Zero-Shot Moonshot: Absci Uses AI Platform to Create and Validate de novo Antibodies
Absci said it achieved its results through its zero-shot generative AI method, which designs antibodies to bind to specific targets without incorporating…
The milestone, Absci asserts, may finally deliver what drug developers have long promised, namely the ability to slash the time it takes to develop new drugs, and thus lower the cost of developing treatments as they reach the market—a reduction the company says could also lead to lower-cost treatments for patients. Absci says its AI-designed antibodies can cut drug development timeframes by more than 50%, from as much as six years down to 18-24 months, while also increasing their probability of success in the clinic.
Absci said it achieved its results through its zero-shot generative AI method, which designs antibodies to bind to specific targets without incorporating any training data on antibodies that are known to bind those targets, forcing the model to design the antibody from scratch. Absci said its model produced antibody designs that were unlike those found in existing antibody databases, and which worked in lab tests without the need for first optimizing the in silico designs.
The company’s wet lab validated the superiority of its de novo antibody candidates to bind to human epidermal growth factor receptor 2 (HER2) and three additional targets—human vascular endothelial growth factor A (VEGF-A), the Omicron variant of SARS-CoV-2 spike receptor-binding domain (COVID-19), and a third, undisclosed target.
“We didn’t want to just show that it could work with just one, but the technology was broadly applicable to really any type of target you want it to work on,” Absci Founder and CEO Sean McClain told GEN Edge.
Added Joshua Meier, Absci Senior VP and Chief AI Officer “This is our moonshot effort. People were telling us this was impossible to do,” Meier added.
In the preprint, Meier and a team of 34 co-authors wrote that while the primary focus of their research was the in silico design of HCDR3, fully de novo antibody design will require the generation of multiple antibody CDR regions.
Initial progress
“We show initial progress toward this goal with a multi-step generative AI approach for designing all three heavy chain CDRs (HCDR1, HCDR2, HCDR3),” Meier and colleagues reported in the preprint. “Taken together, this work paves the way for rapid progress toward fully de novo antibody design using generative AI, which has the potential to revolutionize the availability of therapeutics for patients.”
Meier and colleagues added that their future work “will expand generative design to enable the de novo design of all CDRs and framework regions, further diversifying possible binding solutions.”
“Developing epitope-specificity across multiple antigens for antibody designs could allow for precise interaction with biologically relevant target regions associated with disease mechanisms of action. In addition to advancements on the generative modeling front, the speed and scale of wet lab validation for AI-generated designs will progressively increase as the time and cost of DNA synthesis continue to decline,” Meier and co-authors predicted. “The controllability of AI-designed antibodies will enable the creation of customized molecules for specific disease targets, leading to safer and more efficacious treatments than would be possible by traditional development approaches.”
Absci said the milestone also marked the first instance of a generative AI engine designing new therapeutic antibodies by designing the heavy chain complementarity determining region 3 (HCDR3) from scratch with generative AI methods using trastuzumab and its target antigen, HER2, as a model system.
“We actually went out after the hardest CDR to work on,” Meier said. He noted that of the six CDRs that serve as the key area for antigen binding and the main area of structural variation in antibodies, CDR3 is the region on the antibody that has the highest sequence diversity in immune repertoires and high density of paratope residues. “If you look across different antibodies, it’s the one that’s most involved in binding, and it’s historically been the one that’s hardest to model with machine learning methods as well.”
440,000 Antibody variants
Absci’s lab designed de novo, then screened approximately 440,000 antibody variants designed for binding to HER2 using its proprietary high-throughput Activity-specific Cell-Enrichment (ACE) assay. From these screens, Absci further characterized 421 binders using surface plasmon resonance (SPR) and estimated the presence of approximately 4,000 binders among its designs.
The company’s investigators found three binders that bound tighter than trastuzumab, the therapeutic antibody marketed as Herceptin® by Roche and its Genentech subsidiary, and also available in biosimilar versions marketed by Amgen, Celltrion, Pfizer, Samsung Bioepis, and Viatris (formerly Mylan).
