Genentech Research and Early Development | USA

Design for Inference and the Power of Random Experiments in Biology   (Sunday, August 29)




As Executive Vice President, Genentech Research and Early Development (gRED), Aviv Regev is responsible for the management of all aspects of Genentech’s drug discovery and drug development activities. She is a member of the Genentech Executive Committee and the expanded Corporate Executive Committee for Roche.


Prior to Genentech, Regev served as Chair of the Faculty, Core Institute Member, founding director of the Klarman Cell Observatory, and member of the Executive Leadership Team of the Broad Institute of MIT and Harvard, as well as Professor of Biology at MIT and Investigator at the Howard Hughes Medical Institute. She is a founding co-chair of the Human Cell Atlas.


Regev has served on multiple corporate advisory, scientific advisory, and journal editorial boards, including the advisory committee to the National Human Genome Research Institute at the National Institutes of Health.


Regev is a leader in deciphering molecular circuits that govern cells, tissues and organs in health and their malfunction in disease. Her lab has pioneered foundational experimental and computational methods in single-cell genomics, working toward greater understanding of the function of cells and tissues in health and disease, including autoimmune disease, inflammation and cancer. She is a member of the National Academy of Sciences and National Academy of Medicine, and she is also a Fellow of the International Society of Computational Biology.


Regev has a Ph.D. in computational biology and a Master of Science from Tel Aviv University.





UC San Diego, Dept of Medicine | USA

Building the Mind of Cancer (Sunday, August 29)


Most drugs entering clinical trials fail, often related to an incomplete understanding of the mechanisms governing drug response. Machine learning techniques hold immense promise for better drug response predictions, but most have not reached clinical practice due to their lack of interpretability and their focus on monotherapies. To address these challenges I will describe development of DrugCell, an interpretable deep learning model of human cancer cells trained on the responses of thousands of tumor cell lines to thousands of approved or exploratory therapeutic agents. The structure of the model is built from a knowledgebase of molecular pathways important for cancer, which can be drawn from literature or formulated directly from integration of data from genomics, proteomics and imaging. Based on this structure, alterations to the tumor genome induce states on specific pathways, which combine with drug structure to yield a predicted response to therapy. The key pathways in  capturing a drug response lead directly to design of synergistic drug combinations, which we validate systematically by combinatorial CRISPR, drug-drug screening in vitro, and patient-derived xenografts. We also explore a recently developed technique, few-shot machine learning, for training versatile neural network models in cell lines that can be tuned to new contexts using few additional samples. The models quickly adapt when switching among different tissue types and in moving to clinical contexts, including patient-derived xenografts and clinical samples. These results begin to outline a blueprint for constructing interpretable AI systems for predictive medicine.


Trey Ideker, Ph.D. is a Professor in the Departments of Medicine, Bioengineering and Computer Science at UC San Diego. Additionally, he is the Director or Co-Director of the National Resource for Network Biology (NRNB), the Cancer Cell Map Initiative (CCMI), the Psychiatric Cell Map Initiative (PCMI), and the UCSD Bioinformatics PhD Program, and former Chief of Genetics in the Department of Medicine. Dr. Ideker received Bachelor’s and Master’s degrees from MIT in Electrical Engineering and Computer Science and his Ph.D. from the University of Washington in Molecular Biology under the supervision of Dr. Leroy Hood.

Dr. Ideker is a pioneer in using genome-scale measurements to construct network models of cellular processes and disease and has founded software tools including the Cytoscape ecosystem for biological network analysis, which has been cited >22,000 times. The Ideker Laboratory seeks to create artificially intelligent models of cancer and other diseases for the translation of patient data to precision diagnosis and treatment.

Dr. Ideker serves on the Editorial Boards for Cell, Cell Reports, Molecular Systems Biology, and PLoS Computational Biology and is a Fellow of AAAS and AIMBE. He was included in the 2020 Web of Science Highly Cited Researchers list, named a Top 10 Innovator by Technology Review and was the recipient of the Overton Prize from the International Society for Computational Biology. His work has been featured in news outlets such as NPR, BBC, New York Times, Scientific American, Smithsonian, Discover, Forbes magazine, Popular Mechanics and People Magazine. 


University of Waterloo | CANADA


Enabling Personalized Cancer Immunotherapy by Deep Learning (Monday, August 30)


Neoantigen discovery are at the heart of personalized cancer immunotherapy as well as for covid-19 T cell vaccine design. Neoantigens can be eluted from the cell surface and measured by mass spectrometry (MS). Deep learning has replaced and significantly improved the previous dynamic programming methods to process MS data.



Ming Li is a Canada Research Chair in Bioinformatics and a University Professor at the University of Waterloo. He is a fellow of Royal Society of Canada, ACM, and IEEE. He is a recipient of the 2010's Killam Prize. Together with Paul Vitanyi they have co-authored the book "An introduction to Kolmogorov complexity and its applications". His recent research interests include proteomics, peptidomics, and NLP.


