Why Should a Biology Problem Come Before the Model?

Pushmeet Kohli says the problem comes first, because treating yourself as only a modeler or only a data person can make the work fail. Be flexible about the solution. Do the modeling when the problem needs modeling, and collect data when the problem needs data.

Machine learning often showed up with a training set and a test set already fixed, then only optimized the model. That approach is broken when the goal is to solve the problem. What goes into the work is data, modeling, and expertise.

AlphaFold used the datasets that already existed. The team did not have the expertise or the resources to enlarge the PDB by a significant order of magnitude, and the investment already in that data was invaluable, so the return was in modeling. Cell genomics went the other way. After work on cell-by-gene data, the data was not there yet for the ambition of building a virtual cell. The aim is to advance the science rather than follow data generation or modeling as a faith.