Absci asserts that its antibody breakthrough shows that generative AI can serve as an alternative to traditional biologic drug discovery by potentially unlocking treatments for traditionally “undruggable” diseases and improving therapeutic possibilities for many others.
Absci is among several companies applying AI to design novel antibodies. Last November, British firm Exscientia—which spent a decade pioneering the use of AI toward designing small molecule drugs—expanded its AI-based platform into novel antibody design as a first step toward designing precision engineered and optimized, fully human biologics. Oxford-based Exscientia says its expanded platform will enable it to develop next-generation therapeutic antibodies through generative AI design—and will enable a near doubling of the universe of potential targets for new treatments.
“Exscientia is pleased to hear of ongoing innovation in AI and efforts to develop new ways of developing antibodies,” Andrew Hopkins, PhD, Exscientia’s founder and CEO, told GEN Edge.
“Our work is focused on antibody by design, not discovery, for specific epitopes beyond what is possible through conventional library screening. Because we don’t have knowledge of the computational methods or visibility into this study’s baseline data, we are unable to comment on it directly, though this work points to a broader ongoing evolution in drug discovery in development.”
BUFFALO, NY- March 11, 2024 – Impact Journals publishes scholarly journals in the biomedical sciences with a focus on all areas of cancer and aging research. Aging is one of the most prominent journals published by Impact Journals.
Credit: Impact Journals
BUFFALO, NY- March 11, 2024 – Impact Journals publishes scholarly journals in the biomedical sciences with a focus on all areas of cancer and aging research. Aging is one of the most prominent journals published by Impact Journals.
Impact Journals will be participating as an exhibitor at the American Association for Cancer Research (AACR) Annual Meeting 2024 from April 5-10 at the San Diego Convention Center in San Diego, California. This year, the AACR meeting theme is “Inspiring Science • Fueling Progress • Revolutionizing Care.”
Visit booth #4159 at the AACR Annual Meeting 2024 to connect with members of the Agingteam.
About Aging-US:
Agingpublishes research papers in all fields of aging research including but not limited, aging from yeast to mammals, cellular senescence, age-related diseases such as cancer and Alzheimer’s diseases and their prevention and treatment, anti-aging strategies and drug development and especially the role of signal transduction pathways such as mTOR in aging and potential approaches to modulate these signaling pathways to extend lifespan. The journal aims to promote treatment of age-related diseases by slowing down aging, validation of anti-aging drugs by treating age-related diseases, prevention of cancer by inhibiting aging. Cancer and COVID-19 are age-related diseases.
Agingis indexed and archived byPubMed/Medline (abbreviated as “Aging (Albany NY)”), PubMed Central, Web of Science: Science Citation Index Expanded (abbreviated as “Aging‐US” and listed in the Cell Biology and Geriatrics & Gerontology categories), Scopus (abbreviated as “Aging” and listed in the Cell Biology and Aging categories), Biological Abstracts, BIOSIS Previews, EMBASE, META (Chan Zuckerberg Initiative) (2018-2022), and Dimensions (Digital Science).
Please visit our website at www.Aging-US.com and connect with us:
NY Fed Finds Medium, Long-Term Inflation Expectations Jump Amid Surge In Stock Market Optimism
One month after the inflation outlook tracked by the NY Fed Consumer Survey extended their late 2023 slide, with 3Y inflation expectations in January sliding to a record low 2.4% (from 2.6% in December), even as 1 and 5Y inflation forecasts remained flat, moments ago the NY Fed reported that in February there was a sharp rebound in longer-term inflation expectations, rising to 2.7% from 2.4% at the three-year ahead horizon, and jumping to 2.9% from 2.5% at the five-year ahead horizon, while the 1Y inflation outlook was flat for the 3rd month in a row, stuck at 3.0%.
