June 9, 2022 @ 12:00 pm – 1:00 pm EDT

Take the Probably Genetic Syngap survey here.
View our Probably Genetic news release here.

These are our introductory comments:

I have the pleasure to introduce today’s speaker, Abby D’Cruz, who is Head of Strategy & Operations at Probably Genetic. Probably Genetic develops technology to find undiagnosed patients
online and helps get them tested. Abby is an expert in genomics, holds a PhD from the University of Oxford and specializes in rare genetic diseases. Before joining Probably Genetic, Abby was a Senior Consultant at Trinity Life Sciences.

THIS IS A TRANSCRIPT ONLY:

0:06i have the pleasure to introduce today’s speaker abby de cruz who is head of strategy and operations at probably genetic probably genetic develops technology

0:15to find undiagnosed patients online and helps them get tested abby is an expert in genomics

0:22holds a phd from the university of oxford and specializes in rare genetic diseases

0:28probably genetic develops technology to find undiagnosed patients online and helps them get

0:33tested before joining probably genetic abby was a senior consultant at trinity life sciences welcome

0:40abby tell us a little bit more about probably genetic and what drove you to join the company

0:46hi everyone thanks very much for having me really excited to be here and with the team at the SRF as well so thanks Corey for the introduction uh and it’s a great question because i’ve been

0:57with probably genetic uh coming up to i think four or five months now and as you mentioned

1:02my background uh after my phd in uh which kind of was oriented around clinical genetics

1:08very much in a lab research focused position after that stint i i joined trinity life sciences where

1:15uh you know i really had an exposure to a whole variety of therapies and also disease areas but

1:22i developed a sort of a focus on rare diseases orphan conditions and then also therapies that

1:28were being developed across those indications so through that position i think got a really broad

1:34exposure to some of the challenges that uh drug development faces uh within those settings and

1:40i think through probably genetic i’ve been able to really zero in on uh the most i think pressing

1:47challenges uh that occur in this space and some of the most kind of incredible and innovative work

1:52that’s going on to address those challenges because you know the mission as you just mentioned Corey at probably genetic we have a very aspirational mission to diagnose uh 200 million

2:03uh genetic conditions uh to diagnose 200 million patients with the rare genetic conditions globally

2:09and you know that’s obviously a pretty impressive target but we’re doing that through really innovative ways that i think are really exciting and we’re kind of looking to leverage some very

2:20sort of cutting edge and and you know newly developed ideas that merge technology uh you know

2:26in addition to you know all of the ridiculously advanced research that’s currently going on

2:31in the genetic field so looking to merge a couple of my areas of interest and tackling challenges

2:36that i’ve come to understand are really complex and obviously you know incredibly worthwhile so

2:42we managed to take quite a few boxes at probably genetic and the work is incredibly rewarding as i think we’re going to get into today wonderful look forward to it perfect well i think everyone

2:54can see the screen that we’ve put up today so we’ve got a short uh presentation where

3:00we can go into really some you know background on what it was that we put together with the SRF

3:07and uh you know what the kind of objectives were for this partnership and and excitingly what’s

3:12kind of come out of that program and uh looking ahead to the future of next steps as well so

3:17to kick it off at a very high level our objective was to figure out whether or not we could identify SYNGAP1 your sort of target condition of interest using machine learning effectively so

3:29what we’ve broken this down into in the next slide if it will move there we go

3:37uh to pursue that objective of developing a what is effectively a symptom checker that we could use to identify SYNGAP1 patient we break that down into essentially a five-step process so

3:48the first step was to develop a prototype which essentially involved the probably genetic team

3:55working really closely with the SRF as well to leverage you know a lot of researchers out there

4:00currently in addition to patient feedback family feedback care feedback to develop a prototype

4:07symptom checker so what we mean by that really at the very initial stages was just effectively

4:13a list of symptoms that would be associated with the target condition so the SYNGAP1 but also a

4:18list of symptoms that would be associated with differential diagnoses that patients experience

4:24in their diagnostic odyssey and then also just kind of you know peripheral symptoms that

4:30might crop up as well so we’re really trying to capture a comprehensive list of symptoms that our

4:36patients might encounter within their journey and feed them into what we developed via our platform

