Browsing by Author "Liang, Shaoheng"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
Item Decoupling Lineage-Associated Genes in Acute Myeloid Leukemia Reveals Inflammatory and Metabolic Signatures Associated With Outcomes(Frontiers, 2021) Abbas, Hussein A.; Mohanty, Vakul; Wang, Ruiping; Huang, Yuefan; Liang, Shaoheng; Wang, Feng; Zhang, Jianhua; Qiu, Yihua; Hu, Chenyue W.; Qutub, Amina A.; Dail, Monique; Bolen, Christopher R.; Daver, Naval; Konopleva, Marina; Futreal, Andrew; Chen, Ken; Wang, Linghua; Kornblau, Steven M.Acute myeloid leukemia (AML) is a heterogeneous disease with variable responses to therapy. Cytogenetic and genomic features are used to classify AML patients into prognostic and treatment groups. However, these molecular characteristics harbor significant patient-to-patient variability and do not fully account for AML heterogeneity. RNA-based classifications have also been applied in AML as an alternative approach, but transcriptomic grouping is strongly associated with AML morphologic lineages. We used a training cohort of newly diagnosed AML patients and conducted unsupervised RNA-based classification after excluding lineage-associated genes. We identified three AML patient groups that have distinct biological pathways associated with outcomes. Enrichment of inflammatory pathways and downregulation of HOX pathways were associated with improved outcomes, and this was validated in 2 independent cohorts. We also identified a group of AML patients who harbored high metabolic and mTOR pathway activity, and this was associated with worse clinical outcomes. Using a comprehensive reverse phase protein array, we identified higher mTOR protein expression in the highly metabolic group. We also identified a positive correlation between degree of resistance to venetoclax and mTOR activation in myeloid and lymphoid cell lines. Our approach of integrating RNA, protein, and genomic data uncovered lineage-independent AML patient groups that share biologic mechanisms and can inform outcomes independent of commonly used clinical and demographic variables; these groups could be used to guide therapeutic strategies.Item Interpretable and Efficient Machine Learning in Cancer Biology(2022-12-01) Liang, Shaoheng; Nakhleh, Luay; Chen, KenThe past decade witnessed the advance of machine learning and cancer biology. In therapeutics, chimeric antigen receptor (CAR) treatments and cancer vaccines give new hope for ending cancer. Single-cell sequencing and mass spectrometry enable personalized high-resolution observations of cancer cell behavior and immune response. Computational cancer biology is no different; the continuous evolution of machine learning models, especially neural networks, provides unprecedented potential in making predictions. However, efforts are still needed to tailor the models to interpret specific biological processes. My research explores how knowledge-informed adaptation of machine learning techniques, such as neural networks, metric learning, and probabilistic classifiers helps answer questions in cancer biology. For example, periodicity in the cell cycle and other biological processes inspired our use of a sinusoidal activation function in an autoencoder to discover the periodicity in single-cell transcriptomic data. To efficiently predict biomarkers driving tumorigenesis and immune cell differentiation, we adapted UMAP with L1 regularization and our implementation of OWLQN (Orthant-Wise Limited-memory Quasi-Newton) optimizer. Inspired by structural motifs in antigen presentation, our white-box positive-example-only classifier based on Naïve Bayes formulation and mutual-information-based combinatorial feature selection achieves state-of-the-art accuracy in antigen presentation prediction, helping design cancer vaccines and understand the antigen presentation process. The differences among patient samples, referred to as the batch effect, informed the development of a power analysis web and a differential expression analysis tool to better identify changes in cell type abundances and omics features. Increasingly large omics data also call for more efficient computational methods. My research utilized multiple modeling and computing techniques, such as conjugate priors, quasi-newton method, parallelism, and GPU acceleration, to address this need. For wider usage by different user groups including method developers, bench scientists, and clinicians, we developed the tools as Python or R packages, or web applications. Overall, my research shows that knowledge-informed interpretable modeling of complex biological processes helps make accurate clinical-relevant predictions and generate new knowledge, both important for cancer biology and broader biomedical applications.