![\"\"](\"https:\/\/www.europesays.com\/britain\/wp-content\/uploads\/2026\/05\/AdobeStock_202780589.jpeg\")
<\/p>\n<\/p>\n
[Adobe Stock]<\/p>\n
Immunai, a startup building a foundation model of the human immune system, has expanded<\/a> its oncology collaboration with AstraZeneca for the third time. Immunai is eligible to receive up to $37.5 million over 2026 and 2027 under the new agreement, which extends its AMICA-OS platform deeper into AstraZeneca\u2019s clinical development pipeline.<\/p>\n The two companies began working together in late 2022, though the relationship traces back to the pandemic. \u201cWe\u2019ve known the AstraZeneca team for about five years,\u201d said Immunai CEO Noam Solomon in a recent interview. The initial collaboration focused on oncology clinical programs and has since widened considerably. \u201cIn October 2025 we announced an expansion into IBD<\/a>, which represents another large department at AZ and reflects our growing interest in expanding to multiple indications,\u201d Solomon said. \u201cWe started in immune oncology, expanded to other oncology areas, then into immunology and inflammation, and now we\u2019re moving into cardiovascular inflammation, neuroinflammation, and even obesity and diabetes. The common thread is the immune system.\u201d<\/p>\n AstraZeneca employs roughly 95,000 people<\/a> and runs more than 100 Phase 3 studies<\/a> across oncology, rare diseases, cardiovascular and metabolic medicine, and respiratory and immunology. Coordinating with an organization that size from a startup is operationally intensive. \u201cOver the years, there are many dozens of people on their side and dozens on our side collaborating,\u201d Solomon said. \u201cWe work with multiple groups: people on the AI and data science side, people in translational medicine, people in clinical development. Each group covers different indications and therapeutic areas.\u201d<\/p>\n Noam Solomon<\/p>\n Why Immunai sees itself as a high-end plumber<\/p>\n That kind of cross-functional coordination points to the deeper challenge Immunai is trying to address: the infrastructure bottlenecks that slow drug development. Bringing a new drug to market costs $2.67 billion on average for top 20 pharma companies, according to a recent Deloitte estimate<\/a>. \u201cI describe myself as a plumber,\u201d Solomon said. \u201cI fix very expensive plumbing issues.\u201d<\/p>\n A big part of the plumbing is data manipulation at scale. \u201cFirst, generating a large volume of data from thousands of samples, creating a digital twin of the patients,\u201d Solomon said. \u201cThen applying our immune profiling and finding the clinical covariates manifesting in the immune system, so our platform can distill clinically meaningful insights from that.\u201d<\/p>\n The pattern across Immunai\u2019s partnerships tends to be pharma companies bringing clinical questions their existing infrastructure can\u2019t resolve. \u201cUsually those questions involve finding a better way to stratify patients for a clinical trial, identifying a biomarker for a toxic event, determining the optimal combination agent because a monotherapy isn\u2019t producing the right efficacy results, or finding the right dose and schedule,\u201d Solomon said.<\/p>\n In April 2025, Immunai and the Parker Institute for Cancer Immunotherapy<\/a> assembled what they described as the largest single-cell dataset for real-world immunotherapy research, drawing from 3,700 blood samples across 1,070 patients treated with immune checkpoint inhibitors. In January 2026, Bristol Myers Squibb signed a separate multi-year partnership<\/a> with Immunai focused on analyzing clinical immune data to clarify mechanisms of action, identify patient subgroups, and guide development decisions.<\/p>\n Turning patient samples into single-cell immune data<\/p>\n Many companies in the AI pharma market claim they apply AI to existing data, but Immunai takes a different approach. \u201cThe signal already exists, but it\u2019s hidden in the clinical patient samples sitting in your biobanks,\u201d Solomon said. \u201cSo in every collaboration, the starting point is the same: send us all the samples you have from the clinical trials, to our lab at 430 East 29th Street in New York. The first step is translating those biological specimens into digital data using single-cell multi-omic profiling of the patient\u2019s immune system.\u201d<\/p>\n In each project, Immunai analyzes how the immune system changes before and after a therapeutic intervention.\u00a0 \u201cFor every patient, think of it as an immune MRI: a profile at single-cell, multi-omic resolution, taken before and after treatment,\u201d Solomon said. \u201cEach profile is effectively a matrix of about 10,000 cells, and for each cell we have a large measurement containing roughly 37,000 gene expressions, around 75 surface proteins, and VDJ sequencing<\/a>.