TED2016
Riccardo Sabatini: How to read the genome and build a human being
Rikardo Sabatini (Riccardo Sabatini): Kako čitati genom i sagraditi ljudsko biće
Filmed:
Readability: 3.6
1,834,677 views
Tajne, bolesti i lepota, sve je to ispisano u ljudskom genomu, kompletnom skupu genetskih uputstava koja su potrebna da bi se sagradilo ljudsko biće. Sad nam, kao naučnik i preduzetnik, Rikardo Sabatini pokazuje da imamo moć da čitamo ovaj složeni kôd, predviđajući stvari poput visine, boje očiju, starosti, pa čak i strukture lica - sve to iz epruvete krvi. A uskoro, kaže Sabatini, naše novo razumevanje genoma će nam omogućiti da personalizujemo tretmane za bolesti poput raka. Imamo moć da promenimo život kakav poznajemo. Kako ćemo da je iskoristimo?
Riccardo Sabatini - Scientist, entrepreneur
Riccardo Sabatini applies his expertise in numerical modeling and data to projects ranging from material science to computational genomics and food market predictions. Full bio
Riccardo Sabatini applies his expertise in numerical modeling and data to projects ranging from material science to computational genomics and food market predictions. Full bio
Double-click the English transcript below to play the video.
00:12
For the next 16 minutes,
I'm going to take you on a journey
I'm going to take you on a journey
0
612
2762
U narednih 16 minuta
ću da vas povedem na putovanje
ću da vas povedem na putovanje
00:15
that is probably
the biggest dream of humanity:
the biggest dream of humanity:
1
3398
3086
koje je verovatno najveći san čovečanstva:
00:18
to understand the code of life.
2
6508
2015
razumevanje životnog koda.
00:21
So for me, everything started
many, many years ago
many, many years ago
3
9072
2743
Za mene je sve počelo
pre mnogo, mnogo godina
pre mnogo, mnogo godina
00:23
when I met the first 3D printer.
4
11839
2723
kad sam saznao za prvi 3D štampač.
00:26
The concept was fascinating.
5
14586
1674
Sami koncept je bio fascinantan.
00:28
A 3D printer needs three elements:
6
16284
2022
3D štampaču su potrbna tri elementa:
00:30
a bit of information, some
raw material, some energy,
raw material, some energy,
7
18330
4134
delić informacije, nešto sirovine,
malo energije
malo energije
00:34
and it can produce any object
that was not there before.
that was not there before.
8
22488
3334
i može da proizvede bilo koji objekat
koji prethodno nije postojao.
koji prethodno nije postojao.
00:38
I was doing physics,
I was coming back home
I was coming back home
9
26517
2137
Bavio sam se fizikom, vraćao sam se kući
00:40
and I realized that I actually
always knew a 3D printer.
always knew a 3D printer.
10
28678
3438
i shvatio da mi je 3D štampač
poznat oduvek.
poznat oduvek.
00:44
And everyone does.
11
32140
1336
Svima jeste.
00:45
It was my mom.
12
33500
1158
Majka je 3D štampač.
00:46
(Laughter)
13
34682
1001
(Smeh)
00:47
My mom takes three elements:
14
35707
2414
Moja majka je uzela tri elementa:
00:50
a bit of information, which is between
my father and my mom in this case,
my father and my mom in this case,
15
38145
3973
delić informacije, koja je u ovom slučaju
između mog oca i moje majke,
između mog oca i moje majke,
00:54
raw elements and energy
in the same media, that is food,
in the same media, that is food,
16
42142
4157
sirovine i energiju
u istom medijumu, to jest hrani,
u istom medijumu, to jest hrani,
00:58
and after several months, produces me.
17
46323
2508
i nakon nekoliko meseci,
proizvela je mene.
proizvela je mene.
01:00
And I was not existent before.
18
48855
1812
A ja pre toga nisam postojao.
01:02
So apart from the shock of my mom
discovering that she was a 3D printer,
discovering that she was a 3D printer,
19
50691
3762
Pored zapanjenosti moje majke
kad je saznala da je 3D štampač,
kad je saznala da je 3D štampač,
01:06
I immediately got mesmerized
by that piece,
by that piece,
20
54477
4738
istog trena sam bio očaran tim delom,
01:11
the first one, the information.
21
59239
1717
prvim delom, informacijom.
01:12
What amount of information does it take
22
60980
2251
Koliko informacija je potrebno
01:15
to build and assemble a human?
23
63255
1936
da se sagradi i sastavi čovek?
01:17
Is it much? Is it little?
24
65215
1574
Da li je potrebno mnogo? Malo?
01:18
How many thumb drives can you fill?
25
66813
2180
Koliko fleš memorija
biste mogli da ispunite?
biste mogli da ispunite?
01:21
Well, I was studying physics
at the beginning
at the beginning
26
69017
2624
Pa, na početku sam studirao fiziku
01:23
and I took this approximation of a human
as a gigantic Lego piece.
as a gigantic Lego piece.
27
71665
5597
i pretpostavio sam da je čovek
poput džinovske lego slagalice.
poput džinovske lego slagalice.
01:29
So, imagine that the building
blocks are little atoms
blocks are little atoms
28
77286
3785
Zamislite da su kockice sitni atomi
01:33
and there is a hydrogen here,
a carbon here, a nitrogen here.
a carbon here, a nitrogen here.
