We introduce a theoretical framework for diffusion-based image editing by formulating it as a reverse-time bridge modeling problem. This approach modifies the backward process of a pretrained diffusion model to construct a bridge that converges to an implicit distribution associated with the editing target at time 0. Building on this frame-work, we propose h-Edit, a novel editing method that utilizes Doob’s h-transform and Langevin Monte Carlo to decompose the update of an intermediate edited sample into two components: a "reconstruction" term and an "editing" term. This decomposition provides flexibility, allowing the reconstruction term to be computed via existing inversion techniques and enabling the combination of multiple editing terms to handle complex editing tasks. To our knowledge, h-Edit is the first training-free method capable of performing simultaneous text-guided and reward-model-based editing. Extensive experiments, both quantitative and qualitative, show that h-Edit outperforms state-of-the-art base-lines in terms of editing effectiveness and faithfulness.

Recovering Markov boundary-the minimal set of variables that maximizes predictive performance for a response variable-is crucial in many applications. While recent advances improve upon traditional constraint-based techniques by scoring local causal structures, they still rely on nonparametric estimators and heuristic searches, lacking theoretical guarantees for reliability. This paper investigates a framework for efficient Markov boundary discovery by integrating conditional entropy from information theory as a scoring criterion. We design a novel masked autoregressive network to capture complex dependencies. A parallelizable greedy search strategy in polynomial time is proposed, supported by analytical evidence. We also discuss how initializing a graph with learned Markov boundaries accelerates the convergence of causal discovery. Comprehensive evaluations on real-world and synthetic datasets demonstrate the scalability and superior performance of our method in both Markov boundary discovery and causal discovery tasks.

Existing score-based methods for directed acyclic graph (DAG) learning from observational data struggle to recover the causal graph accurately and sample-efficiently. To overcome this, in this study, we propose DrBO (DAG recovery via Bayesian Optimization)—a novel DAG learning framework leveraging Bayesian optimization (BO) to find high-scoring DAGs. We show that, by sophisticatedly choosing the promising DAGs to explore, we can find higher-scoring ones much more efficiently. To address the scalability issues of conventional BO in DAG learning, we replace Gaussian Processes commonly employed in BO with dropout neural networks, trained in a continual manner, which allows for (i) flexibly modeling the DAG scores without overfitting, (ii) incorporation of uncertainty into the estimated scores, and (iii) scaling with the number of evaluations. As a result, DrBO is computationally efficient and can find the accurate DAG in fewer trials and less time than existing state-of-the-art methods. This is demonstrated through an extensive set of empirical evaluations on many challenging settings with both synthetic and real data. Our implementation is available at https://github.com/baosws/DrBO.

Telling apart the cause and effect between two random variables with purely observational data is a challenging problem that finds applications in various scientific disciplines. A key principle utilized in this task is the algorithmic Markov condition, which postulates that the joint distribution, when factorized according to the causal direction, yields a more succinct codelength compared to the anti-causal direction. Previous approaches approximate these codelengths by relying on simple functions or Gaussian processes (GPs) with easily evaluable complexity, compromising between model fitness and computational complexity. To address these limitations, we propose leveraging the variational Bayesian learning of neural networks as an interpretation of the codelengths. This allows the improvement of model fitness, while maintaining the succinctness of the codelengths, and the avoidance of the significant computational complexity of the GP-based approaches. Extensive experiments on both synthetic and real-world benchmarks in cause-effect identification demonstrate the effectiveness of our proposed method, showing promising performance enhancements on several datasets in comparison to most related methods.

Diffusion bridges have shown potential in paired image-to-image (I2I) translation tasks. However, existing methods are limited by their unidirectional nature, requiring separate models for forward and reverse translations. This not only doubles the computational cost but also restricts their practicality. In this work, we introduce the Bidirectional Diffusion Bridge Model (BDBM), a scalable approach that facilitates bidirectional translation between two coupled distributions using a single network. BDBM leverages the Chapman-Kolmogorov Equation for bridges, enabling it to model data distribution shifts across timesteps in both forward and backward directions by exploiting the interchangeability of the initial and target timesteps within this framework. Notably, when the marginal distribution given endpoints is Gaussian, BDBM's transition kernels in both directions possess analytical forms, allowing for efficient learning with a single network. We demonstrate the connection between BDBM and existing bridge methods, such as Doob's h-transform and variational approaches, and highlight its advantages. Extensive experiments on high-resolution I2I translation tasks demonstrate that BDBM not only enables bidirectional translation with minimal additional cost but also outperforms state-of-the-art bridge models. Our source code is available at https://github.com/kvmduc/BDBM.

