How we're using AI to discover new antibiotics | Jim Collins

41,124 views ใƒป 2020-05-26

TED


ืื ื ืœื—ืฅ ืคืขืžื™ื™ื ืขืœ ื”ื›ืชื•ื‘ื™ื•ืช ื‘ืื ื’ืœื™ืช ืœืžื˜ื” ื›ื“ื™ ืœื”ืคืขื™ืœ ืืช ื”ืกืจื˜ื•ืŸ.

ืชืจื’ื•ื: zeeva Livshitz ืขืจื™ื›ื”: Nurit Noy
00:12
So how are we going to beat this novel coronavirus?
0
12917
2908
ืื– ืื™ืš ื ื ืฆื— ืืช ื•ื™ืจื•ืก ื”ืงื•ืจื•ื ื” ื”ื–ื”?
00:16
By using our best tools:
1
16317
2631
ื‘ืืžืฆืขื•ืช ื”ื›ืœื™ื ื”ื˜ื•ื‘ื™ื ื‘ื™ื•ืชืจ ืฉืœื ื•:
00:18
our science and our technology.
2
18972
2039
ื”ืžื“ืข ื•ื”ื˜ื›ื ื•ืœื•ื’ื™ื” ืฉืœื ื•.
00:21
In my lab, we're using the tools of artificial intelligence
3
21594
3132
ื‘ืžืขื‘ื“ื” ืฉืœื™ ืื ื• ืžืฉืชืžืฉื™ื ื‘ื›ืœื™ื ืฉืœ ื‘ื™ื ื” ืžืœืื›ื•ืชื™ืช
00:24
and synthetic biology
4
24750
1579
ื•ื‘ื™ื•ืœื•ื’ื™ื” ืกื™ื ืชื˜ื™ืช
00:26
to speed up the fight against this pandemic.
5
26353
3060
ื›ื“ื™ ืœื”ืื™ืฅ ืืช ื”ืžืื‘ืง ื ื’ื“ ืžื’ื™ืคื” ื–ื•.
00:30
Our work was originally designed
6
30078
1863
ื”ืขื‘ื•ื“ื” ืฉืœื ื• ืชื•ื›ื ื ื” ื‘ืžืงื•ืจ
00:31
to tackle the antibiotic resistance crisis.
7
31965
2853
ืœื”ืชืžื•ื“ื“ ืขื ืžืฉื‘ืจ ื”ืขืžื™ื“ื•ืช ืœืื ื˜ื™ื‘ื™ื•ื˜ื™ืงื”,
00:34
Our project seeks to harness the power of machine learning
8
34842
4689
ื”ืคืจื•ื™ืงื˜ ืฉืœื ื• ืžื‘ืงืฉ ืœืจืชื•ื ืืช ื›ื•ื— ืœืžื™ื“ืช ื”ืžื›ื•ื ื”
00:39
to replenish our antibiotic arsenal
9
39555
1846
ื›ื“ื™ ืœื—ื“ืฉ ืืช ืืจืกื ืœ ื”ืื ื˜ื™ื‘ื™ื•ื˜ื™ืงื” ืฉืœื ื•
00:41
and avoid a globally devastating postantibiotic era.
10
41425
3838
ื•ืœื”ืžื ืข ืžืขื™ื“ืŸ ืคื•ืกื˜-ืื ื˜ื™ื‘ื™ื•ื˜ื™ืงื” ื”ืจืกื ื™, ื’ืœื•ื‘ืœื™.
00:45
Importantly, the same technology can be used
11
45685
2820
ื—ืฉื•ื‘ ืžื›ืš, ื‘ืื•ืชื• ืื•ืคืŸ ื ื™ืชืŸ ืœื”ืฉืชืžืฉ ื‘ื˜ื›ื ื•ืœื•ื’ื™ื”
00:48
to search for antiviral compounds
12
48529
2072
ื›ื“ื™ ืœื—ืคืฉ ืชืจื›ื•ื‘ื•ืช ืื ื˜ื™-ื•ื™ืจืืœื™ื•ืช
00:50
that could help us fight the current pandemic.
13
50625
2678
ืฉื™ื•ื›ืœื• ืœืขื–ื•ืจ ืœื ื• ืœื”ื™ืœื—ื ื‘ืžื’ื™ืคื” ื”ื ื•ื›ื—ื™ืช.
00:54
Machine learning is turning the traditional model of drug discovery
14
54080
3902
ืœืžื™ื“ืช ืžื›ื•ื ื” ื”ื•ืคื›ืช ืืช ื”ืžื•ื“ืœ ื”ืžืกื•ืจืชื™ ืฉืœ ื’ื™ืœื•ื™ ืชืจื•ืคื•ืช
00:58
on its head.
15
58006
1404
ืขืœ ืคื™ื•.
