EGFI: drug-drug interaction extraction and generation with fusion of enriched entity and sentence information.

MOTIVATION: The rapid growth in literature accumulates diverse and yet comprehensive biomedical knowledge hidden to be mined such as drug interactions. However, it is difficult to extract the heterogeneous knowledge to retrieve or even discover the latest and novel knowledge in an efficient manner. To address such a problem, we propose EGFI for extracting and consolidating drug interactions from large-scale medical literature text data. Specifically, EGFI consists of two parts: classification and generation. In the classification part, EGFI encompasses the language model BioBERT which has been comprehensively pretrained on biomedical corpus. In particular, we propose the multihead self-attention mechanism and packed BiGRU to fuse multiple semantic information for rigorous context modeling. In the generation part, EGFI utilizes another pretrained language model BioGPT-2 where the generation sentences are selected based on filtering rules. RESULTS: We evaluated the classification part on 'DDIs 2013' dataset and 'DTIs' dataset, achieving the F1 scores of 0.842 and 0.720 respectively. Moreover, we applied the classification part to distinguish high-quality generated sentences and verified with the existing growth truth to confirm the filtered sentences. The generated sentences that are not recorded in DrugBank and DDIs 2013 dataset demonstrated the potential of EGFI to identify novel drug relationships. AVAILABILITY: Source code are publicly available at https://github.com/Layne-Huang/EGFI.

DNA Repair-Responsive Engineered Whole Cell Microbial Sensors for Sensitive and High-Throughput Screening of Genotoxic Impurities.

Genotoxic impurities (GTIs) occurred in drugs, and food and environment pose a threat to human health. Accurate and sensitive evaluation of GTIs is of significance. Ames assay is the existing gold standard method. However, the pathogenic bacteria model lacks metabolic enzymes and requires mass GTIs, leading to insufficient safety, accuracy, and sensitivity. Whole-cell microbial sensors (WCMSs) can use normal strains to simulate the metabolic environment, achieving safe, sensitive, and high-throughput detection and evaluation for GTIs. Here, based on whether GTIs causing DNA alkylation required metabolic enzymes or not, two DNA repair-responsive engineered WCMS systems were constructed including Escherichia coli-WCMS and yeast-WCMS. A DNA repair-responsive promoter as a sensing element was coupled with an enhanced green fluorescent protein as a reporter to construct plasmids for introduction into WCMS. The ada promoter was screened out in the E. coli-WCMS, while the MAG1 promoter was selected for the yeast-WCMS. Different E. coli and yeast strains were modified by gene knockout and mutation to eliminate the interference and enhance the GTI retention in cells and further improved the sensitivity. Finally, GTI consumption of WCMS for the evaluation of methyl methanesulfonate (MMS) and nitrosamines was decreased to 0.46-8.53 µg and 0.068 ng-2.65 µg, respectively, decreasing 2-3 orders of magnitude compared to traditional methods. This study provided a novel approach to measure GTIs with different DNA damage pathways at a molecular level and facilitated the high-throughput screening and sensitive evaluation of GTIs.

3D Shape Completion on Unseen Categories: A Weakly-Supervised Approach.

3D shapes captured by scanning devices are often incomplete due to occlusion. 3D shape completion methods have been explored to tackle this limitation. However, most of these methods are only trained and tested on a subset of categories, resulting in poor generalization to unseen categories. In this paper, we propose a novel weakly-supervised framework to reconstruct the complete shapes from unseen categories. We first propose an end-to-end prior-assisted shape learning network that leverages data from the seen categories to infer a coarse shape. Specifically, we construct a prior bank consisting of representative shapes from the seen categories. Then, we design a multi-scale pattern correlation module for learning the complete shape of the input by analyzing the correlation between local patterns within the input and the priors at various scales. In addition, we propose a self-supervised shape refinement model to further refine the coarse shape. Considering the shape variability of 3D objects across categories, we construct a category-specific prior bank to facilitate shape refinement. Then, we devise a voxel-based partial matching loss and leverage the partial scans to drive the refinement process. Extensive experimental results show that our approach is superior to state-of-the-art methods by a large margin. We will make the source code publicly available at https://github.com/ltwu6/WSSC.

Source Free Semi-Supervised Transfer Learning for Diagnosis of Mental Disorders on fMRI Scans.

