the last few years. However, the success of deep learning is attributed to large-scale clean high-quality labeled data, which is generally unavailable in drug discovery practices.n In this paper, we address this issue by proposing an end-to-end deep learning framework in a semi-supervised learning fashion. That is said, the proposed deep learning approach can utilize both labeled and unlabeled data. While labeled data is of very limited availability, the amount of available unlabeled data is generally huge. The proposed framework, named as seq3seq fingerprint, automatically learns a strong representation of each molecule in an unsupervised way from a huge training data pool containing a mixture of both unlabeled and labeled molecules. In the meantime, the representation is also adjusted to further help predictive tasks, e.g., acidity, alkalinity or solubility classification. The entire framework is trained end-to-end and simultaneously learn the representation and inference results. Extensive experiments support the superiority of the proposed framework.