More Like this

1. Single-cell generalized trend model (scGTM): a flexible and interpretable model of gene expression trend along cell pseudotime

   https://doi.org/10.1093/bioinformatics/btac423  

   Cui, Elvis Han ; Song, Dongyuan ; Wong, Weng Kee ; Li, Jingyi Jessica ; Mathelier, ed., Anthony ( June 2022 , Bioinformatics)

   Modeling single-cell gene expression trends along cell pseudotime is a crucial analysis for exploring biological processes. Most existing methods rely on nonparametric regression models for their flexibility; however, nonparametric models often provide trends too complex to interpret. Other existing methods use interpretable but restrictive models. Since model interpretability and flexibility are both indispensable for understanding biological processes, the single-cell field needs a model that improves the interpretability and largely maintains the flexibility of nonparametric regression models.

   Here, we propose the single-cell generalized trend model (scGTM) for capturing a gene’s expression trend, which may be monotone, hill-shaped or valley-shaped, along cell pseudotime. The scGTM has three advantages: (i) it can capture non-monotonic trends that are easy to interpret, (ii) its parameters are biologically interpretable and trend informative, and (iii) it can flexibly accommodate common distributions for modeling gene expression counts. To tackle the complex optimization problems, we use the particle swarm optimization algorithm to find the constrained maximum likelihood estimates for the scGTM parameters. As an application, we analyze several single-cell gene expression datasets using the scGTM and show that scGTM can capture interpretable gene expression trends along cell pseudotime and reveal molecular insights underlying biological processes.

   The Python package scGTM is open-access and available at https://github.com/ElvisCuiHan/scGTM.

   Supplementary data are available at Bioinformatics online.

    

   more » « less
2. Cross-dependent graph neural networks for molecular property prediction

   https://doi.org/10.1093/bioinformatics/btac039  

   Ma, Hehuan ; Bian, Yatao ; Rong, Yu ; Huang, Wenbing ; Xu, Tingyang ; Xie, Weiyang ; Ye, Geyan ; Huang, Junzhou ; Lu, ed., Zhiyong ( January 2022 , Bioinformatics)

   The crux of molecular property prediction is to generate meaningful representations of the molecules. One promising route is to exploit the molecular graph structure through graph neural networks (GNNs). Both atoms and bonds significantly affect the chemical properties of a molecule, so an expressive model ought to exploit both node (atom) and edge (bond) information simultaneously. Inspired by this observation, we explore the multi-view modeling with GNN (MVGNN) to form a novel paralleled framework, which considers both atoms and bonds equally important when learning molecular representations. In specific, one view is atom-central and the other view is bond-central, then the two views are circulated via specifically designed components to enable more accurate predictions. To further enhance the expressive power of MVGNN, we propose a cross-dependent message-passing scheme to enhance information communication of different views. The overall framework is termed as CD-MVGNN.

   We theoretically justify the expressiveness of the proposed model in terms of distinguishing non-isomorphism graphs. Extensive experiments demonstrate that CD-MVGNN achieves remarkably superior performance over the state-of-the-art models on various challenging benchmarks. Meanwhile, visualization results of the node importance are consistent with prior knowledge, which confirms the interpretability power of CD-MVGNN.

   The code and data underlying this work are available in GitHub at https://github.com/uta-smile/CD-MVGNN.

   Supplementary data are available at Bioinformatics online.

    

   more » « less
3. Small molecule generation via disentangled representation learning

   https://doi.org/10.1093/bioinformatics/btac296  

   Du, Yuanqi ; Guo, Xiaojie ; Wang, Yinkai ; Shehu, Amarda ; Zhao, Liang ; Xu, ed., Jinbo ( May 2022 , Bioinformatics)

   Expanding our knowledge of small molecules beyond what is known in nature or designed in wet laboratories promises to significantly advance cheminformatics, drug discovery, biotechnology and material science. In silico molecular design remains challenging, primarily due to the complexity of the chemical space and the non-trivial relationship between chemical structures and biological properties. Deep generative models that learn directly from data are intriguing, but they have yet to demonstrate interpretability in the learned representation, so we can learn more about the relationship between the chemical and biological space. In this article, we advance research on disentangled representation learning for small molecule generation. We build on recent work by us and others on deep graph generative frameworks, which capture atomic interactions via a graph-based representation of a small molecule. The methodological novelty is how we leverage the concept of disentanglement in the graph variational autoencoder framework both to generate biologically relevant small molecules and to enhance model interpretability.

