# Xaira Therapeutics > Source: https://aiwiki.ai/wiki/xaira_therapeutics > Updated: 2026-10-28 > Fact-checked: 2026-10-27 > Categories: AI Companies, Drug Discovery, Healthcare AI > License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/) - attribute to "AI Wiki (aiwiki.ai)" > Cite as: AI Wiki. "Xaira Therapeutics." aiwiki.ai, 28 Oct 2026. https://aiwiki.ai/wiki/xaira_therapeutics > From AI Wiki (https://aiwiki.ai), the free encyclopedia of artificial intelligence. Reuse freely with attribution. **Xaira Therapeutics** is an American [AI-driven drug discovery](https://aiwiki.ai/wiki/ai_drug_discovery) company based in South San Francisco, California, that launched publicly on April 23, 2024 with more than $1 billion in committed capital, one of the largest initial funding commitments in biotechnology history. [1][2][6] It was incubated by [ARCH Venture Partners](https://aiwiki.ai/wiki/arch_venture_partners) and Foresite Labs to apply foundation-model-scale [machine learning](https://aiwiki.ai/wiki/generative_ai) and [generative protein design](https://aiwiki.ai/wiki/protein_design) to discovering and developing medicines, building on computational protein design from the laboratory of [David Baker](https://aiwiki.ai/wiki/david_baker). [1][6] The company is led by chief executive [Marc Tessier-Lavigne](https://aiwiki.ai/wiki/marc_tessier_lavigne), a neuroscientist who previously served as chief scientific officer of Genentech and as president of both Rockefeller University and [Stanford University](https://aiwiki.ai/wiki/stanford_university). [3][5]
Xaira Therapeutics logo
Xaira Therapeutics logo, from the official website xaira.com. Trademark of its owner.
ARCH co-founder Robert Nelsen called the financing of "more than $1 billion" the largest initial funding commitment in ARCH's history. [1][5] Xaira's scientific foundation builds on the methods developed by David Baker, the University of Washington biochemist who shared the 2024 Nobel Prize in Chemistry and is a Xaira co-founder. [26] Through 2025 the company's public output was mostly datasets and models. In 2026 it released the X-Cell virtual cell model, described its X-Design antibody design model alongside a preclinical pipeline of nine de novo biologics programs, and introduced the agentic research system X-Scientist and the lab robotics system X-Automate. [13][19][21][22][23] As of October 2026 its disclosed programs were preclinical and it had no approved products. [20][21] ## What is Xaira Therapeutics? Xaira Therapeutics is an AI-first biotechnology company that pairs generative [artificial intelligence](https://aiwiki.ai/wiki/artificial_intelligence) with large-scale, in-house data generation and wet-lab biology to discover and develop new medicines. Rather than licensing in a portfolio of existing drug candidates, Xaira set out to build an AI and data platform first and let a therapeutic pipeline follow from it. The company organizes its work around three integrated capabilities: foundation-model-scale [machine learning](https://aiwiki.ai/wiki/machine_learning), in-house experimental biology, and the generation of very large proprietary datasets to train those models. [1] Marc Tessier-Lavigne framed the opportunity at launch: "Witnessing how AI is impacting other industries and the considerable progress in applications of AI in biology, I believe we are poised for a revolution." [1][4] ARCH co-founder Robert Nelsen, who led the financing, described the bet as a chance to "rethink drug discovery entirely." [4][5] By 2026 Xaira was presenting its technology as the "X-Suite", made of three groups of components: AI models (X-Cell to find targets, X-Design to design molecules, and X-Patient to identify the patients most likely to respond), what it calls AI accelerators (the agentic research system X-Scientist and the robotics system X-Automate), and X-Pipeline, its portfolio of AI-derived therapeutics. [24][39] The company states its ambition as developing 10 times more medicines for 10 times more patients within 10 years. [23][39] ## When did Xaira launch and who founded it? Xaira emerged from roughly six months of stealth operation when it announced its launch on April 23, 2024. [1][3] ARCH Venture Partners and Foresite Labs, an incubator affiliated with Foresite Capital, jointly incubated the company, and ARCH and Foresite Capital led the financing of "more than $1 billion". ARCH described it as the firm's largest-ever initial funding commitment. [1][4][5] A broad syndicate of additional investors participated, including F-Prime, NEA ([New Enterprise Associates](https://aiwiki.ai/wiki/new_enterprise_associates)), [Sequoia Capital](https://aiwiki.ai/wiki/sequoia_capital), [Lux Capital](https://aiwiki.ai/wiki/lux_capital), [Lightspeed Venture Partners](https://aiwiki.ai/wiki/lightspeed_venture_partners), [Menlo Ventures](https://aiwiki.ai/wiki/menlo_ventures), Two Sigma Ventures, the Parker Institute for Cancer Immunotherapy, Byers Capital, Rsquared, and SV Angel. [1][5] Rather than starting from a single academic spinout, Xaira was assembled from several technology and talent sources. It integrated the functional genomics research-and-development unit formerly run inside Illumina, along