1
00:00:15,316 --> 00:00:23,036
Speaker 1: Pushkin. If you took a COVID test recently, you probably

2
00:00:23,036 --> 00:00:26,076
Speaker 1: took it at home, and if you tested positive, you

3
00:00:26,156 --> 00:00:29,356
Speaker 1: probably didn't report the results to your local health department,

4
00:00:29,636 --> 00:00:32,756
Speaker 1: which you know fair enough, no judgment. But in the

5
00:00:32,756 --> 00:00:36,156
Speaker 1: big picture this does create a problem. How do we

6
00:00:36,276 --> 00:00:40,476
Speaker 1: keep track of COVID levels as public testing declines. How

7
00:00:40,476 --> 00:00:42,396
Speaker 1: do we look out for new variants? How do we

8
00:00:42,556 --> 00:00:47,276
Speaker 1: monitor new outbreaks? The answer, in a word, is poop.

9
00:00:52,316 --> 00:00:54,996
Speaker 1: I'm Jacob Goldstein and this is what's your problem. My

10
00:00:55,036 --> 00:00:58,956
Speaker 1: guest today is Mariana Matus, co founder and CEO of

11
00:00:59,076 --> 00:01:04,036
Speaker 1: biobot Analytics. The company analyzes sewage samples from hundreds of

12
00:01:04,076 --> 00:01:07,436
Speaker 1: water treatment plants across the US and Canada. They provide

13
00:01:07,436 --> 00:01:10,556
Speaker 1: an aggregate picture of the cod status of tens of

14
00:01:10,676 --> 00:01:14,956
Speaker 1: millions of people. Marianna's problem is this, how do you

15
00:01:15,036 --> 00:01:18,556
Speaker 1: move beyond COVID to turn raw sewage into data that

16
00:01:18,596 --> 00:01:24,076
Speaker 1: can help improve global public health. As it's become clear

17
00:01:24,076 --> 00:01:26,236
Speaker 1: that sampling sewage is one of the best ways to

18
00:01:26,276 --> 00:01:29,996
Speaker 1: track the COVID pandemic, the field of wastewater epidemiology has

19
00:01:30,076 --> 00:01:33,236
Speaker 1: become a big deal. But when Marianna discovered the field,

20
00:01:33,356 --> 00:01:36,956
Speaker 1: it wasn't particularly popular or flashy. It was years before

21
00:01:36,956 --> 00:01:39,796
Speaker 1: the pandemic when she was working on her PhD and

22
00:01:39,916 --> 00:01:45,596
Speaker 1: computational biology at MIT. But Marianna told me studying wastewater

23
00:01:45,716 --> 00:01:48,196
Speaker 1: seemed like a great fit for what she wanted to do.

24
00:01:48,596 --> 00:01:52,796
Speaker 1: When I came across this space of voicewatermology through through

25
00:01:52,796 --> 00:01:56,436
Speaker 1: my laboratory, it was perfect, I think for me as

26
00:01:56,556 --> 00:02:01,156
Speaker 1: a combination of cutting edge science but also like a

27
00:02:01,316 --> 00:02:06,716
Speaker 1: very big societal impact. When you imagined having a big

28
00:02:06,756 --> 00:02:11,436
Speaker 1: societal impact through your study of wastewater epidemiology, like what

29
00:02:11,556 --> 00:02:15,596
Speaker 1: did you imagine? What was like your big, big dream.

30
00:02:15,716 --> 00:02:18,796
Speaker 1: I grew up in Mexico City and in a you know,

31
00:02:18,836 --> 00:02:21,836
Speaker 1: in a very sort of like slummy part of Mexico City,

32
00:02:21,916 --> 00:02:25,076
Speaker 1: not on the nice part of Mexico City. So I

33
00:02:25,076 --> 00:02:33,556
Speaker 1: grew up basically with zero government resources, you know, in

34
00:02:33,636 --> 00:02:37,356
Speaker 1: areas that are ignored and that don't receive any sort

35
00:02:37,356 --> 00:02:41,476
Speaker 1: of like government resources. And I grew up thinking that

36
00:02:41,636 --> 00:02:45,196
Speaker 1: life was like that. And then my career took me

37
00:02:45,236 --> 00:02:49,196
Speaker 1: to study in great universities and places, you know, in

38
00:02:49,236 --> 00:02:52,676
Speaker 1: the Netherlands, in the UK, in Boston, and then I

39
00:02:52,716 --> 00:02:56,676
Speaker 1: just began to realize that it actually it's not like that.

40
00:02:56,796 --> 00:02:59,756
Speaker 1: Not every places like that, And to me, you know,

41
00:02:59,796 --> 00:03:01,836
Speaker 1: I think like the more that dug into it through

42
00:03:01,876 --> 00:03:05,796
Speaker 1: my peach D studies, like I realized that a big

43
00:03:05,836 --> 00:03:09,956
Speaker 1: part of the solution starts with collecting the data to

44
00:03:10,116 --> 00:03:14,356
Speaker 1: demonstrate those health disparities that you know, I know that

45
00:03:14,396 --> 00:03:16,316
Speaker 1: are out there and everybody sort of like knows that

46
00:03:16,356 --> 00:03:19,716
Speaker 1: are out there. But it's just hard to to really

47
00:03:19,796 --> 00:03:22,316
Speaker 1: take action when you just don't have it in your

48
00:03:22,316 --> 00:03:25,556
Speaker 1: face and not don't have a way to measure progress.

49
00:03:25,636 --> 00:03:28,516
Speaker 1: So what I would imagine is, how can we use

50
00:03:29,196 --> 00:03:32,516
Speaker 1: the data from the waste water to give everybody a

51
00:03:32,636 --> 00:03:37,916
Speaker 1: voice and to create maps of what's happening near real

52
00:03:37,996 --> 00:03:43,196
Speaker 1: time everywhere and to and to design action around that data.

