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?

Con­quer­ing a silent killer: HDV and Eiger Bio­Phar­ma­ceu­ti­cals

Hepatitis delta, also known as hepatitis D, is a liver infection caused by the hepatitis delta virus (HDV) that results in the most severe form of human viral hepatitis for which there is no approved therapy.

HDV is a single-stranded, circular RNA virus that requires the envelope protein (HBsAg) of the hepatitis B virus (HBV) for its own assembly. As a result, hepatitis delta virus (HDV) infection occurs only as a co-infection in individuals infected with HBV. However, HDV/HBV co-infections lead to more serious liver disease than HBV infection alone. HDV is associated with faster progression to liver fibrosis (progressing to cirrhosis in about 80% of individuals in 5-10 years), increased risk of liver cancer, and early decompensated cirrhosis and liver failure.
HDV is the most severe form of viral hepatitis with no approved treatment.
Approved nucleos(t)ide treatments for HBV only suppress HBV DNA, do not appreciably impact HBsAg and have no impact on HDV. Investigational agents in development for HBV target multiple new mechanisms. Aspirations are high, but a functional cure for HBV has not been achieved nor is one anticipated in the forseeable future. Without clearance of HBsAg, anti-HBV investigational treatments are not expected to impact the deadly course of HDV infection anytime soon.

Am­gen chops 172 more staffers in R&D, op­er­a­tions and sales amid neu­ro­science ex­it, rev­enue down­turn

Neuroscience wasn’t the only unit that’s being hit by a reorganization underway at Amgen. As well as axing 149 employees in its Cambridge office, the company has disclosed that 172 others nationwide, including some from its Thousand Oaks, CA headquarters, are being let go.

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 66,100+ biopharma pros reading Endpoints daily — and it's free.

Ahead of strate­gic up­date, new Sanofi CEO mulls op­tions for con­sumer health­care arm — re­ports

Big pharma has made moves to sharpen its focus on developing new medicines, while slow-growing consumer health divisions fall by the wayside. Looks like another large drugmaker is considering a similar move. On Thursday, reports citing sources indicated that Sanofi is reportedly mulling a joint venture, sale, or a public listing of its consumer health arm.

The French group is in discussions for options that could value the division at $30 billion, Bloomberg and Reuters reported, citing sources familiar with the matter.

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 66,100+ biopharma pros reading Endpoints daily — and it's free.

The triple crown in biotech: An all-or-noth­ing bet on an FDA ap­proval of 3 drugs over 16 months starts to­day

Bristol-Myers Squibb’s $74 billion Celgene deal closed as expected Wednesday evening. And now a new clock has begun to tick down for Celgene shareholders who came away from the deal with CVRs — contingent value rights — worth $9 or nothing. Those CVRs start trading today as $BMYRT.

The new deadline they have is the end of March 2021, a little more than 16 months from now, when Bristol-Myers will need to gain approvals on 3 late-stage drugs it’s picking up in the buyout: Ozanimod and liso-cel (JCAR017) are due up at the end of 2020, with bb2121 deadlined at the end of Q1 in 2021.

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 66,100+ biopharma pros reading Endpoints daily — and it's free.

Genap­sys fi­nal­ly un­veils vaunt­ed se­quencer, but can it dent Il­lu­mi­na?

Hesaam Esfandyarpour holds what looks like a mini-cooler up to the computer screen in his California office.

Esfandyarpour is in his late-30s, with crows feet creeping up against a youthful face. He wears a gray polo and the device in his hand — with its hard plastic-looking shell, blue-and-white pattern, and a white plastic paddle resembling a handle jutting out the front — might contain diced strawberries and peanut-butter sandwiches to meet mom and the kids at a SoCal park. Instead, Esfandyarpour tells me it’s going to change medicine and biopharma research.

UP­DAT­ED: Make that 2 ap­proved RNAi drugs at Al­ny­lam af­ter the FDA of­fers a speedy OK on ul­tra-rare dis­ease drug

Seventeen years into the game, Alnylam’s pivot into commercial operations is picking up speed.
The bellwether biotech $ALNY has nabbed their second FDA OK for an RNAi drug, this time for givosiran, the only therapy now approved for acute hepatic porphyria. This second approval came months ahead of the February deadline — even after winning priority review following their ‘breakthrough’ title earlier.
AHP is an extremely rare disease, with some 3,000 patients in Europe and the US, not all diagnosed, and analysts have projected peak revenue of $600 million to $700 million a year. The drug will be sold as Givlaari.

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 66,100+ biopharma pros reading Endpoints daily — and it's free.

David Ricks. Eli Lilly

Eli Lil­ly touts $400M man­u­fac­tur­ing ex­pan­sion, 100 new jobs to much fan­fare in In­di­anapo­lis — even though it's been chop­ping staff

Eli Lilly is pouring in $400 million to beef up manufacturing facilities at its home base of Indianapolis. The investment, which was lauded by the city’s mayor, is expected to create 100 new jobs.

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 66,100+ biopharma pros reading Endpoints daily — and it's free.

Brii Bio backs in­fec­tious dis­ease start­up while ink­ing deal for its lead TB drug, dou­bling down on an­tibi­otics

Almost two years after leaving GSK to launch Brii Bio with a whopping $260 million in funding, Zhi Hong is seeing the trans-Pacific infectious disease specialist he set out to build take shape.

“Our pipeline is coming together,” he told Endpoints News, with 12 partnered assets plus some internal programs.

As its latest partner, AN2 Therapeutics, comes into the limelight for the first time with a $12 million seed round, so is Brii’s plans in the antibiotics space. Brii has obtained China rights to AN2’s antibacterial targeting mycobacterium tuberculosis for multi-drug resistant TB, which it says is in the clinical stage.

No­var­tis, Bay­er, Long­wood back ge­nomics start­up to speed search for im­munother­a­py tar­gets

Nearly a century passed between the first proto-immunotherapy attempts in cancer — crude and obscure but nonetheless with some scientific basis — and Jim Allison’s first T cell paper. Thirty-plus years flipped between the discovery of CTLA-4 as an off-switch and the approval of Yervoy. Twenty-two rolled between PD-1’s isolation and Opdiva and Keytruda. 

Longwood co-founder Lea Hachigian is betting she can hasten that. It’s a bet on newly established single-cell genomic analysis tech and the ability to crunch endless troves of data at a rate few others can, and investors including Leaps by Bayer and Novartis Venture Fund just put $39 million behind it. They call it Immunitas.