with a proteomics group and personnel from Interline Therapeutics, and recruited scientists who had built the leading protein and antibody design models in David Baker's lab at the University of Washington [Institute for Protein Design](https://aiwiki.ai/wiki/institute_for_protein_design). [1][6] Don Kirkpatrick, a former Interline chief technology officer and Genentech scientist, and Arvind Rajpal, a former Genentech and Bristol Myers Squibb antibody-engineering leader, were among the executives brought in to the founding team. [4][8] The launch announcement named Baker and Hetu Kamisetty as co-founders, and GEN also listed Foresite's Vik Bajaj among the co-founders. [1][4] In a later article GEN additionally described ARCH's Robert Nelsen as a co-founder, and Fierce has referred to Tessier-Lavigne as Xaira's cofounder and CEO. [12][35] ## Who leads Xaira Therapeutics? Marc Tessier-Lavigne was named chief executive at launch [3][5], and as of October 2026 the company listed him as chairman and chief executive. [25] His appointment drew notice because he had resigned the Stanford presidency in 2023 following a review of research conducted in his earlier academic laboratories; the review found that he had not engaged in fraud or personally manipulated data, while flagging problems in papers from labs he led. [3][4] At Xaira he returned to industry drug discovery, the field in which he had run research at Genentech. [17] David Baker co-founded the company and serves as a scientific founder and adviser while continuing to direct the Institute for Protein Design. [1][6][25] Other co-founders include Hetu Kamisetty, a former [Meta AI](https://aiwiki.ai/wiki/meta_ai) scientist who had been a postdoctoral fellow in Baker's lab, served as senior vice president from the company's 2023 founding, and became chief technology officer in December 2024, with responsibility for foundational AI models [9][26]; Xaira's 2026 publications spell his surname Kamichetty. [19][21] Vik Bajaj was at launch the chief executive of Foresite Labs, which he co-founded, after earlier work at Google X and as a co-founder of Verily. [1][4][32] In November 2025 he was reported to have left Foresite to become co-chief executive, alongside Jeff Bezos, of the AI startup [Project Prometheus](https://aiwiki.ai/wiki/project_prometheus_bezos); he remained on Xaira's board as of October 2026. [32][25] Debbie Law was appointed chief scientific officer in 2024, alongside chief people officer Julia Tran. [25][26] In 2025 Xaira expanded its leadership. Paulo Fontoura, who had spent about 16 years at Roche overseeing translational medicine and clinical development across neuroscience, immunology, infectious disease, and rare disease, joined as chief medical officer under an appointment announced in December 2024. [9][26] In April 2025 Bo Wang, a University of Toronto associate professor who led development of the single-cell foundation model scGPT, joined as senior vice president and head of biomedical AI. [12][27] Jeff Jonker, a former chief executive of Belharra Therapeutics and Ambys Medicines, was appointed president and chief operating officer in July 2025. [29] Leadership changed again in 2026. Rachel Lane, formerly chief business officer of Belharra Therapeutics, joined in March as senior vice president for business development and operations. [28] In July the company hired Ian McCaffery from AbbVie, where he had been vice president and global head of precision medicine and companion diagnostics, as senior vice president for translational science and early clinical development, responsible for the X-Patient stratification work and clinical development. At the same time it promoted Ci Chu, who had led high-content phenotyping and functional genomics teams at [insitro](https://aiwiki.ai/wiki/insitro) before joining Xaira, to chief discovery officer, and Bo Wang to chief AI scientist. [27] Fontoura left to become Sanofi's head of research and development, a move Sanofi announced in June 2026 with a September 1 start date [30][31], and by October 2026 Jonker had become an advisor to the company. [20] | Role (October 2026) | Person | | --- | --- | | Chairman and chief executive officer | Marc Tessier-Lavigne | | Chief technology officer | Hetu Kamisetty (Kamichetty) | | Chief scientific officer | Debbie Law | | Chief discovery officer | Ci Chu | | Chief AI scientist | Bo Wang | | SVP, translational science and early clinical development | Ian McCaffery | | SVP, business development and operations | Rachel Lane | | Chief people officer | Julia Tran | Source: company leadership page. [25] The board of directors at launch included Robert Nelsen of ARCH, Stephen Knight of F-Prime, Vik Bajaj, former FDA commissioner Scott Gottlieb, 2022 Nobel laureate chemist Carolyn Bertozzi, former Johnson & Johnson chairman and chief executive Alex Gorsky, former Genentech research head Richard Scheller, Mathai Mammen, Kaye Foster, and Bryan White, together with Tessier-Lavigne. [1][4] The company's website listed the same directors in October 2026, with Sean Parker of the Parker Institute for Cancer Immunotherapy and Foresite Capital founder Jim Tananbaum as board observers. Its listed advisors included