Computational biotechnology
We find drug targets and design medicines with computation.
Vivofold combines machine learning, physics-based simulation and multi-omics data to identify targets, design small molecules and biologics, and build the analysis platforms that discovery teams rely on.
Areas of work
Six areas, one set of methods.
Shared data infrastructure, models and simulation tools run through every area, so a finding in one can be tested quickly in another.
Read about our science- 01Generative AI & physics-based drug discoveryGenerative models explore chemical space; physics-based simulation decides which ideas deserve a chemist’s time.
- 02De novo molecular & protein designComputational design of new molecules and proteins against a defined target profile, ranked with the same physical models we use in discovery.
- 03Multi-omics integration & spatial biologyGenomes, transcriptomes, proteomes and tissue maps analysed together, so a signal is checked from several angles before anyone acts on it.
- 04First-in-class target discoveryEvidence-ranked target hypotheses from human genetics, perturbation data and biological networks, with the uncertainty stated.
- 05AI platform for biopharmaOne reproducible platform from raw data to decision: pipelines, models, dashboards and reports that a discovery team can rerun and audit.
- 06Novel biologics: ADCs, mRNA, cell & gene therapyComputational and data-analysis support for programmes in antibody–drug conjugates, mRNA medicines and cell and gene therapy, delivered with partner laboratories.
Method
Each design cycle starts from what the last one learned.
Generative models propose candidates, fast learned filters remove most of them, physics-based simulation ranks the shortlist and the assay has the final word. Its results go back into the models before the next round.
For partners
From a single analysis to a multi-year programme.
AI drug-discovery partnerships
Data, biomarkers & clinical genomics
Infrastructure & operations
Industry landscape
What the market is telling us in 2026.
Partnerships are multiplying, but headline value is not cash
Industry trackers count 114 AI/ML drug-discovery partnerships signed in 2025 (84 in 2024) and about $45.9 billion in headline value in the first half of 2026, of which roughly $1.9 billion was committed upfront.
IntuitionLabs deal trackerAI-enabled small-molecule discovery attracts large pharma
Takeda’s collaboration with Iambic Therapeutics is valued at more than $1.7 billion, covering oncology and gastrointestinal targets.
IntuitionLabs deal trackerOpen models now approach free-energy accuracy, and hybrids follow
Boltz-2, released openly by MIT and Recursion, predicts binding affinity at accuracy approaching free-energy calculations while running far faster. Recursion researchers then published a pipeline that feeds it into absolute binding free-energy methods.
BioPharmaTrend; Bio-IT World- 01Validated Methods & Scientific SoftwareClean-room implementations of published algorithms, tested against known answers and shipped as browser software.
- 02Genomics & TranscriptomicsRobust analysis of bulk, single-cell and spatial transcriptomes and genomic variation.
- 03Structural Bioinformatics & Computational Drug DiscoveryValidation-first docking, QSAR and structure analysis for early drug discovery.
- 04AI & Machine Learning for BiologyTrustworthy machine learning for sequences, molecules and omics: baselines, honest splits and stated limits.
- 05Microbial Genomics & Antimicrobial ResistanceGenomic epidemiology of resistance using public bacterial genomes and open tools.
- 06Spatial & Health Data ScienceGeoinformatics and health-data standards applied to public health, agriculture and ecology.
- 07Molecular & Cell Biology (Wet Lab)Bench research linking experiments with computation, alongside Vedicgen’s laboratory training.
Also from Vivofold
Training and software, run by the same team.
Knowledge hub
Practical guides from the people who run the analyses.
Vivofold is a computational biotechnology company. We use machine learning, physics-based simulation and multi-omics data to identify drug targets and design candidate medicines, and we provide computational discovery, clinical-genomics and bio-IT work to biopharma, biotech and research partners.
Usually with a short, fixed-scope pilot. You describe the target, dataset or decision you face; we reply with a proposed approach, a timeline and a fixed price. A useful pilot can then grow into a longer programme with agreed milestones.
We work under a confidentiality agreement. Partner data, and any model trained on it, are used only for that partner’s project. Methods, code and models are delivered so that your team can rerun and audit the work.
Yes. RNA-seq, whole-genome and exome analysis, single-cell, docking, QSAR, multi-omics integration, image analysis, pipelines and data engineering are offered as fixed-scope services, each with a free written quote.
They are part of Vivofold. Vedicgen is our school, with wet-lab and computational courses, programmes and internships. Nayancode is our software, including analysis studios and free tools that run in a web browser.
Yes, during the public preview. It needs no account and runs in your browser, so your files are not uploaded. Institutional licences and self-hosted deployments are available on request.
Contact
Tell us what you need to decide.
Describe your target, dataset or question. We reply within two working days with a proposed approach.