00:59
With this approach,
16
59434
1225
ื‘ื’ื™ืฉื” ื–ื•,
01:00
instead of painstakingly testing thousands of existing molecules
17
60683
4078
ื‘ืžืงื•ื ืœื‘ื“ื•ืง ื‘ืงืคื™ื“ื” ืืœืคื™ ืžื•ืœืงื•ืœื•ืช ืงื™ื™ืžื•ืช
01:04
one by one in a lab
18
64785
1436
ืื—ืช ืื—ืช ื‘ืžืขื‘ื“ื”,
01:06
for their effectiveness,
19
66245
1587
ื›ื“ื™ ืœื”ืขืจื™ืš ืืช ื™ืขื™ืœื•ืชืŸ,
01:07
we can train a computer to explore the exponentially larger space
20
67856
4657
ืื ื—ื ื• ื™ื›ื•ืœื™ื ืœื”ื›ืฉื™ืจ ืžื—ืฉื‘ ืœื—ืงื•ืจ ืืช ื”ืžืจื—ื‘ ื”ืืงืกืคื•ื ื ืฆื™ืืœื™ ื”ื’ื“ื•ืœ ื™ื•ืชืจ
01:12
of essentially all possible molecules that could be synthesized,
21
72537
3584
ืฉืœ ื›ืœ ื”ืžื•ืœืงื•ืœื•ืช ื”ืืคืฉืจื™ื•ืช ืฉืืคืฉืจ ืœืกื ืชื–,
01:16
and thus, instead of looking for a needle in a haystack,
22
76145
5614
ื•ื›ืš, ื‘ืžืงื•ื ืœื—ืคืฉ ืžื—ื˜ ื‘ืขืจื™ืžืช ืฉื—ืช,
01:21
we can use the giant magnet of computing power
23
81783
3760
ืื ื• ื™ื›ื•ืœื™ื ืœื”ืฉืชืžืฉ ื‘ืžื’ื ื˜ ื”ืขื ืง ืฉืœ ื›ื•ื— ื”ืžื—ืฉื•ื‘
01:25
to find many needles in multiple haystacks simultaneously.
24
85567
3915
ื›ื“ื™ ืœืžืฆื•ื ืžื—ื˜ื™ื ืจื‘ื•ืช ื‘ืขืจื™ืžื•ืช ืฉื—ืช ืžืจื•ื‘ื•ืช ื‘ื• ื–ืžื ื™ืช.
01:30
We've already had some early success.
25
90423
1992
ื”ื™ื• ืœื ื• ื›ื‘ืจ ื›ืžื” ื”ืฆืœื—ื•ืช ืžื•ืงื“ืžื•ืช.
01:33
Recently, we used machine learning to discover new antibiotics
26
93010
5465
ืœืื—ืจื•ื ื” ื”ืฉืชืžืฉื ื• ื‘ืœืžื™ื“ืช ืžื›ื•ื ื” ื›ื“ื™ ืœื’ืœื•ืช ืื ื˜ื™ื‘ื™ื•ื˜ื™ืงื•ืช ื—ื“ืฉื•ืช
01:38
that can help us fight off the bacterial infections
27
98499
2560
ืฉื™ื›ื•ืœื•ืช ืœืขื–ื•ืจ ืœื ื• ืœื”ื™ืœื—ื ื‘ื–ื™ื”ื•ืžื™ื ื—ื™ื™ื“ืงื™ื™ื
01:41
that can occur alongside SARS-CoV-2 infections.
28
101083
3611
ืฉืขืœื•ืœื™ื ืœื”ืชืจื—ืฉ ืœืฆื“ ื–ื™ื”ื•ืžื™ื ืžืกื•ื’ SARS-CoV-2.
ืœืคื ื™ ื—ื•ื“ืฉื™ื™ื, ื”ืžื™ื–ื TED's Audacious Project ืื™ืฉืจ ืขื‘ื•ืจื ื• ืžื™ืžื•ืŸ
01:45
Two months ago, TED's Audacious Project approved funding for us
29
105181
4169
01:49
to massively scale up our work
30
109374
2188
ื›ื“ื™ ืœื”ื’ื“ื™ืœ ื‘ืื•ืคืŸ ืžืกื™ื‘ื™ ืืช ื”ืขื‘ื•ื“ื” ืฉืœื ื•
01:51
with the goal of discovering seven new classes of antibiotics
31
111586
4628
ื‘ืžื˜ืจื” ืœื’ืœื•ืช 7 ืกื•ื’ื™ื ืฉืœ ืื ื˜ื™ื‘ื™ื•ื˜ื™ืงื•ืช ื—ื“ืฉื•ืช
01:56
against seven of the world's deadly bacterial pathogens
32
116238
3483
ื ื’ื“ ืฉื‘ืขื” ืžื”ืคืชื•ื’ื ื™ื ื”ืงื˜ืœื ื™ื™ื ื‘ื™ื•ืชืจ ื‘ืขื•ืœื,
01:59
over the next seven years.