4:42was a really user-friendly symptom checker that patients would go in and for example you

4:48know use more patient-friendly terms for some of these phenotypic symptoms that might crop up so

4:53we initially developed that prototype uh and then what we did again leveraging the this the SRF

4:58community was that we put that out for feedback effectively um we put that prototype out to say

5:04are these the symptoms that you’re seeing is this comprehensive is this accurate um is there anything that we’ve missed really importantly um you know there are any terms that

5:12maybe are surprising to you um that would help you to use to identify what’s going on with you

5:18in a way that uh you know would enable you to input this into a data capture form so we honed

5:25that prototype in the feedback step and once we were pretty confident that we had a really

5:31comprehensive and accurate symptom checker we then set out to collect training data uh effectively so

5:38our target here was on 100 patients so what we mean by collecting training data is essentially

5:44just getting people to fill out the symptom checker so uh sending this link out um that

5:49was live on uh you know definitely within the SRF community lives on your website as well we got an

5:55enormous response but effectively we just wanted to get that link out to as many people as possible

6:01uh so that we can collect training data on patients within the community to see how those responses look when we submit you know this huge list of symptoms to them

6:12uh what what’s coming up right so what are the patients within this community how are they characterizing their symptoms what’s the what we call a phenotypic profile for this community

6:22so that was kind of the training data step and and like i mentioned we’ll go into data a little bit

6:27later but our target there was was for a hundred patients um for a really good comprehensive

6:33snapshot so once we’ve developed the symptom checker we’ve received the feedback on it we’ve uh

6:38basically unleashed it on the community uh we’re then training it so the training step it’s uh it’s you know encompassed in three words here but it’s it’s a little bit more complex

6:48than that this is where our machine learning technology our sort of algorithm-driven technology

6:53comes into play so what the symptom checker can do with our machine learning algorithms is it will

6:59ideally get really good at distinguishing patients that have the target condition to SYNGAP1

7:05um from other patients or patients that don’t have signed up one so we would know that in the you

7:10know within the community we know patients that have previously received a diagnosis of SYNGAP1 so the goal there when we say training the symptom checker is that we would get it to a point where

7:19it becomes really good at identifying when someone who’s submitted the phenotypic profile to the

7:25symptom checker has a high likelihood or does have SYNGAP1 as the target condition so that’s

7:32that fourth step um and then finally you know the the kind of the why or the so what of this whole

7:38exercise is to basically provide um the SRF with an incredibly rich source of you know information

7:46uh really useful information uh for their community and i think that the fifth step

7:51is really obviously the really exciting one definitely for the SRF but also for us because um you know that’s the real value add i think and that really enables us to zoom out

8:01a little bit on the why um because you know as we know and as as certainly everyone at the SRF knows

8:07within the rare disease community you know the more patients that you can find and the more you can draw attention to how many people are either living with your target condition or you

8:16know trying to find answers um in the space within which your kind of condition exists

8:21the more people you can identify in that space the more attention you can drive onto that disease the more potential r d f that you can drive and the whole kind of you know biotech and research cycle

8:30can um have a bit more energy put into it so that was a little bit of an overview of of the initial

8:36five steps let me pause query to see if we’ve had any feedback or questions or if i can keep going

8:42let’s see i don’t see any questions as of yet great i must be doing a spectacular job or they’re

8:50all just holding up so i’ll keep going so this is basically the overview um where we’ve broken down

8:56into steps uh how we were kind of addressing this overall objective to develop a symptom checker to identify SYNGAP1 patient so let’s get into how this actually fared so um like i mentioned just

9:08before the initial objective was that um you know in that training step where we were going to collect submissions we were we were targeting 100 as a really healthy data set what we achieved

9:18at the end of our initial pilot was 603 unique submissions uh and that was right across the globe

9:24certainly right across the um the united states and you can see from uh on the left the the growth

9:30tracker in terms of number of symptom checkers this program uh had just phenomenal growth which

9:36was powered um by the uh you know enormous level of motivation and engagement driven within the srf

9:42um for people to submit their symptoms and and create those symptom checkers submissions so we had uh we saw we witnessed rapid growth of the program and the geographic spread as well

9:53is a really powerful um i think example of just how much appetite there is um and just how um