53
00:03:43,316 --> 00:03:45,676
Speaker 1: How did you go from that initial kind of big

54
00:03:45,796 --> 00:03:49,276
Speaker 1: dream to starting a company? So when I came to MT,

55
00:03:49,756 --> 00:03:51,956
Speaker 1: it sort of like I had all these dreams in

56
00:03:51,996 --> 00:03:56,116
Speaker 1: my head about like, oh, imagine using science to you know,

57
00:03:56,436 --> 00:04:00,476
Speaker 1: just impact society. Wouldn't that be amazing? But I didn't

58
00:04:00,556 --> 00:04:03,316
Speaker 1: know what that meant in practice. And when I came

59
00:04:03,356 --> 00:04:09,476
Speaker 1: to MT, I discovered entrepreneurship. Entrepreneurship, h yes, I mean

60
00:04:09,556 --> 00:04:13,036
Speaker 1: just like the concept that anybody can be a founder

61
00:04:13,116 --> 00:04:16,196
Speaker 1: and start their own company, right, Like, just that concept,

62
00:04:16,756 --> 00:04:18,636
Speaker 1: I would believe it or not. I mean, I just

63
00:04:18,916 --> 00:04:21,236
Speaker 1: didn't know about that before I came to a m

64
00:04:21,236 --> 00:04:24,236
Speaker 1: I T. I always thought only people that already have

65
00:04:24,916 --> 00:04:28,996
Speaker 1: family money, or like you know that studied business for underground,

66
00:04:29,276 --> 00:04:31,996
Speaker 1: they are the ones who can start businesses. And just

67
00:04:32,116 --> 00:04:35,516
Speaker 1: that concept completely blew my mind. And I think it

68
00:04:35,556 --> 00:04:38,516
Speaker 1: was for me like the missing piece. I realized, Oh, wow, well,

69
00:04:39,356 --> 00:04:41,836
Speaker 1: then that's how I do it. That's how I create

70
00:04:41,916 --> 00:04:43,956
Speaker 1: a company based on science to go and solve a

71
00:04:43,956 --> 00:04:47,196
Speaker 1: big problem. One thing I heard you talking about and

72
00:04:47,276 --> 00:04:52,476
Speaker 1: another interview was when you were starting the company, people

73
00:04:52,596 --> 00:04:57,116
Speaker 1: seem to misunderstand and think that you should be starting

74
00:04:57,116 --> 00:04:59,516
Speaker 1: a nonprofit instead of a company. Is that right and

75
00:04:59,556 --> 00:05:03,196
Speaker 1: if so, can you tell me about that? Absolutely so.

76
00:05:04,076 --> 00:05:09,196
Speaker 1: The idea of selling to government, the idea of of

77
00:05:09,636 --> 00:05:14,956
Speaker 1: operating in the space of public health, and the idea

78
00:05:14,956 --> 00:05:19,516
Speaker 1: of having two women co founders out of MIT basically

79
00:05:19,556 --> 00:05:22,716
Speaker 1: two very technical women co founders. Kind of it was

80
00:05:22,756 --> 00:05:26,716
Speaker 1: a kind of a perfect trifecta for investors to think

81
00:05:26,716 --> 00:05:31,956
Speaker 1: about US as a nonprofit. You mentioned gender, You mentioned

82
00:05:31,996 --> 00:05:33,996
Speaker 1: the fact that that you and your co founder are

83
00:05:33,996 --> 00:05:36,196
Speaker 1: both women, and that that played into it. How did that?

84
00:05:36,796 --> 00:05:41,156
Speaker 1: How did that work? What was going on there? Yeah,

85
00:05:41,436 --> 00:05:44,316
Speaker 1: it seems that we you know, I had to be

86
00:05:44,436 --> 00:05:50,076
Speaker 1: very proactive about kind of explaining I'm doing this not

87
00:05:50,196 --> 00:05:54,796
Speaker 1: just to have public impact, not just to have a

88
00:05:54,876 --> 00:05:58,036
Speaker 1: social impact. I'm doing this because I'm also looking to

89
00:05:58,116 --> 00:06:02,356
Speaker 1: have a financial outcome. And I just found it funny

90
00:06:02,436 --> 00:06:05,156
Speaker 1: that I had to be saying like, hey, I want

91
00:06:05,196 --> 00:06:08,556
Speaker 1: to make money, like you know, I personally also want

92
00:06:08,596 --> 00:06:13,636
Speaker 1: to make any Why wouldn't I? Right, So, okay, so

93
00:06:13,636 --> 00:06:16,876
Speaker 1: so you found the company. So so let's jump to

94
00:06:17,356 --> 00:06:21,676
Speaker 1: say twenty nineteen, like beginning of twenty twenty. Now you

95
00:06:21,716 --> 00:06:23,916
Speaker 1: have this little company that's been up and running for

96
00:06:23,916 --> 00:06:27,156
Speaker 1: a couple of years. It's analyzing wastewater, but you have

97
00:06:27,196 --> 00:06:29,916
Speaker 1: no revenue. You have a staff of just like five people.

98
00:06:30,196 --> 00:06:32,596
Speaker 1: You built this little machine that goes into the sewer

99
00:06:32,676 --> 00:06:36,116
Speaker 1: to collect sewage, and you're working on one pilot project.

100
00:06:36,196 --> 00:06:39,396
Speaker 1: And that project isn't even a fur infectious disease. Right,

101
00:06:39,436 --> 00:06:42,476
Speaker 1: You're looking at opioids, You're you're sort of studying the

102
00:06:42,516 --> 00:06:47,116
Speaker 1: opioid epidemic. And yet this is this moment when history

103
00:06:47,236 --> 00:06:50,716
Speaker 1: is like barreling towards you. Right, this pandemic is about

104
00:06:50,756 --> 00:06:54,156
Speaker 1: to you know, change everything, right, And so I'm curious

105
00:06:54,596 --> 00:06:56,956
Speaker 1: when did you start to hear about, you know, about

106
00:06:56,996 --> 00:07:00,756
Speaker 1: this new coronavirus outbreak. Yeah, I think for us, UM

107
00:07:00,996 --> 00:07:05,836
Speaker 1: it really began to catch our attention in like early

108
00:07:06,036 --> 00:07:10,076
Speaker 1: twenty twenty, like January twenty twenty. Do you remember any

109
00:07:10,156 --> 00:07:14,516
Speaker 1: particular moments, any particular conversations or reading anything or talking

110
00:07:14,516 --> 00:07:19,596
Speaker 1: to anybody. I mean definitely, so some of those like

111
00:07:19,716 --> 00:07:23,916
Speaker 1: first conversations that happened where we had been forming a

112
00:07:23,956 --> 00:07:29,556
Speaker 1: relationship with folks within HHS, like the federal HHS Department

113
00:07:29,556 --> 00:07:31,596
Speaker 1: of Health and Human Services, the big federal Apartment of

114
00:07:31,636 --> 00:07:35,996
Speaker 1: Health and Human Services in DC. So I remember we

