Computational Medicine Night is Tuesday, March 5, 2019.

Register here to attend.

Calendar

Mar
5
Tue
2019
Smita Krishnaswamy, Yale University, “Manifold Learning Yields Insight into Cellular State Space under Complex Experimental Conditions”
Mar 5 @ 11:00 am – 12:00 pm

Jump to:

Bio

Manifold Learning Yields Insight into Cellular State Space under Complex Experimental Conditions

Dr. Smita Krishnaswamy is an Assistant Professor in the department of Genetics at the Yale School of Medicine and Department of Computer Science in the Yale School of Applied Science and Engineering. She is also affiliated with the Yale Center for Biomedical Data Science, Yale Cancer Center, and Program in Applied Mathematics. Smita’s research focuses on developing unsupervised machine learning methods (especially graph signal processing and deep-learning) to denoise, impute, visualize and extract structure, patterns and relationships from big, high throughput, high dimensional biomedical data. Her methods have been applied variety of datasets from many systems including embryoid body differentiation, zebrafish development, the epithelial-to-mesenchymal transition in breast cancer, lung cancer immunotherapy, infectious disease data, gut microbiome data and patient data.

Smita teaches three courses: Machine Learning for Biology (Fall), Deep Learning Theory and applications (spring), Advanced Topics in Machine Learning & Data Mining (Spring). She completed her postdoctoral training at Columbia University in the systems biology department where she focused on learning computational models of cellular signaling from single-cell mass cytometry data. She was trained as a computer scientist with a Ph.D. from the University of Michigan’s EECS department where her research focused on algorithms for automated synthesis and probabilistic verification of nanoscale logic circuits. Following her time in Michigan, Smita spent 2 years at IBM’s TJ Watson Research Center as a researcher in the systems division where she worked on automated bug finding and error correction in logic.

Click here to view webcast.

Abstract

Manifold Learning Yields Insight into Cellular State Space under Complex Experimental Conditions

Recent advances in single-cell technologies enable deep insights into cellular development, gene regulation, cell fate and phenotypic diversity. While these technologies hold great potential for improving our understanding of cellular state space, they also pose new challenges in terms of scale, complexity, noise, measurement artifact which require advanced mathematical and algorithmic tools to extract underlying biological signals. Further as experimental designs become more complex, there are multiple samples (patients) or conditions under which single-cell RNA sequencing datasets are generated and must be batch corrected and the corresponding populations of single cells compared. In this talk, I cover one of most promising techniques to tackle these problems: manifold learning. Manifold learning provides a powerful structure for algorithmic approaches to denoise the data, visualize the data and understand progressions, clusters and other regulatory patterns, as well as correct for batch effects to unify data. I will cover two alternative approaches to manifold learning, graph signal processing (GSP) and deep learning (DL), and show results in several projects including: 1) MAGIC (Markov Affinity-based Graph Imputation of Cells): an algorithm that low-pass filters data after learning a data graph, for denoising and transcript recover of single cells, validated on HMLE breast cancer cells undergoing an epithelial-to-mesenchymal transition. 2) PHATE (Potential of Heat-diffusion Affinity-based Transition Embedding): a visualization technique that offers an alternative to tSNE in that it preserves local and global structures, clusters as well as progressions using an information-theoretic distance between diffusion probabilities. 3) MELD (Manifold-enhancement of latent variables): an analysis technique that filters the experimental label on the graph learned from single-cell data in order to boost experimental signal and associated correlations. 4) SAUCIE (Sparse AutoEncoders for Clustering Imputation and Embedding), our highly scalable neural network architecture that simultaneously performs denoising, batch normalization, clustering and visualization via custom regularizations on different hidden layers. We demonstrate the power of SAUCIE on a massive single-cell dataset consisting of 180 samples of PBMCs from Dengue patients, with a total of 20 million cells. We find that SAUCIE performs all the above tasks efficiently and can further be used for stratifying patients themselves on the basis of their single cell populations. Finally, I will preview ongoing work in neural network architectures for predicting dynamics and other biological tasks.

 

Click here to view webcast.

Computational Medicine Night 2019
Mar 5 @ 5:00 pm – 7:15 pm

Computational Medicine (CM) Night is the Institute for Computational Medicine’s annual networking event for undergraduates and trainees who are interested in academic programs in Computational Medicine and the research conducted in ICM labs. Held each spring term, Computational Medicine Night showcases trainee research and provides a forum for interested students to meet and mingle with ICM faculty, students, and postdoctoral fellows, to gather information, and to ask questions.

A typical Computational Medicine Night includes:

• Overview of academic programs in CM

• Trainee Research Presentations

• Poster Session

• Meet, Mingle & Eat

Register here. Registration deadline: Feb. 26.

Apr
30
Tue
2019
Steven Niederer, King’s College London, “Applying Cardiac Modelling to Study Drugs, Devices and Diagnosis”
Apr 30 @ 11:00 am – 12:00 pm

Jump to:

Bio

“Applying Cardiac Modelling to Study Drugs, Devices and Diagnosis”

Dr. Steven Niederer received his DPhil in computer science from the University of Oxford in 2009, where he developed a detailed biophysical model of the rat heart. At the end of his DPhil he was awarded a research fellowship from the UK Engineering and Physical Sciences Research Council (EPSRC) to create pre-clinical models of heart failure. In 2010, he was appointed as a lecturer at King’s College London (KCL). At KCL he set up a research group focused on the clinical translation of cardiac models. Since joining KCL he has received a UK research council fellowship to work on the clinical translation of cardiac models to study heart failure, funding from the British Heart Foundation to work on simulating heart failure, ventricular arrhythmias and atrial fibrillation and industry support from pharmaceutical (Pfizer), device (EBR systems, Abbot, Boston Scientific, Medtronic) and imaging (Siemens) companies to use computer models for commercial applications. The combination of engineering, clinical and industrial research drives the translational focus of the group.

 

Click here to view webcast.

Abstract

“Applying Cardiac Modelling to Study Drugs, Devices and Diagnosis”

The ability to measure the heart, its shape, its structure and its function across multiple spatial and temporal scales continues to grow. Interpreting this data remains challenging. Computational biophysical models of the heart allow us to quantitatively link and interpret these large disparate data sets within the context of known cardiac physiology and invariable physical constraints. Within these models, we can infer unobservable states, propose and test new hypothesis and predict how systems will respond to challenges increasing our ability to interrogate and understand biological systems. We are increasingly applying this approach to modelling human hearts to investigate clinical applications. In this presentation, I will give an overview on our modelling work simulating anthracycline-induced heart failure, how we are using models of individual patients to study cardiac resynchronisation therapy and how we are using simulations to characterise the anatomy and pathophysiology of atrial fibrillation patients. Finally, I will present some of our preliminary results on simulating the four-chamber heart to begin simulating the interactions between atrial and ventricular function.

 

Click here to view webcast.

JHU - Institute for Computational Medicine