Search for: All records

Precise estimation of treatment effects is crucial for accurately evaluating the intervention. While deep learning models have exhibited promising performance in learning counterfactual representations for treatment effect estimation (TEE), a major limitation in most of these models is that they often overlook the diversity of treatment effects across potential subgroups that have varying treatment effects and characteristics, treating the entire population as a homogeneous group. This limitation restricts the ability to precisely estimate treatment effects and provide targeted treatment recommendations. In this paper, we propose a novel treatment effect estimation model, named SubgroupTE, which incorporates subgroup identification in TEE. SubgroupTE identifies heterogeneous subgroups with different responses and more precisely estimates treatment effects by considering subgroup-specific treatment effects in the estimation process. In addition, we introduce an expectation–maximization (EM)-based training process that iteratively optimizes estimation and subgrouping networks to improve both estimation and subgroup identification. Comprehensive experiments on the synthetic and semi-synthetic datasets demonstrate the outstanding performance of SubgroupTE compared to the existing works for treatment effect estimation and subgrouping models. Additionally, a real-world study demonstrates the capabilities of SubgroupTE in enhancing targeted treatment recommendations for patients with opioid use disorder (OUD) by incorporating subgroup identification with treatment effect estimation. 

Abstract Plant roots dynamically respond to nitrogen availability by executing a signaling and transcriptional cascade resulting in altered plant growth that is optimized for nutrient uptake. The NIN-LIKE PROTEIN 7 (NLP7) transcription factor senses nitrogen and, along with its paralog NLP6, partially coordinates transcriptional responses. While the post-translational regulation of NLP6 and NLP7 is well established, their upstream transcriptional regulation remains understudied in Arabidopsis (Arabidopsis thaliana) and other plant species. Here, we dissected a known sub-circuit upstream of NLP6 and NLP7 in Arabidopsis, which was predicted to contain multiple multi-node feedforward loops suggestive of an optimized design principle of nitrogen transcriptional regulation. This sub-circuit comprises AUXIN RESPONSE FACTOR 18 (ARF18), ARF9, DEHYDRATION-RESPONSIVE ELEMENT-BINDING PROTEIN 26 (DREB26), Arabidopsis NAC-DOMAIN CONTAINING PROTEIN 32 (ANAC032), NLP6 and NLP7 and their regulation of NITRITE REDUCTASE 1 (NIR1). Conservation and divergence of this circuit and its influence on nitrogen-dependent root system architecture were similarly assessed in tomato (Solanum lycopersicum). The specific binding sites of these factors within their respective promoters and their putative cis-regulatory architectures were identified. The direct or indirect nature of these interactions was validated in planta. The resulting models were genetically validated in varying concentrations of available nitrate by measuring the transcriptional output of the network revealing rewiring of nitrogen regulation across distinct plant lineages. 

Deep learning-based predictive models, leveraging Electronic Health Records (EHR), are receiving increasing attention in healthcare. An effective representation of a patient's EHR should hierarchically encompass both the temporal relationships between historical visits and medical events, and the inherent structural information within these elements. Existing patient representation methods can be roughly categorized into sequential representation and graphical representation. The sequential representation methods focus only on the temporal relationships among longitudinal visits. On the other hand, the graphical representation approaches, while adept at extracting the graph-structured relationships between various medical events, fall short in effectively integrate temporal information. To capture both types of information, we model a patient's EHR as a novel temporal heterogeneous graph. This graph includes historical visits nodes and medical events nodes. It propagates structured information from medical event nodes to visit nodes and utilizes time-aware visit nodes to capture changes in the patient's health status. Furthermore, we introduce a novel temporal graph transformer (TRANS) that integrates temporal edge features, global positional encoding, and local structural encoding into heterogeneous graph convolution, capturing both temporal and structural information. We validate the effectiveness of TRANS through extensive experiments on three real-world datasets. The results show that our proposed approach achieves state-of-the-art performance. 

Although recent advances in machine learning have shown its success to learn from independent and identically distributed (IID) data, it is vulnerable to out-of-distribution (OOD) data in an open world. Domain generalization (DG) deals with such an issue and it aims to learn a model from multiple source domains that can be generalized to unseen target domains. Existing studies on DG have largely focused on stationary settings with homogeneous source domains. However, in many applications, domains may evolve along a specific direction (e.g., time, space). Without accounting for such non-stationary patterns, models trained with existing methods may fail to generalize on OOD data. In this paper, we study domain generalization in non-stationary environment. We first examine the impact of environmental non-stationarity on model performance and establish the theoretical upper bounds for the model error at target domains. Then, we propose a novel algorithm based on adaptive invariant representation learning, which leverages the non-stationary pattern to train a model that attains good performance on target domains. Experiments on both synthetic and real data validate the proposed algorithm.