Baker, Anima Anandkumar, Regina Barzilay, Sarah Teichmann, Jonathan Weissman and Rod MacKinnon. [25] ## How does Xaira's technology work? Xaira's stated goal is to shift drug discovery from an empirical science toward what it calls a more precise engineering discipline by tightly coupling generative AI, large-scale proprietary data generation, and wet-lab biology in an iterative loop. [1] The company organizes its work around three integrated capabilities: foundation-model-scale machine learning, in-house experimental biology, and the generation of very large proprietary datasets to train those models. [18] On the protein side, Xaira's scientists are associated with the [diffusion-based](https://aiwiki.ai/wiki/diffusion_model) generative tools that came out of the Baker lab, including [RFdiffusion](https://aiwiki.ai/wiki/rfdiffusion) and RFantibody for de novo protein and antibody design, and ProteinMPNN for sequence design. [6] These methods extend the structure-prediction advances popularized by tools such as [AlphaFold](https://aiwiki.ai/wiki/alphafold) and [RoseTTAFold](https://aiwiki.ai/wiki/rosettafold) into the generative regime, designing entirely new proteins to hit molecular targets that have resisted conventional approaches. This connects Xaira's work to the broader fields of [protein folding](https://aiwiki.ai/wiki/protein_folding) and [computational protein design](https://aiwiki.ai/wiki/protein_design). In November 2025 Nature published "Atomically accurate de novo design of antibodies with RFdiffusion", a Baker-lab study whose first two authors, Nathaniel Bennett and Joseph Watson, were among four authors the paper lists as Xaira employees. It reported computationally designed single-domain antibodies (VHHs), single-chain variable fragments and full antibodies that bound user-specified epitopes, with cryo-electron microscopy confirming the designed binding poses. [33] On the data and cell-modeling side, Xaira has pursued the construction of "virtual cell" models that predict how cells respond to genetic perturbations. In June 2025 it released X-Atlas/Orion, which it described as the largest publicly available genome-wide Perturb-seq atlas, covering about 8 million single cells across all human protein-coding genes with deep sequencing of more than 16,000 unique molecular identifiers per cell, roughly an eightfold jump over prior public datasets. [10][11][12] The atlas was enabled by an internally developed, scalable screening platform the company calls Fix-Cryopreserve-ScRNAseq (FiCS) Perturb-seq, and was released under a non-commercial license alongside a bioRxiv preprint. [10] On March 17, 2026 Xaira launched X-Cell, described as its first virtual cell model and, at up to 4.9 billion parameters, the largest such model reported to date. [13][14] X-Cell was trained on a successor dataset, X-Atlas/Pisces, comprising 25.6 million perturbed single-cell transcriptomes across seven biologically diverse cellular contexts (16 conditions in total), more than three times the scale of X-Atlas/Orion. [13][15] Unlike the autoregressive single-cell models that had dominated the field, X-Cell uses a diffusion [language model](https://aiwiki.ai/wiki/language_model) architecture that iteratively refines its predictions by progressively transforming control-state gene expression toward a perturbed state. [13][16] Xaira reported that X-Cell was the first virtual cell model to demonstrate a clear scaling law, with perturbation-prediction accuracy following power-law improvements as data and model size grow, mirroring the scaling behavior seen in [large language model](https://aiwiki.ai/wiki/large_language_model)s. [13][14] The company said the model generalized to previously unseen contexts such as iPSC-derived melanocyte progenitors and primary human T cells, and said it would make a subset of the Pisces dataset and the X-Cell model available to the research community. [13][16] Xaira framed these models as tools for target and mechanism-of-action discovery, patient stratification, and toxicity prediction. [14][15] The accompanying bioRxiv preprint, posted March 20, 2026 with Ci Chu and Bo Wang as corresponding authors, reported that X-Cell outperformed existing models by up to fivefold on metrics such as Pearson delta (the correlation between predicted and observed perturbation-induced expression changes) and predicted T cell inactivating perturbations zero-shot in stimulated Jurkat cells; the 4.9-billion-parameter version is called X-Cell-Ultra. [34] In September 2026 Fierce reported that Xaira's biology teams had begun using X-Cell to generate and prioritize hypotheses before committing preclinical resources. [35] ### X-Design antibody design Xaira gave its first detailed look at X-Design, its generative AI for designing antibody and protein therapeutics, in a company post on October 2, 2026. [19][24] The post introduced the "Vega" class of X-Design models, which Xaira said were built from public and proprietary data and optimized at once for what it calls progressable binders: molecules that are human-like, potent, selective, cross-reactive with the matching protein in animal test species, and developable. [19] Xaira said Vega tripled the rate