|in | Written by

Immunotherapy Response Prediction in Melanoma

2025 DF/HCC Cancer Data Sciences Program Lunch Workshop

Tuesday June 3, 2025
1:00-4:00PM
Yawkey Conference Center, Dana-Farber Cancer Institute

RSVP, seating limited: https://bit.ly/dfhcc-cds25

Speakers:

  • Alexander Gusev, PhD, Associate Professor, Harvard Medical School and Dana-Farber Cancer Institute
  • Rizwan Haq, MD, PhD, Assistant Professor, Harvard Medical School and Dana-Farber Cancer Institute
  • David Liu, MD, MPH, Associate Professor, Harvard Medical School and Dana-Farber Cancer Institute
  • Manuel Schürch, PhD, Postdoctoral Fellow, Dana-Farber Cancer Institute and Harvard University
  • Eugene Semenov, MD, Assistant Professor, Harvard Medical School and Mass General Hospital
  • Tuulia Vallius, MD, PhD, Postdoctoral Fellow, Harvard Medical School

Moderated by Franziska Michor, PhD, Charles A. Dana Chair of Human Cancer Genetics, DFCI, and Professor of Computational Biology, Harvard University

|in | Written by

Statistics for Computational Biology Projects

HBC Current Topics in Bioinformatics
June 18, 2025, 01:00-4:00 PM
Register here.

Erica Holdmore, PhD
Computational Biologist, Knowledge Systems
DFCI Department of Data Sciences

Statistics is an important tool for computational biologists because it helps us quantitatively understand and analyze biological data. This interactive training session will cover an introduction to statistical concepts. Topics will include: experimental design, data cleaning, common analysis methods (logistic regression, ANOVA, GLM, multiple comparisons), and interpreting results.

|in | Written by

Complex Disease Modeling And Efficient Drug Discovery With Large Language Models

HSPH Biostatistics and DFCI Data Science Seminar
Tuesday April 29 from 11:00-12:00pm
Zoom only (Link to be posted shortly)

Yu Li, PhD
Assistant Professor, CSE
The Chinese University of Hong Kong

Large language models, which can integrate and process large amounts of data in biomedicine, have great potential in modeling complex diseases and discovering functional biomolecules for potential therapeutics. To model complex diseases and identify the potential drug targets for such diseases, we built a language model trained on the insurance claims of around 123 million US people. With the model, we can give a unified representation of all the common complex diseases, which enables us to predict the genetic parameters of the diseases and discover unique genetic loci related to them efficiently. Then, we developed models based on protein language models to efficiently discover remote homologs and functional biomolecules from nature, such as signal peptides and antimicrobial peptides. With the model, we can identify remote homologs 22 times faster than PSI-BLAST and discover diverse functional peptides with sequence similarity lower than 20% against the known ones. Finally, we developed an RNA language model to model the RNA sequence and structure relation, which enables us to perform RNA structure prediction and reverse design effectively. Within two months, we designed and experimentally validated 19 RNA aptamers that are structurally similar, yet sequence dissimilar, to known light-up aptamers. More importantly, 10 designed aptamers show higher fluorescence than the native Mango-I. The above projects demonstrate the great potential of large language models in promoting fundamental computational biological research and potential transformational development.

|in | Written by

Modeling Multiscale Genome and Cellular Organization

HSPH Biostatistics and DFCI Data Science Seminar
Tuesday April 15 at 4:00pm
Dana-Farber Cancer Institute
Center for Life Sciences Building, 11th Floor, Room 11081

Jian Ma, PhD
Ray and Stephanie Lane Professor of Computational Biology
Carnegie Mellon University

 