33
119745
2055
ื‘ืžื”ืœืš ืฉื‘ืข ื”ืฉื ื™ื ื”ื‘ืื•ืช.
02:02
For context:
34
122206
1733
ื›ื“ื™ ืœื”ื›ื ื™ืก ื–ืืช ืœื”ืงืฉืจ:
02:03
the number of new class of antibiotics
35
123963
1928
ืžืกืคืจ ืกื•ื’ื™ ื”ืื ื˜ื™ื‘ื™ื•ื˜ื™ืงื” ื”ื—ื“ืฉื™ื
02:05
that have been discovered over the last three decades is zero.
36
125915
3235
ืฉื”ืชื’ืœื• ื‘ืฉืœื•ืฉืช ื”ืขืฉื•ืจื™ื ื”ืื—ืจื•ื ื™ื ื”ื•ื - ืืคืก.
02:10
While the quest for new antibiotics is for our medium-term future,
37
130030
3571
ื•ืื™ืœื• ื”ื—ื™ืคื•ืฉ ืื—ืจ ืื ื˜ื™ื‘ื™ื•ื˜ื™ืงื” ื—ื“ืฉื” ื”ื•ื ืœืžืขืŸ ื”ืขืชื™ื“ ืœื˜ื•ื•ื— ื”ื‘ื™ื ื•ื ื™ ืฉืœื ื•,
02:13
the novel coronavirus poses an immediate deadly threat,
38
133625
4652
ื•ื™ืจื•ืก ื”ืงื•ืจื•ื ื” ื”ื—ื“ืฉ ืžื”ื•ื•ื” ืื™ื•ื ืงื˜ืœื ื™ ืžื™ื™ื“ื™,
02:18
and I'm excited to share that we think we can use the same technology
39
138301
3793
ื•ืื ื™ ื ืจื’ืฉ ืœื—ืœื•ืง ืืช ื–ื” ืฉืื ื• ื—ื•ืฉื‘ื™ื ืฉื ื•ื›ืœ ืœื”ืฉืชืžืฉ ื‘ืื•ืชื” ื˜ื›ื ื•ืœื•ื’ื™ื”
02:22
to search for therapeutics to fight this virus.
40
142118
2809
ื›ื“ื™ ืœื—ืคืฉ ื˜ื™ืคื•ืœื™ื ืฉื™ืœื—ืžื• ื‘ื ื’ื™ืฃ ื”ื–ื”.
02:25
So how are we going to do it?
41
145486
1719
ืื– ืื™ืš ื ืขืฉื” ื–ืืช?
02:27
Well, we're creating a compound training library
42
147229
2948
ื•ื‘ื›ืŸ, ืื ื—ื ื• ื™ื•ืฆืจื™ื ืกืคืจื™ื™ืช ื”ื“ืจื›ื” ืžื•ืจื›ื‘ืช
02:30
and with collaborators applying these molecules to SARS-CoV-2-infected cells
43
150201
5542
ื•ืขื ืขืžื™ืชื™ื, ืžื™ื™ืฉืžื™ื ืžื•ืœืงื•ืœื•ืช ืืœื• ืœืชืื™ื ื ื’ื•ืขื™ื ื‘- SARS-CoV-2
02:35
to see which of them exhibit effective activity.
44
155767
3894
ื›ื“ื™ ืœืจืื•ืช ืžื™ ืžื”ื ืžืฆื™ื’ ืคืขื™ืœื•ืช ื™ืขื™ืœื”.
02:40
These data will be use to train a machine learning model
45
160175
3192
ื ืชื•ื ื™ื ืืœื” ื™ืฉืžืฉื• ืœื”ื“ืจื›ืช ืžื•ื“ืœ ืœืžื™ื“ืช ืžื›ื•ื ื”
02:43
that will be applied to an in silico library of over a billion molecules
46
163391
4070
ืฉื™ื•ื—ืœ ืขืœ ืกืคืจื™ืช ืื™ืŸ-ืกื™ืœื™ืงื• ื‘ืช ื™ื•ืชืจ ืžืžื™ืœื™ืืจื“ ืžื•ืœืงื•ืœื•ืช
02:47
to search for potential novel antiviral compounds.
47
167485
4204
ื›ื“ื™ ืœื—ืคืฉ ืคื•ื˜ื ืฆื™ืืœ ืฉืœ ืชืจื›ื•ื‘ื•ืช ืื ื˜ื™-ื•ื™ืจืืœื™ื•ืช ื—ื“ืฉื•ืช.
02:52
We will synthesize and test the top predictions
48
172324
2658
ืื ื• ื ืกื ืชื– ื•ื ื‘ื“ื•ืง ืืช ื”ืชื—ื–ื™ื•ืช ื”ืžื‘ื˜ื™ื—ื•ืช ื‘ื™ื•ืชืจ
02:55
and advance the most promising candidates into the clinic.
