Causality plays an essential role in multiple scientific disciplines, including the social, behavioral, and biological sciences and portions of statistics and artificial intelligence. Manual-based causality assessment from a large number of free text-based documents is very time-consuming, labor-intensive, and sometimes even impractical. Herein, we proposed a general causal inference framework named DeepCausality to empirically estimate the causal factors for suspected endpoints embedded in the free text. The proposed DeepCausality seamlessly incorporates AI-powered language models, named entity recognition and Judea Pearl's Do-calculus, into a general framework for causal inference to fulfill different domain-specific applications. We exemplified the utility of the proposed DeepCausality framework by employing the LiverTox database to estimate idiosyncratic drug-induced liver injury (DILI)-related causal terms and generate a knowledge-based causal tree for idiosyncratic DILI patient stratification. Consequently, the DeepCausality yielded a prediction performance with an accuracy of 0.92 and an F-score of 0.84 for the DILI prediction. Notably, 90% of causal terms enriched by the DeepCausality were consistent with the clinical causal terms defined by the American College of Gastroenterology (ACG) clinical guideline for evaluating suspected idiosyncratic DILI (iDILI). Furthermore, we observed a high concordance of 0.91 between the iDILI severity scores generated by DeepCausality and domain experts. Altogether, the proposed DeepCausality framework could be a promising solution for causality assessment from free text and is publicly available through https://github.com/XingqiaoWang/https-github.com-XingqiaoWang-DeepCausality-LiverTox.
Artificial intelligence (AI) has played a crucial role in advancing biomedical sciences but has yet to have the impact it merits in regulatory science. As the field advances, in silico and in vitro approaches have been evaluated as alternatives to animal studies, in a drive to identify and mitigate safety concerns earlier in the drug development process. Although many AI tools are available, their acceptance in regulatory decision-making for drug efficacy and safety evaluation is still a challenge. It is a common perception that an AI model improves with more data, but does reality reflect this perception in drug safety assessments? Importantly, a model aiming at regulatory application needs to take a broad range of model characteristics into consideration. Among them is adaptability, defined as the adaptive behavior of a model as it is retrained on unseen data. This is an important model characteristic which should be considered in regulatory applications. In this study, we set up a comprehensive study to assess adaptability in AI by mimicking the real-world scenario of the annual addition of new drugs to the market, using a model we previously developed known as DeepDILI for predicting drug-induced liver injury (DILI) with a novel Deep Learning method. We found that the target test set plays a major role in assessing the adaptive behavior of our model. Our findings also indicated that adding more drugs to the training set does not significantly affect the predictive performance of our adaptive model. We concluded that the proposed adaptability assessment framework has utility in the evaluation of the performance of a model over time.
Genotype imputation has a wide range of applications in genome-wide association study (GWAS), including increasing the statistical power of association tests, discovering trait-associated loci in meta-analyses, and prioritizing causal variants with fine-mapping. In recent years, deep learning (DL) based methods, such as sparse convolutional denoising autoencoder (SCDA), have been developed for genotype imputation. However, it remains a challenging task to optimize the learning process in DL-based methods to achieve high imputation accuracy. To address this challenge, we have developed a convolutional autoencoder (AE) model for genotype imputation and implemented a customized training loop by modifying the training process with a single batch loss rather than the average loss over batches. This modified AE imputation model was evaluated using a yeast dataset, the human leukocyte antigen (HLA) data from the 1,000 Genomes Project (1KGP), and our in-house genotype data from the Louisiana Osteoporosis Study (LOS). Our modified AE imputation model has achieved comparable or better performance than the existing SCDA model in terms of evaluation metrics such as the concordance rate (CR), the Hellinger score, the scaled Euclidean norm (SEN) score, and the imputation quality score (IQS) in all three datasets. Taking the imputation results from the HLA data as an example, the AE model achieved an average CR of 0.9468 and 0.9459, Hellinger score of 0.9765 and 0.9518, SEN score of 0.9977 and 0.9953, and IQS of 0.9515 and 0.9044 at missing ratios of 10% and 20%, respectively. As for the results of LOS data, it achieved an average CR of 0.9005, Hellinger score of 0.9384, SEN score of 0.9940, and IQS of 0.8681 at the missing ratio of 20%. In summary, our proposed method for genotype imputation has a great potential to increase the statistical power of GWAS and improve downstream post-GWAS analyses.
Here we study the semantic search and retrieval problem in biomedical digital libraries. First, we introduce MedGraph, a knowledge graph embedding-based method that provides semantic relevance retrieval and ranking for the biomedical literature indexed in PubMed. Second, we evaluate our approach using PubMed's Best Match algorithm. Moreover, we compare our method MedGraph to a traditional TF-IDF-based algorithm. Third, we use a dataset extracted from PubMed, including 30 million articles' metadata such as abstracts, author information, citation information, and extracted biological entity mentions. We pull a subset of the dataset to evaluate MedGraph using predefined queries with ground truth ranked results. To our knowledge, this technique has not been explored before in biomedical information retrieval. In addition, our results provide some evidence that semantic approaches to search and relevance in biomedical digital libraries that rely on knowledge graph modeling offer better search relevance results when compared with traditional methods in terms of objective metrics.