10:00you know just the need i guess the high level of need for people out there who are looking for answers people out there who are looking for remote testing programs and patient initiated

10:10uh solutions so we love this slide um you know it really illustrates the scale of um

10:16you know what we’re doing and certainly illustrates on how motivated the srf community is in particular um to you know click on the link basically and distribute the link to patients and

10:26their families who are looking for for answers so what we’re at now is 3287 unique submissions

10:33and we’re seeing that continue to grow and seeing that to continue come in from around the world so massively exceeded our our growth expectations in terms of program submissions

10:46so the next piece is just what those submissions or what that kind of snapshot of the community looks like so the people that are submitting to this program um again this is for the current

10:56data so i think by the end of the pilot we had about an 80 we had 80 saying get one patient submit to the program we’re currently at 100 sign up one patient submitting to the program and uh 20

11:07different diagnoses as well um that are submitting uh phenotypes to uh you know to the program and

11:13contributing to the richness of that data set and contributing to the richness of information that we have of patients that are within the SRF community so this is a really powerful graphic as

11:23well just because it illustrates just a variety of you know differential diagnoses and also just the

11:28variety of conditions that are present within this community which again you know on this on this

11:34graph we’re showing some incredibly rare disorders um and again it shows uh you know what we think

11:39kind of underlines the um diagnostic odyssey that a lot of patients go through and again provides a

11:44lot of really really useful information for the srf and similar organizations that are really

11:50looking to shed light on some of these conditions so some pretty extraordinary numbers in here

11:58so on the next slide uh what we’re showing here and what we think is really powerful is um you

12:04know in terms of objective of achieving that objective of a symptom checker that can identify SYNGAP1 patients what we found through the program is that SYNGAP1 has that distinct phenotypic

12:15profile as compared to patients that don’t have SYNGAP1. so those are the patients that haven’t submitted you know a diagnosis of of syngap so what we’re seeing on the left here is essentially

12:26a uh ranked uh snapshot of the symptoms of everyone that self-identified as having SYNGAP1

12:33so those are 84 patients that we use there and you can see that the global developmental delay

12:39the intellectual disability motor delay are the top symptoms that are incredibly frequent within

12:45patients that have the same gut one diagnosis whereas on the right hand side you can see that patients that don’t have that SYNGAP1 their phenotypic profile often looks

12:55very very different to those SYNGAP1 patients so this is really just underlining the power

13:01of sort of addressing the question that we had around you know can our technology can a very comprehensive symptom checker and our machine learning algorithms can that you know

13:11with a high degree of likelihood identify a sign got one patient from a non sign up one patient

13:17and what we found is that look the snapshot looks pretty good this is really promising uh this is what we like to see again we love this slide um because it’s just sort

13:25of illustrating the power of this program because it is a patient-initiated program so we’re just sort of putting this out there in the community and these kind of

13:33stock results is really kind of underlining the power of the program in terms of predictiveness

13:42so we’re just going to dive a little bit into um some of the i guess the science or the step four if you remember of the training um for our tech because we think that this is kind of really

13:52powerful and it’s sort of the nuts and bolts of the slide that you saw previously so this is just a little bit on what our model actually does and what it does is that it will look at

14:03all of the users that are the SYNGAP1 submissions all of those profiles and it looks at the symptoms

14:09that those patients submitted and it’ll rank those symptoms by importance so what that means is

14:14essentially um you know if there’s a symptom that the vast majority of patients with syngap have

14:20that’ll be a really important symptom for the model it’ll prioritize that symptom and kind of flag it as something that is uh seen very often very often with saying get one patient

14:32and it’ll also mean that um you know the importance of that symptom will increase relative to non-SYNGAP1 patient so this is basically just a quick look behind the scenes

14:42and again really important information for communities like the SRF where they’re looking to

14:47really sort of have an indication of the symptoms not only that their patients are experiencing but

14:53also the the symptoms that really distinguish or differentiate their target condition and can

15:00be used to sort of identify patients that have a high likelihood of having SYNGAP1 in this instance

15:06so this is what we refer to as feature importances but it’s essentially just allocating an importance to the submitted symptoms

15:18so what we’ve called out here is just a couple of examples where you know we you can what this enables us to do so for example it will enable us to identify for example a simple a symptom

