Biology-Based Mathematical Models to Optimize Chemotherapy Treatments @KeckMedUSC (EP 17) #DataTalk


– Hello and welcome to
Experian’s Weekly Data Talk, a show where we talk
to data science leaders from around the world. Today’s topic is biology-based
mathematical models to optimize chemotherapy treatments, and we’re super excited
to have Doctor Paul Newton who serves as a professor of aerospace and mechanical engineering, mathematics, and medicine at USC. He’s also the editor in chief of the Journal of Non-Linear Science. This is a very special edition, ’cause we’ve never
really covered anything, Dr. Newton, about medicine and data, and so this is a very
special episode for me. It’s an honor to have you. I thought maybe we can get started with you kind of just sharing your story, your journey academically,
and what, where, the path that you took
to where you are now. – Sure, so by training, I’m
an applied mathematician. So I was actually an
undergraduate at Harvard and I majored in physics and applied math. And then I got my PhD in
applied math at Brown University which actually has a separate
applied math department than a math department, so they have two separate departments. And those are really two
different tracks, I mean, if you get a PhD in applied
math, you’re learning all kinds of things
from probability theory to computational science
to data analytic methods to differential equations
to linear algebra, those are sort of the
topics that you would do as an applied mathematician. Whereas if you go on the pure math track, you’re proving theorems and you’re doing all kinds of different things. I like science a lot, I was
always interested in physics and biology, and so I went on that track. And so that’s my background. I did not really have any training in caner biology
particularly, that came really about 10 years ago when I
teamed up with a group of people at the Scripps Research
Institute down in San Diego. We were working, actually
I got a phone call, sort of a cold call from a guy down there by the name of Peter
Coon who is a specialist doing circulating tumor cell biology, where he actually takes
blood samples from patients working with the Scripps
Green Hospital there and then they extract the
small number of tumor cells that come from a tumor
in a cancer patient. And then they look at the
genomics of that cell. They look at the, all kinds
of the physical properties associated with that cell. So he thought, okay, let’s try to get one of these physical science oncology centers that the National Cancer
Institute was announcing, this was about, as I said, 10 years ago, let’s write a proposal and try to get one of these national centers where we would have a group of applied
mathematicians, engineers, physicists, working together
with biologists and oncologists doing sort of what they call
a physical sciences approach to cancer biology. So we teamed up and we wrote
a proposal having to do with the fluid mechanics
of blood flow in the body and how circulating tumor cells travel through the bloodstream
and how they get trapped at various sites and then
eventually form metastases. So we wrote our proposal,
which I look back on now and I kind of smile at
because a lot of the things that we thought we were
gonna be able to do really didn’t pan out. – Interesting. – On the other hand, a lot of
the stuff that did pan out, we didn’t mention at all in our proposal. (laughs) Anyway, we got one of these
centers and there were I think, there were I think 11
or 12 of these centers throughout the United
States, and so we got one of these centers and so I
was working with that group for five years, going to San Diego a lot. That I think was between
maybe 2009 and 2014. And then since then, I’ve
branched out and I work with groups of oncologists and biologists at various places around the
country in cancer centers, including USC Keck. – It is so cool how you started
like building this center. Was this really like
the first of its kind? Because I’ve never heard
of anything like this. – Right, right, well the,
it was sort of the first of its kind in the sense that
the National Cancer Institute had this big initiative and a big push, because they felt sort
of that cancer research had become a little bit internalized. You know, people make progress for sure, but the progress that people were making had kind of plateaued a little bit, and so the National Cancer
Institute and NIH in general were looking for new ways to invest money that might have a bigger payoff. So their big push was to
try to get data people, try to get physicists,
try to get engineers, try to get quantitative science people, really, really mixing it up
with biologists and oncologists who are, you know, tremendously
smart and dedicated people, but they don’t necessarily have the same quantitative training that
somebody who comes through an engineering, applied math, physics, data analysis sort of background. So that was their, really
I’d say the brainchild of the National Cancer Institute,
and then they supported, they had a big call and
initiative and probably had, you know 50 or so
proposals, or maybe more, I don’t know actually how many they had. And they ended up funding
about 10 or 11 of them. – That’s awesome. So we have a lot of people
in our data science community that are wanting to start their careers, looking at different paths,
and I’m kind of curious, for your center, when
you’re looking to hire or bring on a data scientist, what skillset is really
important for them to have? – Yeah, that’s a good question. So for me, I think it’s
really important to have a mix of different kinds of people,
because it’s such a broad area that there’s not gonna be
any one person who’s gonna have a really strong
background in statistics, a really strong background