Long COVID, or Post-Acute Sequelae of SARS-CoV-2 infection (PASC), affects an estimated 10-20% of COVID-19 patients and presents persistent multisystemic symptoms. Although demographic and clinical factors, such as age, sex, and comorbidities, contribute to risk, the genetic mechanisms underlying this risk remain poorly defined. To address this gap, we developed a multi-omics framework that integrates Transcriptome-Wide Mendelian Randomization (TWMR), Control Theory (CT), Expression Quantitative Trait Loci (eQTL), Genome-Wide Association Studies (GWAS), RNA sequencing (RNA-seq), and Protein-Protein Interaction (PPI) network to identify putative causal genes and network drivers in Long COVID. Our approach prioritized 32 candidate genes, including 19 previously reported and 13 novel, with roles in the SARS-CoV-2 response, viral carcinogenesis, immune regulation, and cell cycle control. Enrichment analyses revealed a shared genetic architecture in syndromic, metabolic, autoimmune, and connective tissue disorders. Using causal gene expression profiles, we identified three distinct symptom-based subtypes of Long COVID, providing information on the heterogeneity of disease mechanisms and clinical presentation. Finally, we developed an open-source Shiny application for interactive exploration of these findings. Together, this integrative framework highlights novel causal mechanisms and therapeutic targets, advancing precision medicine strategies for Long COVID.

Identifying root causes of anomalies in causal processes is vital across disciplines. Once identified, one can isolate the root causes and implement necessary measures to restore the normal operation. Causal processes are often modelled as graphs with entities being nodes and their paths/interconnections as edge. Existing work only consider the contribution of nodes in the generative process, thus can not attribute the outlier score to the edges of the mechanism if the anomaly occurs in the connections. In this paper, we consider both individual edge and node of each mechanism when identifying the root causes. We introduce a noisy functional causal model to account for this purpose. Then, we employ Bayesian learning and inference methods to infer the noises of the nodes and edges. We then represent the functional form of a target outlier leaf as a function of the node and edge noises. Finally, we propose an efficient gradient-based attribution method to compute the anomaly attribution scores which scales linearly with the number of nodes and edges. Experiments on simulated datasets and two real-world scenario datasets show better anomaly attribution performance of the proposed method compared to the baselines. Our method scales to larger graphs with more nodes and edges.

Post-nonlinear (PNL) causal models stand out as a versatile and adaptable framework for modeling intricate causal relationships. However, accurately capturing the invertibility constraint required in PNL models remains challenging in existing studies. To address this problem, we introduce CAF-PoNo (Causal discovery via Normalizing Flows for Post-Nonlinear models), harnessing the power of the normalizing flows architecture to enforce the crucial invertibility constraint in PNL models. Through normalizing flows, our method precisely reconstructs the hidden noise, which plays a vital role in cause-effect identification through statistical independence testing. Furthermore, the proposed approach exhibits remarkable extensibility, as it can be seamlessly expanded to facilitate multivariate causal discovery via causal order identification, empowering us to efficiently unravel complex causal relationships. Extensive experimental evaluations on both simulated and real datasets consistently demonstrate that the proposed method outperforms several state-of-the-art approaches in both bivariate and multivariate causal discovery tasks.

Bayesian causal discovery offers the power to quantify epistemic uncertainties among a broad range of structurally diverse causal theories potentially explaining the data, represented in forms of directed acyclic graphs (DAGs). However, existing methods struggle with efficient DAG sampling due to the complex acyclicity constraint. In this study, we propose a scalable Bayesian approach to effectively learn the posterior distribution over causal graphs given observational data thanks to the ability to generate DAGs without explicitly enforcing acyclicity. Specifically, we introduce a novel differentiable DAG sampling method that can generate a valid acyclic causal graph by mapping an unconstrained distribution of implicit topological orders to a distribution over DAGs. Given this efficient DAG sampling scheme, we are able to model the posterior distribution over causal graphs using a simple variational distribution over a continuous domain, which can be learned via the variational inference framework. Extensive empirical experiments on both simulated and real datasets demonstrate the superior performance of the proposed model compared to several state-of-the-art baselines.

While most generative models show achievements in image data generation, few are developed for tabular data generation. Recently, due to success of large language models (LLM) in diverse tasks, they have also been used for tabular data generation. However, these methods do not capture the correct correlation between the features and the target variable, hindering their applications in downstream predictive tasks. To address this problem, we propose a LLM-based method with three important improvements to correctly capture the ground-truth feature-class correlation in the real data. First, we propose a novel permutation strategy for the input data in the fine-tuning phase. Second, we propose a feature-conditional sampling approach to generate synthetic samples. Finally, we generate the labels by constructing prompts based on the generated samples to query our fine-tuned LLM. Our extensive experiments show that our method significantly outperforms 10 SOTA baselines on 20 datasets in downstream tasks. It also produces highly realistic synthetic samples in terms of quality and diversity. More importantly, classifiers trained with our synthetic data can even compete with classifiers trained with the original data on half of the benchmark datasets, which is a significant achievement in tabular data generation.