of human-like VHH designs meeting all of its developability criteria compared with a baseline model trained without proprietary data. [19] The criteria had been set out in a June 29, 2026 post by Law and Kamisetty, which arranged them as three questions asked in sequence: whether a molecule is a real binder, whether it is drug-like, and whether it amounts to a therapeutic program. That post also recommended that the field report design success as validated binders, not initial hits, divided by designs tested. [21] The October post used two pipeline programs as case studies, with molecules generated zero-shot (no data from earlier campaigns was used to train the model). [19] | Campaign | Target | Results reported by Xaira | | --- | --- | --- | | XA-1 (lead oncology program) | Undisclosed protein; a defined epitope, selective over closely related family members | 182 VHH designs gave 25 initial hits and 18 confirmed binders (a 10% binder rate). The best binder had a dissociation constant of 17 nM to the human target and 83 nM to the surrogate-species protein and passed all developability assays. About 3 weeks of lab work produced the progressable binder and one further optimization round gave a preclinical lead, 7 weeks from DNA synthesis in total. | | XA-4 | Undisclosed GPCR with extensive post-translational modification and a small, flexible extracellular region | Two naive VHH library campaigns and a llama immunization had yielded no functional binders. A designed library of 60,000 VHHs was screened against the target; of 92 enriched candidates, seven bound target-expressing cells and six were confirmed as inhibitors. The best reached more than 96% maximum inhibition (IC50 183 nM), bound human target cells with an EC50 of 32 nM, cross-reacted with monkey and mouse forms, and moved into lead optimization. | | CXCR4 and APJ (comparison GPCRs with known structures) | Chemokine receptor CXCR4; apelin receptor APJ | 32 of 91 designs (35%) bound CXCR4-expressing cells and 26 of 91 (29%) bound APJ-expressing cells; the best EC50s were 12.8 nM and 8.4 nM, close to the positive controls. | The results appeared as a company post rather than a peer-reviewed paper, and Xaira said a systematic assessment of X-Design would follow. [19] Baker said in a statement that "X-Design shows that AI is beginning to design those antibodies from scratch", referring to disease proteins on which traditional antibody discovery had failed, and Tessier-Lavigne told Fierce that "Most AI design work stops at finding hits, molecules that bind" and that "What sets X-Design apart is that it designs for drug readiness from the start." [20] ### X-Scientist agentic research system On October 21, 2026 Xaira described X-Scientist, a multi-agent [agentic AI](https://aiwiki.ai/wiki/agentic_ai) "harness" that connects frontier language models with bioinformatics tools, internal datasets and the company's own models (X-Cell, X-Design and X-Patient), which it reaches through APIs and [Model Context Protocol](https://aiwiki.ai/wiki/model_context_protocol) servers. [22] A lead agent plans an investigation as a dynamic task graph, delegates stages to persistent worker agents, and judges their results against explicitly defined evaluation criteria. [22] The results below are as reported by Xaira in that post. [22] | Evaluation | Setup | Result reported by Xaira | | --- | --- | --- | | DrugDiscoveryBench (Scale AI, 82 tasks) | [GPT-6 Astra](https://aiwiki.ai/wiki/gpt_6_astra) at maximum reasoning effort in each harness | X-Scientist scored 7.4 percentage points above [Codex](https://aiwiki.ai/wiki/openai_codex) and 4.1 points above mini-SWE-agent | | DrugDiscoveryBench | [Claude Sonnet 5](https://aiwiki.ai/wiki/claude_sonnet_5) at maximum effort | 13.4 points above [Claude Code](https://aiwiki.ai/wiki/claude_code); its 58.1% was also 4.4 points above Claude Code running [Claude Opus 5](https://aiwiki.ai/wiki/claude_opus_5) | | [Terminal-Bench-Science 0.1](https://aiwiki.ai/wiki/terminal_bench), life sciences subset | GPT-6 Astra | 7.1 points above Codex at maximum effort and 3.5 points at low effort | | Wet-lab test in HepG2 liver cells | Genetic perturbations to reverse a TGF-beta-induced state, measured by Perturb-seq | 7.1% hit rate (381 perturbations) versus 6.9% for human-curated picks (321) and 0.9% for random genes (433); nominations took about 20 minutes versus more than 3 hours for human curation | | PerturbQA pilot | Four-hour run with a $100 API budget cap | Validation AUROC of 0.6789 versus 0.6728 for AutoScientists and 0.6441 for [Andrej Karpathy](https://aiwiki.ai/wiki/andrej_karpathy)'s AutoResearch, at an estimated API cost of $30.52 versus $93.27 and $18.75 | The benchmark runs used the harness without domain-specific tools or skills. [22] In the liver-cell test, X-Scientist's hits included canonical pathway genes such as TGFBR1, TGFBR2, SMAD3 and SMAD4 as well as non-canonical genes that did not appear in the human-curated list. [22] ### X-Automate lab robotics Two days later Xaira described X-Automate, its laboratory automation system. It combines industrial workcells that produce and purify proteins at a rate of thousands of samples per week, X-Bot (a vision-guided, six-degree-of-freedom