Back to Newsroom

29-Jul-2020

Pittsburgh Technology Council interviews Cybergenetics about better DNA justice through TrueAllele science


In Episode 24 of Summer of 50 PGH Tech Stories, Pittsburgh Technology Council (PTC) Vice President of Communications and Media Jonathan Kersting interviews Cybergenetics founder Dr. Mark Perlin. The 23½ minute video interview is posted on PTC’s website. A podcast transcript, edited for readability, is provided below.

For twenty years, Cybergenetics has been solving complex DNA evidence. Most forensic items are mixtures of two or more people, often in small amounts. Many crime labs can't get information from these DNA items. They incorrectly call them "inconclusive," or report a wrong match statistic.

Cybergenetics "unmixes" DNA mixtures. The Pittsburgh company's TrueAllele® technology uses math and computers to find the right answer. A big match number shows that someone left their DNA, while a small statistic (a lot less than one) shows they didn't. Courts and investigators need accurate DNA match numbers to catch criminals and free the innocent.

In this #50PGHSummerStories video podcast interview, PTC’s Jonathan Kersting talks with Cybergenetics. Kersting examines what the company’s automated TrueAllele technology does that forensic DNA analysts can’t do, and how its probabilistic genotyping innovation revolutionized criminal justice. He asks Dr. Perlin what happened down in Texas with Lydell Grant’s DNA exoneration, and how TrueAllele freed Mr. Grant from prison for a crime he did not commit.

Kersting and Perlin discuss why software companies need trade secret protection to innovate. They talk about technology transparency, and how Cybergenetics makes its proprietary TrueAllele source code available to defendants. The podcast explores how the HR 4368 "Justice in Forensic Algorithms Act" bill pending in Congress would reduce technology innovation. By stripping power from impartial judges, the bill would make it harder for people to defend themselves against criminal charges needing better technology.

This exclusive PTC interview gets the whole story from Cybergenetics Chief Scientist and Executive Dr. Mark Perlin.

Transcript

Episode 24: "Mark Perlin of Cybergenetics"
PTC Vice President Jonathan Kersting, interviewer
23½ minute video podcast
Summer of 50 PGH Tech Stories is powered by Comcast

Everybody, this is Jonathan Kersting, with the Pittsburgh Technology Council bringing you our Summer of 50 Pittsburgh Tech Stories with Comcast. And some of the stories we do just, some of them really just they get to me in this crazy way. And that's what's happening here with Cybergenetics like this to me is the ultimate of how technology empowers justice. I can't put words to describe it, that's why we're going to talk to Mark Perlin from Cybergenetics. This is a company you probably never heard of, but they're doing such transformative work behind the scenes when it comes to criminal justice. When it comes to all things around just DNA and being able to prove who did or didn't do a crime, and they're doing this like at the highest levels possible. And to know they're in Pittsburgh doing this to me is just so exciting. So Mark, welcome to the show today. I've got so many questions for you because I think you're one of the unsung heroes of Pittsburgh with some of the work that you guys are doing.

Well, thank you very much. It's a pleasure to be on.

Very, very cool stuff. So quickly, just give us your background real fast. Now I know you got a pretty cool background, and you're doing the work that you do with Cybergenetics.

Well, I have education in different areas. A PhD in Computer Science from Carnegie Mellon, where I was faculty for ten years. I have a Mathematics PhD and a Medical Degree from the University of Chicago. And putting that all together really puts Cybergenetics, which we formed about twenty-five years ago, in a very good position to build technologies based on math, computers, and biology, that can solve problems that people can't.

Absolutely, absolutely. And so tell us about the quick overview of Cybergenetics, and give us the nickel tour and your role with Cybergenetics and everything like that.

I was faculty at Carnegie Mellon in computer science in the early 90’s working on The Human Genome Project. I invented some technologies that let us accelerate gene discovery, automated diagnosis of disease. And it turned out that those technologies also had use in Forensic Science. So in 1994, I left Carnegie Mellon to found Cybergenetics around the corner on Craig Street.

We were approached by the British government in 1998. We were mainly working with drug companies and academics on diagnostics with genetics, and gene discovery and drug discovery. And the Brits asked us a question, "Could we get rid of their backlog of 350,000 reference samples where they had almost 100 people working three shifts in a building in Birmingham and replace it with our genetic software?"

And the answer was, yes. And we did it. When they released our technology, basically 95 people found something else to do. A few desktop computers gave much better results in a process much faster without people. And this was the easy problem of how to interpret DNA data with simple data from a cheek swab.