29
81095
4653
i vodonik je ovde,
ugljenik ovde, azot ovde.
ugljenik ovde, azot ovde.
01:37
So in the first approximation,
30
85772
1571
Prema prvoj pretpostavci,
01:39
if I can list the number of atoms
that compose a human being,
that compose a human being,
31
87367
4343
ako bih mogao da nabrojim atome
od kojih se sastoji ljudsko biće,
od kojih se sastoji ljudsko biće,
01:43
I can build it.
32
91734
1387
mogao bih ga sagraditi.
01:45
Now, you can run some numbers
33
93145
2029
Sad, možete da proverite brojke
01:47
and that happens to be
quite an astonishing number.
quite an astonishing number.
34
95198
3277
i to je izgleda prilično zapanjujući broj.
01:50
So the number of atoms,
35
98499
2757
Pa je broj atoma,
01:53
the file that I will save in my thumb
drive to assemble a little baby,
drive to assemble a little baby,
36
101280
4755
dokument koji bih sačuvao na fleš memoriji
da bih sastavio bebicu,
da bih sastavio bebicu,
01:58
will actually fill an entire Titanic
of thumb drives --
of thumb drives --
37
106059
4667
zapravo bi ispunio
čitav Titanik fleš memorijama -
čitav Titanik fleš memorijama -
02:02
multiplied 2,000 times.
38
110750
2718
pomnoženo 2000 puta.
02:05
This is the miracle of life.
39
113957
3401
Ovo je čudo života.
02:09
Every time you see from now on
a pregnant lady,
a pregnant lady,
40
117382
2612
Od sad, svaki put kad ugledate trudnicu,
02:12
she's assembling the biggest
amount of information
amount of information
41
120018
2856
ona sklapa najveću količinu informacija
02:14
that you will ever encounter.
42
122898
1556
na koju ćete ikad naići.
02:16
Forget big data, forget
anything you heard of.
anything you heard of.
43
124478
2950
Zaboravite velike podatke,
zaboravite bilo šta što ste čuli.
zaboravite bilo šta što ste čuli.
02:19
This is the biggest amount
of information that exists.
of information that exists.
44
127452
2881
Ovo je najveća količina informacija
koja postoji.
koja postoji.
02:22
(Applause)
45
130357
3833
(Aplauz)
02:26
But nature, fortunately, is much smarter
than a young physicist,
than a young physicist,
46
134214
4644
Ali priroda je srećom
daleko pametnija od mladog fizičara
daleko pametnija od mladog fizičara
02:30
and in four billion years, managed
to pack this information
to pack this information
47
138882
3576
i za četiri milijarde godina
je uspela da upakuje ove informacije
je uspela da upakuje ove informacije
02:34
in a small crystal we call DNA.
48
142482
2705
u maleni kristal koji nazivamo DNK.
02:37
We met it for the first time in 1950
when Rosalind Franklin,
when Rosalind Franklin,
49
145605
4312
Prvi put smo saznali za njega 1950.
kada ga je Rozalind Frenklin,
kada ga je Rozalind Frenklin,
02:41
an amazing scientist, a woman,
50
149941
1556
neverovatna naučnica,
02:43
took a picture of it.
51
151521
1389
fotografisala.
02:44
But it took us more than 40 years
to finally poke inside a human cell,
to finally poke inside a human cell,
52
152934
5188
Ali trebalo nam je preko 40 godina
da konačno prodremo unutar ljudske ćelije,
da konačno prodremo unutar ljudske ćelije,
02:50
take out this crystal,
53
158146
1602
izvadimo kristal,
02:51
unroll it, and read it for the first time.
54
159772
3080
odmotamo ga i prvi put ga pročitamo.
02:55
The code comes out to be
a fairly simple alphabet,
a fairly simple alphabet,
55
163615
3241
Ispostavilo se da je kôd
prilično jednostavna abeceda,
prilično jednostavna abeceda,
02:58
four letters: A, T, C and G.
56
166880
3772
četiri slova: A, T, C i G.
03:02
And to build a human,
you need three billion of them.
you need three billion of them.
57
170676
3490
A da biste sagradili čoveka,
potrebno vam je tri milijarde njih.
potrebno vam je tri milijarde njih.
03:06
Three billion.
58
174933
1179
Tri milijarde.
03:08
How many are three billion?
59
176136
1579
Koliko je tri milijarde?
03:09
It doesn't really make
any sense as a number, right?
any sense as a number, right?
60
177739
2762
Sami broj zaista nema
nikakvog smisla, zar ne?
nikakvog smisla, zar ne?
03:12
So I was thinking how
I could explain myself better
I could explain myself better
61
180525
4085
Pa sam razmišljao kako da bolje objasnim
03:16
about how big and enormous this code is.
62
184634
3050
koliko je velik i ogroman ovaj kod.
03:19
But there is -- I mean,
I'm going to have some help,
I'm going to have some help,
63
187708
3054
Ali evo ga - mislim, imaću malu pomoć,
03:22
and the best person to help me
introduce the code
introduce the code
64
190786
3227
a najbolja osoba da mi pomogne
da predstavim kôd
da predstavim kôd
03:26
is actually the first man
to sequence it, Dr. Craig Venter.
to sequence it, Dr. Craig Venter.
65
194037
3522
je zapravo prvi čovek
koji ga je sekvencirao, dr Kreg Venter.
koji ga je sekvencirao, dr Kreg Venter.
03:29
So welcome onstage, Dr. Craig Venter.