robotic arm the company built from an inexpensive off-the-shelf arm, open-source tools and in-house control software), mobile robots, and X-Scientist, which uses a [vision language model](https://aiwiki.ai/wiki/vision_language_model) to read the scene and coordinate each workflow. [23] In a first seven-day deployment the system moved 18 96-well protein plates from the production workcell to an Agilent HPLC instrument and analyzed them, 80% more plates than a modeled weekday 9-to-5 loading schedule, with HPLC utilization of 97.2% against a modeled 53.6%. Four interruptions in upstream plate storage needed manual recovery. [23] Xaira said its longer-term aim is a self-driving lab with about 100 instrument-level robotic arms coordinated by X-Scientist, and it credited [NVIDIA](https://aiwiki.ai/wiki/nvidia) for technical discussions on Isaac ROS and [Isaac Sim](https://aiwiki.ai/wiki/nvidia_isaac_sim) and [AWS](https://aiwiki.ai/wiki/amazon_web_services) for input on X-Bot. [23] ## What is Xaira's pipeline and therapeutic focus? Xaira has emphasized building its AI and data platform first and allowing a therapeutic pipeline to follow from it, rather than licensing in a portfolio of preexisting drug candidates. [3][16] Executives have described the company's experimental and clinical work as itself a vehicle for generating the data that improves its models, so that drug development and model development reinforce each other. [1][17] Public statements pointed to therapeutic interest in [oncology](https://aiwiki.ai/wiki/oncology) and in [immunology](https://aiwiki.ai/wiki/immunology) and inflammation, with the Parker Institute for Cancer Immunotherapy among its backers. [1][20][21] Xaira began disclosing its pipeline in 2026. A chart in its June 29, 2026 post on progressable binders showed nine de novo biologics programs, XA-1 through XA-9, none of them yet at the IND-enabling stage. [21] In October 2026 Tessier-Lavigne told Fierce Biotech that XA-1 and XA-4 address targets in which the company has "great conviction" but where earlier attempts to make antibodies had failed, and that Xaira plans to take both into human studies, though he gave no timing. Fierce reported that the company might partner some assets and was in discussions about applying its antibody design platform to other companies' targets. The targets have not been disclosed. [20] | Program | Area | Stage shown in June 2026 chart | Later disclosures | | --- | --- | --- | --- | | XA-1 | Oncology | Lead optimization | Lead oncology program; preclinical lead reported in October 2026 [19][20] | | XA-2 | Immunology and inflammation | Lead optimization | Described by Fierce as a preclinical candidate [20] | | XA-3 | Immunology and inflammation | Lead optimization | Described by Fierce as a preclinical candidate [20] | | XA-4 | Immunology and inflammation | De novo hit generation and validation | GPCR target; lead molecule moved to lead optimization by October 2026 [19][20] | | XA-5 | Oncology | De novo hit generation and validation | No further details | | XA-6 to XA-9 | Undisclosed | Target validation and epitope discovery | No further details | Tessier-Lavigne has said the ultimate measure of success will be whether the company's models can be used to make medicines and a difference for patients [14][17]; as of October 2026 its disclosed programs were preclinical, and none had been reported to enter human testing. [20][21] Operationally, Xaira maintained early teams in Seattle focused on foundational AI modeling and in December 2024 announced the move of its headquarters to the Gateway of Pacific III campus in South San Francisco to expand its experimental capabilities while retaining the Seattle modeling group. [9][26] By 2026 it described itself as headquartered in South San Francisco with innovation centers in Seattle and London. [27][28] The very large committed capital base is intended to let the company invest in expensive data generation and model training over a multiyear horizon without needing near-term revenue, a structure that distinguishes it from more conventional venture-funded biotech startups. [3][5] ## How much funding did Xaira raise, and who are its backers? The financing was anchored by ARCH Venture Partners and Foresite Capital, with Foresite Labs' Vik Bajaj and ARCH's Robert Nelsen closely involved in the company's creation and governance. [1][5] The participating investor list spans crossover and venture firms active in both technology and life sciences, reflecting the company's positioning at the intersection of AI and biology. As of October 2026 Xaira had not announced any financing after its launch round and had not disclosed a valuation. In October 2026 Tessier-Lavigne declined to discuss the company's cash position, telling Fierce Biotech, "We wanted to capitalize the company so as not to have to go back to the capital markets until we had molecules in the clinic." He added that he was open to raising money sooner "if there's appropriate investor interest or the opportunity to accelerate or extend our programs." [20] | Fact | Detail | | --- | --- | | Public launch | April 23, 2024 | | Committed capital | More than $1 billion | | Lead investors | ARCH