115
00:07:35,996 --> 00:07:40,396
Speaker 1: were in DC in February of twenty twenty, basically like

116
00:07:40,436 --> 00:07:43,236
Speaker 1: already pitching that we should begin to test the waste

117
00:07:43,236 --> 00:07:46,556
Speaker 1: water of all of the major airports across the country

118
00:07:46,596 --> 00:07:50,116
Speaker 1: to start getting a sense of the level of import

119
00:07:50,996 --> 00:07:54,676
Speaker 1: And we were told, well, this outbreak is going to

120
00:07:54,756 --> 00:07:58,116
Speaker 1: be contained within two weeks, so it would be a

121
00:07:58,156 --> 00:08:01,436
Speaker 1: waste of your resources to try to develop a solution

122
00:08:01,476 --> 00:08:03,836
Speaker 1: around this now because you're not going to be ready

123
00:08:03,836 --> 00:08:05,516
Speaker 1: in less than two weeks. They were like, by the

124
00:08:05,516 --> 00:08:07,196
Speaker 1: time you figure out how to do this test in

125
00:08:07,196 --> 00:08:09,036
Speaker 1: a few weeks, this all things going to have blown over.

126
00:08:09,396 --> 00:08:12,996
Speaker 1: It's not going exactly so. But despite that sort of

127
00:08:13,036 --> 00:08:17,876
Speaker 1: like very strong feedback, we came back from DC and

128
00:08:17,916 --> 00:08:20,636
Speaker 1: we this was February of twenty twenty, and we make

129
00:08:20,716 --> 00:08:23,196
Speaker 1: the decision that we were going to build a COVID

130
00:08:23,636 --> 00:08:26,876
Speaker 1: solution based on the waste water and tell me about

131
00:08:26,876 --> 00:08:30,756
Speaker 1: building that. We had to basically change everything. We had

132
00:08:30,836 --> 00:08:35,316
Speaker 1: to throw away sort of like all of the progress

133
00:08:35,356 --> 00:08:38,236
Speaker 1: that we had made up until that point to start

134
00:08:38,316 --> 00:08:43,436
Speaker 1: over given the constraints at hand. Number one, this was

135
00:08:43,676 --> 00:08:47,676
Speaker 1: there was a sense of emergency and that time was

136
00:08:47,716 --> 00:08:53,356
Speaker 1: of the essence. So the idea of having to manufacture

137
00:08:53,436 --> 00:08:59,196
Speaker 1: hardware in order to collect data at scale just seemed

138
00:08:59,236 --> 00:09:01,916
Speaker 1: pretty hard or impossible in that moment. Also, do you

139
00:09:01,996 --> 00:09:04,156
Speaker 1: know the supply chain issues all of You're not going

140
00:09:04,156 --> 00:09:05,956
Speaker 1: to be able to make this special device. You're not

141
00:09:05,996 --> 00:09:07,796
Speaker 1: gonna be only like a thousand of them in a

142
00:09:07,836 --> 00:09:11,476
Speaker 1: couple of months or whatever, exactly exactly, So we decided, okay,

143
00:09:11,636 --> 00:09:16,556
Speaker 1: where how else can we get wastewater easily? And we realize, oh,

144
00:09:16,596 --> 00:09:22,396
Speaker 1: actually actually, there are sixteen thousand wastewater treatment plants in

145
00:09:22,436 --> 00:09:26,316
Speaker 1: the US, covering eighty percent of the US population, and

146
00:09:26,956 --> 00:09:30,476
Speaker 1: turns out most of them already have a similar type

147
00:09:30,476 --> 00:09:34,316
Speaker 1: of equipment. So it's not portable, it's not as sophisticated,

148
00:09:35,036 --> 00:09:38,516
Speaker 1: but it does the job at collecting that continues twenty

149
00:09:38,556 --> 00:09:42,676
Speaker 1: four hour sample. The minimum viable product already exists at

150
00:09:42,756 --> 00:09:45,876
Speaker 1: sixteen thousand wastewater plants all across the US, so we

151
00:09:45,876 --> 00:09:50,876
Speaker 1: were like, okay, check. Second was the lab component. We

152
00:09:50,956 --> 00:09:55,556
Speaker 1: had been building a chemistry platform, and obviously and COVID

153
00:09:55,836 --> 00:10:00,876
Speaker 1: is caused by an RNA virus, so the detection or

154
00:10:00,916 --> 00:10:02,996
Speaker 1: detest in the lab would need to be more of

155
00:10:03,036 --> 00:10:06,156
Speaker 1: a molecular biology type of approach. We didn't have any

156
00:10:06,196 --> 00:10:12,756
Speaker 1: of those capabilities, but we had raised seat round, like

157
00:10:12,796 --> 00:10:15,756
Speaker 1: a you know, a four point two million dollars seat round,

158
00:10:16,276 --> 00:10:19,636
Speaker 1: and so we had some money to just start getting

159
00:10:19,676 --> 00:10:23,636
Speaker 1: some basic new equipment in the lab. And also we

160
00:10:23,676 --> 00:10:28,036
Speaker 1: have a good relationship with my PhD advisor at MT

161
00:10:28,876 --> 00:10:32,876
Speaker 1: so together with him, we actually used a lot of

162
00:10:33,116 --> 00:10:36,436
Speaker 1: his lab early on in the pandemic and collaborated with

163
00:10:36,556 --> 00:10:39,836
Speaker 1: his students. So you know, that's how we got started,

164
00:10:39,916 --> 00:10:45,916
Speaker 1: and it took us like four weeks to just go

165
00:10:46,116 --> 00:10:50,676
Speaker 1: from the decision point until having actually not just a

166
00:10:50,796 --> 00:10:56,756
Speaker 1: proof that the test works with waste water, but also

167
00:10:57,196 --> 00:11:02,436
Speaker 1: we wrote a scientific preprint, like a you know, a paper.

168
00:11:02,756 --> 00:11:04,796
Speaker 1: So we were the first ones in the country to

169
00:11:05,236 --> 00:11:10,636
Speaker 1: demonstrate that you can detect and quantify the virus causing

170
00:11:10,636 --> 00:11:14,716
Speaker 1: COVID nineteen in wastewater samples and that it works well.