in data analysis, let’s say machine learning,
let’s say topics like that and a really strong background
in mathematical modeling, let’s say differential
equations, and physical modeling, and a really strong background
in let’s say, Python, and coding and things
like that, it’s very, I mean I’d say it’s
impossible to find one person but when you get lots of people together, let’s say five, six, seven,
eight, nine, 10 people and then you throw in a
specialist, an oncologist who works with patients,
and you throw in a biologist who has a wet lab, who’s
doing single cell genomics and cell analysis, it becomes
a really powerful thing. So I would say all of those
tools potentially are useful. So we look for a team approach really, more than just trying to find one person or two people who can cover everything. – Well I think what’s really cool is that the work you’re doing is truly using, ’cause people talk about
using data for good, and data philanthropy, it’s
kind of like a buzz word, but what’s great about
what you’re doing is it’s truly using data science
for good for all of humanity. – Yeah I mean, to be honest,
USC, the engineering school, Viterbi School of Engineering
has also had a big push which our dean calls Engineering Plus which is a kind of a buzz word
as well but it makes sense, and that is there are lot
of things to do in life, there are lots of, you know,
there are certainly lots of interesting things that
one can do as an engineer or an applied mathematician
or a scientist. A lot of schools are moving
towards trying to identify areas where you’re really doing
more than just, you know, doing science for science sake,
but you’re actually trying to have some sort of a social goal in mind or some sort of a purpose in a sense. So that’s also a big push at
lots of different schools, this sort of Engineering Plus or science plus kind of approach. – Well it’s beautiful to see
that, beautiful to see the work that you’re doing at USC and your team. So what initially, for those
that are new to the podcast, I saw this article that
was on the USC website about Dr. Newton and his work
on chemotherapy treatments. What was interesting
to me was I had no idea how much data and mathematics
worked alongside medicine. I just never thought about it. (chuckles) And when I read this article
I was like fascinated. Can you kinda share,
first, what the traditional kind of chemotherapy treatments are like? And then move into what you decided to do with your research? – Sure, so I would say
in the 1950s or ’60s is when chemotherapy started, and scientists and oncologists
started developing protocols and basically at that
point in time the idea was that a tumor was made up of a collection of identical cancer cells that
were growing at a faster rate than the healthy cells in the body. And they might not have
exactly believed that all cells were equal, but that was
basically the operating assumption because they had no ability
to distinguish among cells. So once you take that point
of view and you view a tumor as a homogeneous collection
of rapidly dividing cells, then clearly the approach
would be to try to kill as many of these dividing
cells as you possibly can, and to eradicate the tumor. And so that was kinda
the operating philosophy, and to a large extent is
still the operating philosophy and it totally makes sense. If you have a group of insects in a field and they’re destroying your field, you’re going to try to
kill as many as possible. Now the problem with that approach, actually before I get into
the problem, let me just say what would follow from
that assumption is that you would try to use the
maximum amount of chemotherapy that you can in order to kill
the maximum amount of cells. But the problem is that
patients obviously can’t tolerate an unlimited
amount of chemotherapy, so there needed to be
some sort of a balance between the maximum amount
that a patient could tolerate and trying to kill as
many cells as possible. And so the protocol that developed is called the maximum tolerated dose, and that was what oncologists developed, and they did lots of clinical trials on what is the maximum
tolerated dose for patients in different age groups,
for males, for females, and so forth and they developed MTD, maximum tolerated dose
protocols which are basically off on kinds of chemotherapeutic regimens where you give somebody a
very high dose of chemotherapy for an hour, let’s say,
they go into the hospital, and then you let them rest for a week, and then they come back in the
next week and you give them another dose and you go through
this for a period of months, and that’s an on off on off schedule, and that’s called MTD
therapy and to large extent, not entirely but to a large extent, that’s kinda the standard
operating procedure. You can tweak the amount, what
the dose level is on that, but MTD is sort of the
operating procedure. Another sort of dose protocol
that people sometimes use is called low dose
metronomic therapy, or LDM, where you’re giving a very
low dose of chemotherapy, but sort of continually, so that’s kind of an interesting approach
that has benefits as well. The total amount of chemo that
you give would more or less be the same as the maximum
tolerated because you’re giving a lower amount, but you’re giving it over long periods of time. So you can think of low
dose metronomic in some ways as being sort of like
taking insulin or trying to treat diabetes where you
always have an insulin pump on you and it’s sort of continually
giving you small amounts in order to keep the disease in check. But no one’s ever really
compared those two things in any kind of a quantitative way, and as you can imagine,
there’s a lot of other things that you could do, those are
sort of the two extreme things that you could do, but