66
197583
3390
Zato, dobro došao na scenu,
dr Kreg Venter.
dr Kreg Venter.
03:32
(Applause)
67
200997
6931
(Aplauz)
03:39
Not the man in the flesh,
68
207952
2256
Ne čovek glavom i bradom,
03:43
but for the first time in history,
69
211448
2345
već prvi put u istoriji,
03:45
this is the genome of a specific human,
70
213817
3462
ovo je genom određenog čoveka,
03:49
printed page-by-page, letter-by-letter:
71
217303
3760
odštampan stranicu po stranicu,
slovo po slovo:
slovo po slovo:
03:53
262,000 pages of information,
72
221087
3996
262.000 stranica informacija,
03:57
450 kilograms, shipped
from the United States to Canada
from the United States to Canada
73
225107
4364
450 kilograma, isporučen
iz SAD-a u Kanadu,
iz SAD-a u Kanadu,
04:01
thanks to Bruno Bowden,
Lulu.com, a start-up, did everything.
Lulu.com, a start-up, did everything.
74
229495
4843
zahvaljujući Brunu Boudenu,
Lulu.com, startap, su sve odradili.
Lulu.com, startap, su sve odradili.
04:06
It was an amazing feat.
75
234362
1463
Bio je to fantastičan podvig.
04:07
But this is the visual perception
of what is the code of life.
of what is the code of life.
76
235849
4297
Ali ovo je vizuelni doživljaj
toga šta je životni kôd.
toga šta je životni kôd.
04:12
And now, for the first time,
I can do something fun.
I can do something fun.
77
240170
2478
A sada, prvi put,
mogu da uradim nešto zabavno.
mogu da uradim nešto zabavno.
04:14
I can actually poke inside it and read.
78
242672
2547
Mogu zapravo da zavirim unutra
i da ga čitam.
i da ga čitam.
04:17
So let me take an interesting
book ... like this one.
book ... like this one.
79
245243
4625
Dozvolite mi da uzmem
zanimljivu knjigu... poput ove.
zanimljivu knjigu... poput ove.
04:25
I have an annotation;
it's a fairly big book.
it's a fairly big book.
80
253077
2534
Imam zabelešku; prilično je obimna knjiga.
04:27
So just to let you see
what is the code of life.
what is the code of life.
81
255635
3727
Prosto da vidite šta je životni kôd.
04:32
Thousands and thousands and thousands
82
260566
3391
Hiljade i hiljade i hiljade
04:35
and millions of letters.
83
263981
2670
i milioni slova.
04:38
And they apparently make sense.
84
266675
2396
I očigledno da imaju smisla.
04:41
Let's get to a specific part.
85
269095
1757
Pođimo do specifičnog dela.
04:43
Let me read it to you:
86
271571
1362
Dozvolite da vam pročitam:
04:44
(Laughter)
87
272957
1021
(Smeh)
04:46
"AAG, AAT, ATA."
88
274002
4006
"AAG, AAT, ATA."
04:50
To you it sounds like mute letters,
89
278965
2067
Vama ovo zvuči kao prazna slova,
04:53
but this sequence gives
the color of the eyes to Craig.
the color of the eyes to Craig.
90
281056
4041
ali ovaj redosled
odaje Kregovu boju očiju.
odaje Kregovu boju očiju.
04:57
I'll show you another part of the book.
91
285633
1932
Pokazaću vam još jedan deo iz knjige.
04:59
This is actually a little
more complicated.
more complicated.
92
287589
2094
Ovo je zapravo nešto komplikovanije.
05:02
Chromosome 14, book 132:
93
290983
2647
Hromozom 14, knjiga 132 -
05:05
(Laughter)
94
293654
2090
(Smeh)
05:07
As you might expect.
95
295768
1277
kao što pretpostavljate -
05:09
(Laughter)
96
297069
3466
(Smeh)
05:14
"ATT, CTT, GATT."
97
302857
4507
"ATT, CTT, GATT."
05:20
This human is lucky,
98
308329
1687
Ovaj čovek ima sreće
05:22
because if you miss just
two letters in this position --
two letters in this position --
99
310040
4517
jer ako ispustite samo dva slova
u ovom redosledu -
u ovom redosledu -
05:26
two letters of our three billion --
100
314581
1877
dva slova od tri milijarde -
05:28
he will be condemned
to a terrible disease:
to a terrible disease:
101
316482
2019
biće osuđen na užasnu bolest:
05:30
cystic fibrosis.
102
318525
1440
cističnu fibrozu.
05:31
We have no cure for it,
we don't know how to solve it,
we don't know how to solve it,
103
319989
3413
Za nju ne postoji lek,
ne znamo kako da je izlečimo,
ne znamo kako da je izlečimo,
05:35
and it's just two letters
of difference from what we are.
of difference from what we are.
104
323426
3755
a samo dva slova
su različita nego kod nas ostalih.
su različita nego kod nas ostalih.
05:39
A wonderful book, a mighty book,
105
327585
2705
Čarobna knjiga, moćna knjiga,
05:43
a mighty book that helped me understand
106
331115
1998
moćna knjiga koja mi je pomogla da shvatim
05:45
and show you something quite remarkable.
107
333137
2753
i da vam pokažem nešto izvanredno.
