TED2019
Leila Pirhaji: The medical potential of AI and metabolites
Leila Pirhaji: Potencijal umjetne inteligencije (AI) i metabolita u medicini
Filmed:
Readability: 5.5
1,210,569 views
Mnoge bolesti pokreću metaboliti -- male molekule u vašem tijelu poput masti, glukoze i kolesterola -- ali ne znamo točno što su oni i kako djeluju. Biotehnička poduzetnica i TED suradnica Leila Pirhaji izlaže svoj plan za izgradnju mreže utemeljene na AI-u kako bi se karakterizirali obrasci metabolita, bolje razumjelo kako se bolest razvija -- i otkrili učinkovitiji načini liječenja.
Leila Pirhaji - Biotech entrepreneur
Leila Pirhaji uses artificial intelligence for drug discovery and the treatment of metabolic diseases. Full bio
Leila Pirhaji uses artificial intelligence for drug discovery and the treatment of metabolic diseases. Full bio
Double-click the English transcript below to play the video.
00:13
In 2003,
0
1507
1889
2003. godine,
00:15
when we sequenced the human genome,
1
3420
2913
kad smo razložili ljudski genom,
00:18
we thought we would have the answer
to treat many diseases.
to treat many diseases.
2
6357
3922
mislili smo da ćemo imati odgovor
za liječenje mnogih bolesti.
za liječenje mnogih bolesti.
00:22
But the reality is far from that,
3
10974
2657
No, stvarnost je daleko od toga,
00:26
because in addition to our genes,
4
14782
1921
jer osim naših gena,
00:28
our environment and lifestyle
could have a significant role
could have a significant role
5
16727
4570
naše okruženje i način života
mogu imati značajnu ulogu
mogu imati značajnu ulogu
00:33
in developing many major diseases.
6
21321
2548
u razvoju mnogih velikih bolesti.
00:35
One example is fatty liver disease,
7
23893
3580
Jedan primjer je bolest masne jetre,
00:39
which is affecting over 20 percent
of the population globally,
of the population globally,
8
27497
4083
koja pogađa preko 20% stanovnika svijeta,
00:43
and it has no treatment
and leads to liver cancer
and leads to liver cancer
9
31604
3034
i nema joj lijeka, a vodi do raka jetre
00:46
or liver failure.
10
34662
1423
ili zatajenja jetre.
00:49
So sequencing DNA alone
doesn't give us enough information
doesn't give us enough information
11
37517
4744
Dakle, sekvenciranje DNK samo po sebi
ne daje nam dovoljno informacija
ne daje nam dovoljno informacija
00:54
to find effective therapeutics.
12
42285
2232
za pronalazak učinkovitih terapija.
00:56
On the bright side, there are
many other molecules in our body.
many other molecules in our body.
13
44541
3756
Dobro je što postoje mnoge druge
molekule u našem tijelu.
molekule u našem tijelu.
01:00
In fact, there are
over 100,000 metabolites.
over 100,000 metabolites.
14
48321
3980
Zaista, postoji preko 100.000 metabolita.
01:04
Metabolites are any molecule
that is supersmall in their size.
that is supersmall in their size.
15
52325
4296
Metaboliti su bilo koja molekula
supermale veličine.
supermale veličine.
01:09
Known examples are glucose,
fructose, fats, cholesterol --
fructose, fats, cholesterol --
16
57193
4972
Poznati primjeri su glukoza, fruktoza,
masti, kolesterol --
masti, kolesterol --
01:14
things we hear all the time.
17
62189
1510
ono o čemu stalno slušamo.
01:16
Metabolites are involved
in our metabolism.
in our metabolism.
18
64273
2983
Metaboliti su uključeni u naš metabolizam.
01:20
They are also downstream of DNA,
19
68066
4028
Oni su na nižoj razini od DNK
01:24
so they carry information
from both our genes as well as lifestyle.
from both our genes as well as lifestyle.
20
72118
5082
pa nose informacije iz naših gena,
kao i stila života.
kao i stila života.
01:29
Understanding metabolites is essential
to find treatments for many diseases.
to find treatments for many diseases.
21
77224
5649
Razumijevanje metabolita je ključno
za pronalazak tretmana za mnoge bolesti.
za pronalazak tretmana za mnoge bolesti.
01:34
I've always wanted to treat patients.
22
82897
2212
Oduvijek sam željela liječiti pacijente.
01:37
Despite that, 15 years ago,
I left medical school,
I left medical school,
23
85934
3858
Unatoč tome, prije 15 godina,
napustila sam medicinsku školu
napustila sam medicinsku školu
01:41
as I missed mathematics.
24
89816
1965
jer mi je nedostajala matematika.
01:45
Soon after, I found the coolest thing:
25
93019
2936
Ubrzo potom otkrila sam sjajnu stvar:
01:48
I can use mathematics to study medicine.
