The AACR Special Conference 2018 was an event that marked a new era in cancer research. This conference provided Ardigen with the boost we needed to confidently move forward in our development. Without a doubt, the acquired information will become instrumental in developing our cutting-edge, cancer immunotherapy product line. Let’s now delve deep into this experience and see the most notable milestones that stood out in our delegate’s memory.
The Shift in Life Sciences: From Wetlabs to Data Hubs
With the increasing amount of biological data available and the advancement of analytical tools devoted to the extraction of meaningful information from such data, we’re acknowledging a fundamental shift in life sciences. Many analytical efforts in biology transfer well from wet lab workbenches to data centers. Also, the involvement of bioinformaticians and data scientists in life sciences is increasing at an unprecedented rate.
This process is evident in cancer research. The available databases (i.e. TCGA, EGA, dbGAP, etc.) allow practitioners to advance the understanding and control of cancer, predicting the development, progression, and malignancy of the disease in both populations and individuals.
The organizers of the 30th Anniversary AACR Special Conference Convergence support this view. In their speech, they state:
“[Artificial Intelligence, Big Data, and Prediction in Cancer] is this interface of cancer biology, computation, and clinical oncology that will most likely produce the future breakthroughs in control of cancer.”
Ardigen at AACR18 Conference – Our Impression
Ardigen’s Lead Scientist in Immunology, Giovanni Mazzocco was in Newport (RI) for this event. He attended presentations and talked to speakers, poster presenters, and exhibitors. The conference was focused on discussing the power and limitations of computational methods (i.e. machine learning, image processing, deep learning, etc.) in the analysis of cancer-related data of different origins. This is a theme residing at the very heart of Ardigen’s vision for a fully personalized cancer treatment. Thus, we have anticipated this event with enthusiasm.
Authorities Debate the ML Development in Life Science and Pharma
Phillip A. Sharp, the Nobel prize-winner and MIT professor, defined three prominent revolutions in life sciences:
- the first represented by advances in molecular and cellular biology (1953-1973),
- the second driven by the advent of genomic sequencing (2001-2009),
- the third one (2009-current), characterized by the convergence of different research fields (e.g. engineering, mathematics, physics, cancer biology) and technologies as a blueprint for innovation in life sciences.
He put particular emphasis on machine learning as a means for extracting knowledge from complex multidimensional data. Dr. Alan Bernstein, the president of the Canadian Institute for Advanced Research, explained the evolution of machine learning and artificial intelligence, highlighting their potential in cancer research. He referred to this as the “fourth revolution in cancer research”.
Many Shades of Cancer: Factors Contributing to Its Emergence
Several speakers underlined the complex multi-factorial nature of cancer. The most esteemed silhouettes that voiced this thought include:
- Prof. Aviv Regev (MIT),
- Dr. Eliezer Van Allen (Dana-Faber),
- Dr. Anna Goldberg (SickKids, University of Toronto),
- Prof. Andrea Califano (Columbia University),
- Dr. William C. Hahn (Dana-Farber),
- Dr. Pasquale Laise (Columbia University),
- Prof. Alison P. Klein (Johns Hopkins).
To faithfully profile this disease, the researchers consider such factors:
- tumor heterogeneity,
- dynamic mutational landscape,
- resistance mechanisms,
- cancer–immune cross-talking,
- gene regulatory networks need.
Such an approach leads to better diagnostics, optimized treatment strategies, and the discovery of novel therapeutic targets. To provide further support, multi-faceted analytical strategies were proposed for some of these aspects. These include such approaches as:
- graph-theory models,
- Bayesian graphical models,
- interpretable deep neural networks,
- and algorithms for master gene regulators detection.
Biases Toward Machine Learning Tech in Biopharma: the Critique
The usage of machine learning methods in Life Science also received some constructive criticism. Interestingly enough, we have observed several trends eminent within the industry. Let us now enumerate the most visible one to understand how the biotech industry is shaping.
The Impracticality of Biological Interpretation of Computational Results
The biological interpretation of computational results is sometimes difficult or impractical – as proven by deep neural networks. Several speakers mentioned this topic, attracting the audience’s attention at any given occasion. Models embedding biologically explicable causal-effect relations – for example, Van Allen, Goldberg, or Califano – were generally more appreciated and less criticized by the audience concerning the “black box” models with obscure biological interpretability. The former models received more appraisal than the latter in testing new scientific hypotheses and explaining the clinical effects. Discussions during networking events confirmed this trend further.
Limitations of Big Data in Cancer Research
As mentioned by dr Bernstein, despite the abundance of Big Data in some areas of cancer research – one of them being histopathology – it isn’t the case for all cancer data. The example of genomic data associated with clinical studies reflects this trend well. They typically have a large number of features (e.g. gene mutations, gene expression) and a small number of observations (e.g. number of treated patients). Some modeling techniques can be useful in such cases. For example, Dr. Goldberg showed the advantage of using a Bayesian approach for the detection of relevant genes of interest in data-scarce situations.
A Peak into the Future: Non-Invasive Diagnostics for Cancer Detection and Monitoring
The presented advancement of liquid biopsy and analytical techniques for the detection of circulating tumor Nucleic Acids (ctNAs) promotes the hope of non-invasive diagnostics for cancer detection and monitoring. Dr. Richard Klausner – founder and director of Juno Therapeutics, founder and director of GRAIL, chairman of Mindstrong, and a director of AnchorDx – illustrated the three mandatory ingredients for the construction of highly specific (>99% specificity) ctNA platforms:
- high-intensity sequencing (x60k sequencing depth) to detect cfNAs,
- large-scale clinical studies,
- and a powerful machine learning approach.
He also highlighted some issues related to cfNTs including the problem of Clonal Hematopoiesis of Indeterminate Potential (CHIP) and the large amount of material needed for sufficient cfNTs detection. Firm, contrasting opinions about the practical usability of ctNA technologies were raised by Dr. Imran S. Haque (ex-CSO of Freenome) who severely doubted the maturity of such technology, sharing his experience in this field.
Immune System vs. Cancer: Delving Deep into Their Reciprocity
The importance of the interaction between cancer and the immune system was the topic of several talks. Dr. Jerome Galon (INSERM Laboratory Integrative Cancer Immunology, founder of HalioDx) showed the immune contexture, which is determined by the density, composition, functional state, and organization of the leukocyte infiltrate of the tumor. It is a valuable source of information relevant to prognosis, treatment response prediction, and various other pharmacodynamic parameters.
An Assay that Predicts: Microbiota Reaction to Advance-Stage Tumor Reocurrence
Dr. Gerome shared the results of his decennial research on Immunoscore® an assay originally designed to predict the risk of relapse in early-stage colon cancer patients. It was later proved capable of predicting metastasis recurrence, extending the prognostic value of the immune tumor microenvironment in advanced-stage cancers (Cell 2018). Dr. Elizabeth M. Jaffee (Johns Hopkins) focused on the neoepitope section for cancer vaccines and combination therapy based on cancer vaccines in association with checkpoint inhibitors and immune adjuvants (e.g. STING, OX40 agonists, etc).
Some sessions were dedicated to predicting cancer phenotypes through histopathological images leveraging both the large abundance of immunohistochemical data and powerful image processing tools such as Convolutional Neural Network (CNN).
AACR Special Conference 2018: Conclusion
The 30th Anniversary AACR Special Conference 2018 undoubtedly represented a historic milestone marking a new phase in cancer research, where clinicians, bioinformatics and data scientists work together to find novel solutions in the fight against cancer. Ardigen is glad to have attended the conference, gathering invaluable information instrumental to the development of its line of products for cancer immunotherapy.