Even with something that simple, they still had two or three people looking at the data generated by the lab, trying to interpret it, and accurately get the right genetic type of that person, the genotype. That was our first major forensic automation, and its impact continued. Another 350,000 samples every year, processed by a few TrueAllele computers in Birmingham, England, automating the DNA for the British DNA database.

That's back in 1998, 22 years ago. I didn't realize you guys were 22 years into this thing. That blows my mind.

Well, once we solved that problem 20 years ago, the Brits said, "All right, that was the cheek swab problem. That's for a reference sample, where the data is easy."

"What about DNA evidence, which are usually mixtures of two or three or six people all mixed in together? We can't solve that at all. People don't know what to do. We throw out almost all the data and almost everything's inconclusive. We don't get any information. Can you solve that?" asked the British government.

And so Cybergenetics did.

You’re so matter of fact about this Mark.

We used Bayesian probability modeling, a type of machine learning. TrueAllele reaches deeply into the DNA data, and thinks about it. The computer tries out 100,000 different solutions, and determines what's more probable and what's less probable.

The technology fully answers the forensic question in an accurate, automated way, but never sees an answer ahead of time. The computer doesn't know who the suspect is or their genotype. It just generates a solution for every possible person who could live or not live, and then makes a comparison. TrueAllele tells you with a number, "What's the support that a person’s DNA is present or not in the evidence?"

Right? Wow. It's just fascinating. And so tell us more about TrueAllele the technology and some of your customers. Obviously, you're working with the British government. I'm assuming you're working with customers of all types of governments, with lawyers, all types of customers.

Some groups buy TrueAllele as products. These government crime labs, about a dozen in the US, use TrueAllele on their own computers in-house. TrueAllele is a database setup. A server computer can have 12 to 100 processors, all solving problems simultaneously in real time. And with client software, an analyst can ask questions. And in a visual way, upload their data and then visually review the answers to look at evidence genotypes and the match results.

If the match statistic number is a million, that suggests that somebody left their DNA in the evidence. But if the match number is only one in a million, as a statistic that points away from the suspect. Those are the crime lab customers.

Cybergenetics also provides services to lawyers. We work with prosecutors, defenders, and innocence groups. We work with police and other investigators. We worked on the World Trade Center project 15 years ago, helping to identify 18,000 victim remains using the TrueAllele Casework technology, through all of this advanced Bayesian statistics.

Mark, you are giving me goosebumps here because this is just so powerful. I mean, everything from the World Trade Center, to finding out who the victims were so their families can have some peace of mind, to checking out DNA to prove if somebody actually did a crime or not based on their DNA actually being there or not. The impact that you're having on society is just massive, I think. I mean, how many court cases has your technology been a part of? It's got to be countless by this point?

Well, including all the crime labs, it's many thousands, Cybergenetics has been to court around a hundred times. Occasionally the opposing side will challenge the evidence, and ask a judge, "Is this technology reliable?" Then we bring to court a hundred documents, including the validation studies that have been done.

Over three dozen validation studies show that TrueAllele is reliable. The software finds the right people. It doesn't find the wrong people. The method is reproducible. Eight of those studies have been published in peer-reviewed journals. We've testified at admissibility hearings over two dozen times in the United States alone. Judges need to be persuaded through evidence about software reliability, based on testing the system.

You bring data to the system, right? At the end of the day, you're bringing data.

That's the concept in science and law. You test systems, whether they're robots or chemistries, machines, test tubes, or software. You test your systems on real data, and you measure how well they work. You measure their error rates. You do all of this testing. You follow standards or guidelines the government sets forth to make sure that you're testing your systems properly.

We test our system. The crime labs test our system. Other people test systems. Every case we're involved in, we offer to the other side the opportunity to test our TrueAllele system at no cost. You can always test our system. We're scientists, and we believe in transparency.

I can just say, I mean, it's transparency 100% all the way that makes this so powerful. You got nothing to hide. It's like the data is the data. And here's how it's being, you know, presented. So that's just amazing.

Also, we published the methods we use. We've been publishing them for 25 years. We've disclosed them in patent filings 20 years ago. We disclosed them in papers 20 years ago. So we have a host of papers that describe the methods, the validations, the results, how our algorithms and methods are applied. What we do is an open book.

Amazing stuff. Let's talk about like an actual case. I think it's always fun to bring this down. You tell us such great stories about how you know your technology has been used. Tell us about what happened in Texas in the Lydell Grant DNA exoneration case. I think this is a pretty cool, pretty cool way for us to explore this.

