Alex Zhavoronkov, Insilico

AI study led by In­sil­i­co's Alex Zha­voronkov bol­sters case for faster, cheap­er drug dis­cov­ery

Drug de­vel­op­ment is an ar­du­ous and ex­pen­sive busi­ness. The promise of ar­ti­fi­cial in­tel­li­gence is that ma­chines can wean man­u­fac­tur­ers away from the breadth of re­sources it takes to dis­cov­er a po­ten­tial­ly po­tent com­pound, and lever­age the med­ical con­di­tions it could be used to treat. Alex Zha­voronkov, whose Hong Kong-based AI-shop In­sil­i­co Med­i­cine has en­trenched it­self in the ten­ta­cles of bio­phar­ma R&D, now has some da­ta to bol­ster the fer­vor and in­vest­ment that AI has drummed up.

On Mon­day, Zha­voronkov and his fel­low AI scouts from Wuxi and sci­en­tists from the Uni­ver­si­ty of Toron­to, pub­lished a pa­per in Na­ture Biotech­nol­o­gy that sup­port­ed the fea­si­bil­i­ty of em­ploy­ing a ma­chine learn­ing ap­proach — gen­er­a­tive ad­ver­sar­i­al net­works (GANs) and re­in­force­ment learn­ing — for de no­vo drug de­sign. The re­searchers found that they were able to iden­ti­fy a myr­i­ad of com­pounds tar­get­ing a pro­tein called Dis­coidin do­main re­cep­tor 1 (DDR1) — which is ex­pressed in ep­ithe­lial cells and in­volved in fi­bro­sis — in a swift 21 days.

Af­ter that, six mol­e­cules were then se­lect­ed for syn­the­sis in the lab — those tests re­vealed four with po­ten­tial. Fur­ther test­ing whit­tled it down to one com­pound, which was test­ed in mice. That da­ta sug­gest­ed the mol­e­cule con­ferred a po­tent ef­fect against the pro­tein — al­though much like any oth­er com­pound, its safe­ty and ef­fi­ca­cy must be val­i­dat­ed in hu­man tri­als.

This study, which was con­duct­ed in re­sponse to a chal­lenge set by a part­ner com­pa­ny, is a taste of things to come, Zha­voronkov not­ed in an in­ter­view with End­points News. The plan was to take an al­go­rithm de­vel­oped a few years ago — an al­go­rithm that is open­ly avail­able, and use it as a proof-of-con­cept to demon­strate the po­ten­tial for AI in drug dis­cov­ery, he as­sert­ed.

“Imag­ine…Pfiz­er putting out all of their pre­clin­i­cal stuff for free for every­body to use, right? They won’t do it. Or J&J putting out all of their da­ta, even the old stuff? They just don’t do it. We de­cid­ed to kind of do a de­mo. So the skep­tics are… a lit­tle bit less skep­ti­cal.”

Re­cent es­ti­mates by the Tufts Cen­ter for the Study of Drug de­vel­op­ment main­tain that tak­ing a drug all the way from dis­cov­ery to ap­proval costs rough­ly $2.6 bil­lion (in 2013 dol­lars). Steven Paul, cur­rent Karuna chief,  pub­lished a study in 2010 in which he high­light­ed the mag­ni­tude of re­sources it cost his for­mer em­ploy­er Eli Lil­ly $LLY to dis­cov­er new com­pounds: the out-of-pock­et cost for lead op­ti­miza­tion came to a hefty $146 mil­lion.

“In this work, we de­signed, syn­the­sized, and ex­per­i­men­tal­ly val­i­dat­ed mol­e­cules tar­get­ing DDR1 ki­nase in less than 2 months and for a frac­tion of the cost as­so­ci­at­ed with a tra­di­tion­al drug dis­cov­ery ap­proach. This il­lus­trates the util­i­ty of our deep gen­er­a­tive mod­el for the suc­cess­ful, rapid de­sign of com­pounds that are syn­thet­i­cal­ly fea­si­ble, ac­tive against a tar­get of in­ter­est, and po­ten­tial­ly in­no­v­a­tive with re­spect to ex­ist­ing in­tel­lec­tu­al prop­er­ties,” Zha­voronkov et al wrote in their pa­per.

Zha­voronkov com­pared the study to Al­pha­Go — the first com­put­er pro­gram de­vel­oped by Al­pha­bet’s AI com­pa­ny Deep­Mind and im­mor­tal­ized in a Net­flix doc­u­men­tary — to de­feat a pro­fes­sion­al hu­man Go play­er. Go, which orig­i­nat­ed in Chi­na over 3,000 years ago, is a de­cep­tive­ly sim­ple strate­gic think­ing board game that has an in­cred­i­ble 10 to the pow­er of 170 pos­si­ble board con­fig­u­ra­tions (which is more than the num­ber of atoms in the known uni­verse.)

