Atom­wise inks Chi­na deal as list of AI col­lab­o­ra­tions length­ens

The long list of ma­jor AI bio­phar­ma col­lab­o­ra­tions has got­ten longer as one of the first ar­ti­fi­cial in­tel­li­gence star­tups has inked its first deal in Chi­na.

San Fran­cis­co-based start­up Atom­wise has signed an agree­ment to de­vel­op tar­get­ed drugs with Han­soh Phar­ma­ceu­ti­cals, a deal that could ul­ti­mate­ly be worth up to $1.5 bil­lion. Han­soh is flush with cash af­ter a $1 bil­lion IPO on the Hong Kong ex­change in June.

The promise of ma­chine learn­ing to speed up pre­clin­i­cal work and save de­vel­op­ers mil­lions of dol­lars has led to a string of new col­lab­o­ra­tions be­tween a hand­ful of soft­ware star­tups and some of the biggest drug de­vel­op­ers and re­search in­sti­tu­tions in­clud­ing Mer­ck, As­traZeneca, J&J, Bris­tol-My­ers Squibb, Pfiz­er and Duke Uni­ver­si­ty School of Med­i­cine. They’ve agreed to work on re­search rang­ing from on­col­o­gy to chron­ic dis­ease.

Part of the swarm like­ly comes from the hype that pe­ri­od­i­cal­ly sur­rounds a new tech­nol­o­gy — and few words are buzzi­er right now in both tech and pop­u­lar cul­ture than “ar­ti­fi­cial in­tell­gien­ce” and “ma­chine learn­ing” — and that has con­cerned some key fig­ures in phar­ma­ceu­ti­cal de­vel­op­ment. But al­though it’s too ear­ly for the AI plat­forms to have brought a drug to mar­ket, ear­ly stud­ies have in­di­cat­ed there could be some­thing be­neath the buzz. That in­cludes last week’s land­mark study from In­sil­i­co in Na­ture Biotech­nol­o­gy, in which over 21 days the com­pa­ny found six mol­e­cules that could be po­ten­tial treat­ments for fi­bro­sis.

At its most ba­sic, ar­ti­fi­cial in­tel­li­gence works like this: You feed an AI sys­tem a vast num­ber of, say, im­ages of a cow and im­ages not of a cow, and you tell it which is which. With each im­age of a cow and not-cow, the AI de­vel­ops a more and more re­fined set of cri­te­ria for what con­sti­tutes a cow (even if that cri­te­ria is far dif­fer­ent from what a hu­man might give). Pret­ty soon it can very ac­cu­rate­ly rec­og­nize whether a new pic­ture has a cow or not. You can al­so do this with, say, an im­age of your mom. It’s how your iPhone’s fa­cial recog­ni­tion works.

And you can do this with a mol­e­cule.

Atom­wise works by what’s called “vir­tu­al screen­ing,” mean­ing it us­es its AI sys­tem to rapid­ly search data­bas­es for mol­e­cules that re­sem­ble what its part­ners are look­ing for. Its June part­ner­ship with Ukraine-based Et­a­mine, the world’s largest chem­i­cal sup­pli­er, gives it ac­cess to a data­base of bil­lions of com­pounds to scan. Atom­wise can scan 10-20 mil­lion per day, up from con­ven­tion­al com­put­er meth­ods that cap out at about 100,000. This lat­est deal with Han­soh will see the com­pa­ny de­sign and dis­cov­er drugs for 11 undis­closed tar­get pro­teins.

How­ev­er, the In­sil­i­co study that grabbed head­lines was for a slight­ly dif­fer­ent form of AI.

This new­er AI, on­ly put forth in 2014, goes fur­ther. Rather than rec­og­niz­ing a face, it can imag­ine a face (or, say, art). The idea In­sil­i­co is bet­ting on and get­ting close to prov­ing is that if it can imag­ine a face, it can imag­ine a drug. Ac­cord­ing­ly, these are called “gen­er­a­tive” net­works, as op­posed to the “con­vo­lu­tion­al” ones Atom­wise us­es.