   Extensive qualitative and quantitative experimental evaluation in comparison with state-of-the-art models demonstrate the superiority of our disentanglement framework. We believe this work is an important step to address key challenges in small molecule generation with deep generative frameworks.

   Training and generated data are made available at https://ieee-dataport.org/documents/dataset-disentangled-representation-learning-interpretable-molecule-generation. All code is made available at https://anonymous.4open.science/r/D-MolVAE-2799/.

   Supplementary data are available at Bioinformatics online.

    

   more » « less
4. Adiposity and pathogen exposure: An investigation of response to iron supplementation and hypothesized predictors in anemic pre‐school‐aged children living in a dual burden environment

   https://doi.org/10.1002/ajpa.24287  

   Dorsey, Achsah F. ; Penny, Mary E. ; Thompson, Amanda L. ( April 2021 , American Journal of Physical Anthropology)

   Peruvians are experiencing rapid dietary and lifestyle changes, resulting in a phenomenon known as the “dual burden of disease.” A common manifestation of the dual burden in individuals is the co‐occurrence of overweight and anemia. Despite recent initiatives introduced to address these concerns, rates continue to be public health concerns. This study investigates the relationship between immune activation and lack of response to iron supplementation after 1 month of treatment and explores variation in body fat stores as a potential moderator between immune function and response to treatment.

   Data come from children, aged 2–5 years (n = 50) from a peri‐urban community in Lima, Peru. Multivariate logistic regression models were used to explore the associations between response to treatment (Hb > =11.0 g/dl) after 1 month of treatment), markers of immune activation (C‐reactive protein [CRP] and reported morbidity symptoms), and measures of body fat (waist‐to‐height ratio, triceps skinfold thickness, and body mass index [BMI]).

   We found that high CRP is associated with a lack of response to iron supplementation after 1 month of treatment and that BMI z‐score may moderate this association. Generally, larger body size is associated with response to iron supplementation whether or not the children in this sample have high immune activation. However, the probability of anemic children responding to iron supplementation treatment differed across adiposity measures.

   Our finding suggesting that adiposity and CRP influence response to iron supplementation, furthers our understanding of the relationship between inflammation and anemia treatment in children and has both theoretical and public health implications.

    

   more » « less
5. A Transfer Learning Approach to Correct the Temporal Performance Drift of Clinical Prediction Models: Retrospective Cohort Study

   https://doi.org/10.2196/38053  

   Zhang, Xiangzhou ; Xue, Yunfei ; Su, Xinyu ; Chen, Shaoyong ; Liu, Kang ; Chen, Weiqi ; Liu, Mei ; Hu, Yong ( January 2022 , JMIR Medical Informatics)

   Clinical prediction models suffer from performance drift as the patient population shifts over time. There is a great need for model updating approaches or modeling frameworks that can effectively use the old and new data.

   Based on the paradigm of transfer learning, we aimed to develop a novel modeling framework that transfers old knowledge to the new environment for prediction tasks, and contributes to performance drift correction.

   The proposed predictive modeling framework maintains a logistic regression–based stacking ensemble of 2 gradient boosting machine (GBM) models representing old and new knowledge learned from old and new data, respectively (referred to as transfer learning gradient boosting machine [TransferGBM]). The ensemble learning procedure can dynamically balance the old and new knowledge. Using 2010-2017 electronic health record data on a retrospective cohort of 141,696 patients, we validated TransferGBM for hospital-acquired acute kidney injury prediction.

   The baseline models (ie, transported models) that were trained on 2010 and 2011 data showed significant performance drift in the temporal validation with 2012-2017 data. Refitting these models using updated samples resulted in performance gains in nearly all cases. The proposed TransferGBM model succeeded in achieving uniformly better performance than the refitted models.

   Under the scenario of population shift, incorporating new knowledge while preserving old knowledge is essential for maintaining stable performance. Transfer learning combined with stacking ensemble learning can help achieve a balance of old and new knowledge in a flexible and adaptive way, even in the case of insufficient new data.

    

   more » « less