15:29that might be um common for SYNGAP1 patients but rarer for non-SYNGAP1 patient so what that

15:36will enable us to do is to flag that symptoms as an as an important one because it distinct

15:41it can potentially distinguish between someone that has signed up one and someone that doesn’t because it’s effectively telling us okay this is a common symptom in saying that

15:49one patient but it isn’t in confirmed non-SYNGAP1 submissions this is really

15:55powerful information when you’re looking to you know go into that sort of characterization of a patient community and flag those symptoms that are really important for your target

16:03disease so the so what of everything that i’ve kind of just

16:10said in terms of you know the things that our model is doing behind the scenes to identify important symptoms and to be able to distinguish 99.1 users is basically shown on this graph so

16:20the key message here is that through all of those mechanisms that our machine learning model uses

16:26um we found that we can use it to identify ninety-seven percent of SYNGAP1 testers

16:31so what that means is of if you had a hundred SYNGAP1 patients that submitted to the program

16:36the machine learning model that we trained just by itself would be able to identify 97 uh 97 of those uh signed up one patient so a really really effective um predictive

16:47uh rate basically um what we did there was uh you know what this this graph is showing is

16:53that we identified a threshold that we used um to basically score um submissions to say this SYNGAP1

17:02submission uh you know is is kind of over the threshold and therefore has a high likelihood of having signed up line or should would therefore be referred to testing or something like that so um

17:11the slide here is basically showing that the ml model uh has a really high uh ability to identify

17:17SYNGAP1 testers which is really good news for us um based on all of the work that we did with the SRF training this into checker and then having it be able to identify sign up one patient

17:33so this is kind of the uh outcome slide and this is accurate for the end of the pilot so um i won’t get too much into this but the the key message here is that with the ml model

17:44that we trained working with the SRF we had 81 syngap submissions that would be offered testing

17:51and really importantly we had 28 uh non-SYNGAP1 submissions that we would also offer testing

17:57so those are patients that we’ve uh that have submitted to not having a SYNGAP1 test and not

18:03having a SYNGAP1 diagnosis but that the program would offer would suggest to offer testing too

18:09which is really interesting and valuable for us and that’s only at the end of the pilot so you know we’ve collected a whole bunch more submissions since then and we would anticipate

18:18that that number will go up so this is exciting on two levels um the first is you know that we’re

18:23identifying um patients that you know the model is kind of accurately identifying patients that

18:28would be offered testing because they um you know look like SYNGAP1 patients but really excitingly

18:34is that it’s identifying patients that haven’t currently got a diagnosis of SYNGAP1 that we

18:39think should be or would be offered testing which is great so again really valuable for um you know

18:46organizations like the SRF who are not only interested in identifying patients in learning

18:51more about their community but also in identifying patients so it was really good news for us

18:56certainly but also this kind of data is really exciting because it hits on both of those kind of

19:02key objectives for patient advocacy organizations and certainly for ones as engaged as the SRF

19:14so this is kind of uh diving in a little bit to what uh to the previous uh phenotypic profile

19:19slide that i showed where um if you kind of double click so on the previous slide we’re kind of zooming in now on the on the 28 and the 81 so of the 28 and 81 so over here

19:30on the left hand side where we know these are patients that have SYNGAP1 that’s their phenotypic profile and this is just kind of illustrating that of those 28 patients that

19:40don’t have a diagnosis of SYNGAP1 that the program has sort of flagged as you know should or

19:46would offer testing for SYNGAP1 their phenotypic profile looks much more similar to patients that

19:53do have SYNGAP1 so this is basically you know the foundation upon which our program suggests that we

19:58would offer that kind of would flag these patients that the SRF can you know connect with these

20:04patients to link them with additional information and resources this is the basis for that where

20:09we’re saying hey these patients have a phenotypic profile that we think is pretty similar to assign

20:14gut one patient and therefore it might be helpful that we you know connect them to resources and ideally additional testing so this is a really sort of exciting and obviously useful output

20:26for programs like foundations like the SRF but also is kind of the key reason behind programs

20:33that we we run like this where we can hopefully use our technology to identify patients that

20:38haven’t yet been given a diagnosis but that um you know could certainly be really good candidates for