05:48
Every one of you -- what makes
me, me and you, you --
me, me and you, you --
108
336480
4435
Svako od vas - ono zbog čega sam ja ja,
a vi ste vi -
a vi ste vi -
05:52
is just about five million of these,
109
340939
2954
je samo oko pet miliona ovih slova,
05:55
half a book.
110
343917
1228
polovina knjige.
05:58
For the rest,
111
346015
1663
Što se tiče ostalog,
05:59
we are all absolutely identical.
112
347702
2562
apsolutno smo identični.
06:03
Five hundred pages
is the miracle of life that you are.
is the miracle of life that you are.
113
351008
4018
Pet stotina stranica
je čudo života koje predstavljate vi.
je čudo života koje predstavljate vi.
06:07
The rest, we all share it.
114
355050
2531
Ostalo svi mi delimo.
Zato se setite toga
kad pomislite kako smo svi različiti.
kad pomislite kako smo svi različiti.
06:09
So think about that again
when we think that we are different.
when we think that we are different.
115
357605
2909
06:12
This is the amount that we share.
116
360538
2221
Ovo je suma koju svi delimo.
06:15
So now that I have your attention,
117
363441
3429
Pa, sad kad imam vašu pažnju,
06:18
the next question is:
118
366894
1359
sledeće pitanje je:
06:20
How do I read it?
119
368277
1151
kako da to pročitam?
06:21
How do I make sense out of it?
120
369452
1509
Kako da pronađem smisao u tome?
06:23
Well, for however good you can be
at assembling Swedish furniture,
at assembling Swedish furniture,
121
371409
4240
Pa, koliko god ste dobri
u sastavljanju švedskog nameštaja,
u sastavljanju švedskog nameštaja,
06:27
this instruction manual
is nothing you can crack in your life.
is nothing you can crack in your life.
122
375673
3563
ovo uputstvo za upotrebu
je nešto što nećete shvatiti dok ste živi.
je nešto što nećete shvatiti dok ste živi.
06:31
(Laughter)
123
379260
1603
(Smeh)
06:32
And so, in 2014, two famous TEDsters,
124
380887
3112
Pa su 2014, dva čuvena Tedovca,
06:36
Peter Diamandis and Craig Venter himself,
125
384023
2540
Piter Dijamandis i Kreg Venter lično,
06:38
decided to assemble a new company.
126
386587
1927
odlučili da osnuju novu firmu.
06:40
Human Longevity was born,
127
388538
1412
Rođen je Hjuman Londževiti,
06:41
with one mission:
128
389974
1370
sa samo jednom misijom:
06:43
trying everything we can try
129
391368
1861
da pokušamo sve što možemo
06:45
and learning everything
we can learn from these books,
we can learn from these books,
130
393253
2759
i da naučimo sve što možemo
da naučimo iz ovih knjiga,
da naučimo iz ovih knjiga,
06:48
with one target --
131
396036
1705
s jednim ciljem -
06:50
making real the dream
of personalized medicine,
of personalized medicine,
132
398862
2801
da ostvarimo san personalizovane medicine,
06:53
understanding what things
should be done to have better health
should be done to have better health
133
401687
3767
da razumemo šta treba da se uradi
kako bismo bili zdraviji
kako bismo bili zdraviji
06:57
and what are the secrets in these books.
134
405478
2283
i koje tajne kriju ove knjige.
07:00
An amazing team, 40 data scientists
and many, many more people,
and many, many more people,
135
408329
4250
Fantastična ekipa, 40 naučnika za podatke
i još mnogo, mnogo ljudi,
i još mnogo, mnogo ljudi,
07:04
a pleasure to work with.
136
412603
1350
s kojima je užitak raditi.
07:05
The concept is actually very simple.
137
413977
2253
Koncept je zapravo veoma jednostavan.
07:08
We're going to use a technology
called machine learning.
called machine learning.
138
416254
3158
Koristićemo tehnologiju
koja se zove mašinsko učenje.
koja se zove mašinsko učenje.
07:11
On one side, we have genomes --
thousands of them.
thousands of them.
139
419436
4539
S jedne strane, imamo genome -
hiljade njih.
hiljade njih.
07:15
On the other side, we collected
the biggest database of human beings:
the biggest database of human beings:
140
423999
3997
S druge strane, sakupili smo
najveću bazu podataka o ljudskim bićima:
najveću bazu podataka o ljudskim bićima:
07:20
phenotypes, 3D scan, NMR --
everything you can think of.
everything you can think of.
141
428020
4296
fenotipe, 3D snimke, nuklearnu magnetnu
rezonancu, sve što vam pada na pamet.
rezonancu, sve što vam pada na pamet.
07:24
Inside there, on these two opposite sides,
142
432340
2899
Unutar toga, na ovim oprečnim stranama,
07:27
there is the secret of translation.
143
435263
2442
nalazi se tajna prevodilaštva.
07:29
And in the middle, we build a machine.
144
437729
2472
A u sredini smo sagradili mašinu.
07:32
We build a machine
and we train a machine --
and we train a machine --
145
440801
2385
Sagradili smo mašinu
i obučili smo mašinu -
i obučili smo mašinu -
07:35
well, not exactly one machine,
many, many machines --
many, many machines --
146
443210
3210
pa, zapravo ne baš jednu mašinu,
mnogo, mnogo mašina -
mnogo, mnogo mašina -
07:38
to try to understand and translate
the genome in a phenotype.
the genome in a phenotype.
147
446444
4544
da pokašaju da razumeju i prevedu
genom u fenotipu.
genom u fenotipu.
