Giving a Talk at NIH

In a change of pace, I’m doing a videocast talk today at the NIH on my research at the NIH March 7, 2018, at 2pm EST (3pm CST). Watch online if you are curious.

Deep Learning the Metabolism and Subsequent Reactivity of Drugs

S. Joshua Swamidass MD PhD,
Assistant Professor, Laboratory and Genomic Medicine, WUSTL
Faculty Lead, Translational Bioinformatics, Institute for Informatics, WUSTL

Many medicines become toxic only after bioactivation by metabolizing enzymes. Often, metabolic enzymes transformed them into chemically reactive species, which subsequently conjugate to proteins and cause adverse events. For example, carbamazepine is epoxidized by P450 enzymes in the liver, but then conjugates to proteins, causing Steven Johnsons Syndrome in some patients. The most difficult to predict drug reactions, idiosyncratic adverse drug reactions (IADRs), often depend on bioactivation. Our group has been using deep learning to model the metabolism of diverse chemicals, and the subsequent reactivity of their metabolites. Deep learning systematically summarizes the information from thousands of publications into quantitative models of bioactivation, modeling precisely how medicines are modified by metabolic enzymes. These models are giving deeper understanding of why some drugs become toxic, and others do not. At the same time, deep learning c how molecules are transformed by an be used to understand drug toxicity as it arises in clinical data, and why some patients are affected, but not others. A conversation between the basic and clinical sciences is now possible, where patient outcomes can be understood in light of bioactivation mechanisms, and these mechanisms can explain why some patients are susceptible to drug toxicity, and others are not. Funded by R01LM012482 and R01LM012222.


1 Like

Suddenly, for some reason, the cachet of giving a talk at NIH seems to have been devalued.

1 Like

Hahah, perhaps. Though mine was sponsored by an NIH institute. It did not inspire nearly as much internent buzz as Sanford’s, so I suppose his was more important.

1 Like

Metabolism of Drugs at NIH Lecture | S. Joshua Swamidass

Now that’s really something: metabolizing drugs during one’s NIH lecture. What a novel idea! (Sounds like a TED Talk in the making.)

Of course, strictly speaking, a number of notable scholars have metabolized drugs at their lectures (though probably not at an NIH presentation.) Timothy Leary comes to mind.

(@Michael_Callen and @Dan_Eastwood, I think this lecture announcement could be a good candidate for the Peaceful Science Commemorative Plate Series™.)


Alas, I think the Missouri laws would frown upon that sort of “seminar enhancement” at the upcoming PS workshop. :wink:


This lecture announcement actually provides a good illustration of an issue which sometimes arises in Biblical Hebrew and Greek exegesis. Consider how the absence of punctuations in most newspaper and webpage titles can create interesting ambiguities or misunderstandings:

Metabolism of Drugs at NIH Lecture

…could be misunderstood by a non-native speaker as:

“Metabolism of Drugs at NIH” Lecture

Yes, he or she might even get the impression that there is a drug problem at NIH. (A non-native speaker of English could easily be unfamiliar with the word “metabolism” and ask someone for a definition. An impromptu, casual answer might be “Metabolism refers to the breakdown and processing of a drug”—such that the inquirer might assume that the word refers to “cutting” of the illegal drug shipment into small bags and distributing them to sellers. If you think that this sounds silly, consider that modern day scholars are sometimes similarly naive when trying to determine the meanings of vocabulary and grammar of an ancient language document from thousands of years ago. After all, there are no native speakers of the ancient language to query. Yes, there is more truth in my illustration than you might think.)

Now consider that ancient Hebrew and Greek lacked so many of the punctuation marks which we take for granted. My favorite example in the Hebrew Old Testament of a punctuation issue creating ambiguity involves the severity of the Noahic Flood in Genesis 7:20. Consider these two English translations:

“The waters prevailed above the mountains, covering them fifteen cubits deep.” — ESV

“Fifteen cubits upward did the waters prevail; and the mountains were covered.” — KJV

The ESV committee decided to translate Genesis 7:20 so that the depth of the flood was basically 15 cubits (about 22 feet) higher than the mountains. [Incidentally, I prefer to translate the Hebrew word as hills rather than mountains but that is an exegetical tangent for another time. Suffice it to say for now that the Hebrew word could refer to a mountain or a hill. We make a strong “magnitude distinction” in English but the ancient Hebrews didn’t necessarily do so.]

In contrast to the ESV, the KJV translators chose to include a full stop, the semicolon, so as to make two separate statements about the flood’s severity:

(1) The flood waters rose fifteen cubits to where everything was submerged. [That is, the waters prevailed.]

(2) The mountains [or hills] were covered.

See the difference? Of course, twenty-two feet deep flood waters make a lot more sense than a flood topping Mt. Everest by twenty-two feet. The KJV in this instance sounds less supportive of traditional Young Earth Creationist “global flood” interpretations than does the ESV!

Another challenging problem in some of the oldest Greek manuscripts was omission of the spaces between words in order to reduce the quantity of vellum or papyrus materials needed to produce the document. This created ambiguities similar to the famous English example of GODISNOWHERE. (Is it “God is now here” or “God is nowhere”?)

Yes, I can’t resist a good Biblical exegesis tangent—and Joshua Swamidass’ announcement title provided such a good illustration of an issue with which Bible translators and commentators must wrestle on a regular basis.

1 Like

Hahaha… that’s exactly what I thought… well similar. I used to drink a couple of beers in the parking lot before heading to my statistics class… I would imagine the stronger stuff is required for NIH lectures…

We’ve all personally witnessed and partaken in the metabolism of caffeine, for example, at the PS Conference over the last couple of days. At least the culpability is mutually shared!

1 Like