CelerisAI combines advanced machine learning with deep biological insights to transform drug discovery, reduce development costs, and bring life-saving therapies to patients faster.
Traditional drug discovery is expensive, time-consuming, and has a high failure rate. The cost to bring a new drug to market exceeds $2.6 billion, with development timelines spanning 10–15 years and a 90% clinical failure rate driven by poor target selection and inadequate early prediction.
CelerisAI addresses these challenges head-on by applying best-in-class, cutting-edge AI and machine learning to identify promising drug candidates earlier, predict clinical outcomes more accurately, and optimize development pathways based on real-world biological evidence.
Our platform focuses on three critical therapeutic areas where unmet medical needs are highest: inflammation and pulmonary diseases, cardiovascular diseases, and oncology.
Explore Our Pipeline →Our AI-driven platform delivers quantifiable improvements across the entire drug discovery pipeline
AI/ML acceleration reduces timelines from years to months
Over 70% reduction via predictive ADMET modeling
From target identification to preclinical validation
Better candidate selection reduces late-stage failures
Our pipeline programs are built on founder-led, peer-reviewed academic and industry research, with an emphasis on high unmet medical needs and biologically validated opportunities aligned with active pharma interest.
Novel molecules designed to target the NLRP3 inflammasome and key anti-inflammatory proteins. Engineered to calm hypoxia- and ischemia-induced overactive immune responses, reduce lung inflammation, activate the body’s intrinsic anti-inflammatory mechanisms, and improve breathing in patients with chronic respiratory conditions.
AI-designed novel molecules that target the DNA Damage Response pathway. The molecules selectively interfere with cancer cells’ ability to repair genomic damage and survive — leaving healthy cells largely unaffected — delivering precision oncology at the molecular level.
Following successful preclinical proof-of-concept in our primary programs, CelerisAI will expand into two additional high-value therapeutic areas in Phase 2, leveraging the same AI/ML platform and biological expertise:
We deploy best-in-class AI tools guided by deep experimental biology. Every CelerisAI program traces directly to Dr. Chintan Raval’s own peer-reviewed published research.
De novo small molecule design using generative AI, optimised for potency, selectivity, and synthetic accessibility. Novel scaffolds unconstrained by existing IP.
ML-based prediction of absorption, distribution, metabolism, excretion, and toxicity. Cuts experimental costs by over 70% and eliminates late-stage attrition.
Systematic prioritisation of biologically and commercially validated pathways. We start where the evidence — and the pharma deal flow — already points.
AI models trained on clinical trial data predict success probability — directly addressing the leading cause of drug failure before patients are enrolled.
During his postdoctoral fellowship at Yale School of Medicine, Dr. Raval spent years studying a precise and devastating phenomenon: how oxygen deprivation — hypoxia — and ischemia-reoxygenation trigger catastrophic lung damage and hyperinflammation. His lab established the mechanisms, mapped the pathways, and demonstrated solutions in animal models. They could protect lung cells and mice from hypoxia-driven lung injury.
Then COVID-19 arrived.
As the pandemic swept the globe, Dr. Raval watched with particular and painful clarity. The virus was simply a trigger. The real killer was hypoxia-mediated hyperinflammation — the exact biology he and his colleagues had spent years solving. The knowledge existed. The solutions existed, at least in principle.
But millions died anyway — not because the science failed, but because it never left the laboratory.
That experience became the founding conviction of CelerisAI. Today, using advanced AI/ML tools, we are designing novel drugs for hypoxia-mediated hyperinflammation across lung diseases — COPD, pulmonary arterial hypertension, fibrotic lung disease, and beyond.
I am a molecular biologist with academic, industry, and entrepreneurial experience — and CelerisAI sits at the precise intersection of those three careers.
My doctoral research at the University of Bath established the mechanistic basis of Bach-1 (and Nrf2)-mediated HO-1 gene regulation. My postdoctoral work at Yale School of Medicine then took me deeper into how hypoxia and ischemia-reoxygenation trigger catastrophic lung damage and systemic hyperinflammation.
Every CelerisAI pipeline program traces directly to research I designed, ran, and published. As Head of R&D and Quality at a US biotech, I led multiple products through CDSCO regulatory approvals and commercialised two collagen hemostat products. I have also co-founded a regenerative medicine company and an agricultural technology venture.
The $2.6 billion cost and 90% failure rate of traditional drug discovery are not inevitable. They are the product of guesswork applied at scale. CelerisAI replaces the guesswork — with biology first, AI second, and a clear path to pharma partnership at every stage.
Science explained. The biology behind our programs, the AI behind our platform, and the mission behind our company.
From Yale postdoc to pandemic witness — how hypoxia research that sat in a laboratory became the founding conviction of CelerisAI.
Millions of heart patients are running out of options — not because the heart can’t be helped, but because today’s drugs hit a wall. CelerisAI is breaking through it.
Millions of patients on blood thinners are denied life-saving surgeries every day. Not because surgery is impossible — but because their medicine makes bleeding unstoppable.
Millions of people suffer from heart attacks, lung diseases, and breathing conditions that share the same hidden root cause. CelerisAI has identified three molecular switches that control this crisis — and is using AI to design a single medicine to address all three at once.
Because every patient waiting for a cure deserves faster, smarter science.