20:43additional information and potentially linking and connecting to testing resources as well

20:52so in summary essentially we wanted to show this slide as kind of a snapshot of at the end of the

20:59pilot so at the end of our pilot that we put together with the SRF we had that objective

21:05that i spoke about earlier to develop a symptom checker for SYNGAP1 and we broke it we had broken

21:10that down into five steps um so the great news was that we met or exceeded all of those steps we developed the prototype and received feedback with a huge amount of help with the by the SRF

21:20and their community um we had that training data huge overshoot 603 patients ended up submitting

21:26so a really powerful training set that we were able to run the symptom checker on uh and developed what i’ve hopefully just shown you uh

21:34to be a really accurate and uh highly predictive symptom checker that’s really powerful for SYNGAP1

21:41and then we were able to provide a huge amount of really exciting data to the SRF as well

21:46that you know has hopefully really empowered them and you know provided them with an additional uh very rich resource um to continually sort of drive engagement um and effectiveness within

21:57their community and we had sort of put in as kind of aspirational bonuses um i remember at the end

22:03of our sort of pilot report with the SRF that um we had two additional points that we were really

22:09excited to get going on which was firstly to build a tool for the SRF to engage you know your

22:14community and your patients where we could put all of this data and all of these abilities together into a really user-friendly portal and then the second piece which is kind of the most

22:24important bit was to launch a free testing program so that we can basically connect

22:29these patients that we’re flagging as you know potential candidates for SYNGAP1 we can connect

22:35them to that potential answer in the form of free testing so this is what we kind of showed

22:41at the end of the pilot that we put together with the srf and we were really delighted to have met all of the uh the project objectives but the exciting uh update uh and i don’t even

22:50know that the srf knows this at the moment but the excited update that we have to share today is that uh we actually have just signed a partner for the uh free testing program and

23:01uh we’ve just signed with uh mighty therapeutics who are gonna basically work with us uh to

23:08essentially be able to offer um potentially offer free testing to any of the srf submissions that

23:13are eligible so we have uh that capability kind of the back end to this uh in process which is really

23:21really exciting and kind of connects up the uh you know the finding with the with the additional sort

23:26of diagnosis piece as well so that’s a piece that we’re really excited to get working on um and and was our sort of eventual goal so that’s a really exciting next step that uh we have to come

23:39wonderful i know everybody is really exciting about the fantastic program

23:47um what else let’s see we’ve got a couple questions let’s see if i can get them pulled up

23:58before you before you jump into that cory can you um i have a question abby so

24:05on bullet three there you say collect train data on 100 600 3 000 200 so that’s amazing right so we’ve got 3 000 plus people have taken this what’s the current number

24:16for patients who are testing probably say syngap because i think earlier on you had a slide around 28 but i feel like that number’s gone up as well do you have that

24:25at your fingertips sir that number has gone up i don’t have it at my fingertips currently

24:30uh i bel it’s i believe it was over a hundred um uh that was less than two weeks ago but i’d

24:36have to double check that but it’s gone up significantly that’s awesome that’s awesome

24:41yeah which is super exciting and the mozzie thing like the ink is drying on the paper right so we don’t even have a press release on that yet that’s exactly right yeah the ink is drying as we speak

24:52we should work on that press release oh yeah we absolutely should i am so excited this is great

24:59okay Corey that was my question that you’re you’re your show let’s see on the slide with the 20 different diagnosis listed um to confirm out of the three

25:13thousand submissions just have a hundred have syngap diagnosis so we kind of answered that

25:20just now um well the hundred was the the patient population that was us that filled out um where

25:28it says SYNGAP1 so that was actually our people um in this list correct yeah so actually this is

25:38uh the snapshot of all of those submissions so um this would be the top diagnosis so these are the

25:44patient diet patient reported diagnoses um so you know when you fill out the symptom checker you um

25:50can input any uh diagnosis that you’ve received clinically um so of those so the question is

25:55correct uh that’s right uh out of the 3 200 odd uh submissions a hundred have self-identified

26:02as having syngap um and then you can see the prevalence of the other sort of top diagnoses uh so to speak noted on the slide so that’s right so we we found in addition to the hundred that we

26:14already knew about we found the additional 100 um patients that fit that profile out of the 3 200.

