AI for the Pharmaceutical Industry
From compound identification and sequence analysis through to a production platform.
Supper & Supper builds AI solutions for pharmaceutical research and development.
Computational life science is not a new department for us
We have been working on biological and pharmaceutical questions since 2019 – from identifying compound candidates for a generics manufacturer, to classifying tumour characteristics, to analysing microbiome sequences for therapeutic applications. Computational Life Science is a category of its own in our project portfolio.
Our data scientists hold PhDs – in biology, chemistry, mathematics, physics, statistics and agronomy. So the people talking to your scientific functions are people who do not need the question explained to them first.
And we deliver end to end: from the first proof of concept to a production platform serving thousands of users, which you will run for years. As an extension of your own team where that suits you better.
What does AI mean in the pharmaceutical industry?
AI combines machine learning with heterogeneous data from research, development and the market – assays, sequence data, patent information, imaging, historical project records – and turns it into a defensible basis for decisions. That addresses the industry's central problems: declining R&D productivity, expensive attrition in late phases, and knowledge scattered across systems and departments.
Reference projects
Product Finder for a generics manufacturer. A tool that makes active substances, indications and pharmaceutical products identifiable while accounting for patent terms, assesses the market attractiveness of potential compounds, and feeds candidates directly into the development pipeline – built on web crawling and natural language processing, delivered through a dashboard for non-technical users. View the use case →
Clustering DNA sequences from microbiome data. A pipeline that groups microbiome sequences by their nucleotide order and maps the resulting clusters to known sequences via BLAST. A basis for understanding host–microbiome interaction and for therapeutic intervention. View the use case →
Assessment of breast tumours. Machine learning models predicting tumour characteristics, implemented in Dataiku. View the use case →
Where we apply it
- Compound and portfolio analysis: identifying candidates and assessing their market attractiveness – including from unstructured sources such as patent filings and scientific literature.
- Sequence and omics analysis: clustering, annotation and interpretation of large sequence datasets.
- Classification and diagnostics: models for assessing biological samples and tissue characteristics.
- Decisions in the compound pipeline: predictive models for go/no-go decisions, with uncertainty stated explicitly rather than a point estimate without context.
- Data foundation and operations: FAIR-ready structures for laboratory and research data, MLOps, monitoring and retraining.
From proof of concept to platform
Most AI initiatives fail not at the model but at the transition into operation. We cover the entire chain ourselves – you do not need a second partner for industrialisation.
- Data Consulting — clarify the question and the data situation
- Data Lab — prototype on your data
- Data Operations — production use with MLOps
- Data Infrastructure — scalable cloud architecture, hosting in Germany and the EU
Working together: data security and regulatory context
We are certified to ISO/IEC 27001:2022 (TÜV Rheinland, reg. no. 01 153 2300149). Processing and hosting take place in Germany and the EU. We use client data solely for the agreed project and never to train our own models. We provide the certificate and our documentation of technical and organisational measures to your procurement team on request.
We know where free research ends and the regulated environment begins: in early research we work independently and fast, and in regulated processes we supply the documentation your validation requires. For the requirements of the EU AI Act we offer our AI Compliance Check.
Let's talk about your project
Whether it is compound identification, sequence analysis or a platform for your scientific teams: we start with an appraisal of your data situation, not with a proposal.