07:43
What are those letters,
and what do they do?
and what do they do?
148
451362
3340
Šta su ta slova i koja je njihova svrha?
07:46
It's an approach that can
be used for everything,
be used for everything,
149
454726
2747
To je pristup
koji može da se koristi svuda,
koji može da se koristi svuda,
07:49
but using it in genomics
is particularly complicated.
is particularly complicated.
150
457497
2993
ali njegova upotreba u genetici
je naročito komplikovana.
je naročito komplikovana.
07:52
Little by little we grew and we wanted
to build different challenges.
to build different challenges.
151
460514
3276
Malo po malo smo rasli i želeli smo
da napravimo nove izazove.
da napravimo nove izazove.
07:55
We started from the beginning,
from common traits.
from common traits.
152
463814
2732
Počeli smo ispočetka,
od zajedničkih osobina.
od zajedničkih osobina.
07:58
Common traits are comfortable
because they are common,
because they are common,
153
466570
2603
Zajedničke osobine su prijatne
jer su zajedničke,
jer su zajedničke,
08:01
everyone has them.
154
469197
1184
svako ih ima.
08:02
So we started to ask our questions:
155
470405
2494
Pa smo počeli da postavljamo naša pitanja:
08:04
Can we predict height?
156
472923
1380
možemo li predvideti visinu?
Možemo li čitanjem ovih knjiga
predvideti visinu?
predvideti visinu?
08:06
Can we read the books
and predict your height?
and predict your height?
157
474985
2177
08:09
Well, we actually can,
158
477186
1151
Pa, zapravo možemo,
08:10
with five centimeters of precision.
159
478361
1793
preciznošću od pet centimetara.
08:12
BMI is fairly connected to your lifestyle,
160
480178
3135
Indeks telesne mase
je usko povezan s vašim načinom života,
je usko povezan s vašim načinom života,
08:15
but we still can, we get in the ballpark,
eight kilograms of precision.
eight kilograms of precision.
161
483337
3864
ali i dalje možemo, možemo da pogodimo
preciznošću od osam kilograma.
preciznošću od osam kilograma.
Možemo li predvideti boju očiju?
08:19
Can we predict eye color?
162
487225
1231
08:20
Yeah, we can.
163
488480
1158
Da, možemo.
08:21
Eighty percent accuracy.
164
489662
1324
Preciznošću od 80 procenata.
08:23
Can we predict skin color?
165
491466
1858
Možemo li predvideti boju kože?
08:25
Yeah we can, 80 percent accuracy.
166
493348
2441
Da, možemo, s 80 procenata tačnosti.
08:27
Can we predict age?
167
495813
1340
Možemo li predvideti starost?
08:30
We can, because apparently,
the code changes during your life.
the code changes during your life.
168
498121
3739
Možemo jer se očigledno
kôd menja tokom vašeg života.
kôd menja tokom vašeg života.
08:33
It gets shorter, you lose pieces,
it gets insertions.
it gets insertions.
169
501884
3282
Postaje kraći, gubite delove,
dodaju se umeci.
dodaju se umeci.
08:37
We read the signals, and we make a model.
170
505190
2555
Čitamo signale i pravimo model.
08:40
Now, an interesting challenge:
171
508438
1475
Sad, zanimljiv izazov:
08:41
Can we predict a human face?
172
509937
1729
možemo li predvideti ljudsko lice?
08:45
It's a little complicated,
173
513014
1278
Malo je komplikovano
08:46
because a human face is scattered
among millions of these letters.
among millions of these letters.
174
514316
3191
jer je ljudsko lice rasuto
među milionima ovih slova.
među milionima ovih slova.
08:49
And a human face is not
a very well-defined object.
a very well-defined object.
175
517531
2629
A ljudsko lice nije
naročito dobro definisan objekat.
naročito dobro definisan objekat.
08:52
So, we had to build an entire tier of it
176
520184
2051
Pa smo morali da napravimo
čitav niz njih
čitav niz njih
08:54
to learn and teach
a machine what a face is,
a machine what a face is,
177
522259
2710
kako bismo naučili i obrazovali
mašinu da zna šta je lice,
mašinu da zna šta je lice,
08:56
and embed and compress it.
178
524993
2037
i da ga ugradi i sažme.
08:59
And if you're comfortable
with machine learning,
with machine learning,
179
527054
2248
A ako vam je poznato mašinsko učenje,
09:01
you understand what the challenge is here.
180
529326
2284
razumećete o kakvom se izazovu ovde radi.
09:04
Now, after 15 years -- 15 years after
we read the first sequence --
we read the first sequence --
181
532108
5991
Sad, nakon 15 godina - 15 godina
nakon što smo pročitali prvi isečak -
nakon što smo pročitali prvi isečak -
09:10
this October, we started
to see some signals.
to see some signals.
182
538123
2902
ovog oktobra, počeli smo
da zapažamo neke signale.
da zapažamo neke signale.
09:13
And it was a very emotional moment.
183
541049
2455
I bio je to izuzetno emotivan trenutak.
09:15
What you see here is a subject
coming in our lab.
coming in our lab.
184
543528
3745
Ovde vidite subjekta
koji je došao u našu laboratoriju.
koji je došao u našu laboratoriju.
09:19
This is a face for us.
185
547619
1928
Ovo je lice za nas.