49
175006
2889
ื•ื ืงื“ื ืืช ื”ืžื•ืขืžื“ื™ื ื”ื›ื™ ืžื‘ื˜ื™ื—ื™ื ืœืงืœื™ื ื™ืงื”.
02:58
Sound too good to be true?
50
178356
1778
ื ืฉืžืข ื˜ื•ื‘ ืžื›ื“ื™ ืœื”ื™ื•ืช ืืžื™ืชื™?
03:00
Well, it shouldn't.
51
180158
1432
ื•ื‘ื›ืŸ, ื–ื” ืœื ืืžื•ืจ ืœื”ื™ืฉืžืข ื›ืš.
03:01
The Antibiotics AI Project is founded on our proof of concept research
52
181614
3325
ืคืจื•ื™ืงื˜ AI ืœื—ื™ืคื•ืฉ ืื ื˜ื™ื‘ื™ื•ื˜ื™ืงื” ื ื•ืกื“ ืขืœ ื‘ืกื™ืก ื”ื•ื›ื—ืช ื”ืžื—ืงืจ ืฉืœื ื•
03:04
that led to the discovery of a novel broad-spectrum antibiotic
53
184963
3401
ืฉื”ื•ื‘ื™ืœ ืœื’ื™ืœื•ื™ ืื ื˜ื™ื‘ื™ื•ื˜ื™ืงื” ื‘ืขืœืช ืงืฉืช ืจื—ื‘ื”
03:08
called halicin.
54
188388
1185
ืฉื ืงืจืืช ื”ืœื•ืฆื™ืŸ.
03:10
Halicin has potent antibacterial activity
55
190443
2813
ืœื”ืœื•ืฆื™ืŸ ืคืขื™ืœื•ืช ืื ื˜ื™ ื‘ืงื˜ืจื™ืืœื™ืช ื—ื–ืงื”
03:13
against almost all antibiotic-resistant bacterial pathogens,
56
193280
4102
ื ื’ื“ ื›ืžืขื˜ ื›ืœ ื”ืคืชื•ื’ื ื™ื ื”ื—ื™ื™ื“ืงื™ื™ื ื”ืขืžื™ื“ื™ื ืœืื ื˜ื™ื‘ื™ื•ื˜ื™ืงื”,
03:17
including untreatable panresistant infections.
57
197406
3641
ื›ื•ืœืœ ื–ื™ื”ื•ืžื™ื ืขืžื™ื“ื™ื ื•ื‘ืœืชื™ ื ื™ืชื ื™ื ืœื˜ื™ืคื•ืœ.
03:21
Importantly, in contrast to current antibiotics,
58
201862
2270
ื™ื•ืชืจ ื—ืฉื•ื‘, ื‘ื ื™ื’ื•ื“ ืœืื ื˜ื™ื‘ื™ื•ื˜ื™ืงื•ืช ื”ื ื•ื›ื—ื™ื•ืช,
03:24
the frequency at which bacteria develop resistance against halicin
59
204156
3694
ื”ืชื“ื™ืจื•ืช ื‘ื” ื—ื™ื™ื“ืงื™ื ืžืคืชื—ื™ื ื”ืชื ื’ื“ื•ืช ืœื”ืœื•ืฆื™ืŸ
03:27
is remarkably low.
60
207874
1484
ื”ื™ื ื ืžื•ื›ื” ืœื”ืคืœื™ื.
03:30
We tested the ability of bacteria to evolve resistance against halicin
61
210303
4710
ื‘ื“ืงื ื• ืืช ื™ื›ื•ืœืชื ืฉืœ ื”ื—ื™ื™ื“ืงื™ื ืœืคืชื— ื”ืชื ื’ื“ื•ืช ืœื”ืœื•ืฆื™ืŸ
03:35
as well as Cipro in the lab.
62
215037
1788
ื›ืžื• ื’ื ืœ"ืฆื™ืคืจื•" ื‘ืžืขื‘ื“ื”.
03:37
In the case of Cipro,
63
217299
1542
ื‘ืžืงืจื” ืฉืœ ืฆื™ืคืจื•,
03:38
after just one day, we saw resistance.
64
218865
2825
ืื—ืจื™ ื™ื•ื ืื—ื“ ื‘ืœื‘ื“, ืจืื™ื ื• ืขืžื™ื“ื•ืช.
03:42
In the case of halicin,
65
222213
1478
ื‘ืžืงืจื” ืฉืœ ื”ืœื•ืฆื™ืŸ
03:43
after one day, we didn't see any resistance.
66
223715
2115
ืื—ืจื™ ื™ื•ื ืื—ื“, ืœื ืจืื™ื ื• ืฉื•ื ืขืžื™ื“ื•ืช.