in principle there’s lots of other things that you could do. So as I said, if you view the tumor as a collection of homogeneous cells, then you would want to try
to kill as many possible, but now people realize, and in the past 10 years
people realized that a tumor is actually made up of a
heterogeneous population of cancer cells that
are all very different, they’re genetically different, they’re different in their growth rates, they’re different in how
they respond to chemotherapy, and all of those things. So now the analogy that you
should have in your mind is suppose you have a field and you have lots of competing kinds of insects
that are ravaging your field and there might be one sort
of dominant group of insects that are the most visible
and doing the most damage, but there might be another smaller group of very damaging insects that
are also potentially harmful. So now your goal, if you just go in, and you blast those insects with DDT and you kill the most
damaging large sub population, the danger there is that
another sub population of insects could very well survive, because maybe they’re resistant to DDT, and then take over the field, and then you’ve got a
worse problem on your hands because what you have done
is you’ve actually selected for that small little sub population that’s actually resistant to the DDT. And that is actually what happens, and as the main mechanism of
chemotherapeutic resistance, that when you blast a tumor
with just a single kind of chemical chemotherapy you
actually can be selecting for a sub group of cells
that are gonna cause way more problems for you down the road. So you can maybe see
benefits in the short run because as you’re killing
the dominant group of cells the tumor might shrink,
and so it looks as if you’re making progress, but
then inevitably what happens is that the tumor recurs
and starts to grow and it’s a much worse
situation because those cells are resistant to the chemotherapy. Then you can ask
yourself, so what would be the best approach now that you know that there are a bunch of
competing sub populations of different kinds of cancer cells or you’re in a field and
you have a whole bunch of different kinds of insects,
then the thing to do is to, let’s say that in an ideal world you could continually
monitor the different levels of those sub populations in the field. Then what you would try
to do would be to manage that competition, you would
take doses of chemotherapy, or doses of DDT, and you would try to kill the most damaging insects but you wouldn’t try to
wipe them out necessarily, you would try to reduce their numbers so that they are then
competing head to head with another sub population
and spending a lot of effort and energy and time
competing against each other in kind of a head to head
battle instead of just one sub population kind of dominating. So then the goal becomes
how do you manage that in order to keep the different
kinds of cancer cells to fight against each other in such a way that the tumor is smaller than it would be if it was untreated but
not completely eradicated? Because then what you’re doing
is you’re managing the cancer instead of trying to wipe it out, and there are some benefits to that. But that becomes a tricky thing for lots of different reasons. One reason is it’s not
really possible at this stage to actually figure out,
continually, all the different sub populations of cells in
a tumor the way it might be to look at all the different
insects in a field, that’s much easier to monitor
that, so that’s a challenge. And then the other
challenge, even if you assume that you can tell what the
different sub populations are and what the different cells
are that are resistant, what are the best approaches to try to manage that competition? So that is how we sort
of view the problem, and there are other groups that
are viewing tumors this way, sort of as an ecology, so
people call this tumor ecology, and using evolutionary
principles to manage a tumor instead of using maximum tolerated dose. So that’s kind of a intro
into the thought process that goes on behind people that use Darwinian
evolution ideas to manage this competition among all
the different kinds of cells. – So that is amazing
what you just explained, and the fact that you’re
using kind of evolutionary, I think the article
talked about game theory, is that the proper term? – Yeah. – To actually make cancer
cells compete with each other. I’ve never heard of that. – Right, it’s a pretty new field. There’s our group and
there’s a group of people at the Moffitt Cancer
Center in Tampa, Florida where my ex-PhD student
is now a a post-doc, his name is Jeffrey
West, and he is working with a group of clinicians down there, and they’re trying to
develop clinical trials based on these ideas, and they
have some very good people down there that are using
these methods to try to test them out in clinical trials. – Wow, that is. Tell me about the role of the,
so you have this amazing team at USC that you’re working with, tell me about the role
of the data scientists or the people that are analyzing data. Where are they, where
are you placing them, and what are they focused
on in this research? – Right, so a couple people, so I have a group of
about five PhD students that are working on
various aspects of this, and then we work with other labs, I mentioned a biologist
by the name of Peter Coon who has a lab and another
oncologist here at Keck named David Agus who is a
clinician working, he has a lab, so we work with different
groups of people, but my students do
several different things. Some of them do mathematical
modeling in the sense that they’re looking at, as you said, game theory models of
evolution and how to balance these competing cell populations using what we call feedback control, adaptive control theory in order to design chemotherapeutic