171
00:11:15,956 --> 00:11:18,116
Speaker 1: And I think, you know, it was just from there

172
00:11:18,156 --> 00:11:21,676
Speaker 1: that everything exploded. I mean, is there fear I assume

173
00:11:21,756 --> 00:11:25,756
Speaker 1: that that there's no risk of transmitting the disease. I mean,

174
00:11:25,756 --> 00:11:30,276
Speaker 1: it's obviously not transmitted through wastewater, but we're people afraid

175
00:11:30,316 --> 00:11:32,436
Speaker 1: that it might be. We didn't know anything about COVID

176
00:11:32,476 --> 00:11:33,796
Speaker 1: at the time. I mean, this is when I was

177
00:11:33,796 --> 00:11:37,076
Speaker 1: still wiping off all my groceries with bleach, right, because

178
00:11:37,236 --> 00:11:40,516
Speaker 1: literally we didn't know. Oh yes, there was a lot

179
00:11:40,556 --> 00:11:43,516
Speaker 1: of concern. And actually that was you know, thank you

180
00:11:43,596 --> 00:11:46,636
Speaker 1: for I feel like my brain probably like tried to

181
00:11:46,676 --> 00:11:50,196
Speaker 1: forget that, but that was a very big deal. Like

182
00:11:50,236 --> 00:11:54,196
Speaker 1: when we just started from for many reasons, nobody knew

183
00:11:54,956 --> 00:11:58,796
Speaker 1: if the virus present in wastewater would be infectious. My

184
00:11:59,076 --> 00:12:02,796
Speaker 1: very small team that we had. They were really afraid

185
00:12:03,116 --> 00:12:06,636
Speaker 1: to have to handle the wastewater sample without knowing if

186
00:12:06,676 --> 00:12:10,036
Speaker 1: they can get infected. So we came up with a

187
00:12:10,076 --> 00:12:15,676
Speaker 1: solution for our lab where every every bottle of wastewater,

188
00:12:15,676 --> 00:12:19,756
Speaker 1: example that arrives to buy a boat is first pasteurized

189
00:12:20,756 --> 00:12:25,996
Speaker 1: in order to basically make it non infectious or like sterile. Yes.

190
00:12:26,116 --> 00:12:28,876
Speaker 1: And the third thing was that I had just I

191
00:12:28,916 --> 00:12:32,356
Speaker 1: was just pregnant at the time. I became pregnant in

192
00:12:32,396 --> 00:12:36,516
Speaker 1: March of twenty twenty, my first pregnancy, my first you

193
00:12:36,556 --> 00:12:40,836
Speaker 1: know baby, and I my husband and I also would

194
00:12:40,876 --> 00:12:43,916
Speaker 1: go into the lab to model to the rest of

195
00:12:43,956 --> 00:12:47,676
Speaker 1: our team that you know this is safe, Like you know,

196
00:12:47,796 --> 00:12:53,156
Speaker 1: I'm pregnant, but I trust that the pasteurization is good

197
00:12:53,276 --> 00:12:56,476
Speaker 1: enough to make this work safe and let me, you know,

198
00:12:56,596 --> 00:12:59,556
Speaker 1: let me demonstrate that with my actions. At the time,

199
00:12:59,676 --> 00:13:02,796
Speaker 1: it was a very big deal. So you have this idea,

200
00:13:03,236 --> 00:13:06,356
Speaker 1: you have the proof that it works, You've convinced the

201
00:13:06,396 --> 00:13:08,796
Speaker 1: staff at your company, at Bio Boat, that it's okay

202
00:13:08,836 --> 00:13:11,996
Speaker 1: to do this. How do you get customers what happens next?

203
00:13:12,316 --> 00:13:15,036
Speaker 1: So we designed a probono campaign where by About would

204
00:13:15,036 --> 00:13:20,716
Speaker 1: absorb the cost of all of the testing for two months,

205
00:13:21,036 --> 00:13:24,636
Speaker 1: and what happened it was beyond our wildest dreams, Like

206
00:13:25,316 --> 00:13:30,516
Speaker 1: it exploded. It got picked up by the media. People

207
00:13:30,836 --> 00:13:38,236
Speaker 1: loft this idea that you can fight COVID with poop. Poop. Yeah,

208
00:13:38,236 --> 00:13:40,716
Speaker 1: you can fight COVID with poop. You know. That was

209
00:13:40,796 --> 00:13:43,196
Speaker 1: that was basically the message being put out there. It

210
00:13:43,276 --> 00:13:48,716
Speaker 1: went viral and we got in just the first ten

211
00:13:48,836 --> 00:13:52,596
Speaker 1: days or so of announcing the campaign, we got four

212
00:13:52,756 --> 00:13:58,396
Speaker 1: hundred plants nationwide wanting to enroll in the program. We

213
00:13:58,436 --> 00:14:03,116
Speaker 1: had aspired to enroll up to one hundred, So it

214
00:14:03,196 --> 00:14:07,036
Speaker 1: was it was crazy. The response was just crazy. But

215
00:14:07,196 --> 00:14:09,836
Speaker 1: you know, that transition was tough because I guess also

216
00:14:09,876 --> 00:14:13,236
Speaker 1: something that I haven't talked about is that in that

217
00:14:13,356 --> 00:14:17,116
Speaker 1: early twenty twenty stage, when we were the first ones,

218
00:14:17,716 --> 00:14:23,996
Speaker 1: the more established academics were skeptical and basically like recommending

219
00:14:24,956 --> 00:14:28,676
Speaker 1: caution with these and slowing things down for us. And

220
00:14:29,116 --> 00:14:32,756
Speaker 1: so it was a very Were they skeptical of wastewater

221
00:14:32,876 --> 00:14:37,356
Speaker 1: sampling in general or were they skeptical of your company?

222
00:14:37,876 --> 00:14:44,836
Speaker 1: Or was it both both both? So, up until twenty twenty,

223
00:14:45,516 --> 00:14:51,796
Speaker 1: the wastewater epidemiology was a very niche and obscure area

224
00:14:51,836 --> 00:14:55,796
Speaker 1: of science, So the entire field was a little bit like,

225
00:14:56,636 --> 00:15:01,156
Speaker 1: you know, not very well known obviously. And if that

226
00:15:01,356 --> 00:15:04,956
Speaker 1: was within science, just imagine within government, you know, like

227
00:15:04,956 --> 00:15:07,956
Speaker 1: it was just nobody was saying, oh, I need wastewater data,

228
00:15:08,036 --> 00:15:10,796
Speaker 1: like who can provide it for me? Why do you

229
00:15:10,836 --> 00:15:12,916
Speaker 1: think that is? I mean, do you think it's partly

230
00:15:12,956 --> 00:15:16,396
Speaker 1: like because it's poop, because it's sewage? Like why do

231
00:15:16,436 --> 00:15:19,836
Speaker 1: you think people were ignoring this source of data? Really?