09:21
So we take the real face of a subject,
we reduce the complexity,
we reduce the complexity,
186
549571
3631
Uzimamo pravo lice subjekta,
svedemo složenost
svedemo složenost
09:25
because not everything is in your face --
187
553226
1970
jer nije sve u vašem licu -
09:27
lots of features and defects
and asymmetries come from your life.
and asymmetries come from your life.
188
555220
3786
mnoge crte i nedostaci
i asimetrija potiču iz vašeg života.
i asimetrija potiču iz vašeg života.
09:31
We symmetrize the face,
and we run our algorithm.
and we run our algorithm.
189
559030
3469
Ujednačavamo simetriju lica
i provlačimo ga kroz naš algoritam.
i provlačimo ga kroz naš algoritam.
09:35
The results that I show you right now,
190
563245
1898
Rezultati koje vam upravo pokazujem,
09:37
this is the prediction we have
from the blood.
from the blood.
191
565167
3372
ova predviđanja dobijamo iz krvi.
09:41
(Applause)
192
569596
1524
(Aplauz)
09:43
Wait a second.
193
571144
1435
Sačekajte sekund.
09:44
In these seconds, your eyes are watching,
left and right, left and right,
left and right, left and right,
194
572603
4692
U ovim trenucima, vaše oči posmatraju
levo i desno, levo i desno,
levo i desno, levo i desno,
09:49
and your brain wants
those pictures to be identical.
those pictures to be identical.
195
577319
3930
a vaš mozak želi
da te slike budu identične.
da te slike budu identične.
09:53
So I ask you to do
another exercise, to be honest.
another exercise, to be honest.
196
581273
2446
Zato tražim od vas drugu vežbu,
da budete iskreni.
da budete iskreni.
09:55
Please search for the differences,
197
583743
2287
Molim vas da tražite razlike,
09:58
which are many.
198
586054
1361
ima ih mnogo.
09:59
The biggest amount of signal
comes from gender,
comes from gender,
199
587439
2603
Najveća količina signala dolazi od roda,
10:02
then there is age, BMI,
the ethnicity component of a human.
the ethnicity component of a human.
200
590066
5201
potom je tu uzrast, indeks telesne mase,
čovekova etnička komponenta.
čovekova etnička komponenta.
10:07
And scaling up over that signal
is much more complicated.
is much more complicated.
201
595291
3711
A prenošenje tog signala na veće razmere
je daleko komplikovanije.
je daleko komplikovanije.
10:11
But what you see here,
even in the differences,
even in the differences,
202
599026
3250
Ali ono što vidite ovde, čak i uz razlike,
10:14
lets you understand
that we are in the right ballpark,
that we are in the right ballpark,
203
602300
3595
dozvoljava vam da shvatite
da su naše pretpostavke tačne,
da su naše pretpostavke tačne,
10:17
that we are getting closer.
204
605919
1348
da smo sve bliži.
10:19
And it's already giving you some emotions.
205
607291
2349
I već imate neki utisak.
10:21
This is another subject
that comes in place,
that comes in place,
206
609664
2703
Ovo je još jedan subjekat
koji se poklopio,
koji se poklopio,
10:24
and this is a prediction.
207
612391
1409
a ovo je predviđanje.
10:25
A little smaller face, we didn't get
the complete cranial structure,
the complete cranial structure,
208
613824
4596
Nešto sitnije lice, nismo pogodili
u potpunosti strukturu lobanje,
u potpunosti strukturu lobanje,
10:30
but still, it's in the ballpark.
209
618444
2651
ali ipak, približno je.
Ovo je subjekat koji je došao
u našu laboratoriju,
u našu laboratoriju,
10:33
This is a subject that comes in our lab,
210
621634
2224
10:35
and this is the prediction.
211
623882
1443
a ovo je predviđanje.
10:38
So these people have never been seen
in the training of the machine.
in the training of the machine.
212
626056
4676
Dakle, mašina tokom obuke
nikad nije videla ove ljude.
nikad nije videla ove ljude.
10:42
These are the so-called "held-out" set.
213
630756
2837
Ovo je takozvani "izostavljeni" skup.
10:45
But these are people that you will
probably never believe.
probably never believe.
214
633617
3740
Ali ovo su verovatno
za vas neuverljivi ljudi.
za vas neuverljivi ljudi.
10:49
We're publishing everything
in a scientific publication,
in a scientific publication,
215
637381
2676
Sve objavljujemo u naučnim časopisima,
10:52
you can read it.
216
640081
1151
možete to da čitate.
10:53
But since we are onstage,
Chris challenged me.
Chris challenged me.
217
641256
2344
Ali kako smo na sceni, Kris me je izazvao.
10:55
I probably exposed myself
and tried to predict
and tried to predict
218
643624
3626
Verovatno sam se izložio
i pokušao sam da predvidim
i pokušao sam da predvidim
10:59
someone that you might recognize.
219
647274
2831
nekoga koga biste možda prepoznali.
11:02
So, in this vial of blood --
and believe me, you have no idea
and believe me, you have no idea
220
650470
4425
Dakle, u ovoj epruveti krvi -
i verujte mi, nemate pojma
i verujte mi, nemate pojma
11:06
what we had to do to have
this blood now, here --
this blood now, here --
221
654919
2880
šta smo morali da da uradimo
da bismo doneli krv ovde -
da bismo doneli krv ovde -
11:09
in this vial of blood is the amount
of biological information
of biological information
222
657823
3901
u ovoj epruveti krvi je količina
bioloških informacija
bioloških informacija
koja nam je potrebna
da sekvenciramo čitav genom.
da sekvenciramo čitav genom.