\u201d<\/p>\n That resolution lets the team track changes weeks and months after treatment. \u201cThen we look at clinical endpoints: which patients had good progression-free survival or overall survival, and which didn\u2019t,\u201d\u00a0 Solomon said. \u201cBy correlating immune surrogate endpoints with clinical endpoints, we identify the immunological features relevant to efficacy, resistance, toxicity, and dosing.\u201d<\/p>\n The advantages of single-cell resolution<\/p>\n Immunai\u2019s AMICA database holds more than 300,000 samples, roughly 50,000 of them at single-cell resolution. Solomon argues the distinction between resolution and scale is where most competitors fall short. \u201cA lot of big numbers in this field don\u2019t actually lead to better decisions or better insights because the data was collected without depth,\u201d he said. He compared low-resolution approaches to scaling black-and-white photographs. \u201cYou\u2019ll never be able to see the difference between green and blue. If that\u2019s the distinction you need to make, you\u2019re stuck.\u201d<\/p>\n The foundation model architecture also changes what Immunai can do with the small cohorts pharma partners typically provide, sometimes as few as 20 patients. \u201cIf you\u2019ve built a foundation model on large-scale data, every new cohort compounds against the others,\u201d Solomon said. \u201cWhen you get a new cohort, you can resolve the signal.\u201d<\/p>\n \u00a0<\/p>\n Filed Under: machine learning and AI<\/a>![\"Noam](\"https:\/\/www.europesays.com\/britain\/wp-content\/uploads\/2026\/05\/images-300x147.webp\")
<\/p>\n
Tagged With: artificial intelligence<\/a>, AstraZeneca<\/a>, biobank<\/a>, bioinformatics<\/a>, biology<\/a>, biomarkers<\/a>, biotechnology<\/a>, cancer research<\/a>, cell biology<\/a>, clinical trials<\/a>, data science<\/a>, digital twin<\/a>, drug discovery<\/a>, foundation model<\/a>, genetics<\/a>, genomics<\/a>, health technology<\/a>, healthcare<\/a>, immunai<\/a>, immune profiling<\/a>, immune system<\/a>, Immunology<\/a>, immunotherapy<\/a>, laboratory<\/a>, machine learning<\/a>, medical science<\/a>, medicine<\/a>, multi-omics<\/a>, oncology<\/a>, pathology<\/a>, pharmaceutical<\/a>, precision medicine<\/a>, scientific research<\/a>, single-cell profiling<\/a>, therapeutics<\/a>
\u00a0<\/p>\n","protected":false},"excerpt":{"rendered":"[Adobe Stock] Immunai, a startup building a foundation model of the human immune system, has expanded its oncology…\n","protected":false},"author":2,"featured_media":44607,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":"","_share_on_mastodon":"0"},"categories":[20662],"tags":[2096,11153,22653,22654,22655,22656,12625,12163,22657,20700,11267,22658,15935,22659,6016,11079,22660,1921,22661,22662,8392,22663,22664,4821,13195,22665,8376,22666,12166,22667,22668,22669,22670,22671,22672],"class_list":["post-44606","post","type-post","status-publish","format-standard","has-post-thumbnail","category-astrazeneca","tag-artificial-intelligence","tag-astrazeneca","tag-biobank","tag-bioinformatics","tag-biology","tag-biomarkers","tag-biotechnology","tag-cancer-research","tag-cell-biology","tag-clinical-trials","tag-data-science","tag-digital-twin","tag-drug-discovery","tag-foundation-model","tag-genetics","tag-genomics","tag-health-technology","tag-healthcare","tag-immunai","tag-immune-profiling","tag-immune-system","tag-immunology","tag-immunotherapy","tag-laboratory","tag-machine-learning","tag-medical-science","tag-medicine","tag-multi-omics","tag-oncology","tag-pathology","tag-pharmaceutical","tag-precision-medicine","tag-scientific-research","tag-single-cell-profiling","tag-therapeutics"],"share_on_mastodon":{"url":"","error":"Validation failed: Text character limit of 500 exceeded"},"_links":{"self":[{"href":"https:\/\/www.europesays.com\/britain\/wp-json\/wp\/v2\/posts\/44606","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.europesays.com\/britain\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.europesays.com\/britain\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/britain\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/britain\/wp-json\/wp\/v2\/comments?post=44606"}],"version-history":[{"count":0,"href":"https:\/\/www.europesays.com\/britain\/wp-json\/wp\/v2\/posts\/44606\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/britain\/wp-json\/wp\/v2\/media\/44607"}],"wp:attachment":[{"href":"https:\/\/www.europesays.com\/britain\/wp-json\/wp\/v2\/media?parent=44606"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.europesays.com\/britain\/wp-json\/wp\/v2\/categories?post=44606"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.europesays.com\/britain\/wp-json\/wp\/v2\/tags?post=44606"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}