26
96692
2763
Mogu koristiti matematiku
za studij medicine.
za studij medicine.
01:53
Since then, I've been developing
algorithms to analyze biological data.
algorithms to analyze biological data.
27
101026
5213
Od tada razvijam algoritme
za analizu bioloških podataka.
za analizu bioloških podataka.
01:59
So, it sounded easy:
28
107092
2283
Dakle, zvučalo je jednostavno:
02:01
let's collect data from all
the metabolites in our body,
the metabolites in our body,
29
109399
3601
prikupimo podatke o svim
metabolitima u našem tijelu,
metabolitima u našem tijelu,
02:05
develop mathematical models to describe
how they are changed in a disease
how they are changed in a disease
30
113024
5128
razvijmo matematičke modele
za opisivanje kako se mijenjaju u bolesti
za opisivanje kako se mijenjaju u bolesti
02:10
and intervene in those
changes to treat them.
changes to treat them.
31
118176
2988
i intervenirajmo u te promjene
kako bismo ih liječili.
kako bismo ih liječili.
02:14
Then I realized why no one
has done this before:
has done this before:
32
122488
3472
Tada sam shvatila zašto
to nitko nije učinio prije:
to nitko nije učinio prije:
02:19
it's extremely difficult.
33
127230
1687
to je iznimno teško.
02:20
(Laughter)
34
128941
1087
(Smijeh)
02:22
There are many metabolites in our body.
35
130052
2412
Postoje mnogi metaboliti u našem tijelu.
02:24
Each one is different from the other one.
36
132783
2500
Svaki od njih različit je od onog drugog.
02:27
For some metabolites,
we can measure their molecular mass
we can measure their molecular mass
37
135307
3728
Nekim metabolitima možemo
mjeriti molekularnu masu
mjeriti molekularnu masu
02:31
using mass spectrometry instruments.
38
139059
2593
instrumentima za spektrometriju mase.
02:33
But because there could be, like,
10 molecules with the exact same mass,
10 molecules with the exact same mass,
39
141676
4393
No kako bi moglo biti, recimo,
10 molekula s istom masom,
10 molekula s istom masom,
02:38
we don't know exactly what they are,
40
146093
1807
ne znamo točno koje su,
02:39
and if you want to clearly
identify all of them,
identify all of them,
41
147924
2774
pa ako ih želite sve jasno identificirati,
02:42
you have to do more experiments,
which could take decades
which could take decades
42
150722
3104
treba raditi još eksperimenata,
što bi moglo trajati desetljećima
što bi moglo trajati desetljećima
02:45
and billions of dollars.
43
153850
1714
i stajati milijarde dolara.
02:48
So we developed an artificial
intelligence, or AI, platform, to do that.
intelligence, or AI, platform, to do that.
44
156207
5563
Tako smo razvili umjetnu inteligenciju,
ili AI, kao platformu koja će to učiniti.
ili AI, kao platformu koja će to učiniti.
02:53
We leveraged the growth of biological data
45
161794
2844
Iskoristili smo rast bioloških podataka
02:56
and built a database of any existing
information about metabolites
information about metabolites
46
164662
4424
i izgradili bazu podataka svih postojećih
informacija o metabolitima
informacija o metabolitima
03:01
and their interactions
with other molecules.
with other molecules.
47
169110
3128
i interakcija njih s drugim molekulama.
03:04
We combined all this data
as a meganetwork.
as a meganetwork.
48
172262
3424
Povezali smo sve te podatke u megamrežu.
03:07
Then, from tissues or blood of patients,
49
175710
3396
Zatim iz tkiva ili krvi bolesnika
03:11
we measure masses of metabolites
50
179130
2751
mjerimo mase metabolita
03:13
and find the masses
that are changed in a disease.
that are changed in a disease.
51
181905
3259
i tražimo one koje se mijenjaju u bolesti.
03:17
But, as I mentioned earlier,
we don't know exactly what they are.
we don't know exactly what they are.
52
185188
3190
Ali, kao što sam spomenula ranije,
ne znamo točno koji su.
ne znamo točno koji su.
03:20
A molecular mass of 180 could be
either the glucose, galactose or fructose.
either the glucose, galactose or fructose.
53
188402
5135
Molekulska masa 180 može biti
glukoza, galaktoza ili fruktoza.
glukoza, galaktoza ili fruktoza.
03:25
They all have the exact same mass
54
193561
2019
Sve one imaju iste mase
03:27
but different functions in our body.
55
195604
2087
ali različite funkcije u našem tijelu.
03:29
Our AI algorithm considered
all these ambiguities.
all these ambiguities.
56
197715
3587
Naš AI algoritam uzima u obzir
sve te nedorečenosti.
sve te nedorečenosti.
