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.”

Sean Parker, AP

Sean Park­er helps cre­ate a CRISPRed cell ther­a­py 2.0 play — and he’s got a high-pro­file set of lead­ers on the team

You can rack up one more high-profile debut effort in the wave of activity forming around cell therapy 2.0. It’s another appealing Bay Area group that’s attracted some of the top hands in the business to a multi-year effort to create a breakthrough. And they have $85 million in hand to make that first big step to the clinic.

Today it’s Ken Drazan and the team at South San Francisco-based ArsenalBio that are coming from behind the curtain for a public bow, backed by billionaire Sean Parker and a collection of investors that includes Beth Seidenberg’s new venture investment operation based in LA.
Drazan — a J&J Innovation vet with a long record of entrepreneurial endeavors — exited the stage in 2018 when his last mission ended as he stepped aside as president of Grail. It wasn’t long, though, before he was helping out with a business plan for ArsenalBio that revolved around the work of a large group of interconnected scientists supported by the Parker Institute for Cancer Immunology.

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 62,400+ biopharma pros reading Endpoints daily — and it's free.

Alice Shaw, Lung Cancer Foundation of America

Top ALK ex­pert and can­cer drug re­searcher Al­ice Shaw bids adieu to acad­e­mia, hel­lo to No­var­tis

Jay Bradner has recruited a marquee oncology drug researcher into the ranks of the Novartis Institutes for BioMedical Research. Alice Shaw is jumping from prestigious posts intertwined through Mass General, Harvard and Dana-Farber to take the lead of NIBR’s translational clinical oncology group.

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 62,400+ biopharma pros reading Endpoints daily — and it's free.

Flu Virus (Source: CDC)

FDA ex­pands Xofluza ap­proval as Roche strug­gles to catch loom­ing flu mar­ket

As a potentially powerful flu season looms, so does a big test for Roche and its new flu drug, Xofluza. The Swiss giant just got a small boost in advance of that test as the FDA expanded Xofluza’s indication to include patients at high risk of developing flu-related complications.

Xofluza (baloxavir marboxil) was approved last October in the US, the first landmark flu drug approval in 20 years and a much-needed green light for a company that had watched its leading flu drug Tamiflu get eaten alive by generics. Like its predecessor, the pill offered a reduction in flu symptoms but not a cure.

Mi­rati preps its first look at their KRAS G12C con­tender, and they have to clear a high bar for suc­cess

If you’re a big KRAS G12C fan, mark your calendars for October 28 at 4:20 pm EDT.

That’s when Mirati $MRTX will unveil its first peek at the early clinical data available on MRTX849 in presentations at the AACR-NCI-EORTC International Conference on Molecular Targets and Cancer Therapeutics in Boston.

Mirati has been experiencing the full effect of a rival’s initial success at targeting the G12C pocket found on KRAS, offering the biotech some support on the concept they’re after — and biotech fans a race to the top. Amgen made a big splash with its first positive snapshot on lung cancer, but deflated sky-high expectations as it proved harder to find similar benefits in other types of cancers.

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 62,400+ biopharma pros reading Endpoints daily — and it's free.

The FDA will hus­tle up an ex­pe­dit­ed re­view for As­traZeneca’s next shot at a block­buster can­cer drug fran­chise

AstraZeneca paid a hefty price to partner with Daiichi Sankyo on their experimental antibody drug conjugate for HER2 positive breast cancer. And they’ve been rewarded with a fast ride through the FDA, with a straight shot at creating another blockbuster oncology franchise.

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 62,400+ biopharma pros reading Endpoints daily — and it's free.

Med­ical an­i­ma­tion: Mak­ing it eas­i­er for the site and the pa­tient to un­der­stand

Medical animation has in recent years become an increasingly important tool for conveying niche information to a varied audience, particularly to those audiences without expertise in the specialist area. Science programmes today, for example, have moved from the piece-to-camera of the university professor explaining how a complex disease mechanism works, to actually showing the viewer first-hand what it might look like to shrink ourselves down to the size of an ant’s foot, and travel inside the human body to witness these processes in action. Effectively communicating a complex disease pathophysiology, or the novel mechanism of action of a new drug, can be complex. This is especially difficult when the audience domain knowledge is limited or non-existent. Medical animation can help with this communication challenge in several ways.
Improved accessibility to visualisation
Visualisation is a core component of our ability to understand a concept. Ask 10 people to visualise an apple, and each will come up with a slightly different image, some apples smaller than others, some more round, some with bites taken. Acceptable, you say, we can move on to the next part of the story. Now ask 10 people to visualise how HIV’s capsid protein gets arranged into the hexamers and pentamers that form the viral capsid that holds HIV’s genetic material. This request may pose a challenge even to someone with some virology knowledge, and it is that inability to effectively visualise what is going on that holds us back from fully understanding the rest of the story. So how does medical animation help us to overcome this visualisation challenge?

Hal Barron, GSK's president of R&D and CSO, speaks to Endpoints News founder and editor John Carroll in London at Endpoints' #UKBIO19 summit on October 8, 2019

[Video] Cel­e­brat­ing tri­al fail­ures, chang­ing the cul­ture and al­ly­ing with Cal­i­for­nia dream­ers: R&D chief Hal Bar­ron talks about a new era at GSK

Last week I had a chance to sit down with Hal Barron at Endpoints’ #UKBIO19 summit to discuss his views on R&D at GSK, a topic that has been central to his life since he took the top research post close to 2 years ago. During the conversation, Barron talked about changing the culture at GSK, a move that involves several new approaches — one of which involves celebrating their setbacks as they shift resources to the most promising programs in the pipeline. Barron also discussed his new alliances in the Bay Area — including his collaboration pact with Lyell, which we covered here — frankly assesses the pluses and minuses of the UK drug development scene, and talks about his plans for making GSK a much more effective drug developer.

This is one discussion you won’t want to miss. Insider and Enterprise subscribers can log-in to watch the video.

Endpoints Premium

Premium subscription required

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

EMA backs sev­en ther­a­pies, in­clud­ing Mer­ck­'s Ebo­la vac­cine

The first-ever Ebola vaccine is on the precipice of approval after the European Medicine’s Agency (EMA) backed the Merck product in this week’s roster of recommendations.

The drugmaker $MRK began developing the vaccine, christened Ervebo, during the West African outbreak that occurred between 2014 and 2016, killing more than 11,000.

The current outbreak in the Democratic Republic of Congo (DRC) has shown case fatality rates of approximately 67%, the agency estimated. Earlier this year, the WHO declared the outbreak — which so far has infected more than 3,000 people — a public health emergency of international concern.

Ronald Herb­st fol­lows Med­Im­mune ex­o­dus to Pyx­is CSO post; Jeff God­dard to suc­ceed CEO of AIT Bio­science

→ The outflow of top execs from MedImmune continues to fill the leadership ranks of smaller biotechs. The latest to take off is Ronald Herbst, the head of oncology research, who’s assuming the CSO post at Pyxis Oncology.  

Herbst was part of the old MedImmune organization AstraZeneca CEO Pascal Soriot restructured earlier this year, reorganizing the company and eliminating the storied subsidiary as a separate organization.

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 62,400+ biopharma pros reading Endpoints daily — and it's free.