Distinguishing the cause and effect from bivariate observational data is the foundational problem that finds applications in many scientific disciplines. One solution to this problem is assuming that cause and effect are generated from a structural causal model, enabling identification of the causal direction after estimating the model in each direction. The heteroscedastic noise model is a type of structural causal model where the cause can contribute to both the mean and variance of the noise. Current methods for estimating heteroscedas-tic noise models choose the Gaussian likelihood as the optimization objective which can be suboptimal and unstable when the data has a non-Gaussian distribution. To address this limitation, we propose a novel approach to estimating this model with Student's t-distribution, which is known for its robustness in accounting for sampling variability with smaller sample sizes and extreme values without significantly altering the overall distribution shape. This adaptability is beneficial for capturing the parameters of the noise distribution in het-eroscedastic noise models. Our empirical evaluations demonstrate that our estimators are more robust and achieve better overall performance across synthetic and real benchmarks.

We propose a novel approach for domain generalisation (DG) leveraging risk distributions to characterise domains, thereby achieving domain invariance. In our findings, risk distributions effectively highlight differences between training domains and reveal their inherent complexities. In testing, we may observe similar, or potentially intensifying in magnitude, divergences between risk distributions. Hence, we propose a compelling proposition: Minimising the divergences between risk distributions across training domains leads to robust invariance for DG. The key rationale behind this concept is that a model, trained on domain-invariant or stable features, may consistently produce similar risk distributions across various domains. Building upon this idea, we propose Risk Distribution Matching (RDM). Using the maximum mean discrepancy (MMD) distance, RDM aims to minimise the variance of risk distributions across training domains. However, when the number of domains increases, the direct optimisation of variance leads to linear growth in MMD computations, resulting in inefficiency. Instead, we propose an approximation that requires only one MMD computation, by aligning just two distributions: that of the worst-case domain and the aggregated distribution from all domains. Notably, this method empirically outperforms optimising distributional variance while being computationally more efficient. Unlike conventional DG matching algorithms, RDM stands out for its enhanced efficacy by concentrating on scalar risk distributions, sidestepping the pitfalls of high-dimensional challenges seen in feature or gradient matching. Our extensive experiments on standard benchmark datasets demonstrate that RDM shows superior generalisation capability over state-of-the-art DG methods.

In Class-Incremental Learning (Class-IL), deep neural networks often fail to learn a sequence of classes incrementally due to catastrophic forgetting, a phenomenon arising from the absence of exposure to old knowledge. To alleviate this issue, conventional rehearsal methods , such as experience replay, store a limited number of old exemplars and then interleave with the current data for joint learning and rehearsal. However, the networks following this training scheme might not successfully reduce forgetting due to the lack of direct consideration of relations between samples of previously learned and new classes. Drawing inspiration from how humans learn by noticing the similarities and differences between classes, we propose a novel Class-IL framework called Relational Replay (RR). RR learns and recalls relations between images across all classes over time. To ensure these relations remain intrinsic and robust to forgetting, we incorporate causal reasoning to RR, resulting in Causal Relational Replay (CRR). CRR analyzes these relations using a causality perspective, aiming to identify intrinsic relations rooted in the images’ semantic features, serving as the cause of these relations. Our proposed method shows a competitive performance compared to the state-of-the-art rehearsal methods in Class-IL with clear and consistent improvements in the majority of settings on standard benchmark datasets.

Abstract Detecting conditional independencies plays a key role in several statistical and machine learning tasks, especially in causal discovery algorithms, yet it remains a highly challenging problem due to dimensionality and complex relationships presented in data. In this study, we introduce LCIT (Latent representation-based Conditional Independence Test)—a novel method for conditional independence testing based on representation learning. Our main contribution involves a hypothesis testing framework in which to test for the independence between X and Y given Z, we first learn to infer the latent representations of target variables X and Y that contain no information about the conditioning variable Z. The latent variables are then investigated for any significant remaining dependencies, which can be performed using a conventional correlation test. Moreover, LCIT can also handle discrete and mixed-type data in general by converting discrete variables into the continuous domain via variational dequantization. The empirical evaluations show that LCIT outperforms several state-of-the-art baselines consistently under different evaluation metrics, and is able to adapt really well to both nonlinear, high-dimensional, and mixed data settings on a diverse collection of synthetic and real data sets.

Abstract Distributional estimates in Bayesian approaches in structure learning have advantages compared to the ones performing point estimates when handling epistemic uncertainty. Differentiable methods for Bayesian structure learning have been developed to enhance the scalability of the inference process and are achieving optimistic outcomes. However, in the differentiable continuous setting, constraining the acyclicity of learned graphs emerges as another challenge. Various works utilize post-hoc penalization scores to impose this constraint which cannot assure acyclicity. The topological ordering of the variables is one type of prior knowledge that contains valuable information about the acyclicity of a directed graph. In this work, we propose a framework to guarantee the acyclicity of inferred graphs by integrating the information from the topological ordering into the inference process. Our integration framework does not interfere with the differentiable inference process while being able to strictly assure the acyclicity of learned graphs and reduce the inference complexity. Our extensive empirical experiments on both synthetic and real data have demonstrated the effectiveness of our approach with preferable results compared to related Bayesian approaches.