We’ll use cows again for the mod­el. These new AIs ac­tu­al­ly con­sist of two sys­tems. Loaded with da­ta, the “gen­er­a­tive” one at­tempts to come up with an im­age of a cow. Then a sec­ond one, which is called the “dis­crim­i­na­tor” and works likes the tech de­scribed above, tells the gen­er­a­tive one if it got a cow or not. The gen­er­a­tor learns from the dis­crim­i­na­tor, which learns from the vast store of up­loaded in­for­ma­tion. You have a learn­ing feed­back loop that should even­tu­al­ly gets you a brand new pret­ty pic­ture of a cow.

In the In­sil­i­co study, they were search­ing for a new ty­ro­sine ki­nase in­hibitor for dis­coidin do­main re­cep­tor 1 (DDR1). The sys­tem was taught all DDRI lit­er­a­ture, a larg­er set of ki­nase in­hibitors, data­bas­es of med­i­c­i­nal­ly ac­tive struc­tures and a data­base of struc­tures that have al­ready been patent­ed. The re­sult? 30,000 can­di­date struc­tures, which the com­pa­ny then whit­tled down to 40. They pro­duced 6 of them in the lab, test­ed 2 of them on cells and one on mice.

Promi­nent sci­ence writer and not­ed skep­tic of biotech AI hype Derek Lowe damp­ened the ex­u­ber­ant head­lines, not­ing the DDRI is al­ready well re­searched (cre­at­ing an ide­al sam­ple size to train the neur­al net­works), the dis­cov­er­ies weren’t drugs but pos­si­ble drug tar­gets, and gen­er­al­iz­ing these tech­niques to oth­er drug ar­eas will take years and lots of cash. This ac­cords with a con­sen­sus view of the tri­al as a proof-of-con­cept. Still, he found it one of the most in­ter­est­ing pa­pers he had read on vir­tu­al screen­ing.

“The good news, though, is that there is no rea­son that vir­tu­al screen­ing can’t do great things, even­tu­al­ly,” he wrote in his blog, In the Pipeline. “We just have to get a lot bet­ter at it than we are now, and that’s as true as it was when I first heard about it in the mid-1980s.”

BiTE® Plat­form and the Evo­lu­tion To­ward Off-The-Shelf Im­muno-On­col­o­gy Ap­proach­es

Despite rapid advances in the field of immuno-oncology that have transformed the cancer treatment landscape, many cancer patients are still left behind.1,2 Not every person has access to innovative therapies designed specifically to treat his or her disease. Many currently available immuno-oncology-based approaches and chemotherapies have brought long-term benefits to some patients — but many patients still need other therapeutic options.3

Pfiz­er’s Doug Gior­dano has $500M — and some ad­vice — to of­fer a cer­tain breed of 'break­through' biotech

So let’s say you’re running a cutting-edge, clinical-stage biotech, probably public, but not necessarily so, which could see some big advantages teaming up with some marquee researchers, picking up say $50 million to $75 million dollars in a non-threatening minority equity investment that could take you to the next level.

Doug Giordano might have some thoughts on how that could work out.

The SVP of business development at the pharma giant has helped forge a new fund called the Pfizer Breakthrough Growth Initiative. And he has $500 million of Pfizer’s money to put behind 7 to 10 — or so — biotech stocks that fit that general description.

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 82,100+ biopharma pros reading Endpoints daily — and it's free.

Stephen Isaacs, Aduro president and CEO (Aduro)

Once a high fly­er, a stag­ger­ing Aduro is auc­tion­ing off most of the pipeline as CEO Stephen Isaacs hands off the shell to new own­ers

After a drumbeat of failure, setbacks and reorganizations over the last few years, Aduro CEO Stephen Isaacs is handing over his largely gutted-out shell of a public company to another biotech company and putting up some questionable assets in a going-out-of-business sale.

Isaacs —who forged a string of high-profile Big Pharma deals along the way — has wrapped a 13-year run at the biotech with one program for kidney disease going to the new owners at Chinook Therapeutics. A host of once-heralded assets like their STING agonist program partnered with Novartis (which dumped their work on ADU-S100 after looking over weak clinical results), the Lilly-allied cGAS-STING inhibitor program and the anti-CD27 program out-licensed to Merck will all be posted for auction under a strategic review process.

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 82,100+ biopharma pros reading Endpoints daily — and it's free.

