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.”

Scott Gottlieb, AP Images

Scott Got­tlieb is once again join­ing a team that en­joyed good times at the FDA un­der his high-en­er­gy stint at the helm

Right after jumping on Michael Milken’s FasterCures board on Monday, the newly departed FDA commissioner is back today with news about another life sciences board post that gives him a ringside chair to cheer on a lead player in the real-world evidence movement — one with very close ties to the FDA.

Aetion is reporting this morning that Gottlieb is joining their board, a group that includes Mohamad Makhzoumi, a general partner at New Enterprise Associates, where Gottlieb returned after stepping out of his role at the FDA 2 years after he started.

Gottlieb — one of the best connected execs in biopharma — knows this company well. As head of FDA he championed the use of real-world evidence to help guide drug developers and the agency in gaining greater efficiencies, which helped set up Aetion as a high-profile player in the game.

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 59,600+ biopharma pros reading Endpoints daily — and it's free.

Deborah Dunsire. Lundbeck

UP­DAT­ED: Deb­o­rah Dun­sire is pay­ing $2B for a chance to leap di­rect­ly in­to a block­buster show­down with a few of the world's biggest phar­ma gi­ants

A year after taking the reins as CEO of Lundbeck, Deborah Dunsire is making a bold bid to beef up the Danish biotech’s portfolio of drugs in what will likely be a direct leap into an intense rivalry with a group of giants now carving up a growing market for new migraine drugs.

Bright and early European time Monday morning the company announced that it will pay up to about $2 billion to buy Alder, a little biotech that is far along the path in developing a quarterly IV formulation of a CGRP drug aimed at cutting back the number of crippling migraines patients experience each month. In a followup call, Dunsire also noted that the company will likely need 200 to 250 reps for this marketing task on both sides of the Atlantic. And analysts were quick to note that the dealmaking at Lundbeck isn’t done, with another $2 billion to $3 billion available for more deals to beef up the pipeline.

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 59,600+ biopharma pros reading Endpoints daily — and it's free.

Tower Bridge in London [Shutterstock]

#UK­BIO19: Join GSK’s Hal Bar­ron and a group of top biotech ex­ecs for our 2nd an­nu­al biotech sum­mit in Lon­don

Over the past 10 years I’ve made a point of getting to know the Golden Triangle and the special role the UK biopharma industry plays there in drug development. The concentration of world class research institutes, some of the most accomplished scientists I’ve ever seen at work and a rising tide of global investment cash leaves an impression that there’s much, much more to come as biotech hubs are birthed and nurtured.

San Diego cou­ple charged with steal­ing trade se­crets, open­ing Chi­nese biotech as DOJ crack­down con­tin­ues

A San Diego couple has been charged with stealing trade secrets from a US hospital and opening a business based off those secrets in China as the controversial industry-wide crackdown on alleged corporate espionage continues. On the same day, the Department of Justice announced they had arrested Beijing representative Zhongsan Liu for allegedly trying to obtain research visas for government recruiters.

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 59,600+ biopharma pros reading Endpoints daily — and it's free.

UP­DAT­ED: Bio­gen pulls the plug on prized IPF drug from $562M+ Stromedix buy­out

One of Biogen’s attempts to branch out has flopped as the biotech scraps a mid-stage program for idiopathic pulmonary fibrosis.

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 59,600+ biopharma pros reading Endpoints daily — and it's free.

Warts for the win: Aclar­is' lead drug clears piv­otal study

Aclaris Therapeutics has found a way to get rid of the warts and all.

The company — which earlier this month decided to focus on its arsenal of kinase inhibitors — on Monday unveiled positive data from a pivotal study testing its lead experimental drug for use in common warts.

The drug, A-101, was tested in a 502-patient study called THWART-2 — patients enrolled had one to six warts before qualifying for the trial. Patients either self-administered A-101 topical solution or a vehicle twice a week over a two-month period. A higher proportion of patients on the drug (a potent hydrogen peroxide topical solution) saw their warts disappear at day 60, versus the vehicle (p<0.0001) — meeting the main goal of the study.  Each secondary endpoint also emerged in favor of A-101, the company said.

Charles Nichols, LSU School of Medicine

Could psy­che­delics tack­le the obe­si­ty cri­sis? A long­time re­searcher in the field says his lat­est mouse study sug­gests po­ten­tial

Psychedelics have experienced a renaissance in recent years amid a torrent of preclinical and clinical research suggesting it might provide a path to treat mood disorders conventional remedies have only scraped at. Now a preclinical trial from a young biotech suggests at least one psychedelic compound has effects beyond the mind, and — if you believe the still very, very early hype — could provide the first single remedy for some of the main complications of obesity.

It’s fi­nal­ly over: Bio­gen, Ei­sai scrap big Alzheimer’s PhI­I­Is af­ter a pre­dictable BACE cat­a­stro­phe rais­es safe­ty fears

Months after analysts and investors called on Biogen and Eisai to scrap their BACE drug for Alzheimer’s and move on in the wake of a string of late-stage failures and rising safety fears, the partners have called it quits. And they said they were dropping the drug — elenbecestat — after the independent monitoring board raised concerns about…safety.

We don’t know exactly what researchers found in this latest catastrophe, but the companies noted in their release that investigators had determined that the drug was flunking the risk/benefit analysis.

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 59,600+ biopharma pros reading Endpoints daily — and it's free.

Ac­celeron drops a de­vel­op­ment pro­gram as #2 drug fails to spark func­tion­al ben­e­fits in pa­tients with a rare neu­ro­mus­cu­lar ail­ment

Acceleron is scrapping a muscular dystrophy development program underway for its number 2 drug in the pipeline after pouring over some failed mid-stage secondary data.

Gone is the ACE-083 project in patients with facioscapulohumeral muscular dystrophy. Their drug hit the primary endpoint on building muscle but flopped on key secondaries for functional improvements in patients, which execs felt was vital to the drug’s success.