THE LIMITS OF BIG DATA
Humans solve problems by using two main cognitive approaches: Pattern Recognition and Reasoning. Unfortunately, we cannot scale to handle the ever-increasing volumes of data and knowledge. Similarly, Artificial Intelligence (AI) is composed of two main schools: Pattern Recognition (Data Mining/Machine Learning using Big Data) and Problem Solving (Reasoning Computing using Complex Knowledge).
The AI market today is mainly focused on data, scaling Pattern Recognition using Machine Learning (ML). The results have been amazing in applications ranging from self-driving cars to skin cancer diagnosis through image recognition, where extracting correlations from Big Data is the goal. These Pattern Recognition systems work extremely well when “digesting” large amounts of data to discover patterns and to build predictive systems, but they are “black boxes”, meaning they can’t provide an explanation for their results.
This is a problem for any decision support system in health, finance, biotech, etc, where explanation is vital to both justify decisions and to improve upon a system. In drug R&D, understanding the cause-and-effect relationships that govern the molecular mechanism level is crucial to better intervene, i.e. target the right causes of the pathological paths.
CAUSAL REASONING
Causation models are the foundation for rational reasoning that any scientific progress depends on; but the ever-growing body of knowledge (models) in each domain is now far too large and complex for any person or team to reason through meaningfully and completely.
We believe that the development of scalable computational reasoning models should be the focus for scientific pursuits in any domain. In most cases they should be built first, even before using any data analysis, because they will inform the right selection of data based on the focus and allow the interpretation of the data analysis outcomes — which in turn will be used to update the models.
ThinkingNode Life Science™ can be used to build causal-based models to run simulations of cellular dynamics, the genome, metabolic networks, the immune system, diagnostic approaches, therapeutic procedures, etc. Once the models have been formalized into Reasoning Networks™, scientists can make sophisticated hypotheses and test them using as many parameters and concepts as needed. Imagine how much faster progress could be made if scientists were able to access all available knowledge and compute them at any level of complexity - way beyond the 5 to 9 concepts that a human mind can handle. ThinkingNode Life Science™ has developed ready-to-use Human Whole-Cell Causal Reasoning Networks™.
Our approach breaks down silos and accelerates drug and biomarker discovery, drug safety analysis, confirmation of diagnoses, and design of combination therapies.
ThinkingNode Life Science™ provides the exponential thinking capability we need to solve complex problems.