Len Schleifer (left) and George Yancopoulos, Regeneron (Vimeo)

Eyes on he­mo­phil­ia prize, Re­gen­eron adds a $100M wa­ger on joint de­vel­op­ment cam­paign with In­tel­lia

When George Yancopoulos first signed up Intellia to be its CRISPR/Cas9 partner on gene editing projects 4 years ago, the upstart smartly ramped up its IPO at the same time. Today, Regeneron $REGN is coming back in, adding $100 million in an upfront fee and equity to significantly boot up a whole roster of new development projects.

And they’re highlighting some clinical hemophilia research plans in the process.

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 82,100+ biopharma pros reading Endpoints daily — and it's free.

Ken Frazier, AP Images

Why Mer­ck wait­ed, and what they now bring to the Covid-19 fight

Nicholas Kartsonis had been running clinical infectious disease research at Merck for almost 2 years when, in mid-January, he got a new assignment: searching the pharma giant’s vast libraries for something that could treat the novel coronavirus.

The outbreak was barely two weeks old when Kartsonis and a few dozen others got to work, first in small teams and then in a larger task force that sucked in more and more parts of the sprawling company as Covid-19 infected more and more of the globe. By late February, the group began formally searching for vaccine and antiviral candidates to license. Still, while other companies jumped out to announce their programs and, eventually and sometimes controversially, early glimpses at human data, Merck remained silent. They made only a brief announcement about a data collection partnership in April and mentioned vaguely a vaccine and antiviral search in their April 28 earnings call.

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 82,100+ biopharma pros reading Endpoints daily — and it's free.

Mark Genovese (Stanford via Twitter)

Gilead woos fil­go­tinib clin­i­cal in­ves­ti­ga­tor from Stan­ford to lead the charge on NASH, in­flam­ma­to­ry dis­eases

With an FDA OK for the use of filgotinib in rheumatoid arthritis expected to drop any day now, Gilead has recruited a new leader from academia to lead its foray into inflammatory diseases.

Mark Genovese — a longtime Stanford professor and most recently the clinical chief in the division of immunology and rheumatology — was the principal investigator in FINCH 2, one of three studies that supported Gilead’s NDA filing. In his new role as SVP, inflammation, he will oversee the clinical development of the entire portfolio.

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 82,100+ biopharma pros reading Endpoints daily — and it's free.

Hill­house re­casts spot­light on Chi­na's biotech scene with $160M round for Shang­hai-based an­ti­body mak­er

Almost two years after first buying into Genor Biopharma’s pipeline of cancer and autoimmune therapies, Hillhouse Capital has led a $160 million cash injection to push the late-stage assets over the finish line while continuing to fund both internal R&D and dealmaking.

The Series B has landed right around the time Genor would have listed on the Hong Kong stock exchange, according to plans reported by Bloomberg late last year. Insiders had said that the company was looking to raise about $200 million.

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 82,100+ biopharma pros reading Endpoints daily — and it's free.

Fangliang Zhang (Imaginechina via AP Images)

The big mon­ey: Poised to make drug R&D his­to­ry, a Chi­na biotech un­veils uni­corn rac­ing am­bi­tions in a bid to raise $350M-plus on Nas­daq

Almost exactly three years after Shanghai-based Legend came out of nowhere to steal the show at ASCO with jaw-dropping data on their BCMA-targeted CAR-T for multiple myeloma, the little player with Big Pharma connections is taking a giant step toward making it big on Wall Street. And this time they want to seal the deal on a global rep after staking out a unicorn valuation in what’s turned out to be a bull market for biotech IPOs — in the middle of a pandemic.

Endpoints Premium

Premium subscription required

Unlock this article along with other benefits by subscribing to one of our paid plans.

Federico Mingozzi (Spark)

Spark touts an­i­mal da­ta for a so­lu­tion to AAV gene ther­a­py's an­ti­body prob­lem

Among all the limitations of using an adeno-associated virus as a vector to deliver a gene — still the most established modality in gene therapy given years of trial and error and finally success — the presence of neutralizing antibodies, whether pre-existing or induced, looms large.

“When I think about the immune responses in AAV, I try to sort of layer them,” Federico Mingozzi, the CSO at Spark Therapeutics, told Endpoints News. “The antibody is the first layer. It’s the first block that you find when you’re trying to do gene transfer.”