Well, that was pretty recent. Our work started last summer. The Innocence Project of Texas contacted Cybergenetics. We did our usual procedure, which is a free screening of the evidence in TrueAllele. We will always let the computer look at somebody's DNA data at no cost and send them back a preliminary report. If they don't like the result, or it disagrees with what they want, no harm done, they can move on.

Now in this case, the Innocence Project saw that we showed two things. First, Lydell Grant was not connected with the murder of Aaron Scheerhoorn. His DNA was not on the DNA from under the victim’s fingernails. But we also found somebody else's DNA, producing this unknown person’s genotype.

So the Innocence Project of Texas found our TrueAllele results useful. They could now show (1) Lydell wasn't connected to the crime. They could also argue (2) it’s worth searching the FBI’s CODIS database (with 14 million convicted offender genotypes) to find the true killer corresponding to our fingernail genotype.

Okay, so they're in the search?

Well, government don't like others running CODIS searches. That has to be done usually by crime labs, done in a certain way. And the rules are set up that it makes it very hard to revisit the past. For example, a lab can't go back and visit a lab 10 years ago, when the work was done.

But we worked very closely with a South Carolina TrueAllele lab. We had spent a year putting protocols together that we thought complied completely with whatever the FBI wanted. And we followed those rules, and the South Carolina lab ran a search with the TrueAllele profile we found.

We found the killer in Georgia. And the response to showing that Lydell Grant was not in the evidence and that the true killer was somebody else in Georgia was – total silence. Absolutely nobody in government cared.

They ignored it? I mean, you're coming back with something saying this is wrong and they're ignoring that?

The District Attorney in Houston wasn't interested because, well, people generally believe they've convicted the right person.

And they don't want to look at that thinking that “Yeah, something happened and it's their fault.”

I think they truly believe what they believe. It's a mindset they get into. The FBI was not happy that we'd run a search, and found somebody who was not the person in jail. We were yelled at a little bit by different groups.

But ultimately, the truth won out. And the Innocence Project of Texas was able, over a few months, to persuade the Houston police investigators to look into the case again. And the police went and found the individual that TrueAllele had identified in Georgia. And he confessed to the murder.

And, after six months, Lydell Grant was finally released from prison. But he still hasn't been exonerated. Nobody has sent us tremendous thanks, except for the Innocence Project of Texas.

Aren’t you on his Christmas card list now or something like that. I mean, come on.

Maybe for the Innocence Project. But that concept of using better technology on the same government data, to get a much better result to find the truth in DNA that science can deliver, and then actually help justice is not really a thankful task. Right?

No, it's not. I want it to be a thankful task. But obviously there's powers that be that don't want that. So I'm assuming you've probably run into lots of opposition over the years, obviously. And it seems to have shaken things up at the national level, because I know that there's some proposed legislation, you know, questioning whether or not to use outside services to test and everything like that.

Well, there's an interesting bill pending in Congress called the "Justice in Forensic Algorithms Act." The House bill is based on very false premises. And it proposes very radical solutions that would harm technology innovation.

When forensic software companies develop innovative technologies, they openly publish their algorithms, and make their software available to others for testing. But their source code is a trade secret. Trade secrets stop copycats from stealing and reselling hard-won innovations. The proposed bill ignores the transparency of disclosing algorithms and testing software, and instead attacks the trade secrets that foster innovation.

Now, what's strange is that Cybergenetics – and the other commercial companies in this area that we know of – will let a defendant, under confidentiality, review their source code. So, we wonder: Why is the House trying to pass a law to revoke the trade secrets that keep all software companies in business, when that same source code is already made available?

Isn't it? Right? I mean, that’s the thing that is their business.

And why would you want to? The purpose of trade secrets is to promote innovation. You already can see the source code. Why do you want to pass a law that revokes trade secrets? The bill goes on.

For a hundred years judges have served as gatekeepers for reliable evidence of all kinds: scientific, forensic. And if an opposing party challenges evidence, then you have to prove your methods are reliable through testing and error rates, through peer-reviewed publication. And good technology can do that. And it’s decided by impartial judges. It gives you the right as a defendant to bring technology that you want to use to help you in court.

Right? Exactly. Like I mean, it’s part of your defense.

The proposed bill’s second prong is to get rid of the judges and the lawyers and your rights. And to put all of this gatekeeper control of admissibility of reliable evidence in the hands of a small federal agency that actually promotes commercial products. So, they would be in a position to promote the products that they support, and legally block better methods.

Definitely.