The increases in both the three-year ahead and five-year ahead measures were most pronounced for respondents with at most high school degrees (in other words, the "really smart folks" are expecting deflation soon). The survey’s measure of disagreement across respondents (the difference between the 75th and 25th percentile of inflation expectations) decreased at all horizons, while the median inflation uncertainty—or the uncertainty expressed regarding future inflation outcomes—declined at the one- and three-year ahead horizons and remained unchanged at the five-year ahead horizon.
Going down the survey, we find that the median year-ahead expected price changes increased by 0.1 percentage point to 4.3% for gas; decreased by 1.8 percentage points to 6.8% for the cost of medical care (its lowest reading since September 2020); decreased by 0.1 percentage point to 5.8% for the cost of a college education; and surprisingly decreased by 0.3 percentage point for rent to 6.1% (its lowest reading since December 2020), and remained flat for food at 4.9%.
We find the rent expectations surprising because it is happening just asking rents are rising across the country.
At the same time as consumers erroneously saw sharply lower rents, median home price growth expectations remained unchanged for the fifth consecutive month at 3.0%.
Turning to the labor market, the survey found that the average perceived likelihood of voluntary and involuntary job separations increased, while the perceived likelihood of finding a job (in the event of a job loss) declined. "The mean probability of leaving one’s job voluntarily in the next 12 months also increased, by 1.8 percentage points to 19.5%."
Mean unemployment expectations - or the mean probability that the U.S. unemployment rate will be higher one year from now - decreased by 1.1 percentage points to 36.1%, the lowest reading since February 2022. Additionally, the median one-year-ahead expected earnings growth was unchanged at 2.8%, remaining slightly below its 12-month trailing average of 2.9%.
Turning to household finance, we find the following:
The median expected growth in household income remained unchanged at 3.1%. The series has been moving within a narrow range of 2.9% to 3.3% since January 2023, and remains above the February 2020 pre-pandemic level of 2.7%.
Median household spending growth expectations increased by 0.2 percentage point to 5.2%. The increase was driven by respondents with a high school degree or less.
Median year-ahead expected growth in government debt increased to 9.3% from 8.9%.
The mean perceived probability that the average interest rate on saving accounts will be higher in 12 months increased by 0.6 percentage point to 26.1%, remaining below its 12-month trailing average of 30%.
Perceptions about households’ current financial situations deteriorated somewhat with fewer respondents reporting being better off than a year ago. Year-ahead expectations also deteriorated marginally with a smaller share of respondents expecting to be better off and a slightly larger share of respondents expecting to be worse off a year from now.
The mean perceived probability that U.S. stock prices will be higher 12 months from now increased by 1.4 percentage point to 38.9%.
At the same time, perceptions and expectations about credit access turned less optimistic: "Perceptions of credit access compared to a year ago deteriorated with a larger share of respondents reporting tighter conditions and a smaller share reporting looser conditions compared to a year ago."
Also, a smaller percentage of consumers, 11.45% vs 12.14% in prior month, expect to not be able to make minimum debt payment over the next three months
Last, and perhaps most humorous, is the now traditional cognitive dissonance one observes with these polls, because at a time when long-term inflation expectations jumped, which clearly suggests that financial conditions will need to be tightened, the number of respondents expecting higher stock prices one year from today jumped to the highest since November 2021... which incidentally is just when the market topped out during the last cycle before suffering a painful bear market.
Homes listed for sale in early June sell for $7,700 more
New Zillow research suggests the spring home shopping season may see a second wave this summer if mortgage rates fall
The post Homes listed for sale in…
A Zillow analysis of 2023 home sales finds homes listed in the first two weeks of June sold for 2.3% more.
The best time to list a home for sale is a month later than it was in 2019, likely driven by mortgage rates.
The best time to list can be as early as the second half of February in San Francisco, and as late as the first half of July in New York and Philadelphia.
Spring home sellers looking to maximize their sale price may want to wait it out and list their home for sale in the first half of June. A new Zillow® analysis of 2023 sales found that homes listed in the first two weeks of June sold for 2.3% more, a $7,700 boost on a typical U.S. home.