Mutual Information (MI) and Conditional Mutual Information (CMI) are multi-purpose tools from information theory that are able to naturally measure the statistical dependencies between random variables, thus they are usually of central interest in several statistical and machine learning tasks, such as conditional independence testing and representation learning. However, estimating CMI, or even MI, is infamously challenging due the intractable formulation. In this study, we introduce DINE (Diffeomorphic Information Neural Estimator)–a novel approach for estimating CMI of continuous random variables, inspired by the invariance of CMI over diffeomorphic maps. We show that the variables of interest can be replaced with appropriate surrogates that follow simpler distributions, allowing the CMI to be efficiently evaluated via analytical solutions. Additionally, we demonstrate the quality of the proposed estimator in comparison with state-of-the-arts in three important tasks, including estimating MI, CMI, as well as its application in conditional independence testing. The empirical evaluations show that DINE consistently outperforms competitors in all tasks and is able to adapt very well to complex and high-dimensional relationships.

Heretofore, learning the directed acyclic graphs (DAGs) that encode the cause-effect relationships embedded in observational data is a computationally challenging problem. A recent trend of studies has shown that it is possible to recover the DAGs with polynomial time complexity under the equal variances assumption. However, this prohibits the heteroscedasticity of the noise, which allows for more flexible modeling capabilities, but at the same time is substantially more challenging to handle. In this study, we tackle the heteroscedastic causal structure learning problem under Gaussian noises. By exploiting the normality of the causal mechanisms, we can recover a valid causal ordering, which can uniquely identify the causal DAG using a series of conditional independence tests. The result is HOST (Heteroscedastic causal STructure learning), a simple yet effective causal structure learning algorithm that scales polynomially in both sample size and dimensionality. In addition, via extensive empirical evaluations on a wide range of both controlled and real datasets, we show that the proposed HOST method is competitive with state-of-the-art approaches in both the causal order learning and structure learning problems.

Score-based approaches in the structure learning task are thriving because of their scalability. Continuous relaxation has been the key reason for this advancement. Despite achieving promising outcomes, most of these methods are still struggling to ensure that the graphs generated from the latent space are acyclic by minimizing a defined score. There has also been another trend of permutation-based approaches, which concern the search for the topological ordering of the variables in the directed acyclic graph in order to limit the search space of the graph. In this study, we propose an alternative approach for strictly constraining the acyclicty of the graphs with an integration of the knowledge from the topological orderings. Our approach can reduce inference complexity while ensuring the structures of the generated graphs to be acyclic. Our empirical experiments with simulated and real-world data show that our approach can outperform related Bayesian score-based approaches.

Out-of-distribution (OOD) generalisation aims to build a model that can generalise well on an unseen target domain using knowledge from multiple source domains. To this end, the model should seek the causal dependence between inputs and labels, which may be determined by the semantics of inputs and remain invariant across domains. However, statistical or non-causal methods often cannot capture this dependence and perform poorly due to not considering spurious correlations learnt from model training via unobserved confounders. A well-known existing causal inference method like back-door adjustment cannot be applied to remove spurious correlations as it requires the observation of confounders. In this paper, we propose a novel method that effectively deals with hidden confounders by successfully implementing front-door adjustment (FA). FA requires the choice of a mediator, which we regard as the semantic information of images that helps access the causal mechanism without the need for observing confounders. Further, we propose to estimate the combination of the mediator with other observed images in the front-door formula via style transfer algorithms. Our use of style transfer to estimate FA is novel and sensible for OOD generalisation, which we justify by extensive experimental results on widely used benchmark datasets.

Many high-performance DTA deep learning models have been proposed, but they are mostly black-box and thus lack human interpretability. Explainable AI (XAI) can make DTA models more trustworthy, and allows to distill biological knowledge from the models. Counterfactual explanation is one popular approach to explaining the behaviour of a deep neural network, which works by systematically answering the question "How would the model output change if the inputs were changed in this way?". We propose a multi-agent reinforcement learning framework, Multi-Agent Counterfactual Drug-target binding Affinity (MACDA), to generate counterfactual explanations for the drug-protein complex. Our proposed framework provides human-interpretable counterfactual instances while optimizing both the input drug and target for counterfactual generation at the same time. We benchmark the proposed MACDA framework using the Davis and PDBBind dataset and find that our framework produces more parsimonious explanations with no loss in explanation validity, as measured by encoding similarity. We then present a case study involving ABL1 and Nilotinib to demonstrate how MACDA can explain the behaviour of a DTA model in the underlying substructure interaction between inputs in its prediction, revealing mechanisms that align with prior domain knowledge.