The bill also proposes having standards for testing. That sounds great, except these standards have already been around for five years, and everybody already follows them. Congress wants to centralize software testing, taking it away from the hundreds of scientific groups that do it now in a decentralized way.

There are other things that the law proposes. But basically, the bill undermines what we value in science and justice: your right to have an impartial judge rule on evidence, to have transparency in the testing process, to be able to defend yourself. When the government is accusing you of a crime based on their own forensic methods, why should that same government be allowed to block more effective methods that might help your defense?

There's nothing about the bill that makes much sense to us.

Yeah, no. I mean, what can people do about this? I mean, should we be reaching out to our elected officials and telling them that this is something we don't want to be thinking about?

That would be a good thing. We're talking with the groups that understand TrueAllele and the situation, whether they're public defenders, whether they're prosecutors, whether they're lawyers, or they're even if they’re not lawyers and they think the bill is a terrible idea. And writing to your Congressman, and saying: I've read about this bill, I've heard this podcast, I've read the links that are attached to it. And I don't understand why I want to surrender my rights and good science in the name of government "protecting" me.

Absolutely. I mean, what kind of legislation do we really need to help justice? I know there's lots of gaps out there. In your eyes what could actually make sure that people are treated equally in front of the law.

Well, the biggest problem we see is government’s own lack of transparency and accountability – they hide their forensic data. The issue is not the methods; they are quite transparent. It's that crime labs and federal agencies lock up the key DNA laboratory and database data. Government secrecy blocks access by independent scientists, experts, or those with better technology.

Suppose you've been accused of a crime and you can't get access to the DNA data the crime labs accusing you with. (Not so much of a problem in Pittsburgh, but a real problem elsewhere in the country where defenders have to fight to get that data.) You can't defend yourself. Prosecutors who want that data in another case may struggle to get it from a crime lab.

Crime labs have scientifically misinterpreted or under-interpreted complex DNA mixtures in a million or more cases. If you want to get justice by going back and revisiting those old cases, you won't get it. There's no law giving you access to the data that government hides from you. But without it, you can’t undo past forensic damage.

In the Lydell Grant case, we got our one historic CODIS search ever done outside of a crime lab in the US. We found the killer, exonerated the innocent man, and got him out of prison. But the government’s response was making up more rules to stop independent scientists from seeking justice through better science.

A better bill would provide transparency for government data, government labs, and government databases. Congress should let citizens see what's going on with forensic evidence. Government should revisit the past, and open up the future, to get better justice.

I mean, did you ever imagine 22 plus years ago, when you started this up that this is where this would be? That you would take it to this level? That it is used around the world, and that I mean, I just feel like this thing has grown to be something quite large and quite impactful. And I'm always curious when someone starts something, you're trying to do something. Something's interesting. You see a solution to a problem, but think of the positive impact that you've had. I think it's pretty amazing. Do you think it was going to be like this?

No, not at all. We were working on some scientific problems. We were asking how much information could math and computers and science and modeling get out of DNA data. We wanted to unravel and solve impossible problems, to get the answer as a single number, and accurately identify the right person. And our initial thought was, well, this is really good. People will just use it; but that's not what happens in technology.

It took us ten years to refine the TrueAllele technology. We first used it in court here in Southwestern Pennsylvania, working with the Attorney General’s Office, in the murder of Blairsville dentist Dr. John Yelenic. In 2009, TrueAllele’s analysis of the DNA under his fingernails really made the case, connecting killer Kevin Foley to the crime. We thought okay, now crime labs will buy this technology, and we'll move on to some other problem.

What happened instead is things were slow in government. We had some crime labs that really liked it. It was a huge fight. Over ten years, we’d proven that TrueAllele worked, demonstrated reliability, published papers, and won admissibility hearings. And by that time, ten other competing groups had adopted our technology and began selling it in the marketplace. Which is always interesting.

On the one hand, it's really good that our ideas are out there and we’re helping as innovators. But as a business, we certainly didn't capture the market. Because once there's a good idea out there, larger companies go out and compliment you by sharing your work.

You're such a gentleman there Mark. I like the way you said that. Very much so. To me it's just an amazing story like a quiet little company on Craig Street there working on some of the world's toughest problems and literally saving people's lives at the end of the day. And that's why I'm so pumped to have just learned a little bit about what Cybergenetics does here, and so proud that you guys are in Pittsburgh. And as I've been saying, all these great stories I'm telling with Comcast, you're making Pittsburgh proud Mark. Simple as that. Making Pittsburgh proud.

Thank you very much.

Great stuff, Cybergenetics. Check these guys out. It's an amazing, amazing company.

Back to top