03:46
Amazingly, after even 30 days,
67
226479
3302
ื‘ืื•ืคืŸ ืžื“ื”ื™ื, ืืคื™ืœื• ืื—ืจื™ 30 ื™ื•ื,
03:49
we didn't see any resistance against halicin.
68
229805
2601
ืœื ืจืื™ื ื• ืฉื•ื ืขืžื™ื“ื•ืช ืœื”ืœื•ืฆื™ืŸ.
03:53
In this pilot project, we first tested roughly 2,500 compounds against E. coli.
69
233098
5526
ื‘ืคืจื•ื™ืงื˜ ื”ืจืฆื” ื–ื” ื‘ื“ืงื ื• ืœืจืืฉื•ื ื” ื›- 2,500 ืชืจื›ื•ื‘ื•ืช ื ื’ื“ E. coli.
03:59
This training set included known antibiotics,
70
239259
2780
ืขืจื›ืช ื ื™ืกื•ื™ ื–ื• ื›ืœืœื” ืื ื˜ื™ื‘ื™ื•ื˜ื™ืงื•ืช ื™ื“ื•ืขื•ืช,
04:02
such as Cipro and penicillin,
71
242063
1746
ื›ืžื• ืฆื™ืคืจื• ื•ืคื ื™ืฆื™ืœื™ืŸ,
04:03
as well as many drugs that are not antibiotics.
72
243833
2272
ื›ืžื• ื’ื ืชืจื•ืคื•ืช ืจื‘ื•ืช ืฉืื™ื ืŸ ืื ื˜ื™ื‘ื™ื•ื˜ื™ืงื”.
04:06
These data we used to train a model
73
246984
2587
ื‘ื ืชื•ื ื™ื ืืœื” ื”ืฉืชืžืฉื ื• ื›ื“ื™ ืœื”ื›ืฉื™ืจ ืžื•ื“ืœ
04:09
to learn molecular features associated with antibacterial activity.
74
249595
3978
ืœืœืžื•ื“ ืชื›ื•ื ื•ืช ืžื•ืœืงื•ืœืจื™ื•ืช ื”ืงืฉื•ืจื•ืช ืœืคืขื™ืœื•ืช ืื ื˜ื™ื‘ืงื˜ืจื™ืืœื™ืช.
04:14
We then applied this model to a drug-repurposing library
75
254269
2701
ืœืื—ืจ ืžื›ืŸ ื™ื™ืฉืžื ื• ืžื•ื“ืœ ื–ื” ืœืกืคืจื™ื™ื” ืฉืžืชืื™ืžื” ืชืจื•ืคื•ืช ืœืชื›ืœื™ืช ื—ื“ืฉื”
04:16
consisting of several thousand molecules
76
256994
2478
ืฉืžื•ืจื›ื‘ืช ืžื›ืžื” ืืœืคื™ ืžื•ืœืงื•ืœื•ืช
04:19
and asked the model to identify molecules
77
259496
2618
ื•ื‘ื™ืงืฉื ื• ืžื”ืžื•ื“ืœ ืœื–ื”ื•ืช ืžื•ืœืงื•ืœื•ืช
04:22
that are predicted to have antibacterial properties
78
262138
2784
ืฉื ื—ื–ื• ืฉื™ืฉ ืœื”ืŸ ืชื›ื•ื ื•ืช ืื ื˜ื™ื‘ืงื˜ืจื™ืืœื™ื•ืช
04:24
but don't look like existing antibiotics.
79
264946
2473
ืื‘ืœ ืœื ื ืจืื•ืช ื›ืžื• ืื ื˜ื™ื‘ื™ื•ื˜ื™ืงื•ืช ืงื™ื™ืžื•ืช.
04:28
Interestingly, only one molecule in that library fit these criteria,
80
268427
4797
ืจืง ืžื•ืœืงื•ืœื” ืื—ืช ื‘ืกืคืจื™ื” ื”ื–ืืช ืชื•ืืžืช ืœืงืจื™ื˜ืจื™ื•ื ื™ื ื”ืืœื”,
04:33
and that molecule turned out to be halicin.
81
273248
2336
ื•ื”ืชื‘ืจืจ ืฉื”ืžื•ืœืงื•ืœื” ื”ื™ื ื”ืœื•ืฆื™ืŸ.
04:36
Given that halicin does not look like any existing antibiotic,
82
276444
3088
ื‘ื”ืชื—ืฉื‘ ื‘ื›ืš ืฉื”ืœื•ืฆื™ืŸ ืœื ื ืจืื™ืช ื›ืžื• ืื ื˜ื™ื‘ื™ื•ื˜ื™ืงื” ืงื™ื™ืžืช ื›ืœืฉื”ื™,
04:39
it would have been impossible for a human, including an antibiotic expert,
83
279556
4154
ื”ื™ื” ื‘ืœืชื™ ืืคืฉืจื™ ืœืื“ื ื›ืœืฉื”ื•, ื’ื ืื ื”ื•ื ืžื•ืžื—ื” ืœืื ื˜ื™ื‘ื™ื•ื˜ื™ืงื”,
04:43
to identify halicin in this manner.