Detecting conditional independencies plays a key role in several statistical and machine learning tasks, especially in causal discovery algorithms, yet it remains a highly challenging problem due to dimensionality and complex relationships presented in data. In this study, we introduce LCIT (Latent representation based Conditional Independence Test) -a novel method for conditional independence testing based on representation learning. Our main contribution involves a hypothesis testing framework in which to test for the independence between X and Y given Z, we first learn to infer the latent representations of target variables X and Y that contain no information about the conditioning variable Z. The latent variables are then investigated for any significant remaining dependencies, which can be performed using a conventional correlation test. The empirical evaluations show that LCIT outperforms several state-of-the-art baselines consistently under different evaluation metrics, and is able to adapt really well to both non-linear and high-dimensional settings on a diverse collection of synthetic and real data sets.

Recommendation systems often face the challenge of cold-start problem where the two parties are completely new to the systems. Previous works introduce the integration of side information of items and users into the systems so that they can learn a representation of the inputs with better generalization, thus potentially solving the cold-start problem. However, using users' or items' side information brings another problem to deep learning based collaborative filtering models known as spurious correlations. In this case, deep learning models fail to adequately generalize and simply capture the idiosyncrasies of the training datasets. In short, deep learning models find a ‘short-cut’ created by the hidden bias in the datasets and make the spurious correlations between specific features and the outcome. In this work, we propose the counterfactual constraint on user/item attributes, allowing the systems to avoid hidden bias in the datasets, thus having the robustness and generalization. The goal is to discourage the disruptive distribution change in the prediction when the distribution shift occurs in the user/item attribute spaces. The proposed model compares favorably with conventional baseline on both synthetic and real-world datasets.

Predicting the drug-target interaction is crucial for drug discovery as well as drug repurposing. Machine learning is commonly used in drug-target affinity (DTA) problem. However, the machine learning model faces the cold-start problem where the model performance drops when predicting the interaction of a novel drug or target. Previous works try to solve the cold start problem by learning the drug or target representation using unsupervised learning. While the drug or target representation can be learned in an unsupervised manner, it still lacks the interaction information, which is critical in drug-target interaction. To incorporate the interaction information into the drug and protein interaction, we proposed using transfer learning from chemical-chemical interaction (CCI) and protein-protein interaction (PPI) task to drug-target interaction task. The representation learned by CCI and PPI tasks can be transferred smoothly to the DTA task due to the similar nature of the tasks. The result on the DTA datasets shows that our proposed method has advantages compared to other pre-training methods in the DTA task.

Predicting the interaction between a compound and a target is crucial for rapid drug repurposing. Deep learning has been successfully applied in drug-target affinity (DTA)problem. However, previous deep learning-based methods ignore modeling the direct interactions between drug and protein residues. This would lead to inaccurate learning of target representation which may change due to the drug binding effects. In addition, previous DTA methods learn protein representation solely based on a small number of protein sequences in DTA datasets while neglecting the use of proteins outside of the DTA datasets. We propose GEFA (Graph Early Fusion Affinity), a novel graph-in-graph neural network with attention mechanism to address the changes in target representation because of the binding effects. Specifically, a drug is modeled as a graph of atoms, which then serves as a node in a larger graph of residues-drug complex. The resulting model is an expressive deep nested graph neural network. We also use pre-trained protein representation powered by the recent effort of learning contextualized protein representation. The experiments are conducted under different settings to evaluate scenarios such as novel drugs or targets. The results demonstrate the effectiveness of the pre-trained protein embedding and the advantages our GEFA in modeling the nested graph for drug-target interaction.

BACKGROUND: Drug response prediction is an important problem in computational personalized medicine. Many machine-learning-based methods, especially deep learning-based ones, have been proposed for this task. However, these methods often represent the drugs as strings, which are not a natural way to depict molecules. Also, interpretation (e.g., what are the mutation or copy number aberration contributing to the drug response) has not been considered thoroughly. METHODS: In this study, we propose a novel method, GraphDRP, based on graph convolutional network for the problem. In GraphDRP, drugs were represented in molecular graphs directly capturing the bonds among atoms, meanwhile cell lines were depicted as binary vectors of genomic aberrations. Representative features of drugs and cell lines were learned by convolution layers, then combined to represent for each drug-cell line pair. Finally, the response value of each drug-cell line pair was predicted by a fully-connected neural network. Four variants of graph convolutional networks were used for learning the features of drugs. RESULTS: We found that GraphDRP outperforms tCNNS in all performance measures for all experiments. Also, through saliency maps of the resulting GraphDRP models, we discovered the contribution of the genomic aberrations to the responses. CONCLUSION: Representing drugs as graphs can improve the performance of drug response prediction. Availability of data and materials: Data and source code can be downloaded athttps://github.com/hauldhut/GraphDRP.