03:33
It then mined that meganetwork
57
201326
2736
Zatim pretražuje tu megamrežu
03:36
to find how those metabolic masses
are connected to each other
are connected to each other
58
204086
4353
da vidi kako su te metaboličke mase
međusobno povezane
međusobno povezane
03:40
that result in disease.
59
208463
1958
kad rezultiraju bolešću.
03:42
And because of the way they are connected,
60
210445
2238
I po načinu na koji su povezani,
03:44
then we are able to infer
what each metabolite mass is,
what each metabolite mass is,
61
212707
4323
onda možemo zaključiti
što je svaka metabolička masa,
što je svaka metabolička masa,
03:49
like that 180 could be glucose here,
62
217054
2924
kao, ovdje bi 180 mogla biti glukoza,
03:52
and, more importantly, to discover
63
220002
2551
i, što je još važnije, otkriti
03:54
how changes in glucose
and other metabolites
and other metabolites
64
222577
3367
kako promjene u glukozi
i drugim metabolitima
i drugim metabolitima
03:57
lead to a disease.
65
225968
1505
dovode do bolesti.
03:59
This novel understanding
of disease mechanisms
of disease mechanisms
66
227497
2995
To novo razumijevanje mehanizama bolesti
04:02
then enable us to discover
effective therapeutics to target that.
effective therapeutics to target that.
67
230516
4492
omogućuje nam zatim otkrivanje
učinkovitih ciljanih terapija.
učinkovitih ciljanih terapija.
04:07
So we formed a start-up company
to bring this technology to the market
to bring this technology to the market
68
235601
3845
Stoga smo osnovali start-up tvrtku kako
bismo tu tehnologiju stavili na tržište
bismo tu tehnologiju stavili na tržište
04:11
and impact people's lives.
69
239470
1805
i poboljšali živote ljudi.
04:13
Now my team and I at ReviveMed
are working to discover
are working to discover
70
241722
3545
Sada moj tim i ja u ReviveMed
radimo na otkrivanju
radimo na otkrivanju
04:17
therapeutics for major diseases
that metabolites are key drivers for,
that metabolites are key drivers for,
71
245291
5105
terapija za glavne bolesti
kojima su ključni pokretači metaboliti,
kojima su ključni pokretači metaboliti,
04:22
like fatty liver disease,
72
250420
1897
poput bolesti masne jetre,
04:24
because it is caused
by accumulation of fats,
by accumulation of fats,
73
252341
2924
jer je uzrokovana nakupljanjem masti,
04:27
which are types
of metabolites in the liver.
of metabolites in the liver.
74
255289
2473
koje su vrste metabolita u jetri.
04:29
As I mentioned earlier,
it's a huge epidemic with no treatment.
it's a huge epidemic with no treatment.
75
257786
3940
Kao što sam spomenula ranije,
to je ogromna epidemija bez lijeka.
to je ogromna epidemija bez lijeka.
04:33
And fatty liver disease
is just one example.
is just one example.
76
261750
2724
A bolest masne jetre je
samo jedan primjer.
samo jedan primjer.
04:36
Moving forward, we are going to tackle
hundreds of other diseases
hundreds of other diseases
77
264498
4178
Ubuduće ćemo se boriti
sa stotinama drugih bolesti
sa stotinama drugih bolesti
04:40
with no treatment.
78
268700
1493
za koje nema lijeka.
04:42
And by collecting more and more
data about metabolites
data about metabolites
79
270217
4554
Prikupljanjem sve više
podataka o metabolitima
podataka o metabolitima
04:46
and understanding
how changes in metabolites
how changes in metabolites
80
274795
3544
i razumijevanjem kako promjene metabolita
04:50
leads to developing diseases,
81
278363
2402
dovode do razvoja bolesti,
04:52
our algorithms will get
smarter and smarter
smarter and smarter
82
280789
3489
naši algoritmi će postajati sve pametniji
04:56
to discover the right therapeutics
for the right patients.
for the right patients.
83
284302
4196
u otkrivanju pravih terapija
za pravog pacijenta.
za pravog pacijenta.
05:00
And we will get closer to reach our vision
84
288522
3770
Približit ćemo se ostvarenju naše vizije:
05:04
of saving lives with every line of code.
85
292316
3863
spašavanja života sa svakim retkom koda.
05:08
Thank you.
86
296203
1321
Hvala vam.
05:09
(Applause)
87
297548
3827
(Pljesak)
ABOUT THE SPEAKER
Leila Pirhaji - Biotech entrepreneurLeila Pirhaji uses artificial intelligence for drug discovery and the treatment of metabolic diseases.
Why you should listen
Leila Pirhaji is the founder of ReviveMed, an AI platform that can quickly and inexpensively characterize large numbers of metabolites (small molecules like glucose or cholesterol) from the blood, urine and tissues of patients. This allows for the detection of molecular mechanisms that lead to disease and the discovery of drugs that target these disease mechanisms.
Leila Pirhaji | Speaker | TED.com