schedules to try to get these cell populations of cells competing against each other. So these would be people
that are getting their PhDs let’s say either in applied
math or physics or engineering and they are doing computational models of a system of equations, typically these are called
replicator equations, but it doesn’t matter what they’re called, or you could do cell-based
models that are stochastic models and do, use game theory
evolutionary principles to try to model this. So that’s one kind of a
person who would be getting typically a PhD in applied
math, engineering, or physics. And then another kind of
data science person would be more of a machine learning and
a big data kind of a person. And I have a kid who’s gonna
be defending his thesis in August, who’s done
an awesome PhD thesis using those kinds of techniques to look at all kinds of different cancer models. He actually got his masters
degree in computer science and then is getting his PhD in aerospace and mechanical engineering. And he got a job already
lined up, a full-time job as a data scientist at JPL. – Oh wow. – So amazingly his whole thesis is all about data science’s approach
to healthcare and biology and he got snapped up by a
data science group at JPL. But he’s happy about it, he
wants to stay in Pasadena. – Yeah, that’s cool. It must be hard to keep
such a smart team together, ’cause everyone’s like wanting
to tear your team apart, they all want. (laughs) – What the challenge really
is that it’s a little bit of a ramp up period when you
get a new graduate student you gotta train them for a couple years, they have to take lots of
classes, they have to pass exams in order to get through the
masters level into the PhD level before they get really
serious about the research, so it’s kind of a big investment
to train for a couple years and then they work on their PhD thesis maybe for two or three years, or sometimes even four years, after that. – Wow, so I’m kinda curious,
what other types of projects have you done with medicine
and math, maybe in the past, that you’re really happy about? – One of the big projects
that we started out with as I mentioned, at the
Scripps Research Institute was basically on forecasting associated with different kinds of cancer. In other words we looked
at metastasis and we wanted to build what are called dynamical systems or forecasting models of
how metastatic cancer’s gonna proceed for
different kinds of cancers. So what we used there were
Markov chain kinds of models which is a certain kind of a relatively simple
dynamical system approach to predicting, if you have data that you can train your models on. This is an ongoing project
that we’ve now written lots of papers on and we work with
groups at Sloan Kettering and we work with groups at
MD Anderson as well as Keck, and what we do basically
with that whole project is we get longitudinal data sets, and longitudinal data sets are data sets that track large cohorts of
patients that have cancer for 10, 15, 20, 25 years let’s say. They track them and they keep
track of every single time they get a treatment, every
time that their cancer spreads to a different site
they mark down the date, and so we have a long-term
dynamical trajectory of thousands of patients
that are of different, let’s say ages, different genetic types, different kinds of cancers. And a lot of these cancer centers have these longitudinal data
sets just sort of stored away in their files but they don’t really know what to do with them, they’ve
never really analyzed them. So seven or eight years ago we realized that these longitudinal data
sets were super interesting and super important and
useful for developing models. And so we started using
those longitudinal data sets to train our models, our Markov
chain models of progression. And that has proven to be pretty useful. I would say probably
our group is most known, probably for those kinds of models, since we’ve been doing that the longest. – I think that’s awesome
that you were thinking about these different studies
that have been going on at these different cancer centers and then going through the process
of collecting the data. When you approach these
different cancer centers, obviously you’re a university,
how do you deal with kind of the privacy aspect of the patients? – Right, right, I mean it’s delicate. So what you, first of
all, you have to have, you can’t just knock at
the door at a cancer center and introduce yourself really and say that you’d like their data,
that’s not gonna work. (laughs) Okay, it might work at Keck
because I’m a professor at USC and so I know people
at Keck, and so there is that. But then you sign privacy laws and you go through some
training having to do with how to deal with medical data. So that is all important. Really the most important thing
if you’re gonna try to work with a data center is to
have someone at that center who you know and who
you’ve met at conferences and who you’ve talked with so that there’s kind of a
ramp up period there, you have to develop a certain level of, I don’t know, trust or
comfort with people. Almost invariably they
will say they have data that is just sitting around
that no one has looked at, and it will be interesting for them if you could do something with that data. The thing that’s amazed me
actually is how much data is out there in the medical community, and my little world is
just the cancer world, so just in the cancer
world there’s so much data that hospitals have that
doctors just collect over years and years, and it’s
just sitting there in files. It has all this information
in it and no one really has extracted that information from it. So I think that’s a huge area
of opportunity to develop, and exploit.