26:26all right and says next this is from ed in the slide showing the symptoms of SYNGAP1

26:34versus non-SYNGAP1 i assume that all other disorders are lumped into the non-SYNGAP1 chart

26:41if so have you looked into whether they are any individual disorders within that group that mirror SYNGAP1 more closely than aggregate of all non-SYNGAP1

26:57so i guess i think i understand this in temperatures one particular phenotype that fits SYNGAP1 out of this bunch more so than the rest of them yeah so that’s a really

27:09interesting question um so the short answer is no in that whether or not we’ve looked whether or not

27:14we’ve run an analysis um that stratifies non-SYNGAP1 submissions according to like

27:23likeliness or likeness to the SYNGAP1 phenotypic profile and the reason that we haven’t done that

27:28is that a it would be quite uh intensive because you’d have to sort of stratify uh you probably saw that list of differential diagnoses and then do a comparison which would involve retraining the

27:38model whereas the approach here is to just sort of use the knowns so what i mean by that is you know

27:46the knowns for this training um for this program and the way in which we set up the training

27:52is that we had our one known be the syngap and then had you know the sort of differential

27:57diagnosis come in so if we wanted to run something like what you’re proposing we’d have to make

28:03sure that that initial step where we you know did the really comprehensive set of symptoms um for each of the fesian gap one and then the comprehensive set for all of s differential

28:12disorders um that we would do that set for every uh diagnosis that we’d want to compare to sanger

28:18which um you know obviously would be quite a few um so the short answer to your question is no

28:23uh we currently just have the sign got one known comparison to the non SYNGAP1 submissions

28:31um he said did any of them previously have a different diagnosis

28:37yes several um so i assume you mean the sign got one um so that’s another really really rich um

28:44you know source or resource both for us and for the SRF so when patients can submit

28:51to the symptom checker they can submit uh you know obviously a really rich uh amount of detail on their symptoms but they also submit information on things like onset

29:01um on things like severity and so what we can map from that for the target condition is a very

29:08very detailed um comprehensive almost we like to call it the diagnostic odyssey right where

29:14we can kind of say all right the majority of one patients are experiencing an age of onset around about this time uh the majority are getting a diagnosis around about this time which you know

29:24allows you to calculate kind of the the average weight effectively for a diagnosis all of those

29:29data points uh you know in many obvious ways very useful um not only for the SRF but for everyone in

29:35the signup community but uh certainly it’s because it’s all patient initiated and patient reported

29:41it’s a really powerful way of getting a snapshot on what patients themselves um inpatient families

29:46and caregivers are experiencing um and kind of the ways in which they characterize their own

29:52experience which i know the SRF is really excited about and we found to be a really powerful tool

29:57yeah i’ll tell you looking through the data that we received it was very interesting to see how many people had already had some type of genetic testing in the past

30:07but it has been you know 10 years five years probably back when they weren’t testing for syngap

30:15um so we’ve gone back and made a recommendation to them to go back to the genetic company that did

30:20the testing and get them to rerun the port is free to them and there might be something even if it’s

30:26not syngap something else might pop up that wasn’t previously known at the time they had the um

30:32original genetic testing done yeah that’s that’s exactly it and that really underlines the power of

30:38um you know the the kind of i guess sister slide to this one where we’re um you know showing the

30:43profiles of the patients that we’re saying hey these you know didn’t submit a SYNGAP1 diagnosis but they really you know the model’s telling us they really maybe have a high likelihood of

30:52um either being a patient or being very close to or having you know a phenotypic profile that would really benefit either from additional testing maybe revisiting testing like you mentioned Corey

31:01um or just you know additional resources and just a little bit more to learn about um you know the specifics of the disease so um in any of you know regardless of which bucket you fall into in terms

31:11of patient and diagnosis and what your previous testing history was which we also captured by the way um so yeah corey we were looking at that data um in terms of you know the tests that previous

31:21uh the patients have previously had no matter what bucket you fall into we’re hoping that the program

31:26is you know producing a resource that’s useful for all of those patients yeah because so many

31:31people don’t realize you can go back and have it re-run they don’t realize the differences between the different types of genetic testing um not everyone tests for everything so it’s important