Venture Partners; Foresite Capital | | Other investors | F-Prime, NEA, [Sequoia Capital](https://aiwiki.ai/wiki/sequoia_capital), [Lux Capital](https://aiwiki.ai/wiki/lux_capital), [Lightspeed Venture Partners](https://aiwiki.ai/wiki/lightspeed_venture_partners), [Menlo Ventures](https://aiwiki.ai/wiki/menlo_ventures), Two Sigma Ventures, Parker Institute for Cancer Immunotherapy, Byers Capital, Rsquared, SV Angel | | Incubated by | ARCH Venture Partners and Foresite Labs | | Valuation | Not disclosed | | Chief executive | Marc Tessier-Lavigne (chairman and CEO; ex-Genentech CSO; ex-Stanford and Rockefeller president) | | Scientific co-founder | David Baker (UW Institute for Protein Design; 2024 Nobel laureate in Chemistry) | | Other co-founders | Hetu Kamisetty (CTO since December 2024, ex-Meta); Vik Bajaj (ex-Foresite Labs CEO; co-CEO of [Project Prometheus](https://aiwiki.ai/wiki/project_prometheus_bezos) from November 2025) | | Chief medical officer | Paulo Fontoura (early 2025 to 2026; left to lead R&D at Sanofi) | | Chief scientific officer | Debbie Law | | Headquarters | South San Francisco, California (innovation centers in Seattle and London) | | Notable datasets / models | X-Atlas/Orion (about 8M-cell Perturb-seq atlas, June 2025); X-Cell virtual cell model with X-Atlas/Pisces (25.6M cells; up to 4.9B parameters, March 17, 2026); X-Design Vega antibody design models (October 2026); X-Scientist and X-Automate (October 2026) | | Therapeutic focus | Oncology; immunology and inflammation; nine preclinical programs, XA-1 to XA-9 | | Approved products | None as of October 2026 | ## Recognition and collaborations Endpoints News named Xaira an Endpoints 11 winner in 2024. [36] In September 2026 Xaira won the Preclinical Development category of the Fierce AI Innovation Awards, with a citation focused on X-Cell. [35] The same month it was one of three companies quoted in [Anthropic](https://aiwiki.ai/wiki/anthropic)'s announcement of its [Life Sciences Verification Program](https://aiwiki.ai/wiki/anthropic_life_sciences_verification_program), saying it was "excited to put Anthropic's frontier models to work across our drug discovery engine" [37], and NVIDIA listed it among the collaborators on the public beta of the [BioNeMo Inference Runtime](https://aiwiki.ai/wiki/nvidia_bionemo_inference_runtime). [38] ## Why is Xaira Therapeutics significant? Xaira's launch was widely cited as a marker of how far investor conviction in AI for biology had advanced by the mid-2020s, both for the unusual size of its initial raise and for the profile of its founders and board. [2][5] By pairing the generative protein design lineage of the Baker lab with industrial-scale functional genomics data generation and large machine-learning models, the company became a prominent test of the thesis that combining better algorithms with proprietary, purpose-built biological data can make drug discovery faster and more predictive. [6] Its public releases of large Perturb-seq datasets and the X-Cell virtual cell model also positioned it within the broader effort across the field to build "virtual cell" [foundation models](https://aiwiki.ai/wiki/foundation_models). [13] As with other [AI in healthcare](https://aiwiki.ai/wiki/ai_in_healthcare) ventures, the central open question remains whether platform and benchmark advances will translate into approved therapies; Xaira itself has stressed that this clinical validation is the standard by which it expects to be judged. [17] Fierce Biotech observed in October 2026 that Xaira had stayed largely quiet in the two years after its launch, and that AI antibody design had become crowded, naming BigHat Biosciences, Absci, [Generate:Biomedicines](https://aiwiki.ai/wiki/generate_biomedicines) and Roche's Chugai among companies using AI to design or optimize antibodies. [20] GEN, reporting on X-Cell in March 2026, noted comparable de novo antibody advances from [Nabla Bio](https://aiwiki.ai/wiki/nabla_bio), [Chai Discovery](https://aiwiki.ai/wiki/chai_discovery) and Absci. [14] ## Timeline | Date | Event | | --- | --- | | April 23, 2024 | Launches with more than $1 billion in committed capital [1] | | September 2024 | Named to the Endpoints 11 list [36] | | October 2024 | Co-founder David Baker shares the Nobel Prize in Chemistry [26] | | December 11, 2024 | Kamisetty named CTO and Fontoura named CMO (effective early 2025); headquarters move to Gateway of Pacific III announced [26] | | April 2025 | Bo Wang joins as SVP and head of biomedical AI [12][16] | | June 17, 2025 | Releases the X-Atlas/Orion Perturb-seq dataset [10] | | July 2025 | Jeff Jonker appointed president and COO [29] | | November 5, 2025 | Nature publishes the Baker-lab RFdiffusion antibody design paper, whose first two authors work at Xaira [33] | | March 17, 2026 | Launches X-Cell and X-Atlas/Pisces [13] | | March 26, 2026 | Rachel Lane joins as SVP, business development and operations [28] | | June 29, 2026 | Publishes progressable-binder criteria and a nine-program pipeline chart [21] | | July 6, 2026 | Hires Ian McCaffery; promotes Ci Chu and Bo Wang [27] | | September 1, 2026 | Fontoura's announced start date as head of R&D at Sanofi [30][31] | | September 2, 2026 | X-Cell wins a 2026 Fierce AI Innovation Award [35] | | October 2, 2026 | Discloses X-Design Vega results for XA-1 and XA-4 [19][20] | | October 21, 2026 | Introduces X-Scientist [22] | | October 23, 2026 | Introduces X-Automate [23] | ## See also - [List of neolabs](https://aiwiki.ai/wiki/list_of_neolabs) - [Neolab](https://aiwiki.ai/wiki/neolab) - [Protein design](https://aiwiki.ai/wiki/protein_design) - [RFdiffusion](https://aiwiki.ai/wiki/rfdiffusion) - [Insitro](https://aiwiki.ai/wiki/insitro) - [Generate Biomedicines](https://aiwiki.ai/wiki/generate_biomedicines) - [Chai Discovery](https://aiwiki.ai/wiki/chai_discovery) - [Nabla Bio](https://aiwiki.ai/wiki/nabla_bio) - [Isomorphic Labs](https://aiwiki.ai/wiki/isomorphic_labs) - [State (Arc Institute virtual cell model)](https://aiwiki.ai/wiki/arc_state_model) ## References 1. Xaira Therapeutics, "Xaira Therapeutics Launches to Deliver Transformative Medicines by Advancing and Harnessing AI for Drug Discovery and Development," Business Wire, April 23, 2024. https://www.businesswire.com/news/home/20240423707240/en/Xaira-Therapeutics-Launches-to-Deliver-Transformative-Medicines-by-Advancing-and-Harnessing-AI-for-Drug-Discovery-and-Development 2. ARCH Venture Partners, "With ARCH funding, Xaira Therapeutics aims to reinvent drug R&D by using artificial intelligence to deliver transformative medicines," April 23, 2024. https://www.archventure.com/with-arch-funding-xaira-therapeutics-aims-to-reinvent-drug-rd-by-using-artificial-intelligence-to-deliver-transformative-medicines/ 3. TechCrunch, "Xaira, an AI drug discovery startup, launches with a massive $1B," April 24, 2024. https://techcrunch.com/2024/04/24/xaira-an-ai-drug-discovery-startup-launches-with-a-massive-1b-says-its-ready-to-start-developing-drugs/ 4. GEN (Genetic Engineering & Biotechnology News), "AI Drug Developer Xaira Therapeutics Launches with $1B+," April 2024. https://www.genengnews.com/topics/artificial-intelligence/ai-drug-developer-xaira-therapeutics-launches-with-1b/ 5. Fierce Biotech, "New AI drug discovery powerhouse Xaira rises with $1B in funding," April 24, 2024. https://www.fiercebiotech.com/biotech/new-ai-drug-discovery-powerhouse-xaira-rises-1b-funding 6. Chemical & Engineering News, "Backed by $1 billion, Xaira Therapeutics is readying AI-generated drugs," April 2024. https://cen.acs.org/business/start-ups/Backed-1-billion-Xaira-Therapeutics/102/i13 7. GeekWire, "Inside the Seattle labs of Xaira, the AI-powered startup launched with $1B from investors," 2024. https://www.geekwire.com/2024/inside-the-seattle-labs-of-xaira-the-ai-powered-startup-launched-with-1b-from-investors/ 8. Pharmaphorum, "Enter Xaira, with $1bn for its AI in drug discovery platform," April 2024. https://pharmaphorum.com/news/enter-xaira-1bn-its-ai-drug-discovery-platform 9. Drug Discovery & Development, "Xaira Therapeutics bolsters leadership team and relocates headquarters to fuel AI-powered drug discovery," December 11, 2024. https://www.drugdiscoverytrends.com/xaira-therapeutics-bolsters-leadership-team-and-relocates-headquarters-to-fuel-ai-powered-drug-discovery/ 10. Xaira Therapeutics, "X-Atlas/Orion: Xaira Therapeutics Unveils Largest Publicly Available Genome-Wide Perturb-seq Dataset to Power Next-Generation AI for Biology," Business Wire, June 17, 2025. https://www.businesswire.com/news/home/20250617146938/en/X-AtlasOrion-Xaira-Therapeutics-Unveils-Largest-Publicly-Available-Genome-Wide-Perturb-seq-Dataset-to-Power-Next-Generation-AI-for-Biology 11. R&D World, "Xaira Therapeutics releases 8 million cell dataset, touting it as the largest public resource for AI drug discovery," June 2025. https://www.rdworldonline.com/xaira-therapeutics-releases-8-million-cell-dataset-touting-it-as-the-largest-public-resource-for-ai-drug-discovery/ 12. GEN, "Xaira Therapeutics Releases Largest Perturb-Seq Dataset to Power the Virtual Cell," June 2025. https://www.genengnews.com/topics/artificial-intelligence/xaira-therapeutics-releases-largest-perturb-seq-dataset-to-power-the-virtual-cell/ 13. Xaira Therapeutics, "Xaira Therapeutics Launches X-Cell, Its First Virtual Cell Model, Trained on the Largest-Ever Genome-Wide Perturbation Dataset, X-Atlas/Pisces," Business Wire, March 17, 2026. https://www.businesswire.com/news/home/20260317710096/en/Xaira-Therapeutics-Launches-X-Cell-Its-First-Virtual-Cell-Model-Trained-on-the-Largest-Ever-Genome-Wide-Perturbation-Dataset-X-AtlasPisces 14. GEN, "Xaira's First Virtual Cell Model Is Largest To-Date, Toward Complex Biology," March 2026. https://www.genengnews.com/topics/artificial-intelligence/xairas-first-virtual-cell-model-is-largest-to-date-toward-complex-biology/ 15. Endpoints News, "Xaira unveils AI model X-Cell for predicting virtual cells," March 2026. https://endpoints.news/xaira-unveils-ai-model-x-cell-for-predicting-virtual-cells/ 16. BioPharmaTrend, "$1 Billion-Backed Xaira Launches Its First Virtual Cell Model," March 2026. https://www.biopharmatrend.com/news/xaira-therapeutics-launches-x-cell-its-first-virtual-cell-model-1532/ 17. Timmerman Report, "Reinventing Drug Discovery with AI: Marc Tessier-Lavigne on The Long Run," November 2025. https://timmermanreport.com/2025/11/reinventing-drug-discovery-with-ai-marc-tessier-lavigne-on-the-long-run/ 