Multimodal dimensional emotion recognition has drawn a great attention from the affective computing community and numerous schemes have been extensively investigated, making a significant progress in this area. However, several questions still remain unanswered for most of existing approaches including: (i) how to simultaneously learn compact yet representative features from multimodal data, (ii) how to effectively capture complementary features from multimodal streams, and (iii) how to perform all the tasks in an end-to-end manner. To address these challenges, in this paper, we propose a novel deep neural network architecture consisting of a two-stream auto-encoder and a long short term memory for effectively integrating visual and audio signal streams for emotion recognition. To validate the robustness of our proposed architecture, we carry out extensive experiments on the multimodal emotion in the wild dataset: RECOLA. Experimental results show that the proposed method achieves state-of-the-art recognition performance.

MOTIVATION: Predicting cell locations is important since with the understanding of cell locations, we may estimate the function of cells and their integration with the spatial environment. Thus, the DREAM challenge on single-cell transcriptomics required participants to predict the locations of single cells in the Drosophila embryo using single-cell transcriptomic data. RESULTS: We have developed over 50 pipelines by combining different ways of preprocessing the RNA-seq data, selecting the genes, predicting the cell locations and validating predicted cell locations, resulting in the winning methods which were ranked second in sub-challenge 1, first in sub-challenge 2 and third in sub-challenge 3. In this paper, we present an R package, SCTCwhatateam, which includes all the methods we developed and the Shiny web application to facilitate the research on single-cell spatial reconstruction. All the data and the example use cases are available in the Supplementary data.

SUMMARY: The development of new drugs is costly, time consuming and often accompanied with safety issues. Drug repurposing can avoid the expensive and lengthy process of drug development by finding new uses for already approved drugs. In order to repurpose drugs effectively, it is useful to know which proteins are targeted by which drugs. Computational models that estimate the interaction strength of new drug-target pairs have the potential to expedite drug repurposing. Several models have been proposed for this task. However, these models represent the drugs as strings, which is not a natural way to represent molecules. We propose a new model called GraphDTA that represents drugs as graphs and uses graph neural networks to predict drug-target affinity. We show that graph neural networks not only predict drug-target affinity better than non-deep learning models, but also outperform competing deep learning methods. Our results confirm that deep learning models are appropriate for drug-target binding affinity prediction, and that representing drugs as graphs can lead to further improvements. AVAILABILITY OF IMPLEMENTATION: The proposed models are implemented in Python. Related data, pre-trained models and source code are publicly available at https://github.com/thinng/GraphDTA. All scripts and data needed to reproduce the post hoc statistical analysis are available from https://doi.org/10.5281/zenodo.3603523. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Unravelling cancer driver genes is important in cancer research. Although computational methods have been developed to identify cancer drivers, most of them detect cancer drivers at population level. However, two patients who have the same cancer type and receive the same treatment may have different outcomes because each patient has a different genome and their disease might be driven by different driver genes. Therefore new methods are being developed for discovering cancer drivers at individual level, but existing personalized methods only focus on coding drivers while microRNAs (miRNAs) have been shown to drive cancer progression as well. Thus, novel methods are required to discover both coding and miRNA cancer drivers at individual level. RESULTS: We propose the novel method, pDriver, to discover personalized cancer drivers. pDriver includes two stages: (i) constructing gene networks for each cancer patient and (ii) discovering cancer drivers for each patient based on the constructed gene networks. To demonstrate the effectiveness of pDriver, we have applied it to five TCGA cancer datasets and compared it with the state-of-the-art methods. The result indicates that pDriver is more effective than other methods. Furthermore, pDriver can also detect miRNA cancer drivers and most of them have been confirmed to be associated with cancer by literature. We further analyze the predicted personalized drivers for breast cancer patients and the result shows that they are significantly enriched in many GO processes and KEGG pathways involved in breast cancer. AVAILABILITY AND IMPLEMENTATION: pDriver is available at https://github.com/pvvhoang/pDriver. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

The classification of clinical samples based on gene expression data is an important part of precision medicine. In this manuscript, we show how transforming gene expression data into a set of personalized (sample-specific) networks can allow us to harness existing graph-based methods to improve classifier performance. Existing approaches to personalized gene networks have the limitation that they depend on other samples in the data and must get re-computed whenever a new sample is introduced. Here, we propose a novel method, called Personalized Annotation-based Networks (PAN), that avoids this limitation by using curated annotation databases to transform gene expression data into a graph. Unlike competing methods, PANs are calculated for each sample independent of the population, making it a more efficient way to obtain single-sample networks. Using three breast cancer datasets as a case study, we show that PAN classifiers not only predict cancer relapse better than gene features alone, but also outperform PPI (protein-protein interactions) and population-level graph-based classifiers. This work demonstrates the practical advantages of graph-based classification for high-dimensional genomic data, while offering a new approach to making sample-specific networks. Supplementary information: PAN and the baselines are implemented in Python. Source code and data are available at https://github.com/thinng/PAN.