The intersection of Al/ML and biomedicine is entering a transformative era, with growing potential to
impact both basic research and translational medicine. Yet, despite remarkable advances in high-
throughput technologies across genomics and cell biology, our understanding of the diverse cell types
in the human body and the underlying principles of intracellular molecular organization and
intercellular spatial interactions remains incomplete. A central challenge lies in developing
computational frameworks that can integrate molecular, cellular, and tissue-level data to advance cell
biology at an unprecedented scale. In this talk, I will present our recent work on machine learning
approaches for regulatory genomics, with a focus on single-cell 3D epigenomics. We introduce methods
that connect different layers of 3D genome architecture and cellular function at single-cell resolution,
including graph- and hypergraph-based models that capture spatial genome organization. I will also
highlight our latest efforts in developing self-supervised learning frameworks to delineate multiscale
cellular interactions within complex tissues, enabling the discovery of previously unrecognized spatially
organized patterns. Together, these Al-driven models provide a foundation for integrative, multiscale
representations of cellular systems, offering new insights into genome structure, gene regulation, and
cell-cell communication. This line of work opens new opportunities toward building cohesive multiscale
cellular models applicable across a broad range of contexts in health and disease.

|in | Written by

Fréchet Regression of Random Objects on Vector Covariates and Its Applications for Single Cell RNA-seq Data Analysis

HSPH Biostatistics and DFCI Data Science Colloquium
Thursday, April 3, 2025
4:00pm
Harvard TH Chan School of Public Health, FXB G13

Hongzhe Li, PhD
Perelman Professor of Biostatistics, Epidemiology and Informatics
Director, Center for Statistics in Big Data Vice Chair for Research Integration, Department of Biostatistics, Epidemiology and Informatics, University of Pennsylvania

Population-level single-cell RNA-seq data captures gene expression profiles across thousands of cells from each individual in a sizable cohort. This data facilitates the construction of cell-type- and individual-specific gene co-expression networks by estimating covariance matrices. Investigating how these co-expression networks relate to individual-level covariates provides critical insights into the interplay between molecular processes and biological or clinical traits. This talk introduces Fréchet regression, modeling covariance matrices as outcomes and vector covariates as predictors, using the Wasserstein distance between covariance matrices as a metric instead of the Euclidean distance. A test statistic is proposed based on the Fréchet mean and covariate-weighted Fréchet mean, with its asymptotic null distribution derived. Analysis of large-scale single-cell RNA-seq data reveals an association between the co-expression network of genes in the nutrient-sensing pathway and age, highlighting perturbations in gene co-expression networks with aging. Additionally, a robust local Fréchet regression approach, leveraging neural unbalanced optimal transport, is briefly discussed to explore how cells are temporally organized during the differentiation of human embryonic stem cells into embryoid bodies.

|in | Written by

2025 Marvin Zelen Memorial Symposium

We invite you to attend the Marvin Zelen Memorial Symposium, an event that celebrates the life and contributions of a remarkable figure in the field of statistics. This symposium will be held on Friday, April 4, 2025, from 1:00 PM to 5:00 PM in the Kresge G1 Auditorium, located in the Harvard TH Chan School of Public Health at 677 Huntington Ave, Boston, MA. A reception will follow.

The Marvin Zelen Memorial Symposium is an opportunity for statisticians, researchers, and professionals in the field to come together and engage in thought-provoking discussions and presentations. We have curated an exceptional lineup of speakers who will share their expertise and insights on this year’s theme, Data-Driven Controversies in Science. The three topics discussed will be:

  • Beyond the Hype: Unveiling the Limits of Machine Learning in Science and Medicine
  • Forecasting the Future: How Accurate Are Our Climate Change Models?
  • Unraveling COVID-19: Origins, Interventions, and Lessons Learned

Full program available here: https://zelen25.my.canva.site/

To ensure your attendance, please RSVP by clicking on this link: https://bit.ly/zelen25.