18. Xaira Therapeutics, "Our Approach" (archived June 23, 2026; the page has since been removed from the company site). https://web.archive.org/web/20260623211110/https://www.xaira.com/our-approach 19. Xaira Design Team, "De Novo Design of Progressable Antibodies to Therapeutic Targets," Xaira Therapeutics, October 2, 2026. https://www.xaira.com/news/de-novo-design-of-progressable-antibodies-to-therapeutic-targets 20. Fierce Biotech, "'We've been taking our time': Buzzy AI biotech Xaira reveals antibody platform, first taste of pipeline," October 2, 2026. https://www.fiercebiotech.com/biotech/weve-been-taking-our-time-xaira-reveals-antibody-platform-and-first-taste-pipeline 21. Debbie Law and Hetu Kamichetty, "Progressable Binders: The Binders that Matter," Xaira Therapeutics, June 29, 2026. https://www.xaira.com/news/progressable-binders-the-binders-that-matter 22. Xaira Therapeutics, "X-Scientist: A Recursive Self-Improving Agentic AI Platform for Drug Discovery," October 21, 2026. https://www.xaira.com/news/x-scientist-recursive-self-improving-agentic-ai-platform 23. Xaira Therapeutics, "X-Automate brings physical and agentic AI to the lab," October 23, 2026. https://www.xaira.com/news/x-automate-brings-physical-and-agentic-ai-to-labs 24. Xaira Therapeutics, "X-Suite: Our full-stack, AI-powered therapeutics engine" (platform page), accessed October 27, 2026. https://www.xaira.com/platform 25. Xaira Therapeutics, "Our Team" (leadership, board and advisors), accessed October 27, 2026. https://www.xaira.com/our-team 26. Xaira Therapeutics, "Xaira Therapeutics Announces the Appointment of Dr. Paulo Fontoura as Chief Medical Officer and Dr. Hetu Kamisetty as Chief Technology Officer," Business Wire, December 11, 2024. https://www.businesswire.com/news/home/20241211004372/en/Xaira-Therapeutics-Announces-the-Appointment-of-Dr.-Paulo-Fontoura-as-Chief-Medical-Officer-and-Dr.-Hetu-Kamisetty-as-Chief-Technology-Officer 27. Xaira Therapeutics, "Xaira Therapeutics Announces the Appointment of Dr. Ian McCaffery as SVP, Translational Science and Early Clinical Development, and the Promotions of Dr. Ci Chu to Chief Discovery Officer and Dr. Bo Wang to Chief AI Scientist," Business Wire, July 6, 2026. https://www.businesswire.com/news/home/20260706699581/en/Xaira-Therapeutics-Announces-the-Appointment-of-Dr.-Ian-McCaffery-as-SVP-Translational-Science-and-Early-Clinical-Development-and-the-Promotions-of-Dr.-Ci-Chu-to-Chief-Discovery-Officer-and-Dr.-Bo-Wang-to-Chief-AI-Scientist 28. Xaira Therapeutics, "Xaira Therapeutics Announces the Appointment of Rachel Lane, Ph.D., as Senior Vice President, Business Development and Operations," Business Wire, March 26, 2026. https://www.businesswire.com/news/home/20260325916932/en/Xaira-Therapeutics-Announces-the-Appointment-of-Rachel-Lane-Ph.D.-as-Senior-Vice-President-Business-Development-and-Operations 29. BioPharmaTrend, "Xaira Therapeutics Appoints Biotech Exec Behind Belharra and Ambys as President and COO to Scale AI-Driven Drug Discovery Platform," July 9, 2025. https://www.biopharmatrend.com/news/xaira-therapeutics-appoints-biotech-exec-behind-belharra-and-ambys-as-president-and-coo-to-scale-ai-driven-drug-discovery-platform-1312/ 30. Pharmaphorum, "Sanofi names ex-Roche exec Fontoura as R&D chief," June 22, 2026. https://pharmaphorum.com/news/sanofi-names-ex-roche-exec-fontoura-rd-chief 31. Sanofi, "Paulo Fontoura, Executive Vice President, Head of Research and Development" (executive committee profile), accessed October 27, 2026. https://www.sanofi.com/en/our-company/governance/executive-committee/paulo-fontoura 32. Ram Iyer, "Jeff Bezos reportedly returns to the trenches as co-CEO of new AI startup, Project Prometheus," TechCrunch (via Yahoo Finance), November 17, 2025. https://finance.yahoo.com/news/jeff-bezos-reportedly-returns-trenches-143330926.html 33. Bennett, N. R., Watson, J. L., et al., "Atomically accurate de novo design of antibodies with RFdiffusion," Nature 649, 183-193 (published online November 5, 2025). https://www.nature.com/articles/s41586-025-09721-5 34. Wang, C., Karimzadeh, M., et al., "X-Cell: Scaling Causal Perturbation Prediction Across Diverse Cellular Contexts via Diffusion Language Models," bioRxiv, March 20, 2026. https://www.biorxiv.org/content/10.64898/2026.03.18.712807v1 35. Fierce Pharma, "2026 Fierce AI Innovation Awards: Preclinical Development (Xaira Therapeutics)," September 2, 2026. https://www.fiercepharma.com/ai-and-machine-learning/preclinical-development 36. Endpoints News, "Endpoints 11 winner Xaira Therapeutics: Biotech's largest AI bet with A-list backers," September 2024. https://endpoints.news/endpoints-11-winner-xaira-therapeutics-biotechs-largest-ai-bet-with-a-list-backers/ 37. Anthropic, "Introducing the Life Sciences Verification Program," September 17, 2026. https://www.anthropic.com/news/life-sciences-verification-program 38. NVIDIA Healthcare (@NVIDIAHealth), post announcing the BioNeMo Inference Runtime public beta, X, September 10, 2026. https://x.com/NVIDIAHealth/status/2098065212767084753 39. Xaira Therapeutics, homepage ("Reimagining how we create medicines"), accessed October 27, 2026. https://www.xaira.com/