232
00:15:20,036 --> 00:15:22,956
Speaker 1: I mean, is it because it's it's poop and people

233
00:15:22,956 --> 00:15:24,756
Speaker 1: are kind of embarrassed by it don't like to talk

234
00:15:24,796 --> 00:15:28,156
Speaker 1: about it? Like has that been a barrier too? I

235
00:15:28,196 --> 00:15:31,036
Speaker 1: mean I think that No. I think that actually people

236
00:15:31,196 --> 00:15:35,436
Speaker 1: love all of the poop jokes and poop humor. I

237
00:15:35,476 --> 00:15:38,276
Speaker 1: feel like that actually tends to be like a plus.

238
00:15:38,276 --> 00:15:40,836
Speaker 1: How do you feel about them at this point? Like

239
00:15:40,916 --> 00:15:43,156
Speaker 1: are you tired of them? Do they work in your favor?

240
00:15:43,596 --> 00:15:45,556
Speaker 1: Like our poop jokes like enough, I never want to

241
00:15:45,556 --> 00:15:47,796
Speaker 1: hear a poop joke again? No, no, no, I love it.

242
00:15:47,836 --> 00:15:50,636
Speaker 1: I love it. And our company culture, you know, celebrates

243
00:15:50,676 --> 00:15:55,276
Speaker 1: the poop humor quite a lot with okay, our you know,

244
00:15:55,396 --> 00:15:59,236
Speaker 1: branding and suave and you know, we we love it.

245
00:15:59,396 --> 00:16:01,716
Speaker 1: We love the users of the poop emoji or they're

246
00:16:01,756 --> 00:16:05,276
Speaker 1: like particularly very big. Oh yeah, the poop emoji is

247
00:16:05,276 --> 00:16:09,556
Speaker 1: the most use emoji in the bay about slack, it

248
00:16:09,676 --> 00:16:12,116
Speaker 1: makes sense. I mean, it's why they're used even at

249
00:16:12,156 --> 00:16:15,836
Speaker 1: places that have nothing to do with it. Right, So yes, no,

250
00:16:15,956 --> 00:16:17,876
Speaker 1: I think that, you know, I think that the barrier

251
00:16:18,796 --> 00:16:22,516
Speaker 1: to research and to you know, first to research and

252
00:16:22,556 --> 00:16:26,556
Speaker 1: then to the adoption of the data is just that

253
00:16:26,636 --> 00:16:30,156
Speaker 1: the bar to get the data in is very high

254
00:16:30,236 --> 00:16:33,516
Speaker 1: in the sense that there's a lot of operational and

255
00:16:33,676 --> 00:16:38,836
Speaker 1: logistical work in order to get data. So when you

256
00:16:38,876 --> 00:16:43,116
Speaker 1: are working within a university or within a government agency,

257
00:16:43,796 --> 00:16:47,396
Speaker 1: who really has the time to be you know, building

258
00:16:47,676 --> 00:16:51,556
Speaker 1: kits to transport wastewater, learning how to the regulations to

259
00:16:51,636 --> 00:16:56,516
Speaker 1: transport it going out there, or finding the relationships to

260
00:16:56,556 --> 00:16:59,316
Speaker 1: send you the waste water in doing all of that

261
00:16:59,476 --> 00:17:03,316
Speaker 1: groundwork in the lab, right groundwork. Right, It's very logistical.

262
00:17:03,556 --> 00:17:06,716
Speaker 1: It's not like high minded, it's not fancy math. It's

263
00:17:06,796 --> 00:17:11,236
Speaker 1: just getting appealed to the lab. Yeah, exactly, exactly. So

264
00:17:11,316 --> 00:17:13,356
Speaker 1: when I was a PITCHD student that in my t

265
00:17:14,796 --> 00:17:19,756
Speaker 1: I was basically like the only one like willing to

266
00:17:19,796 --> 00:17:23,876
Speaker 1: do the groundwork because I started working on always what

267
00:17:24,076 --> 00:17:27,476
Speaker 1: epidemiology during my PhD. That's what my pitchd PSIS was about.

268
00:17:28,476 --> 00:17:32,876
Speaker 1: But you know, I really struggled with just like recruiting

269
00:17:32,916 --> 00:17:37,276
Speaker 1: a team around me, because folks were wanting to help

270
00:17:37,316 --> 00:17:41,516
Speaker 1: with the data analysis, the data visualization, but not the

271
00:17:41,596 --> 00:17:44,996
Speaker 1: eighty percent groundwork that goes behind it. So nobody wants

272
00:17:45,556 --> 00:17:49,556
Speaker 1: get the proof exactly. So that's why I thought, always thought,

273
00:17:49,596 --> 00:17:57,316
Speaker 1: you know, if this science is going to really go mainstream,

274
00:17:57,436 --> 00:18:02,036
Speaker 1: it needs an organization dedicated like one to it so

275
00:18:02,036 --> 00:18:05,356
Speaker 1: that we can do that around work and then the scientists. Yes,

276
00:18:05,516 --> 00:18:08,316
Speaker 1: of course, the power is in the data, in the

277
00:18:08,356 --> 00:18:10,396
Speaker 1: insights that you can get out of it, but you

278
00:18:10,436 --> 00:18:12,876
Speaker 1: know there's an eighty percent around work behind it. Well,

279
00:18:12,916 --> 00:18:14,796
Speaker 1: I mean maybe that's part of the case for a

280
00:18:14,796 --> 00:18:18,756
Speaker 1: for profit company, right Like profit is a very good

281
00:18:18,796 --> 00:18:23,996
Speaker 1: incentive to do groundwork, absolutely absolutely Well. How big is

282
00:18:24,036 --> 00:18:28,876
Speaker 1: the company now? Oh yeah, buy about now has one

283
00:18:28,956 --> 00:18:31,756
Speaker 1: hundred employees. How much revenue do you have? More or less?