INRIA (French Institute for Research in Computer Science and Automation) Lyon
University of Lyon | FRANCE

Precision tango (Tuesday, August 31)

In this talk, I’ll present the combinatorial algorithms that we have been developing since a few years now to address some problems in biology. Exact algorithms have been privileged whenever possible, hence the term precision in the title. Moreover, when there is more than one solution, all are enumerated (listed). Such solutions correspond to elements that verify some a priori well-identified characteristics which may include optimising a given function.  Enumeration is crucial because of other differences such solutions may present that can be biologically important. These differences may be shared among subsets of the solutions. I’ll then also present some of the recent approaches we have developed to address this in ways that are efficient complexity-wise and in practice while remaining exact.
In doing so, three main contexts in the area of computational biology will be covered. These are genomics/transcriptomics, co-phylogeny/co-evolution, and metabolism. The desire to investigate these contexts has a specific biological motivation. This is to arrive at a better understanding of the interactions that most, if not all living systems have among themselves and with their environment.
This leads us to the term tango in the title. As may be well known, tango is a partner dance – a dance of interaction. It is also a dance of improvisation that however requires high precision, leading back again to the first term of the title. We will see that there is another scientific motivation for wanting to use the term tango in the title, that is related to the informal meaning of an expression it gave birth to. This is the expression “it takes two to tango”.


Marie-France Sagot is director of research at the French Institute for Research in Computer Science and Automation (INRIA) and a member of staff at the University of Lyon/CNRS where she works on computational biology, algorithm analysis and design, and combinatorics. As concerns computational biology, she is more specifically interested by comparative genomics, (co-)evolution, RNA structures, (co-)phylogeny, regulation, biological networks, NGS, and symbiosis. She is a Fellow of the International Society for Computational Biology (ISCB).





University of California San Francisco | USA

Sequence-structure-function modeling for DNA (Tuesday, August 31)


The human genome sequence folds in three dimensions (3D) into a rich variety of locus-specific contact patterns. Despite growing appreciation for the importance of 3D genome folding in evolution and disease, we lack models for relating mutations in genome sequences to changes in genome structure and function. Towards that goal, we developed a comparative genomics approach to quantify evolutionary constraint across genomic elements important to 3D genome folding. We discovered that specific sequences that sit at boundaries between chromatin domains are under strong negative selection in the human population and over primate evolution. Motivated by this signature of functional importance, we developed a deep convolutional neural network, called Akita, that accurately predicts genome folding from DNA sequence alone. Representations learned by Akita underscore the importance of the structural protein CTCF but also reveal a complex grammar beyond CTCF binding sites that underlies genome folding. Akita enabled rapid in silico predictions for effects of sequence mutagenesis on the 3D genome, including differences in genome folding across species and in disease cohorts, which we are validating with CRISPR-edited genomes. This prediction-first strategy exemplifies my vision for a more proactive, rather than reactive, role for data science in biomedical research.


Dr. Katherine S. Pollard is Director of the Gladstone Institute of Data Science & Biotechnology, Investigator at the Chan Zuckerberg Biohub, and Professor in the Department of Epidemiology & Biostatistics and Bioinformatics Graduate Program at UCSF. Her lab develops statistical models and open source bioinformatics software for the analysis of massive genomic datasets. Previously, Dr. Pollard was an assistant professor in the University of California, Davis Genome Center and Department of Statistics. She earned her PhD in Biostatistics from the University of California, Berkeley and was a comparative genomics postdoctoral fellow at the University of California, Santa Cruz. She was awarded the Thomas J. Watson Fellowship, the Sloan Research Fellowship, and the Alumna of the Year from UC Berkeley. She is a Fellow of the International Society for Computational Biology, American Institute for Medical and Biological Engineering, and of the California Academy of Sciences.


Department of Computer Science & Lewis-Sigler Institute for Integrative Genomics, Princeton University | USA


Algorithms for deciphering disease networks (Wednesday, September 1)



Networks of molecular interactions underlie virtually all functions executed within a cell.  Networks thus provide a powerful foundation within which to interpret a wide range of rapidly accumulating biological data.   In this talk, I will present formulations and algorithms that leverage the structure and function of biological networks in order to gain insights into diseases such as cancer.  First, I will introduce a framework that can rapidly integrate multiple sources of information about molecular functionality in order to discover key interactions within a network that tend to be disrupted in cancers.  Crucially, our approach is based on analytical calculations that obviate the need to perform time-prohibitive permutation-based significance tests. Second, I will describe algorithms that map prior and newly collected data onto network nodes in order to uncover disease-relevant subnetworks.  Finally, I will discuss methods for uncovering noncoding mutations that can alter regulatory networks in cancer.    Overall, our work showcases the versatility and power of a network viewpoint in advancing biomedical discovery.

Mona Singh is Professor in the Department of Computer Science and the Lewis-Sigler Institute of Integrative Genomics at Princeton University.    Her research focuses on developing algorithmic and machine learning approaches for inferring protein interactions, specificity and networks, often from a structural perspective; for characterizing protein sequences and domains; for predicting the impact of mutations and variation, especially in the context of diseases such as cancer; and for analyzing biological networks in order to uncover cellular organization, functioning, and pathways. Among her awards are the Presidential Early Career Award for Scientists and Engineers (PECASE) in 2001,  She is a Fellow of the International Society for Computational Biology and a Fellow for the Association for Computing Machinery, She is Editor-In-Chief of the Journal of Computational Biology.