The high prevalence of mental disorders gradually poses a huge pressure on the public healthcare services. Deep learning-based computer-aided diagnosis (CAD) has emerged to relieve the tension in healthcare institutions by detecting abnormal neuroimaging-derived phenotypes. However, training deep learning models relies on sufficient annotated datasets, which can be costly and laborious. Semi-supervised learning (SSL) and transfer learning (TL) can mitigate this challenge by leveraging unlabeled data within the same institution and advantageous information from source domain, respectively. This work is the first attempt to propose an effective semi-supervised transfer learning (SSTL) framework dubbed S3TL for CAD of mental disorders on fMRI data. Within S3TL, a secure cross-domain feature alignment method is developed to generate target-related source model in SSL. Subsequently, we propose an enhanced dual-stage pseudo-labeling approach to assign pseudo-labels for unlabeled samples in target domain. Finally, an advantageous knowledge transfer method is conducted to improve the generalization capability of the target model. Comprehensive experimental results demonstrate that S3TL achieves competitive accuracies of 69.14%, 69.65%, and 72.62% on ABIDE-I, ABIDE-II, and ADHD-200 datasets, respectively. Furthermore, the simulation experiments also demonstrate the application potential of S3TL through model interpretation analysis and federated learning extension.

Federated Multi-Task Learning for Joint Diagnosis of Multiple Mental Disorders on MRI Scans.

OBJECTIVE: Deep learning (DL) techniques have been introduced to assist doctors in the interpretation of medical images by detecting image-derived phenotype abnormality. Yet the privacy-preserving policy of medical images disables the effective training of DL model using sufficiently large datasets. As a decentralized computing paradigm to address this issue, federated learning (FL) allows the training process to occur in individual institutions with local datasets, and then aggregates the resultant weights without risk of privacy leakage. METHODS: We propose an effective federated multi-task learning (MTL) framework to jointly identify multiple related mental disorders based on functional magnetic resonance imaging data. A federated contrastive learning-based feature extractor is developed to extract high-level features across client models. To ease the optimization conflicts of updating shared parameters in MTL, we present a federated multi-gate mixture of expert classifier for the joint classification. The proposed framework also provides practical modules, including personalized model learning, privacy protection, and federated biomarker interpretation. RESULTS: On real-world datasets, the proposed framework achieves robust diagnosis accuracies of 69.48 ± 1.6%, 71.44 ± 3.2%, and 83.29 ± 3.2% in autism spectrum disorder, attention deficit/hyperactivity disorder, and schizophrenia, respectively. CONCLUSION: The proposed framework can effectively ease the domain shift between clients via federated MTL. SIGNIFICANCE: The current work provides insights into exploiting the advantageous knowledge shared in related mental disorders for improving the generalization capability of computer-aided detection approaches.

Using Contextual Learning to Improve Diagnostic Accuracy: Application in Breast Cancer Screening.

Clinicians need to routinely make management decisions about patients who are at risk for a disease such as breast cancer. This paper presents a novel clinical decision support tool that is capable of helping physicians make diagnostic decisions. We apply this support system to improve the specificity of breast cancer screening and diagnosis. The system utilizes clinical context (e.g., demographics, medical history) to minimize the false positive rates while avoiding false negatives. An online contextual learning algorithm is used to update the diagnostic strategy presented to the physicians over time. We analytically evaluate the diagnostic performance loss of the proposed algorithm, in which the true patient distribution is not known and needs to be learned, as compared with the optimal strategy where all information is assumed known, and prove that the false positive rate of the proposed learning algorithm asymptotically converges to the optimum. In addition, our algorithm also has the important merit that it can provide individualized confidence estimates about the accuracy of the diagnosis recommendation. Moreover, the relevancy of contextual features is assessed, enabling the approach to identify specific contextual features that provide the most value of information in reducing diagnostic errors. Experiments were conducted using patient data collected at a large academic medical center. Our proposed approach outperforms the current clinical practice by 36% in terms of false positive rate given a 2% false negative rate.

[Location selection for Shenyang urban parks based on GIS and multi-objective location allocation model].

Based on geographic information system (GIS) technology and multi-objective location-allocation (LA) model, and in considering of four relatively independent objective factors (population density level, air pollution level, urban heat island effect level, and urban land use pattern), an optimized location selection for the urban parks within the Third Ring of Shenyang was conducted, and the selection results were compared with the spatial distribution of existing parks, aimed to evaluate the rationality of the spatial distribution of urban green spaces. In the location selection of urban green spaces in the study area, the factor air pollution was most important, and, compared with single objective factor, the weighted analysis results of multi-objective factors could provide optimized spatial location selection of new urban green spaces. The combination of GIS technology with LA model would be a new approach for the spatial optimizing of urban green spaces.