“We kind of thought about this pa­per as a kind of mi­ni Al­pha­Go,” Zha­voronkov said. “I hope that the big ex­ec­u­tives will al­so kind of hear this and un­der­stand that…we ac­tu­al­ly put the en­tire dis­cov­ery process on dis­play.”

“Every sec­ond stu­dent in Chi­na wants to be an AI sci­en­tist…this (Al­pha­Go) mir­a­cle might not have im­pact­ed their lives sig­nif­i­cant­ly, but it re­al­ly changed the men­tal­i­ty for every­body,” he added. “So that is what we need in phar­ma. Peo­ple should fo­cus less on geopol­i­tics or…war­fare. This is the stuff to watch right on TV. This is the cool thing.”

A pla­toon of bio­phar­mas have linked up with the emerg­ing crop of AI spe­cial­ists itch­ing to cap­i­tal­ize on how large datasets can be har­nessed to dri­ve new ther­a­pies in­to the clin­ic. Zha­voronkov is well con­nect­ed — last year he raised funds at the be­hest of Shang­hai high-fly­er WuXi AppTec, Sin­ga­pore’s Temasek, Pe­ter Dia­man­dis and Ju­ve­nes­cence.

Iso­lat­ing com­pounds for de­vel­op­ment is one as­pect of the bal­loon­ing AI in­dus­tri­al com­plex — it al­so has ap­peal in an­oth­er is­sue drug de­vel­op­ers reg­u­lar­ly con­tend with — the low odds of suc­cess, even with com­pounds that show great po­ten­tial in ear­ly test­ing. Then there’s the gold­en ques­tion — even if AI can help make the process of drug de­vel­op­ment bet­ter, faster and cheap­er — will that trans­late to less ex­pen­sive treat­ments?

Up­dat­ed: FDA re­mains silent on or­phan drug ex­clu­siv­i­ty af­ter last year's court loss

Since losing a controversial court case over orphan drug exclusivity last year, the FDA’s Office of Orphan Products Development has remained entirely silent on orphan exclusivity for any product approved since last November, leaving many sponsors in limbo on what to expect.

That silence means that for more than 70 orphan-designated indications for more than 60 products, OOPD has issued no public determination on the seven-year orphan exclusivity in the Orange Book, and no new listings of orphan exclusivity appear in OOPD’s searchable database, as highlighted recently by George O’Brien, a partner in Mayer Brown’s Washington, DC office.

Illustration: Assistant Editor Kathy Wong for Endpoints News

As mon­ey pours in­to dig­i­tal ther­a­peu­tics, in­sur­ance cov­er­age crawls



Talk therapy didn’t help Lily with attention deficit hyperactivity disorder, or ADHD. But a video game did.

As the 10-year-old zooms through icy waters and targets flying creatures on the snow-capped planet Frigidus, she builds attention skills, thanks to Akili Interactive Labs’ video game EndeavorRx. She’s now less anxious and scattered, allowing her to stay on a low dose of ADHD medication, according to her mom Violet Vu.

Endpoints Premium

Premium subscription required

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

Eli Lil­ly’s Alzheimer’s drug clears more amy­loid ear­ly than Aduhelm in first-ever head-to-head. Will it mat­ter?

Ahead of the FDA’s decision on Eli Lilly’s Alzheimer’s drug donanemab in February, the Big Pharma is dropping a first cut of data from one of the more interesting trials — but less important in a regulatory sense — at an Alzheimer’s conference in San Francisco.

In the unblinded 148-person study, Eli Lilly pitted its drug against Aduhelm, Biogen’s drug that won FDA approval but lost Medicare coverage outside of clinical trials. Notably, the study didn’t look at clinical outcomes, but rather the clearance of amyloid, a protein whose buildup is associated with Alzheimer’s disease, in the brain.

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 153,900+ biopharma pros reading Endpoints daily — and it's free.

Ei­sai’s ex­pand­ed Alzheimer’s da­ta leave open ques­tions about safe­ty and clin­i­cal ben­e­fit

Researchers still have key questions about Eisai’s investigational Alzheimer’s drug lecanemab following the publication of more Phase III data in the New England Journal of Medicine Tuesday night.