284
00:18:32,396 --> 00:18:37,956
Speaker 1: This year? We are on track to make over twenty

285
00:18:37,956 --> 00:18:41,956
Speaker 1: million dollars in revenue, okay, which is great also to

286
00:18:42,036 --> 00:18:44,516
Speaker 1: be here given that two years ago we were basically

287
00:18:44,596 --> 00:18:47,796
Speaker 1: pre revenue. So yes, two years ago was zero. From

288
00:18:47,876 --> 00:18:53,756
Speaker 1: zero to twenty million, there's a lot. Are you profitable, No,

289
00:18:53,996 --> 00:18:57,996
Speaker 1: not yet. I mean we are investing heavily in our

290
00:18:58,156 --> 00:19:00,476
Speaker 1: R and D so that we can look at other

291
00:19:00,516 --> 00:19:06,676
Speaker 1: types of data. So story so far. Three years ago,

292
00:19:07,156 --> 00:19:10,156
Speaker 1: Mariana barely had a company, and waste water surveillance was

293
00:19:10,196 --> 00:19:14,076
Speaker 1: this little niche thing in the US. And then by

294
00:19:14,116 --> 00:19:16,956
Speaker 1: the beginning of this year, when the omicron wave hit

295
00:19:16,996 --> 00:19:21,276
Speaker 1: the country, BAA was this big, real company. Wastewater surveillance

296
00:19:21,356 --> 00:19:24,156
Speaker 1: was one of the most important tools public health officials

297
00:19:24,236 --> 00:19:27,116
Speaker 1: used to figure out where cases were spiking, so that

298
00:19:27,156 --> 00:19:29,956
Speaker 1: they could direct resources into the right neighborhoods and you know,

299
00:19:30,276 --> 00:19:33,956
Speaker 1: plan for surges and hospital admissions. And the story is

300
00:19:33,996 --> 00:19:37,396
Speaker 1: not over in a minute. What we still don't know

301
00:19:37,596 --> 00:19:48,356
Speaker 1: about poop and disease. It's a lot. Now back to

302
00:19:48,396 --> 00:19:52,396
Speaker 1: the show. And one thing I'm curious about, Well, what

303
00:19:52,596 --> 00:19:55,036
Speaker 1: is your company's moat? Right? Like, how is what you

304
00:19:55,156 --> 00:19:57,956
Speaker 1: do not just some commodity thing that anybody with the

305
00:19:58,036 --> 00:20:04,236
Speaker 1: lab can do. Yeah, I think that that's a great question. Everybody, anybody,

306
00:20:04,276 --> 00:20:09,036
Speaker 1: anybody out there could go and let's say open amunthole

307
00:20:10,516 --> 00:20:14,796
Speaker 1: and get a bucket in pull up wastewater, take it

308
00:20:14,796 --> 00:20:18,196
Speaker 1: to a lab and they would get a number, a

309
00:20:18,356 --> 00:20:20,996
Speaker 1: number meaning like an amount of COVID that's in there

310
00:20:21,076 --> 00:20:23,716
Speaker 1: or something. You may get an amount of COVID, you make,

311
00:20:23,916 --> 00:20:27,236
Speaker 1: an amount of opioids, an amount of influenza, right like

312
00:20:27,596 --> 00:20:30,836
Speaker 1: any any number. You may get a number, But what

313
00:20:30,876 --> 00:20:36,516
Speaker 1: does that number mean? Like that number in isolation really

314
00:20:36,556 --> 00:20:42,196
Speaker 1: doesn't mean anything. So our secret sauce is how do

315
00:20:42,276 --> 00:20:48,716
Speaker 1: we create how do we make wastewater a data platform?

316
00:20:48,756 --> 00:20:53,996
Speaker 1: And that really means it's a systems level type of

317
00:20:54,036 --> 00:20:58,396
Speaker 1: design and product. We actually need to use the same

318
00:20:58,436 --> 00:21:03,996
Speaker 1: method in every sample. If we want to calculate, if

319
00:21:03,996 --> 00:21:07,436
Speaker 1: we want to compare across time, if we want to

320
00:21:07,476 --> 00:21:13,716
Speaker 1: compare across locations, we want to build a state statewide trend,

321
00:21:13,756 --> 00:21:16,156
Speaker 1: if we want to compare regions, if we want to

322
00:21:16,236 --> 00:21:21,036
Speaker 1: calculate a national average, it's imperative to actually use the

323
00:21:21,156 --> 00:21:26,716
Speaker 1: same methods at every stage for every sample. Otherwise you

324
00:21:26,756 --> 00:21:30,436
Speaker 1: don't have that comparability wastewater. Again, the power of the

325
00:21:30,476 --> 00:21:34,356
Speaker 1: wastewater isn't about what you about the number that you

326
00:21:34,396 --> 00:21:38,636
Speaker 1: get from a single wastewater sample. The power of wastewater

327
00:21:38,756 --> 00:21:43,076
Speaker 1: is about having that bird's eye view, that systems level

328
00:21:43,156 --> 00:21:46,196
Speaker 1: view of what's happening in an entire country, in an

329
00:21:46,316 --> 00:21:50,956
Speaker 1: entire state. You can drill in more geographically narrow, but

330
00:21:51,036 --> 00:21:54,316
Speaker 1: you can also zoom out. That's the platform, that's the

331
00:21:54,356 --> 00:21:57,596
Speaker 1: power that we're building. So in order to accomplish that,

332
00:21:58,316 --> 00:22:01,876
Speaker 1: you know, that's where we come in, all of the relationships,

333
00:22:01,956 --> 00:22:07,596
Speaker 1: all of the scale that eight you know, groundwork that

334
00:22:07,636 --> 00:22:12,316
Speaker 1: I talked about. To accomplish that level of visibility, that's

335
00:22:12,316 --> 00:22:14,836
Speaker 1: a tough problem. So it's like a network effect. There's

336
00:22:14,836 --> 00:22:17,556
Speaker 1: a network effect thing people would want to use your

337
00:22:17,596 --> 00:22:20,756
Speaker 1: company because you have the most data and therefore you

338
00:22:20,916 --> 00:22:24,796
Speaker 1: have the best understanding of what one particular sample means

339
00:22:24,836 --> 00:22:26,516
Speaker 1: because you can put it in the context of all

340
00:22:26,516 --> 00:22:30,876
Speaker 1: the other data that you have gotten, have processed exactly exactly.

341
00:22:30,996 --> 00:22:35,516
Speaker 1: So we have the largest network of sites in the world.

342
00:22:36,796 --> 00:22:40,716
Speaker 1: It's mostly US, some Canada. How big is it now?