2025 Speakers:

Alina Chan, PhD,Broad Institute
Auroop R. Ganguly, PhD,Northeastern University
Sayash Kapoor,Princeton University
Marc Lipsitch, DPhil, Harvard TH Chan School of Public Health
Arjun Manrai, PhD,Harvard Medical School
Gavin A. Schmidt, PhD,Climate Scientist

|in | Written by

William Lotter Wins Prestigious Awards in Oncology and Radiology

Dr. William (Bill) Lotter, PhD, a leading researcher in artificial intelligence (AI) for medical imaging, has been honored with three prestigious accolades for his contributions to oncology and radiology.

Dr. Lotter was named one of the recipients of the Wong Family Awards in Translational Oncology for FY25 for his innovative project, “Bridging spatial biology with routine histopathology using AI to improve cancer prognostication.” His work will study the tumor microenvironment by combining spatial biology data with conventional histopathology using AI, paving the way for more accurate and actionable cancer prognoses. This award goes to advancing the careers of early career investigators as they pursue innovative projects in clinical and/or translational oncology, biotechnology development, precision medicine, or immunotherapy approaches.

In addition, Dr. Lotter has been named to the Radiology Business Forty Under 40 Class of 2024, a distinguished list highlighting emerging leaders under 40 who are driving innovation and progress in the field of radiology. The recognition underscores the impact of his efforts in using AI to enhance medical imaging and diagnostic practices.

Furthermore, Dr. Lotter has received a Trailblazer Award from the National Institute of Biomedical Imaging and Bioengineering (NIBIB) for his proposal “Improving prognosis prediction and therapy selection for cutaneous squamous cell carcinomas using artificial intelligence.” His project will leverage AI to more accurately identify aggressive cutaneous squamous cell carcinomas, a type of skin cancer, to guide treatment selection. Trailblazer Awards are designed to fund early career investigators for high-risk, high-reward projects at the interface of quantitative and biomedical sciences.

Dr. Lotter is an Investigator in the Department of Data Science at the Dana-Farber Cancer Institute and Assistant Professor at the Harvard Medical School, where he focuses on integrating computational methodologies with medical imaging to improve patient outcomes. His honors showcase his dedication to bridging technology with clinical impact, where his work highlights the transformative potential of AI in medicine.

|in | Written by

Heng Li, PhD Named International Society of Computational Biology Fellow

The International Society of Computational Biology (ISCB) welcomes Heng Li, PhD to the prestigious 2023 ISCB Fellows cohort. Dr. Li is Assistant Professor of Biomedical informatics, Dana-Farber Cancer Institute and Harvard Medical School.

Per ISCB’s release: The Fellows program was created to honor members who have distinguished themselves through outstanding contributions to the fields of computational biology and bioinformatics. Begun in 2009, 2023 marks the 14th anniversary of the program. Each year, ISCB seeks Fellows’ nominations from our members who meet the eligibility criteria for significant scientific and leadership contributions to the field of computational biology and bioinformatics.

Dr. Li is recognized for his influential tools for the processing of sequence data and his dedication to open-source software, including the detailed documentation which has permitted numerous researchers to learn and build from his work.

|in | Written by

BioC2023: the Bioconductor Annual Conference

We are incredibly excited that Bioc2023 the annual Bioconductor meeting will be in Boston at the Dana-Farber Cancer Institute from August 2-4. It is a hybrid meeting to enable maximum outreach to our global community. Registration is now open and scholarships are available. 

Contact us for sponsorship opportunities. 

Speakers include:

  • JJ Allaire (Founder and CEO of RStudio, Posit PBC)
  • Heng Li (Associate Professor, Dana-Farber Cancer Institute, Harvard Medical School)
  • Beth Cimini (Senior Group Leader, Broad Institute of MIT & Harvard)
  • Jeffrey Moffitt (Assistant Professor, Harvard Medical School and Boston Children’s Hospital) 
  • Sam Lent (Senior Computational Biologist at Freenome)

Connect with talented R/Bioconductor users & developers, data scientists, biostatisticians, and bioinformaticians at #Bioc2023

|in | Written by

David Harrington, PhD Receives 2023 Marvin Zelen Award

Article courtesy of Harvard T.H. Chan School of Public Health, Department of Biostatistics:

We are pleased to announce Dr. David Harrington, Emeritus Professor of Statistics Professor of Biostatistics, Harvard T.H. Chan School of Public Health and former Chair of the Department of Data Science at DFCI, will be the recipient of the 2023 Marvin Zelen Leadership Award in Statistical Science.