Privacy preservation is important. Prescriptive analytics is a method to extract corrective actions to avoid undesirable outcomes. We propose a privacy preserving prescriptive analytics algorithm to protect the data used during the construction of the prescriptive analytics algorithm. We use differential privacy mechanism to achieve strong privacy guarantee. Differential privacy mechanism requires computation of sensitivity: maximum change in the output between two training datasets, which is differed by only one instance. The main challenge we addressed is the computation of sensitivity of the prescription vector. In absence of any analytical form, we construct a nested global optimization problem to compute the sensitivity. We solve the optimization problem using constrained Bayesian optimization, as the nested structure makes the objective function expensive. We demonstrate our algorithm on two real world datasets and observe that the prescription vectors remains useful even after making them private.

Introducing variability while maintaining coherence is a core task in learning to generate utterances in conversation. Standard neural encoder-decoder models and their extensions using conditional variational autoencoder often result in either trivial or digressive responses. To overcome this, we explore a novel approach that injects variability into neural encoder-decoder via the use of external memory as a mixture model, namely Variational Memory Encoder-Decoder (VMED). By associating each memory read with a mode in the latent mixture distribution at each timestep, our model can capture the variability observed in sequential data such as natural conversations. We empirically compare the proposed model against other recent approaches on various conversational datasets. The results show that VMED consistently achieves significant improvement over others in both metric-based and qualitative evaluations.

This letter proposes an effective method to improve object location in Chamfer template matching (CTM) based object detection using image segmentation. In our method, object bounding boxes are iteratively adjusted to fit with the object images obtained from image segmentation in a probabilistic model. The proposed method was tested with state-of-the-art CTM-based object detectors. Experimental results have shown the proposed method improved the location accuracy of the object detectors and reduce the false alarms rate.

Efficient and reliable monitoring of wild animals in their natural habitats is essential to inform conservation and management decisions. Automatic covert cameras or "camera traps" are being an increasingly popular tool for wildlife monitoring due to their effectiveness and reliability in collecting data of wildlife unobtrusively, continuously and in large volume. However, processing such a large volume of images and videos captured from camera traps manually is extremely expensive, time-consuming and also monotonous. This presents a major obstacle to scientists and ecologists to monitor wildlife in an open environment. Leveraging on recent advances in deep learning techniques in computer vision, we propose in this paper a framework to build automated animal recognition in the wild, aiming at an automated wildlife monitoring system. In particular, we use a single-labeled dataset from Wildlife Spotter project, done by citizen scientists, and the state-of-the-art deep convolutional neural network architectures, to train a computational system capable of filtering animal images and identifying species automatically. Our experimental results achieved an accuracy at 96.6% for the task of detecting images containing animal, and 90.4% for identifying the three most common species among the set of images of wild animals taken in South-central Victoria, Australia, demonstrating the feasibility of building fully automated wildlife observation. This, in turn, can therefore speed up research findings, construct more efficient citizen sciencebased monitoring systems and subsequent management decisions, having the potential to make significant impacts to the world of ecology and trap camera images analysis.

Discovering dynamics of emotion and mood changes for individuals has the potential to enhance the diagnosis and treatment of mental disorders. In this paper we study affective transitions and dynamics among individuals in online mental health communities. Using social media as form of `sensor', we crawl a large dataset of blogs posted by online communities whose descriptions declared to be associated with affective disorder conditions such as depression, anxiety, or autism. We then apply nonnegative matrix factorization model to extract the common and individual factors of affective transitions across groups of individuals in different levels of affective disorders. We examine the latent patterns of emotional transitions and investigate the effects of emotional transitions across the cohorts. Our framework is novel as it utilizes social media as an online sensing platform of mood and emotional dynamics. Hence, our work has implication in constructing systems to screen individuals and communities at high risks of mental health problems in online settings.

Mental illness has a deep impact on individuals, families, and by extension, society as a whole. Social networks allow individuals with mental disorders to communicate with others sufferers via online communities, providing an invaluable resource for studies on textual signs of psychological health problems. Mental disorders often occur in combinations, e.g., a patient with an anxiety disorder may also develop depression. This co-occurring mental health condition provides the focus for our work on classifying online communities with an interest in depression. For this, we have crawled a large body of 620 000 posts made by 80 000 users in 247 online communities. We have extracted the topics and psycholinguistic features expressed in the posts, using these as inputs to our model. Following a machine learning technique, we have formulated a joint modeling framework in order to classify mental health-related co-occurring online communities from these features. Finally, we performed empirical validation of the model on the crawled dataset where our model outperforms recent state-of-the-art baselines.

People are increasingly using social media, especially online communities, to discuss mental health issues and seek supports. Understanding topics, interaction, sentiment and clustering structures of these communities informs important aspects of mental health. It can potentially add knowledge to the underlying cognitive dynamics, mood swings patterns, shared interests, and interaction. There has been growing research interest in analyzing online mental health communities; however sentiment analysis of these communities has been largely under-explored. This study presents an analysis of online Live Journal communities with and without mental health-related conditions including depression and autism. Latent topics for mood tags, affective words, and generic words in the content of the posts made in these communities were learned using nonparametric topic modelling. These representations were then input into a nonparametric clustering to discover meta-groups among the communities. The best performance results can be achieved on clustering communities with latent mood-based representation for such communities. The study also found significant differences in usage latent topics for mood tags and affective features between online communities with and without affective disorders. The findings reveal useful insights into hyper-group detection of online mental health-related communities.