84
283734
2184
ืœื–ื”ื•ืช ืืช ื”ื”ืœื•ืฆื™ืŸ ื‘ืื•ืคืŸ ื›ื–ื”.
04:46
Imagine now what we could do with this technology
85
286574
2630
ืชืืจื• ืœืขืฆืžื›ื ื›ืขืช ืžื” ื”ื™ื™ื ื• ื™ื›ื•ืœื™ื ืœืขืฉื•ืช ืขื ื˜ื›ื ื•ืœื•ื’ื™ื” ื–ื•
04:49
against SARS-CoV-2.
86
289228
1741
ื ื’ื“ SARS-CoV-2.
04:51
And that's not all.
87
291783
1365
ื•ื–ื” ืœื ื”ื›ืœ.
04:53
We're also using the tools of synthetic biology,
88
293172
2820
ืื ื• ืžืฉืชืžืฉื™ื ื’ื ื‘ื›ืœื™ื ืฉืœ ื‘ื™ื•ืœื•ื’ื™ื” ืกื™ื ืชื˜ื™ืช,
04:56
tinkering with DNA and other cellular machinery,
89
296016
2611
ืฉืขื•ืกืงืช ื‘ DNA ื•ืžื ื’ื ื•ื ื™ื ืชืื™ื™ื ืื—ืจื™ื,
04:58
to serve human purposes like combating COVID-19,
90
298651
3910
ื›ื“ื™ ืœืฉืจืช ืžื˜ืจื•ืช ืื ื•ืฉื™ื•ืช ื›ืžื• ืžืื‘ืง ื‘- COVID-19,
05:02
and of note, we are working to develop a protective mask
91
302585
3647
ื•ืฉื™ืžื• ืœื‘, ืื ื—ื ื• ืขื•ื‘ื“ื™ื ืขืœ ืคื™ืชื•ื— ืžืกื›ืช ืžื’ืŸ
05:06
that can also serve as a rapid diagnostic test.
92
306256
3432
ืฉื™ื›ื•ืœื” ื’ื ืœืฉืจืช ืœื‘ื“ื™ืงืช ืื‘ื—ื•ืŸ ืžื”ื™ืจื”.
05:10
So how does that work?
93
310192
1472
ืื– ืื™ืš ื–ื” ืขื•ื‘ื“?
05:11
Well, we recently showed
94
311688
1205
ื•ื‘ื›ืŸ, ืœืื—ืจื•ื ื” ื”ืจืื™ื ื•
05:12
that you can take the cellular machinery out of a living cell
95
312917
2943
ืฉื ื™ืชืŸ ืœื”ื•ืฆื™ื ืืช ื”ืžื ื’ื ื•ืŸ ื”ืชืื™ ืžืชื•ืš ืชื ื—ื™,
05:15
and freeze-dry it along with RNA sensors onto paper
96
315884
4092
ืœื™ื™ื‘ืฉ ืื•ืชื• ื‘ื”ืงืคืื” ื™ื—ื“ ืขื ื—ื™ื™ืฉื ื™ RNA ืขืœ ื ื™ื™ืจ
05:20
in order to create low-cost diagnostics for Ebola and Zika.
97
320000
4916
ืขืœ ืžื ืช ืœื™ืฆื•ืจ ืื‘ื—ื•ืŸ ืœืื‘ื•ืœื” ื•ืœื–ื™ืงื” ื‘ืขืœื•ืช ื ืžื•ื›ื”.
05:25
The sensors are activated when they're rehydrated by a patient sample
98
325503
5227
ื”ื—ื™ื™ืฉื ื™ื ืžื•ืคืขืœื™ื ื›ืืฉืจ ื”ื ืžื•ืจื˜ื‘ื™ื ืžื—ื“ืฉ ืขืœ ื™ื“ื™ ื“ื’ื™ืžืช ืžื˜ื•ืคืœ
05:30
that could consist of blood or saliva, for example.
99
330754
2822
ื”ื™ื ื™ื›ื•ืœื” ืœื”ื™ื•ืช ืžื•ืจื›ื‘ืช ืžื“ื ืื• ืจื•ืง, ืœืžืฉืœ.
05:33
It turns out, this technology is not limited to paper
100
333600
3261
ืžืกืชื‘ืจ ืฉื”ื˜ื›ื ื•ืœื•ื’ื™ื” ื”ื–ื• ืื™ื ื” ืžื•ื’ื‘ืœืช ืœื ื™ื™ืจ
05:36
and can be applied to other materials, including cloth.