343
00:22:41,596 --> 00:22:45,516
Speaker 1: We have over five hundred sites. What's something you haven't

344
00:22:45,516 --> 00:22:48,236
Speaker 1: figured out yet? What's a problem your story of still

345
00:22:48,276 --> 00:22:50,156
Speaker 1: trying to figure out how to solve Maybe you've tried

346
00:22:50,196 --> 00:22:52,556
Speaker 1: it hasn't quite worked yet. What's something you're still working

347
00:22:52,596 --> 00:22:56,676
Speaker 1: on in the lab. There is a lot of interest

348
00:22:56,756 --> 00:23:01,196
Speaker 1: in looking at different targets, so not just COVID, but

349
00:23:01,276 --> 00:23:06,876
Speaker 1: also influenza, neural virus. You can you know, at least

350
00:23:06,956 --> 00:23:10,556
Speaker 1: keeps going right like monkey box where right now in

351
00:23:10,636 --> 00:23:13,396
Speaker 1: advanced R and D for monkey pops, we're gonna have

352
00:23:13,396 --> 00:23:16,036
Speaker 1: a start testing with water for monkey pops too. But

353
00:23:16,956 --> 00:23:20,356
Speaker 1: it remains a challenge to know kind of how to

354
00:23:21,236 --> 00:23:23,516
Speaker 1: which types of data we can collect and how to

355
00:23:23,556 --> 00:23:29,996
Speaker 1: interpret them because we don't really know which pathogens are

356
00:23:30,676 --> 00:23:36,276
Speaker 1: shed in poop. Huh, that's surprising. I would think people

357
00:23:36,316 --> 00:23:38,076
Speaker 1: would just sort of have figured that out by now.

358
00:23:38,196 --> 00:23:39,556
Speaker 1: Is that Does that go back to the fact that

359
00:23:39,636 --> 00:23:44,716
Speaker 1: it's kind of an understudied area exactly exactly. There's a

360
00:23:44,756 --> 00:23:48,316
Speaker 1: lot of information about how you can diagnose a disease

361
00:23:48,556 --> 00:23:52,996
Speaker 1: in a person via like a serom sample, via maybe

362
00:23:53,036 --> 00:23:57,116
Speaker 1: a blood test, yeah, a blood test, or maybe a

363
00:23:57,716 --> 00:24:00,556
Speaker 1: you know, a swab or like a you know, a

364
00:24:00,596 --> 00:24:05,036
Speaker 1: nasal swab or a saliva suab sometimes in in p

365
00:24:05,796 --> 00:24:09,596
Speaker 1: But but pooh, I mean, why would they have to

366
00:24:09,676 --> 00:24:12,796
Speaker 1: I mean, the clinic the worst way to get us

367
00:24:12,836 --> 00:24:15,436
Speaker 1: to a sample for the doctor, right exactly, So so

368
00:24:15,476 --> 00:24:18,316
Speaker 1: for the doctor like you know, again, poop is an

369
00:24:18,396 --> 00:24:23,196
Speaker 1: understudied like sort of like diagnostic matrix. So you know,

370
00:24:23,276 --> 00:24:26,476
Speaker 1: one wild dream of mine is for us to develop

371
00:24:27,076 --> 00:24:31,156
Speaker 1: the clinical collaborations to to be able to know in

372
00:24:31,276 --> 00:24:36,236
Speaker 1: people like how different diseases are um shedding in poop,

373
00:24:36,356 --> 00:24:39,676
Speaker 1: because that that will help us to understand which targets

374
00:24:39,676 --> 00:24:44,036
Speaker 1: will be easier to track via the waste water and

375
00:24:44,156 --> 00:24:47,916
Speaker 1: how to interpret it. You mentioned sort of starting out

376
00:24:47,956 --> 00:24:52,196
Speaker 1: in the field with this the dream of being able

377
00:24:52,276 --> 00:24:56,956
Speaker 1: to to look at a city like Mexico City and

378
00:24:57,036 --> 00:24:58,916
Speaker 1: get you know, sort of a map of what's going

379
00:24:58,956 --> 00:25:02,076
Speaker 1: on with the health of people in the city. How

380
00:25:02,076 --> 00:25:03,796
Speaker 1: do you get to there from where you are now?

381
00:25:04,276 --> 00:25:08,356
Speaker 1: Because we have done some pilots in Mexico Ecuador Ry

382
00:25:09,476 --> 00:25:12,756
Speaker 1: in partnership already with a World Bank, so you know,

383
00:25:12,916 --> 00:25:14,796
Speaker 1: it's kind of how do we build on top of

384
00:25:14,836 --> 00:25:18,636
Speaker 1: those early pilots that were very successful. So you sample,

385
00:25:18,916 --> 00:25:22,916
Speaker 1: you know, big sewage systems in the US that allows

386
00:25:22,916 --> 00:25:26,236
Speaker 1: you to capture something like eighty percent of the population,

387
00:25:26,716 --> 00:25:29,516
Speaker 1: but it seems like in large parts of the developing

388
00:25:29,556 --> 00:25:32,636
Speaker 1: world you have places you know, that are less developed,

389
00:25:32,676 --> 00:25:35,116
Speaker 1: where where there are not sewage systems. What do you

390
00:25:35,156 --> 00:25:39,356
Speaker 1: do there. There's many areas that don't have any sort

391
00:25:39,356 --> 00:25:44,356
Speaker 1: of sanitation, right, so I think that for those areas

392
00:25:45,076 --> 00:25:48,956
Speaker 1: there's just immediate action, which is we can use basically

393
00:25:49,036 --> 00:25:54,156
Speaker 1: the same type of sampling approaches to open sewers, like

394
00:25:54,196 --> 00:25:58,036
Speaker 1: basically which are rivers where the waste makes it into

395
00:25:58,076 --> 00:26:01,276
Speaker 1: the river, and that that is possible, that that works,

396
00:26:01,316 --> 00:26:04,156
Speaker 1: that's how some people already do waste. What are epithimolity

397
00:26:04,156 --> 00:26:07,756
Speaker 1: You work in areas without the infrastructure. But I think

398
00:26:07,756 --> 00:26:13,516
Speaker 1: you're right at over time this technology could be a

399
00:26:13,596 --> 00:26:17,156
Speaker 1: new reason to invest in waste, what in building the

400
00:26:17,196 --> 00:26:21,436
Speaker 1: waste water infrastructure where it doesn't exist, because now we're