We will host Dave for a lecture on “The special relationship between survival analysis and cancer research — successes and persistent problems.” on Wednesday, April 26th in FXB G11 at 4pm, followed by a reception in the FXB Atrium.

Over the course of his exceptional 45-year career, Dave has served as both a scholar and a leader in the theory and practice of statistics in medical research. In addition to being on the forefront of the development of the new field of biostatistics, he played a crucial role in preparing a new generation of statisticians and physicians, leading the field of medicine towards a more rational use of data. The breadth of his contributions in both research and pedagogy reflect the fundamental vision of Marvin Zelen, making Dave a natural recipient for this prestigious award.

Dave received his PhD in 1976 from the University of Maryland with a focus on statistical theory and methods and spent nearly all of his 45-year career in the development of statistical methods and their application in medical and public health research, as reflected in his extensive CV. He joined the faculty at the Harvard School of Public Health and the Dana-Farber Cancer Institute (DFCI) in 1984 and worked as a professor of Biostatistics from 1990-2018. He chaired the Department of Biostatistics and Computational Biology (now the Department of Data Science) of the Dana-Farber Cancer Institute from 1998–2009, and the Department of Statistics at Harvard from 2012–2014. While at Harvard he developed and taught a course attended by hundreds of students each year providing a data-driven introduction to biostatistics. He also co-wrote a text on the subject and introduced it online as an open-source resource. During the 11 years he was Chair of the Biostatistical Department at DFCI, Dave led the expansion of membership as well as the scope of research, embracing the new field of computational biology.

Dave’s contributions in academia were paralleled by his outstanding contributions to the field of cancer research. From 2001 to 2014, Dave served as principal investigator of the NCI sponsored Statistical Coordinating Center for the Cancer Care Outcomes Research and Surveillance (CanCORS) Consortium, a study of access to and outcomes from cancer care in a cohort of 10,000 patients with colorectal or lung cancer. Dave led nation-wide clinical trial statistical coordinating centers and was instrumental in establishing the DF/HCC Biostatistics research program. He also served on the Scientific Advisory Board for St. Jude’s Children’s Hospital for five years and on the standing Data Safety Monitoring Committees for NIAID HIV studies in Sub-Saharan Africa (2001-17, Chair from 2015), as well as cancer trials at Memorial Sloan Kettering for 20 years. From 2000-2008 he served on the US FDA Oncologic Advisory committee with continued service as an Ad hoc member.

The importance of Dave’s contributions is reflected in the many teaching awards and accolades he earned over his career. These included the Nichols Award for Teaching Excellence, the Levenson Memorial Teaching Prize, and the Hoopes Prize for Senior Thesis Mentoring from Harvard, as well as the Herman Callert Leadership Award from Hasselt University, Belgium. Dave is also an elected fellow of the International Statistical Institute, the Institute of Mathematical Sciences, and the American Statistical Association. Throughout his career, he also contributed his expertise to major medical publications, serving as the lead statistical editor for the New England Journal of Medicine.

Marvin Zelen had a vision for the future of the field of Biostatistics, recognizing the importance of faculty and students meaningfully expanding its applications in classroom and hospital settings. Dr. Zelen’s vision was exemplified by his recruitment of David Harrington to join his department nearly four decades ago. Though he followed in Martin’s footsteps, Dave’s pathways were innovative, and his style was thoughtful. His career and accomplishments exceeded Marvin’s high expectations and he stewarded the development of a foundation for the study of Biostatistics at Harvard that continues to be fertile ground for the growth and expansion of the field.