101
336885
2886
ื•ื ื™ืชืŸ ืœื™ื™ืฉื ืื•ืชื” ืœื—ื•ืžืจื™ื ืื—ืจื™ื, ื›ื•ืœืœ ื‘ื“.
05:40
For the COVID-19 pandemic,
102
340671
1942
ืœืžื’ื™ืคืช COVID-19,
05:42
we're designing RNA sensors to detect the virus
103
342637
4346
ืื ื• ืžืขืฆื‘ื™ื ื—ื™ื™ืฉื ื™ RNA ืœืื™ืชื•ืจ ื”ื ื’ื™ืฃ
05:47
and freeze-drying these along with the needed cellular machinery
104
347007
3210
ื•ื™ื™ื‘ื•ืฉื• ื‘ื”ืงืคืื” ื™ื—ื“ ืขื ื”ืžื ื’ื ื•ื ื™ื ื”ืชืื™ื™ื ื”ื“ืจื•ืฉื™ื
05:50
into the fabric of a face mask,
105
350241
2707
ืœืชื•ืš ื”ื‘ื“ ืฉืœ ืžืกื›ืช ืคื ื™ื,
05:52
where the simple act of breathing,
106
352972
2229
ืฉืฉื ื”ืคืขื•ืœื” ื”ืคืฉื•ื˜ื” ืฉืœ ื”ื ืฉื™ืžื”,
05:55
along with the water vapor that comes with it,
107
355225
2277
ื™ื—ื“ ืขื ืื“ื™ ื”ืžื™ื ืฉืžื’ื™ืขื™ื ืื™ืชื”,
05:57
can activate the test.
108
357526
1760
ื™ื›ื•ืœื™ื ืœื”ืคืขื™ืœ ืืช ื”ื‘ื“ื™ืงื”.
05:59
Thus, if a patient is infected with SARS-CoV-2,
109
359804
4260
ื›ืš,ื‘ืžืงืจื” ืฉื—ื•ืœื” ื ื’ื•ืข ื‘ SARS-CoV-2,
06:04
the mask will produce a fluorescent signal
110
364088
2073
ื”ืžืกื›ื” ืชื™ื™ืฆืจ ืื•ืช ืคืœื•ืื•ืจืกืฆื ื˜ื™
06:06
that could be detected by a simple, inexpensive handheld device.
111
366185
3830
ืฉื ื™ืชืŸ ื™ื”ื™ื” ืœื–ื”ื•ืช ื‘ืืžืฆืขื•ืช ืžื›ืฉื™ืจ ื™ื“ื ื™ ืœื ื™ืงืจ.
06:10
In one or two hours, a patient could thus be diagnosed
112
370534
4484
ืชื•ืš ืฉืขื” ืื• ืฉืขืชื™ื™ื, ื ื™ืชืŸ ื™ื”ื™ื” ืœืื‘ื—ืŸ ืžื˜ื•ืคืœ.
06:15
safely, remotely and accurately.
113
375042
2972
ื‘ื‘ื˜ื—ื”, ืžืจื—ื•ืง, ื•ื‘ืื•ืคืŸ ืžื“ื•ื™ืง.
06:18
We're also using synthetic biology
114
378735
2520
ืื ื• ืžืฉืชืžืฉื™ื ื’ื ื‘ื‘ื™ื•ืœื•ื’ื™ื” ืกื™ื ืชื˜ื™ืช
06:21
to design a candidate vaccine for COVID-19.
115
381279
2720
ื›ื“ื™ ืœืชื›ื ืŸ ื—ื™ืกื•ืŸ ืžื•ืขืžื“ ืœ-COVID-19.
06:25
We are repurposing the BCG vaccine,
116
385014
2653
ืื ื• ืžื™ืขื“ื™ื ืžื—ื“ืฉ ืืช ื—ื™ืกื•ืŸ ื” BCG,
06:27
which had been used against TB for almost a century.
117
387691
2870
ืฉืฉื™ืžืฉ ื ื’ื“ ืฉื—ืคืช ื‘ืžืฉืš ืžืื” ืฉื ื™ื ื‘ืงื™ืจื•ื‘.
06:30
It's a live attenuated vaccine,
118
390585
1541
ื–ื” ื—ื™ืกื•ืŸ ื—ื™ ืžื•ื—ืœืฉ
06:32
and we're engineering it to express SARS-CoV-2 antigens,
119
392150
4657
ื•ืื ื—ื ื• ืžื”ื ื“ืกื™ื ืื•ืชื• ืœื’ืœื•ืช ืื ื˜ื™ื’ื ื™ื ืฉืœ SARS-CoV-2,
06:36
which should trigger the production of protective antibodies
120
396831
2814
ืฉืืžื•ืจื™ื ืœื”ืคืขื™ืœ ื™ื™ืฆื•ืจ ืฉืœ ื ื•ื’ื“ื ื™ื ืžื’ื ื™ื
06:39
by the immune system.