The best time to list consistently had been early May in the years leading up to the pandemic. The shift to June suggests mortgage rates are strongly influencing demand on top of the usual seasonality that brings buyers to the market in the spring. This home-shopping season is poised to follow a similar pattern as that in 2023, with the potential for a second wave if the Federal Reserve lowers interest rates midyear or later.
The 2.3% sale price premium registered last June followed the first spring in more than 15 years with mortgage rates over 6% on a 30-year fixed-rate loan. The high rates put home buyers on the back foot, and as rates continued upward through May, they were still reassessing and less likely to bid boldly. In June, however, rates pulled back a little from 6.79% to 6.67%, which likely presented an opportunity for determined buyers heading into summer. More buyers understood their market position and could afford to transact, boosting competition and sale prices.
The old logic was that sellers could earn a premium by listing in late spring, when search activity hit its peak. Now, with persistently low inventory, mortgage rate fluctuations make their own seasonality. First-time home buyers who are on the edge of qualifying for a home loan may dip in and out of the market, depending on what’s happening with rates. It is almost certain the Federal Reserve will push back any interest-rate cuts to mid-2024 at the earliest. If mortgage rates follow, that could bring another surge of buyers later this year.
Mortgage rates have been impacting affordability and sale prices since they began rising rapidly two years ago. In 2022, sellers nationwide saw the highest sale premium when they listed their home in late March, right before rates barreled past 5% and continued climbing.
Zillow’s research finds the best time to list can vary widely by metropolitan area. In 2023, it was as early as the second half of February in San Francisco, and as late as the first half of July in New York. Thirty of the top 35 largest metro areas saw for-sale listings command the highest sale prices between May and early July last year.
Zillow also found a wide range in the sale price premiums associated with homes listed during those peak periods. At the hottest time of the year in San Jose, homes sold for 5.5% more, a $88,000 boost on a typical home. Meanwhile, homes in San Antonio sold for 1.9% more during that same time period.
We use cookies on our website to give you the most relevant experience by remembering your preferences and repeat visits. By clicking “Accept”, you consent to the use of ALL the cookies.
This website uses cookies to improve your experience while you navigate through the website. Out of these, the cookies that are categorized as necessary are stored on your browser as they are essential for the working of basic functionalities of the website. We also use third-party cookies that help us analyze and understand how you use this website. These cookies will be stored in your browser only with your consent. You also have the option to opt-out of these cookies. But opting out of some of these cookies may affect your browsing experience.
Necessary cookies are absolutely essential for the website to function properly. These cookies ensure basic functionalities and security features of the website, anonymously.
Cookie
Duration
Description
cookielawinfo-checbox-analytics
11 months
This cookie is set by GDPR Cookie Consent plugin. The cookie is used to store the user consent for the cookies in the category "Analytics".
cookielawinfo-checbox-functional
11 months
The cookie is set by GDPR cookie consent to record the user consent for the cookies in the category "Functional".
cookielawinfo-checbox-others
11 months
This cookie is set by GDPR Cookie Consent plugin. The cookie is used to store the user consent for the cookies in the category "Other.
cookielawinfo-checkbox-necessary
11 months
This cookie is set by GDPR Cookie Consent plugin. The cookies is used to store the user consent for the cookies in the category "Necessary".
cookielawinfo-checkbox-performance
11 months
This cookie is set by GDPR Cookie Consent plugin. The cookie is used to store the user consent for the cookies in the category "Performance".
viewed_cookie_policy
11 months
The cookie is set by the GDPR Cookie Consent plugin and is used to store whether or not user has consented to the use of cookies. It does not store any personal data.
Functional cookies help to perform certain functionalities like sharing the content of the website on social media platforms, collect feedbacks, and other third-party features.
Performance cookies are used to understand and analyze the key performance indexes of the website which helps in delivering a better user experience for the visitors.
Analytical cookies are used to understand how visitors interact with the website. These cookies help provide information on metrics the number of visitors, bounce rate, traffic source, etc.
Advertisement cookies are used to provide visitors with relevant ads and marketing campaigns. These cookies track visitors across websites and collect information to provide customized ads.