401
00:26:21,476 --> 00:26:26,076
Speaker 1: giving it a second second use, a second mission. This

402
00:26:26,156 --> 00:26:29,796
Speaker 1: is no longer just about the collection and safe disposal

403
00:26:29,876 --> 00:26:33,836
Speaker 1: of waste from people. This is about intelligence that you

404
00:26:33,876 --> 00:26:38,316
Speaker 1: cannot really get any in any other way. So hopefully

405
00:26:38,316 --> 00:26:42,556
Speaker 1: it can be a virtual cycle where it can foster

406
00:26:43,396 --> 00:26:47,836
Speaker 1: the investment in the building of this infrastructure, which would

407
00:26:47,836 --> 00:26:52,516
Speaker 1: only of course also improve public health because then would

408
00:26:52,516 --> 00:26:59,396
Speaker 1: reduce the spread of disease. In a minute, the lightning

409
00:26:59,436 --> 00:27:04,076
Speaker 1: round with questions about immigration, entrepreneurship, and what not to

410
00:27:04,196 --> 00:27:15,196
Speaker 1: flush down the toilet now back to the show. Let's

411
00:27:15,236 --> 00:27:18,036
Speaker 1: just do let's do like a lightning round. I'm just

412
00:27:18,076 --> 00:27:19,996
Speaker 1: gonna ask you a bunch of fast questions and you

413
00:27:20,036 --> 00:27:24,116
Speaker 1: can answer them fast. Why do you think immigrants are

414
00:27:24,156 --> 00:27:30,156
Speaker 1: more likely than native born citizens to become entrepreneurs? That's

415
00:27:30,156 --> 00:27:32,316
Speaker 1: a good question, so I I mean, I can only

416
00:27:32,356 --> 00:27:35,956
Speaker 1: speak about my kind of experience, but at least in

417
00:27:35,956 --> 00:27:39,636
Speaker 1: my case, I felt that a little bit like I

418
00:27:39,676 --> 00:27:44,316
Speaker 1: had nothing to lose, So why not try? Like, why

419
00:27:44,316 --> 00:27:48,436
Speaker 1: wouldn't I try? What's one thing people should never ever

420
00:27:48,596 --> 00:27:59,836
Speaker 1: flush down the toilet? Well, that's a great question. Never

421
00:27:59,996 --> 00:28:06,596
Speaker 1: flushed down the so called flushable wipes okay, not actually

422
00:28:06,836 --> 00:28:13,556
Speaker 1: flushable at do not actually flushable. They don't dissolve in water,

423
00:28:14,356 --> 00:28:18,876
Speaker 1: So what happens is that they create this massive the

424
00:28:19,116 --> 00:28:23,276
Speaker 1: glock systems everywhere. The Q tips are also pretty bad

425
00:28:23,396 --> 00:28:26,876
Speaker 1: because they have size tends to be the same as

426
00:28:26,996 --> 00:28:30,836
Speaker 1: like some of the sort of like filters that capture

427
00:28:31,316 --> 00:28:33,716
Speaker 1: just like big, big junk out of the waste water,

428
00:28:33,756 --> 00:28:37,036
Speaker 1: so they also block those systems. The Q tips are

429
00:28:37,076 --> 00:28:41,436
Speaker 1: not great to fulush either. Feel like I touch the

430
00:28:41,556 --> 00:28:46,916
Speaker 1: nerve here? Yes? Oh yeah? If everything goes well, what

431
00:28:47,076 --> 00:28:49,236
Speaker 1: problem will you be trying to solve in five years,

432
00:28:50,756 --> 00:28:55,076
Speaker 1: due to climate change, we can expect to see more

433
00:28:55,996 --> 00:29:00,996
Speaker 1: infectious outbreaks than before in a more frequent manner. The

434
00:29:01,036 --> 00:29:07,596
Speaker 1: patterns of you know, just wildlife of insects, factor insects

435
00:29:07,596 --> 00:29:12,756
Speaker 1: are just changing, so so we can expect to see

436
00:29:12,796 --> 00:29:17,876
Speaker 1: more zonoric events of infectious diseases jumping to humans. So,

437
00:29:18,756 --> 00:29:20,836
Speaker 1: in my opinion, I think that the next five to

438
00:29:20,956 --> 00:29:25,356
Speaker 1: ten years should be more about that international collaboration around

439
00:29:25,356 --> 00:29:29,396
Speaker 1: health understanding. You know, what we do here won't be enough.

440
00:29:29,556 --> 00:29:32,476
Speaker 1: We need to be connected. So I would love if

441
00:29:32,996 --> 00:29:35,916
Speaker 1: we have been so successful at collecting, you know, at

442
00:29:35,916 --> 00:29:40,116
Speaker 1: building this data asset and having the trust of different

443
00:29:40,156 --> 00:29:43,236
Speaker 1: governments that we can even begin to be part of

444
00:29:43,276 --> 00:29:48,516
Speaker 1: that collaboration. What's the most interesting thing you ever saw

445
00:29:48,756 --> 00:29:52,196
Speaker 1: pulled out of a sewer? Oh? Wow, Yeah, that's another

446
00:29:52,276 --> 00:29:59,076
Speaker 1: good one. Well, I mean I didn't pull this myself,

447
00:29:59,436 --> 00:30:03,276
Speaker 1: but we were touring one of the plants that we

448
00:30:03,396 --> 00:30:07,396
Speaker 1: work with in in Portland, Maine just a few weeks ago,

449
00:30:08,076 --> 00:30:12,356
Speaker 1: and they were telling us that they recently pulled the

450
00:30:12,436 --> 00:30:19,116
Speaker 1: door of a car. I don't know what happened, but

451
00:30:19,196 --> 00:30:22,156
Speaker 1: there was a door of a car that they had

452
00:30:22,196 --> 00:30:30,796
Speaker 1: to pull out of the stream. Marianna Matus is co

453
00:30:30,916 --> 00:30:35,596
Speaker 1: founder and CEO of biobot Analytics. Today's show was produced

454
00:30:35,596 --> 00:30:39,276
Speaker 1: by Edith Ruslow, engineered by Amanda ka Wong, and edited

455
00:30:39,276 --> 00:30:42,276
Speaker 1: by Robert Smith. I'm Jacob Goldstein, and we'll be back

456
00:30:42,316 --> 00:30:53,116
Speaker 1: next week with another episode of What's Your Problem