The Internet has provided an ever increasingly popular platform for individuals to voice their thoughts, and like-minded people to share stories. This unintentionally leaves characteristics of individuals and communities, which are often difficult to be collected in traditional studies. Individuals with autism are such a case, in which the Internet could facilitate even more communication given its social-spatial distance being a characteristic preference for individuals with autism. Previous studies examined the traces left in the posts of online autism communities (Autism) in comparison with other online communities (Control). This work further investigates these online populations through the contents of not only their posts but also their comments. We first compare the Autism and Control blogs based on three features: topics, language styles and affective information. The autism groups are then further examined, based on the same three features, by looking at their personal (Personal) and community (Community) blogs separately. Machine learning and statistical methods are used to discriminate blog contents in both cases. All three features are found to be significantly different between Autism and Control, and between autism Personal and Community. These features also show good indicative power in prediction of autism blogs in both personal and community settings.

The circadian system regulates 24 hour rhythms in biological creatures. It impacts mood regulation. The disruptions of circadian rhythms cause destabilization in individuals with affective disorders, such as depression and bipolar disorders. Previous work has examined the role of the circadian system on effects of light interactions on mood-related systems, the effects of light manipulation on brain, the impact of chronic stress on rhythms. However, such studies have been conducted in small, preselected populations. The deluge of data is now changing the landscape of research practice. The unprecedented growth of social media data allows one to study individual behavior across large and diverse populations. In particular, individuals with affective disorders from online communities have not been examined rigorously. In this paper, we aim to use social media as a sensor to identify circadian patterns for individuals with affective disorders in online communities.We use a large scale study cohort of data collecting from online affective disorder communities. We analyze changes in hourly, daily, weekly and seasonal affect of these clinical groups in contrast with control groups of general communities. By comparing the behaviors between the clinical groups and the control groups, our findings show that individuals with affective disorders show a significant distinction in their circadian rhythms across the online activity. The results shed light on the potential of using social media for identifying diurnal individual variation in affective state, providing key indicators and risk factors for noninvasive wellbeing monitoring and prediction.

A large number of people use online communities to discuss mental health issues, thus offering opportunities for new understanding of these communities. This paper aims to study the characteristics of online depression communities (CLINICAL) in comparison with those joining other online communities (CONTROL). We use machine learning and statistical methods to discriminate online messages between depression and control communities using mood, psycholinguistic processes and content topics extracted from the posts generated by members of these communities. All aspects including mood, the written content and writing style are found to be significantly different between two types of communities. Sentiment analysis shows the clinical group have lower valence than people in the control group. For language styles and topics, statistical tests reject the hypothesis of equality on psycholinguistic processes and topics between two groups. We show good predictive validity in depression classification using topics and psycholinguistic clues as features. Clear discrimination between writing styles and contents, with good predictive power is an important step in understanding social media and its use in mental health.

Current growth of individuals on the autism spectrum disorder (ASD) requires continuous support and care. With the popularity of social media, online communities of people affected by ASD emerge. This paper presents an analysis of these online communities through understanding aspects that differentiate such communities. In this paper, the aspects given are not expressed in terms of friendship, exchange of information, social support or recreation, but rather with regard to the topics and linguistic styles that people express in their on-line writing. Using data collected unobtrusively from LiveJournal, we analyze posts made by ten autism communities in conjunction with those made by a control group of standard communities. Significant differences have been found between autism and control communities when characterized by latent topics of discussion and psycholinguistic features. Latent topics are found to have greater predictive power than linguistic features when classifying blog posts as either autism or control community. This study suggests that data mining of online blogs has the potential to detect clinically meaningful data. It opens the door to possibilities including sentinel risk surveillance and harnessing the power in diverse large datasets.

Social capital indicative of community interaction and support is intrinsically linked to mental health. Increasing online presence is now the norm. Whilst social capital and its impact on social networks has been examined, its underlying connection to emotional response such as mood, has not been investigated. This paper studies this phenomena, revisiting the concept of “online social capital” in social media communities using measurable aspects of social participation and social support. We establish the link between online capital derived from social media and mood, demonstrating results for different cohorts of social capital and social connectivity. We use novel Bayesian nonparametric factor analysis to extract the shared and individual factors in mood transition across groups of users of different levels of connectivity, quantifying patterns and degree of mood transitions. Using more than 1.6 million users from Live Journal, we show quantitatively that groups with lower social capital have fewer positive moods and more negative moods, than groups with higher social capital. We show similar effects in mood transitions. We establish a framework of how social media can be used as a barometer for mood. The significance lies in the importance of online social capital to mental well-being in overall. In establishing the link between mood and social capital in online communities, this work may suggest the foundation of new systems to monitor online mental well-being.