Every act of biological generation has the same structure: something that carries information (an enzyme, a gene regulator, a sperm cell) engages with something receptive (a substrate, a strand of DNA, an egg) - and something new is born from the encounter. Aristotle described this as form meeting matter. The Kabbalistic tradition has its own names for the same polarity.
Every standard analytical tool in biology measures the output of this encounter. How much product formed. How fast. Under what conditions. Useful - but it only tells you what happened after the fact.
I've been working on something that measures the engagement itself - the generative potential between form-giver and matter-receiver, as it unfolds in time, independently of whether the product actually appears.
Why does that distinction matter? Think about what happens when a drug suppresses an enzyme not by blocking it directly, but by nudging it into a less active shape from a distance - the enzyme is still there, still engaged with its substrate, still trying. Standard tools show you a flat output curve and conclude nothing is happening. This framework, tested on real E. coli data, scores those inhibited enzymes as having the highest generative potential - because it's measuring the engagement, not just the yield.
Built in Python and Julia, tested on both simulated and real-world enzyme data. Would love to hear what people working at the biology/ML crossover think.
Every standard analytical tool in biology measures the output of this encounter. How much product formed. How fast. Under what conditions. Useful - but it only tells you what happened after the fact.
I've been working on something that measures the engagement itself - the generative potential between form-giver and matter-receiver, as it unfolds in time, independently of whether the product actually appears.
Why does that distinction matter? Think about what happens when a drug suppresses an enzyme not by blocking it directly, but by nudging it into a less active shape from a distance - the enzyme is still there, still engaged with its substrate, still trying. Standard tools show you a flat output curve and conclude nothing is happening. This framework, tested on real E. coli data, scores those inhibited enzymes as having the highest generative potential - because it's measuring the engagement, not just the yield.
Built in Python and Julia, tested on both simulated and real-world enzyme data. Would love to hear what people working at the biology/ML crossover think.