– Yeah that’s amazing. And like you said, there’s
so much time involved in building those relationships,
building that trust. – Right, it helps a lot
to be at a big university that has a medical school and
lots of professional schools, so then you typically
would start out working within your university
system as a graduate student, or even some undergraduates
that get into this, but mostly graduate students,
post-docs, and faculty members that work together with the oncologists that are at that university. – What’s interesting
is I’ve seen a parallel talking about data ethics and
also the medical community, ’cause when someone becomes
a doctor they take the oath to do everything that they
can to save human life. There’s now kind of a movement,
and I think it was started by DJ Patil who was the Chief Data Officer for the White House under Barack Obama, I see him now talking
about we need to have a set of data ethics standards that
data scientists ascribe to, to make sure that we’re
doing everything we can, in the data science community, to protect data, protect privacy. And I’m kinda curious
about your thoughts on, like what sort of training or guidelines do your scientists
subscribe to to make sure that data’s gonna be
properly taken care of? – Yeah, that’s very delicate,
I mean, no question. I mean the whole data
question, as we’ve seen in the last couple weeks
is a really delicate issue, and healthcare data and medical
data is even worse, so yeah. Most universities have training programs and systems in place
that train researchers in the basics of how to
maintain confidentiality and things like that. And there are checks
and balances in place. I’m not saying that it’s not difficult, I mean it is difficult and you do have to sort of learn some basic tools there. But yeah, it’s a big subject, no question, and there’s definitely
room for improvement there, ’cause the whole field of data science is just moving so fast
and is ahead of the, basically ahead of a lot
of the checks and balances, as you can see from Mark
Zuckerberg’s latest testimony, that my sense is that he’s
trying to do the best he can, but you know the field is moving so fast, and he can’t control it all, and they’re trying to stay
ahead of a moving wave. – Yeah, huge. So Dr. Newton just one last question. And it’s a question that comes up a lot in our data science community, and it’s around what advice
would you give somebody who is finishing up graduate
school or finishing up college and is looking to start
their career in data science and what advice would you give them to kind of help them on their way? – That’s a good question. I think that the key to
making yourself marketable, if that’s your goal, which it
probably is for most people, would be to really get a broad training in lots of different things, so that when you go in to an interview, and you have a team of
people interviewing you, let’s say at a place
like Google or Facebook, they’re gonna be asking
questions from all kinds of directions from machine
learning to statistics to mathematical modeling
to computer science. And if you have at least one
course in each of those areas, but of course you’re gonna be specializing in one of those areas, but
if you have a little bit of broad training in
some of these other areas so that you can at least
understand the questions they’re asking and at
least you can sort of see how those techniques could be
useful, it really helps a lot. I think that was the
key to the grad student I was telling you about
who got this job at JPL, he’s very broad-based and he can converse on lots of different kinds of topics, from modeling to statistics to
genetics to machine learning. And so if you, I think taking one class in all those different areas
that you’re not specializing in can really pay off. – It’s great advice. Dr. Newton thank you so
much for being our guest in this week’s data talk. For those listening to
the podcast, if you’d like to watch the video or
read the transcription, you can go to the blog and the short URL is just ex.pn/newton,
and that’s also the place where we’ll be embedding
the podcast, sorry. So anyways, Dr. Newton, thank you so much for being our guest, it
was an honor to have you. You guys are doing tremendous
work, truly data for good, using maths, using
medicine to help humanity, so thank you for everything
that you’re doing, and it’s an honor to
have you on our podcast. – Thanks very much Michael. – Okay, take care. – Bye.
– Buh-bye.

Add a Comment

Your email address will not be published. Required fields are marked *