31:42that they go back and really try to fight for that diagnosis because so many people just don’t know

31:47to ask the different questions that’s exactly it yeah and it really speaks to you know there are

31:53the srs um you know particularly good at this but the role of patient advocacy orgs of of that empowerment piece right so even if we’re not saying oh you know you look a lot like

32:03a sign get one patient that that the power of that knowledge that um you know you can go through hey

32:08you know you can ask your doctor to revisit this you can ask your testing service to revisit this or hey you know look at this gene or this variant or whatever it might be those are the really kind

32:16of empowering pieces um that this kind of information can hopefully provide a link to

32:23i also wanted to make note we did create a probably syngap facebook page so anybody that

32:30got a high probability test result back from the survey we made sure we’ve let them know

32:37hey we’ve got a facebook page it’s a probably syngap and you can kind

32:42of go in here and and talk to other parents that have also tested highly probable and uh

32:49talk about your stories and different things about your kids and it’s been really great to for them to have a home too because they’ve been so long without knowing and just it at the very

32:58least finding people that have similar phenotypes as their children has been so beneficial to them

33:06yeah i mean that was just such an incredible um piece of this of this program you know i know that in in our you know we had weekly checkpoints um as as we were running the program and certainly

33:17hearing from the parents uh hearing the testimonials that came in i mean we had people who were using the program that had just been you know like elbows deep in this diagnostic

33:27odyssey for just years and years and years um and like any light that you can shed there

33:32um is just so impactful and powerful and so being able to hear all of that through the SRF and you know seeing the impact that you guys are having and that we can have any small hand

33:41in uh you know providing you with any tools or resources that was definitely really powerful for us um and i think just exactly what you said Corey you know the the impact of information the

33:51impact of community was definitely underlined by by this program um and yeah i mean that growth

33:57curve like mike said that growth curve speaks for itself uh the srf community enormously engaged and

34:02um yeah you guys are definitely a role model for all the other all the other programs we’re putting together we’ve been hanging out in the undiagnosed parent groups a lot and you know it’s

34:12funny you can kind of hang out in those groups and see when they talk about their children um that

34:19they seem to have very you know similar symptoms and so we try to reach out and put the link in

34:24there to let them know hey here’s a chance to to maybe kind of narrow down that your odyssey so

34:31um hopefully we’ll continue to find some more people out of that sorry my dog went nuts

34:37that’s okay i mean that’s actually a great segue and i’m going to pounce at that opportunity corey um to basically just make that exact point so you know there’s a reason why i’ve just flipped this

34:46slide again um obviously we’re incredibly excited srf is really excited that we’ve signed a partner

34:52um to connect up these two pieces you know the patient finding and then the actual testing on the diagnosis piece um which we’re really excited about but you know soon that what that means in

35:02terms of next steps and what your community is going to see is that soon we’re going to have the whole process connected up and you know your the people within your community are going to start to

35:11see the link pop up and they’re going to have that opportunity to you know be considered for the free

35:16genetic testing and you know we can only implore you um and everyone in the community to do exactly

35:22what you just mentioned right if there’s any corner of you know the internet of social media of

35:28any kind of you know disease influences and whatnot um that you know you interact with during

35:34your diagnostic odyssey that you can get get a link to um or you know just share some information

35:40with about the program that’s so powerful um and that’s exactly what we need um because

35:45you know that all we’re trying to do is all we can do is develop mechanisms right and develop tools and it’s really just uh the communities that we serve so the communities like the srf

35:55and patient communities that are the power behind that so you guys really power the mechanism

36:00um and it’s only you know without the actual srf community we wouldn’t have any of the results that i was just able to show today and i think that you know the fact that

36:08all of it all of our expectations are exceeded um we’ve been able to produce this really you

36:13know data rich really important sort of powerful uh resource that’s giving us so

36:19many insights on the on the community uh that’s all down to you know the community itself it’s

36:25you know we can develop all the mo tools in the world but they’ve got to be used so uh yeah we’re really excited to have this opportunity come up and we’re excited to see

36:31you guys put the link in every corner of the internet once again one thing i would like to

36:37you to speak on is the privacy um while we are in these you know these undiagnosed parents

36:44groups or epilepsy groups um there has been some hesitancy for people to give their information you

