Russell Schwartz
Professor and Department Head Carnegie Mellon University
- Pittsburgh PA
Russell Schwartz works in computational biology and the use of algorithms, AI, machine learning, and simulation in biomedical science.
Biography
Areas of Expertise
Media Appearances
Pittsburgh’s AI-Powered Renaissance
CMU News online
2024-10-09
"There is tremendous excitement about the new generation of AI tools and nowhere could their impact be greater than in improving human health. AI tools seem to hold great promise for personalized medicine but also warrant caution as we see what they do not do well and how much we do not yet understand about how they work and how they might be improved. The big leaps in AI we are seeing now are neither the beginning nor the end of the field. They were built on a foundation of decades of research into AI fundamentals and their application to real-world problems in human health and disease, areas in which Pittsburgh researchers have long been world leaders. And there is much more to be done to fully realize their potential."
Computer science professor Sorin Istrail wins award recognizing algorithms research
The Brown Daily Herald online
2022-12-02
Through the paper and its surrounding work, Istrail and colleagues made use of one of the pillars of computer science in genomics — recognizing that a genome can be modeled as a computational artifact and that, in doing so, one is able to access a powerful set of tools for analyzing it, according to Russell Schwartz, co-author of the paper and head of the computational biology department at Carnegie Mellon University.
Media
Social
Industry Expertise
Education
Massachusetts Institute of Technology
Ph.D.
Computer Science
Links
Articles
A Clonal Evolution Simulator for Planning Somatic Evolution Studies
Journal of Computational Biology2023
Somatic evolution plays a key role in development, cell differentiation, and normal aging, but also in diseases such as cancer. Understanding mechanisms of somatic mutability and how they can vary between cell lineages will likely play a crucial role in biological discovery and medical applications. This need has led to a proliferation of new technologies for profiling single-cell variation, each with distinctive capabilities and limitations that can be leveraged alone or in combination with other technologies. The enormous space of options for assaying somatic variation, however, presents unsolved informatics problems with regard to selecting optimal combinations of technologies for designing appropriate studies for any particular scientific questions.
Simulating the distortion of clonal fractions in ctDNA due to spatially heterogenous selection
Cancer Research2023
Time-series circulating tumor DNA (ctDNA) sequencing has the potential to reveal emerging variants in the tissue in real time, and there is now substantial evidence that it can detect tumor growth and treatment-resistant mutations long before growth is visible. However, the reliability of ctDNA for profiling the primary tumor may be compromised by spatial heterogeneity in the tumor genetics, for example due to selective effects of differential drug penetration, immune infiltration, and oxygenation. We explore the influence of spatial factors on tumor genetics through a lattice-based branching process model of solid tumor evolution and ctDNA shedding with the goal of understanding where spatially variable selection pressure could lead to a significant difference between the clonal fractions in the blood and the tissue.
Reconstructing tumor clonal lineage trees incorporating single-nucleotide variants, copy number alterations and structural variations
Bioinformatics2022
Motivation
Cancer develops through a process of clonal evolution in which an initially healthy cell gives rise to progeny gradually differentiating through the accumulation of genetic and epigenetic mutations. These mutations can take various forms, including single-nucleotide variants (SNVs), copy number alterations (CNAs) or structural variations (SVs), with each variant type providing complementary insights into tumor evolution as well as offering distinct challenges to phylogenetic inference.
Interpretable deep learning for chromatin-informed inference of transcriptional programs driven by somatic alterations across cancers
Nucleic Acids Research2022
Cancer is a disease of gene dysregulation, where cells acquire somatic and epigenetic alterations that drive aberrant cellular signaling. These alterations adversely impact transcriptional programs and cause profound changes in gene expression. Interpreting somatic alterations within context-specific transcriptional programs will facilitate personalized therapeutic decisions but is a monumental task. Toward this goal, we develop a partially interpretable neural network model called Chromatin-informed Inference of Transcriptional Regulators Using Self-attention mechanism (CITRUS). CITRUS models the impact of somatic alterations on transcription factors and downstream transcriptional programs.
Semi-deconvolution of bulk and single-cell RNA-seq data with application to metastatic progression in breast cancer
Bioinformatics2022
Motivation
Identifying cell types and their abundances and how these evolve during tumor progression is critical to understanding the mechanisms of metastasis and identifying predictors of metastatic potential that can guide the development of new diagnostics or therapeutics. Single-cell RNA sequencing (scRNA-seq) has been especially promising in resolving heterogeneity of expression programs at the single-cell level, but is not always feasible, e.g. for large cohort studies or longitudinal analysis of archived samples.