11:13
that we need to do a full genome sequence.
223
661748
2277
11:16
We just need this amount.
224
664049
2070
Svega ovoliko nam je dovoljno.
11:18
We ran this sequence,
and I'm going to do it with you.
and I'm going to do it with you.
225
666528
3205
Odradili smo sekvenciranje,
i uradiću to s vama.
i uradiću to s vama.
11:21
And we start to layer up
all the understanding we have.
all the understanding we have.
226
669757
3979
I počeli smo da raslojavamo
sve znanje koje imamo.
sve znanje koje imamo.
11:25
In the vial of blood,
we predicted he's a male.
we predicted he's a male.
227
673760
3350
Iz ove epruvete krvi,
predvideli smo da je muškarac u pitanju.
predvideli smo da je muškarac u pitanju.
11:29
And the subject is a male.
228
677134
1364
Subjekat je muškarac.
11:30
We predict that he's a meter and 76 cm.
229
678996
2438
Predvideli smo da je visok metar i 76 cm.
11:33
The subject is a meter and 77 cm.
230
681458
2392
Subjekat je visok metar i 77 centimetara.
11:35
So, we predicted that he's 76;
the subject is 82.
the subject is 82.
231
683874
4110
Dakle, predvideli smo da je '76. godište,
zapravo je '82.
zapravo je '82.
11:40
We predict his age, 38.
232
688701
2632
Predvideli smo da ima 38 godina.
11:43
The subject is 35.
233
691357
1904
Subjekat ima 35 godina.
11:45
We predict his eye color.
234
693851
2124
Predvideli mo njegovu boju očiju.
11:48
Too dark.
235
696824
1211
Suviše je tamna.
11:50
We predict his skin color.
236
698059
1555
Predvideli smo boju kože.
11:52
We are almost there.
237
700026
1410
Skoro da smo pogodili.
11:53
That's his face.
238
701899
1373
Ovo je njegovo lice.
11:57
Now, the reveal moment:
239
705172
3269
A sad, trenutak razotkrivanja:
12:00
the subject is this person.
240
708465
1770
subjekat je ova osoba.
12:02
(Laughter)
241
710259
1935
(Smeh)
12:04
And I did it intentionally.
242
712218
2058
Namerno sam to uradio.
12:06
I am a very particular
and peculiar ethnicity.
and peculiar ethnicity.
243
714300
3692
Ja sam veoma karakterističan
i karakterističnog sam porekla.
i karakterističnog sam porekla.
12:10
Southern European, Italians --
they never fit in models.
they never fit in models.
244
718016
2950
Južnoevropljani, Italijani -
nikad se ne uklapaju u kalupe.
nikad se ne uklapaju u kalupe.
12:12
And it's particular -- that ethnicity
is a complex corner case for our model.
is a complex corner case for our model.
245
720990
5130
A karakteristično je - da je narodnost
kompleksan izuzetak za naš model.
kompleksan izuzetak za naš model.
12:18
But there is another point.
246
726144
1509
Ali ima tu još nešto.
12:19
So, one of the things that we use
a lot to recognize people
a lot to recognize people
247
727677
3477
Dakle, nešto što uveliko koristimo
da bismo prepoznali ljude
da bismo prepoznali ljude
12:23
will never be written in the genome.
248
731178
1722
nikada neće da bude upisano u genom.
12:24
It's our free will, it's how I look.
249
732924
2317
To je naša slobodna volja, naš izgled.
12:27
Not my haircut in this case,
but my beard cut.
but my beard cut.
250
735265
3229
Ne moja frizura, u ovom slučaju,
već moja brada.
već moja brada.
12:30
So I'm going to show you, I'm going to,
in this case, transfer it --
in this case, transfer it --
251
738518
3553
Pa ću da vam pokažem,
u ovom slučaju ću da to prenesem -
u ovom slučaju ću da to prenesem -
12:34
and this is nothing more
than Photoshop, no modeling --
than Photoshop, no modeling --
252
742095
2765
a ovo nije ništa više od fotošopa,
nije modelarstvo -
nije modelarstvo -
12:36
the beard on the subject.
253
744884
1713
brada na subjektu.
12:38
And immediately, we get
much, much better in the feeling.
much, much better in the feeling.
254
746621
3472
I momentalno imamo
mnogo, mnogo bolji utisak.
mnogo, mnogo bolji utisak.
12:42
So, why do we do this?
255
750955
2709
Dakle, zašto ovo radimo?
12:47
We certainly don't do it
for predicting height
for predicting height
256
755938
5140
Sigurno to ne radimo
da bismo predvideli visinu
da bismo predvideli visinu
12:53
or taking a beautiful picture
out of your blood.
out of your blood.
257
761102
2372
ili da bismo izradili lepu sliku
iz vaše krvi.
iz vaše krvi.
12:56
We do it because the same technology
and the same approach,
and the same approach,
258
764390
4018
Radimo to jer ista ova tehnologija
i isti pristup,
i isti pristup,
13:00
the machine learning of this code,
259
768432
2520
mašinsko učenje ovog koda,
13:02
is helping us to understand how we work,
260
770976
3137
pomaže nam da razumemo kako funkcionišemo,
13:06
how your body works,
261
774137
1486
kako vaše telo funkcioniše,
13:07
how your body ages,
262
775647
1665
kako vaše telo stari,
13:09
how disease generates in your body,
263
777336
2769
kako bolesti nastaju u vašem telu,
13:12
how your cancer grows and develops,
264
780129
2972
kako vaš rak raste i razvija se,
13:15
how drugs work
265
783125
1783
kako lekovi funkcionišu
13:16
and if they work on your body.