36:50know information is very critical nowadays and their people are much more hesitant to

36:56give out that data could you speak to a little bit to ease some of the people that may be more hesitant to fill out a survey because they’re they’re worried about that information being sent

37:06yeah absolutely um and and it’s a key point and we really understand this we’ve got a couple of um you know our team members who have rare genetic conditions and so

37:15have you know first-hand experience of um yes you’re on that diagnostic odyssey and you’re you’re really looking for answers but also you’re you have that wariness right about your data so

37:24um that data privacy has been centered in our in how we’ve developed the symptom checker and also

37:30all of our processes so from end to end um so what that means is from the point at which a user even

37:36clicks clicks um on a link to the symptom checker or you know enters any information whatsoever

37:41um we’re compliant with everything that you need to be compliant with so the primary piece there is hipaa um every single aspect of our system so not only our you know website where you input any

37:51information in the databases that we use those are all hipaa compliant um which protects your data and means that it’s all completely adherent to um the relevant you know laws that protect any

38:01personal um identifying health into information so that is all very secure um in terms of where any

38:07information is stored if at all um and that’s end to end so that’s not only when you input

38:12your information it’s also at any point you know when your data is sent to our sequencing provider

38:18to our report generate to our analysis it’s all completely hipaa compliant all the way through which isn’t it’s a bit of a gray area whether that’s actually required but we’ve kind of gone

38:26through like ironclad and made sure that every single step in our process is compliant so there’s that piece where you know on an institutional on us on a legislative level we’re completely you

38:36know almost extra compliant um but the second piece is um you know our responsibility so we

38:42take this really seriously um around how we use data that we would have and there’s two key

38:48pieces here the first is that anything uh that is personally identifiable anything that could be in

38:55any way linked back to you or anything like that is completely um you know de-anonymized and also

39:01is protected by consent so we will never share any part of your data um without your explicit

39:07consent um so nothing is assumed the consent has to be explicit um and so that’s the first piece

39:13around explicit consent of personal health data and then the second piece is that any data that um

39:19we do share so for example the data that i just showed everyone um in this presentation

39:24everything is anonymized um in a very uh stringent way so for example any location information so

39:31you know when you complete the symptom checker that ip even is completely anonymized uh to zip

39:37three level so uh you know the last two digits of any zip is taken out so even those dots if

39:42you zoomed in on that location map all you would get is like a pretty sizable region um because that would be the zip3 level so you wouldn’t be able to see anything further than that so that

39:51kind of thing as well we take really seriously um so any kind of information that would be passed on to any prospective partner even for example um would be completely de-anonymized and again would

40:00require that consent um so i think that those uh i could probably talk about that for a long time

40:06um but the two the two key pieces are basically that we take it really seriously um you know and that’s driven by the patients that we have within our organization um and the second

40:14piece is that we’re you know extra compliant um with all of the regulations uh that that serve

40:20uh health data that’s great thank you very much for that all right and then we did have one more

40:26question that came through um from an anonymous attendee attendee she said um just to clarify how

40:32many months were the 3 200 submissions over yeah that’s a great point i can actually jump to that

40:41so it’s from i think about fab yeah there we go so basically from uh early fab to june so what’s that about four months yeah is that right yeah so it’s

40:53it’s honestly it’s it’s astonishing growth um i think by the end of the pilot uh like i mentioned we had i think 600 so you can see the growth just from that period alone uh we’re seeing submissions

41:04continue to come in so uh you know we’re still getting uh i think upwards of 50 a week

41:10um and even that is like a slight drop off you can see uh that the rate’s kind of uh evened off a little bit in the in recent days but that growth trend with that um

41:19you know that the rate of growth is just is is remarkable and definitely exceeded everything that we thought would would happen so uh yeah about four months to date great all right well i think

41:31we are done with questions unless anybody has the last minute when they want to pop in the chat

41:38we appreciate it abby and we look forward to a question finding out more and getting more data from you guys that’s amazing it’s been great yeah

41:48we’re so excited for next steps so um yeah can’t wait for everything that’s about to happen and uh yeah definitely echoing mike’s excitement we’re really raring to go on this

41:58well you have a wonderful day thanks everybody you too thanks for having me