Guangrong Li

Clinical Documents Clustering Based on Medication/Symptom Names Using Multi-View Nonnegative Matrix Factorization

Clinical documents are rich free-text data sources containing valuable medication and symptom information, which have a great potential to improve health care. In this paper, we build an integrating system for extracting medication names and symptom names from clinical notes. Then we apply nonnegative matrix factorization (NMF) and multi-view NMF to cluster clinical notes into meaningful clusters based on sample-feature matrices. Our experimental results show that multi-view NMF is a preferable method for clinical document clustering. Moreover, we find that using extracted medication/symptom names to cluster clinical documents outperforms just using words.

Visualization of genetic disease-phenotype similarities by multiple maps t-SNE with Laplacian regularization.

BackgroundFrom a phenotypic standpoint, certain types of diseases may prove to be difficult to accurately diagnose, due to specific combinations of confounding symptoms. Referred to as phenotypic overlap, these sets of disease-related symptoms suggest shared pathophysiological mechanisms. Few attempts have been made to visualize the phenotypic relationships between different human diseases from a machine learning perspective. The proposed research, it is anticipated, will visually assist researchers in quickly disambiguating symptoms which can confound the timely and accurate diagnosis of a disease.MethodsOur method is primarily based on multiple maps t-SNE (mm-tSNE), which is a probabilistic method for visualizing data points in multiple low dimensional spaces. We improved mm-tSNE by adding a Laplacian regularization term and subsequently provide an algorithm for optimizing the new objective function. The advantage of Laplacian regularization is that it adopts clustering structures of variables and provides more sparsity to the estimated parameters.ResultsIn order to further assess our modified mm-tSNE algorithm from a comparative standpoint, we reexamined two social network datasets used by the previous authors. Subsequently, we apply our method on phenotype dataset. In all these cases, our proposed method demonstrated better performance than the original version of mm-tSNE, as measured by the neighbourhood preservation ratio.ConclusionsPhenotype grouping reflects the nature of human disease genetics. Thus, phenotype visualization may be complementary to investigate candidate genes for diseases as well as functional relations between genes and proteins. These relationships can be modelled by the modified mm-tSNE method. The modified mm-tSNE can be applied directly in other domain including social and biological datasets.

Inference of microbial interactions from time series data using vector autoregression model

Microbial interaction, such as species competition and symbiotic relationships, plays important role to enable microorganisms to survive by establishing a homeostasis between microbial neighbors and local environments. Thanks to the recent accumulation of large-scale high-throughput sequencing data of complex microbial communities, there are increasing interests in identifying microbial interactions. Computational methods for microbial interactions inference are currently focused on the similarity among microbial individuals (i.e. cooccurrence and correlation patterns), however, less methods considered the dynamics of a single complex community over time. In this paper, we propose to use a multivariate statistical method - Multivariate Vector Autoregression (MVAR) to infer dynamic microbial interactions from the time series of human gut microbiomes. Specifically, we apply MVAR model on a time series data of human gut microbiomes which were treated with repeated antibiotics. The referred microbial interactions identify novel interactions which may provide a novel complementary to similarity or correlation-based methods.

Mining Biomedical Knowledge Using Chi-Square Association Rule

This paper presents a Mining Biomedical Knowledge method Using Chi-Square Association Rule ABC, it significantly reduces irrelevant connections. The experiment result shows that compared to chi-square, and mutual info ABC approach, Chi-Square Association Rule ABC method generates much fewer rules and a lot of computation time is saved.

A semantic-based approach for mining undiscovered public knowledge from biomedical literature

The problem of mining undiscovered public knowledge from biomedical literature was exemplified by Swansons pioneering work on Raynaud disease/fish-oil discovery in 1986. Since then, there have been many approaches to mine undiscovered public knowledge from biomedical literature. This paper presents a semantic-based approach for mining undiscovered public knowledge from biomedical literature. The method takes advantages of the biomedical ontologies, MeSH and UMLS, as the source of semantic knowledge. A prototype system Biomedical Semantic-based Knowledge Discovery System (Bio-SbKDS) is designed to uncover novel hypothesis/connections hidden in the biomedical literature. Using the semantic types and semantic relations of the biomedical concepts, Bio-SbKDS can identify the relevant concepts collected from Medline and generate the novel hypothesis between these concepts. Bio-SbKDS successfully replicates Dr. Swansons two famous discoveries: Raynaud disease/fish oil and migraine/magnesium. Compared with previous approaches, our method searches much less articles, generates much less but more relevant novel hypotheses, requires much less human intervention in the discovery procedure.

Mining Biomedical Knowledge Using Mutual information ABC

The novel connection between Raynaud disease and fish oils was uncovered from two disjointed biomedical literature sets by Swanson in 1986. Since then, there have been many approaches to uncover novel connections by mining the biomedical literatures. This paper presents a Mining Biomedical Knowledge method Using Mutual information ABC. For a given starting medical concept, it discovers new, potentially meaningful relations/connection with other concepts that have not been published in the medical literature before. The discovered relations/connections are novel and can be useful for domain expert to conduct new experiment and try new treatment.

A text mining method for discovering hidden links

This paper presents a Biomedical Semantic-based Association Rule method that significantly reduces irrelevant connections through semantic filtering. The experiment result shows that compared to traditional association rule-based approach, our approach generates much fewer rules and a lot of these rules represent relevant connections among biological concepts.

Nonmetric property of diabetes-related genes in human gut microbiome

In recent years, a huge number of microbiomic data provide a great opportunity for investigation of microbe-related questions. We find that nonmetric property is a prevalent property in microbiomic data and this property should be considered as a factor in development of computational methods for visualization and dimension reduction of microbiomic data.

Selecting Protein Families for Environmental Features Based on Manifold Regularization

Recently, statistics and machine learning have been developed to identify functional or taxonomic features of environmental features or physiological status. Important proteins (or other functional and taxonomic entities) to environmental features can be potentially used as biosensors. A major challenge is how the distribution of protein and gene functions embodies the adaption of microbial communities across environments and host habitats. In this paper, we propose a novel regularization method for linear regression to adapt the challenge. The approach is inspired by local linear embedding (LLE) and we call it a manifold-constrained regularization for linear regression (McRe). The novel regularization procedure also has potential to be used in solving other linear systems. We demonstrate the efficiency and the performance of the approach in both simulation and real data.