In the paper, which was released in conjunction with presentations at an Alzheimer’s conference, trial investigators write that a definition of clinical meaningfulness “has not been established.” And the relative lack of new information, following topline data unveiled in September, left experts asking for more — setting up a potential showdown to precisely define how big a difference the drug makes in patients’ lives.

Endpoints Premium

Premium subscription required

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

Lynn Baxter, Viiv Healthcare's head of North America

Vi­iV dri­ves new cor­po­rate coali­tion in­clud­ing Uber, Tin­der and Wal­mart, aimed at end­ing HIV

ViiV Healthcare is pulling together an eclectic coalition of consumer businesses in a new White House-endorsed effort to end HIV by the end of the decade.

The new US Business Action to End HIV includes pharma and health companies — Gilead Sciences, CVS Health and Walgreens — but extends to a wide range of consumer companies that includes Tinder, Uber and Walmart.

ViiV is the catalyst for the group, plunking down more than half a million dollars in seed money and taking on ringmaster duties for launch today on World AIDS Day, but co-creator Health Action Alliance will organize joint activities going forward. ViiV and the alliance want and expect more companies to not only join the effort, but also pitch in funding.

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 153,900+ biopharma pros reading Endpoints daily — and it's free.

Matt Gline, Roivant Sciences CEO (Photo by John Sciulli/Getty Images for GLG)

Pfiz­er and Roivant team up again for an­oth­er 'Van­t', set­ting up an­ti-in­flam­ma­to­ry show­down with Prometheus

Pfizer and Roivant are teaming up to launch a new ‘Vant’ aimed at bringing a mid-stage anti-inflammatory drug to market, the pair announced Thursday.

There’s no name for the startup yet, nor are there any employees. Thus far, the new company and Roivant can be considered “one and the same,” Roivant CEO Matt Gline tells Endpoints News. But Pfizer is so enthusiastic about the target that it elected to keep 25% of equity in the drug rather than take upfront cash from Roivant, Gline said.

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 153,900+ biopharma pros reading Endpoints daily — and it's free.

Roche HQ in Basel, Switzerland. (Image credit: Kyle LaHucik/Endpoints News)

As com­peti­tors near FDA goal­post, Roche spells out its re­peat Alzheimer's set­back

Before Roche can turn all eyes on a new version of its more-than-once-failed Alzheimer’s drug gantenerumab, the Big Pharma had to flesh out data on the November topline failure at an annual conference buzzier than in years past thanks to hotly watched rivals in the field: Eisai and Biogen’s lecanemab, and Eli Lilly’s donanemab.

There was less than a 10% difference between Roche’s drug and placebo at slowing cognitive decline across two Phase III trials, which combined enrolled nearly 2,000 Alzheimer’s patients. In its presentation at the conference Wednesday, Roche said it saw less sweeping away of toxic proteins than it had anticipated. For years, researchers and investors have put their resources behind the idea that more amyloid removal would equate to reduced cognitive decline.

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 153,900+ biopharma pros reading Endpoints daily — and it's free.

SQZ Biotech slash­es head­count by 60% as founder/CEO hits ex­it — while Syn­log­ic lays off 25%

It’s a tough time for early-stage companies developing highly promising, but largely unproven, new technologies.

Just ask SQZ Biotechnologies and Synlogic. The former is bidding farewell to its founder and CEO and slashing the headcount by 60% as it pivots from its original cell therapy platform to a next-gen approach; the latter — a synthetic biology play founded by MIT’s Jim Collins and Tim Lu — is similarly “optimizing” the company to focus on lead programs. The resulting realignment means 25% of the staffers will be laid off.

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 153,900+ biopharma pros reading Endpoints daily — and it's free.

Illustration: Assistant Editor Kathy Wong for Endpoints News

Twit­ter dis­ar­ray con­tin­ues as phar­ma ad­ver­tis­ers ex­tend paus­es and look around for op­tions, but keep tweet­ing

Pharma advertisers on Twitter are done — at least for now. Ad spending among the previous top spenders flattened even further last week, according to the latest data from ad tracker Pathmatics, amid ongoing turmoil after billionaire boss Elon Musk’s takeover now one month ago.

Among 18 top advertisers tracked for Endpoints News, only two are spending: GSK and Bayer. GSK spending for the full week through Sunday was minimal at just under $1,900. Meanwhile, German drugmaker Bayer remains the industry outlier upping its spending to $499,000 last week from $480,000 the previous week. Bayer’s spending also marks a big increase from a month ago and before the Musk takeover, when it spent $16,000 per week.

Endpoints Premium

Premium subscription required

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