121
399669
1635
ืขืœ ื™ื“ื™ ืžืขืจื›ืช ื”ื—ื™ืกื•ืŸ.
06:41
Importantly, BCG is massively scalable
122
401328
2734
ื—ืฉื•ื‘ ืœืฆื™ื™ืŸ, ืœ BCG ื™ืฉ ื™ื›ื•ืœืช ืžื“ืจื’ื™ืช ื’ื‘ื•ื”ื”
06:44
and has a safety profile that's among the best of any reported vaccine.
123
404086
4573
ื•ืคืจื•ืคื™ืœ ื”ื‘ื˜ื™ื—ื•ืช ืฉืœื• ื˜ื•ื‘ ื™ื•ืชืจ ืžื›ืœ ื—ื™ืกื•ืŸ ืžื“ื•ื•ื—.
06:49
With the tools of synthetic biology and artificial intelligence,
124
409881
5105
ืขื ื”ื›ืœื™ื ืฉืœ ื”ื‘ื™ื•ืœื•ื’ื™ื” ื”ืกื™ื ืชื˜ื™ืช ื•ื”ื‘ื™ื ื” ื”ืžืœืื›ื•ืชื™ืช,
06:55
we can win the fight against this novel coronavirus.
125
415010
3348
ืื ื—ื ื• ื™ื›ื•ืœื™ื ืœื ืฆื— ื‘ืžืื‘ืง ื ื’ื“ ื•ื™ืจื•ืก ื”ืงื•ืจื•ื ื” ื”ื–ื”
06:58
This work is in its very early stages, but the promise is real.
126
418844
3319
ืขื‘ื•ื“ื” ื–ื• ื ืžืฆืืช ื‘ืฉืœื‘ื™ื” ื”ืจืืฉื•ื ื™ื ืžืื•ื“, ืื‘ืœ ืกื™ื›ื•ื™ ื”ื”ืฆืœื—ื” ื”ื•ื ืืžื™ืชื™.
07:02
Science and technology can give us an important advantage
127
422798
3445
ืžื“ืข ื•ื˜ื›ื ื•ืœื•ื’ื™ื” ื™ื›ื•ืœื™ื ืœืชืช ืœื ื• ื™ืชืจื•ืŸ ื—ืฉื•ื‘
07:06
in the battle of human wits versus the genes of superbugs,
128
426267
3161
ื‘ืžืื‘ืง ืฉืœ ื”ืฉื›ืœ ื”ืื ื•ืฉื™ ื›ื ื’ื“ ื”ื’ื ื™ื ืฉืœ ื—ื™ื™ื“ืงื™ ื”ืขืœ,
07:09
a battle we can win.
129
429452
1747
ืงืจื‘ ืฉืื ื—ื ื• ื™ื›ื•ืœื™ื ืœื ืฆื—.
07:11
Thank you.
130
431990
1233
ืชื•ื“ื” ืจื‘ื”.
ืขืœ ืืชืจ ื–ื”

ืืชืจ ื–ื” ื™ืฆื™ื’ ื‘ืคื ื™ื›ื ืกืจื˜ื•ื ื™ YouTube ื”ืžื•ืขื™ืœื™ื ืœืœื™ืžื•ื“ ืื ื’ืœื™ืช. ืชื•ื›ืœื• ืœืจืื•ืช ืฉื™ืขื•ืจื™ ืื ื’ืœื™ืช ื”ืžื•ืขื‘ืจื™ื ืขืœ ื™ื“ื™ ืžื•ืจื™ื ืžื”ืฉื•ืจื” ื”ืจืืฉื•ื ื” ืžืจื—ื‘ื™ ื”ืขื•ืœื. ืœื—ืฅ ืคืขืžื™ื™ื ืขืœ ื”ื›ืชื•ื‘ื™ื•ืช ื‘ืื ื’ืœื™ืช ื”ืžื•ืฆื’ื•ืช ื‘ื›ืœ ื“ืฃ ื•ื™ื“ืื• ื›ื“ื™ ืœื”ืคืขื™ืœ ืืช ื”ืกืจื˜ื•ืŸ ืžืฉื. ื”ื›ืชื•ื‘ื™ื•ืช ื’ื•ืœืœื•ืช ื‘ืกื ื›ืจื•ืŸ ืขื ื”ืคืขืœืช ื”ื•ื•ื™ื“ืื•. ืื ื™ืฉ ืœืš ื”ืขืจื•ืช ืื• ื‘ืงืฉื•ืช, ืื ื ืฆื•ืจ ืื™ืชื ื• ืงืฉืจ ื‘ืืžืฆืขื•ืช ื˜ื•ืคืก ื™ืฆื™ืจืช ืงืฉืจ ื–ื”.

https://forms.gle/WvT1wiN1qDtmnspy7