Article: Will artificial intelligence help to crack biology? (The Economist)
Short overview on progress and challenges of AI firms — behemoths and startups — in health care in 2017
These two paragraphs I found insightful:
Scientific output doubles every nine years. And data are, increasingly, salami-sliced for publication, to lengthen researchers’ personal bibliographies. That makes information hard to synthesise. A century ago someone could still, with effort, be an expert in most fields of medicine. Today, as Niven Narain of BERG Health, an AI and biotechnology firm in Framingham, Massachusetts, points out, it is not humanly possible to comprehend all the various types of data.
This is where AI comes in. Not only can it “ingest” everything from papers to molecular structures to genomic sequences to images, it can also learn, make connections and form hypotheses. It can, in weeks, elucidate salient links and offer new ideas that would take lifetimes of human endeavour to come up with. It can also weigh up the evidence for its hypotheses in an even-handed manner. In this it is unlike human beings, who become unreasonably attached to their own theories and pursue them doggedly. Such wasted effort besets the best of pharmaceutical firms.
In the last part of the piece, the Economist highlights the current challenges of reliably modelling proteins, let alone full human cells. They reference the Chan Zuckerberg Initiative’s (CZI) Biohub project to create a ‘cell atlas’, categorizing all cells and generating data that reveals their inner structures and processes. I hadn’t looked into CZI’s Biohub before, but upon reading, seems like the atlas could be a tremendous data set for AI practitioners.
If you want to go even deeper on understanding machine learning modelling in health care, the podcast below featuring Brendan Frey of Toronto’s Deep Genomics is super informative, particularly on genetics applications of AI. Note as the podcast goes on, it gets pretty technical, and in some instances the conversation may go over your head (as it did mine).