266
784932
2314
i da li deluju na vaše telo.
13:19
This is a huge challenge.
267
787713
1667
Ovo je ogorman izazov.
13:21
This is a challenge that we share
268
789894
1638
Ovo je zajednički izazov
13:23
with thousands of other
researchers around the world.
researchers around the world.
269
791556
2579
nas i hiljada drugih
istraživača širom sveta.
istraživača širom sveta.
13:26
It's called personalized medicine.
270
794159
2222
Naziva se personalizovanom medicinom.
13:29
It's the ability to move
from a statistical approach
from a statistical approach
271
797125
3460
To je mogućnost da se pomerimo
sa statističkog pristupa,
sa statističkog pristupa,
13:32
where you're a dot in the ocean,
272
800609
2032
u kom ste tačkica u okeanu,
13:34
to a personalized approach,
273
802665
1813
do personalizovanog pristupa,
13:36
where we read all these books
274
804502
2185
gde čitamo sve ove knjige
13:38
and we get an understanding
of exactly how you are.
of exactly how you are.
275
806711
2864
i stičemo saznanje o tome
tačno kako ste vi.
tačno kako ste vi.
13:42
But it is a particularly
complicated challenge,
complicated challenge,
276
810260
3362
Ali je naročito složen izazov
13:45
because of all these books, as of today,
277
813646
3998
jer od svih ovih knjiga, do danas,
13:49
we just know probably two percent:
278
817668
2642
znamo verovatno samo dva procenta:
13:53
four books of more than 175.
279
821027
3653
četiri knjige od preko 175.
13:58
And this is not the topic of my talk,
280
826021
3206
A ovo nije tema mog govora
14:02
because we will learn more.
281
830145
2598
jer ćemo saznati više.
14:05
There are the best minds
in the world on this topic.
in the world on this topic.
282
833378
2669
Najveći umovi na svetu
se bave ovim pitanjem.
se bave ovim pitanjem.
14:09
The prediction will get better,
283
837048
1834
Predviđanje će postati bolje,
14:10
the model will get more precise.
284
838906
2253
model će biti sve precizniji.
14:13
And the more we learn,
285
841183
1858
A što više naučimo,
14:15
the more we will
be confronted with decisions
be confronted with decisions
286
843065
4830
više ćemo biti suočeni s odlukama
14:19
that we never had to face before
287
847919
3021
s kojima se pre nismo morali suočavati
14:22
about life,
288
850964
1435
o životu,
14:24
about death,
289
852423
1674
o smrti,
14:26
about parenting.
290
854121
1603
o roditeljstvu.
14:32
So, we are touching the very
inner detail on how life works.
inner detail on how life works.
291
860626
4746
Dakle, dodirujemo samu unutrašnju
pojedinost kako život funkcioniše.
pojedinost kako život funkcioniše.
14:38
And it's a revolution
that cannot be confined
that cannot be confined
292
866118
3158
A to je revolucija
koja ne može da bude ograničena
koja ne može da bude ograničena
14:41
in the domain of science or technology.
293
869300
2659
u domenu nauke ili tehnologije.
14:44
This must be a global conversation.
294
872960
2244
Ovo mora da bude globalna diskusija.
14:47
We must start to think of the future
we're building as a humanity.
we're building as a humanity.
295
875798
5217
Moramo početi da razmišljamo o budućnosti
koju kao čovečanstvo gradimo.
koju kao čovečanstvo gradimo.
14:53
We need to interact with creatives,
with artists, with philosophers,
with artists, with philosophers,
296
881039
4064
Moramo da sarađujemo sa kreativcima,
umetnicima, filozofima,
umetnicima, filozofima,
14:57
with politicians.
297
885127
1510
političarima.
14:58
Everyone is involved,
298
886661
1158
Svi su uključeni
14:59
because it's the future of our species.
299
887843
2825
jer se radi o budućnosti naše vrste.
15:03
Without fear, but with the understanding
300
891273
3968
Bez straha, ali uz razumevanje
15:07
that the decisions
that we make in the next year
that we make in the next year
301
895265
3871
da će odluke koje donesemo naredne godine
15:11
will change the course of history forever.
302
899160
3789
zauvek da promene pravac istorije.
15:15
Thank you.
303
903732
1160
Havala vam.
15:16
(Applause)
304
904916
10159
(Aplauz)
ABOUT THE SPEAKER
Riccardo Sabatini - Scientist, entrepreneurRiccardo Sabatini applies his expertise in numerical modeling and data to projects ranging from material science to computational genomics and food market predictions.
Why you should listen
Data scientist Riccardo Sabatini harnesses numerical methods for a surprising variety of fields, from material science research to the study of food commodities (as a past director of the EU research project FoodCAST). His most recent research centers on computational genomics and how to crack the code of life.
In addition to his data research, Sabatini is deeply involved in education for entrepreneurs. He is the founder and co-director of the Quantum ESPRESSO Foundation, an advisor in several data-driven startups, and funder of The HUB Trieste, a social impact accelerator.
Riccardo Sabatini | Speaker | TED.com