Senior Data Scientist · PhD · Computational Biology

Amy
Francis

Data science, ML & drug discovery - for everyone.

I'm a Senior Data Scientist bridging computational biology and experimental research, with expertise in machine learning, bioinformatics, and tool development across cancer genomics, immunology, and drug discovery. I think a lot about how AI is changing science - and about making sure those changes reach every researcher, not just those with a machine learning background. My work tries to do that: building practical tools, leading interdisciplinary teams, and figuring out how to get the most out of modern AI in real biological research.

Cancer Genomics Drug Discovery Protein ML RNA-seq Foundation Models AI in Science 2× Hackathon Winner
View projects Get in touch
2×Hackathon First Place
4Publications
PhDBioinformatics & ML · Bristol
RocheAI Internship · Basel & Zürich
NatureBiomed Engineering · Published

About me

Where biology meets
machine learning.

I came from the biology side, and I've always thought the most interesting work happens where disciplines overlap.

I'm a Senior Data Scientist at Nexus BioQuest, a contract research organisation in Bristol, where I work across data science, machine learning, and analytical tool development in support of research programmes spanning pharmaceutical and biotech clients.

My PhD at the University of Bristol, funded by a competitive Cancer Research UK studentship, focused on predicting the functional impact of genetic variants in cancer genomes. I've since worked at Roche in Basel and Zürich, exploring protein language models and antibody optimisation - and published four peer-reviewed papers across cancer genomics, variant prediction, and drug discovery.

Beyond the code, I've led interdisciplinary teams to back-to-back hackathon victories - at Cambridge and the Wellcome Collection - and co-organised Bristol's first AI in Health meeting, securing two interdisciplinary research grants. I believe the best science happens at the edges of disciplines, and I love building the teams and environments where that becomes possible.

Based in
Bristol, UK
Experience
5+ Years
Current role
Senior Data Scientist, Nexus BioQuest
PhD
Bioinformatics & ML, Bristol
Funded by
Cancer Research UK
Interests
AI in science, open collaboration

A perspective on AI in science

AI is going to be part of everyday science.
It should work for everyone.

The tools exist. The clinical evidence is starting to follow. The harder question is who can actually use them.

"Some of the most powerful tools in the history of biology are sitting in research papers and GitHub repos that most bench scientists have never heard of. That feels like a problem worth working on."

AlphaFold more or less solved protein structure prediction in 2021 - a problem that had been open for 50 years. AI-designed drugs are now reaching clinical trials. The industry is reorganising around this, with pharma companies partnering with specialist AI firms and embedding NVIDIA infrastructure directly into their R&D pipelines. These are not future possibilities. They are happening now, and the pace is accelerating.

But using these tools well still requires an unusual combination of skills - enough ML to run and adapt the models, enough compute to work with them, and enough domain knowledge to ask the right questions. Most biologists have one of those things, maybe two. That gap is real, and it matters. I came into data science from the biology side, so I know what it feels like to have a question you cannot answer because the tools are out of reach. That is what drives most of what I build and write about.

The deeper analysis - the specific partnerships, what the clinical evidence actually shows, what NVIDIA's infrastructure deals mean in practice, and the honest open questions about whether this produces better drugs - is in the blog.

Foundation models reshaping biology

AlphaFold 2 & 3
DeepMind / Google
Predicted structures for 200M+ proteins by 2022. AlphaFold 3 (2024) extends to DNA, RNA, and small molecules - relevant to structure-based drug design.
ESM-2 & ESMFold
Meta AI
Protein language models trained on 250M sequences. Enable zero-shot fitness and function prediction - models I've used directly in my own research at Roche.
Evo 1 & 2
Arc Institute
Genomic foundation models trained across the tree of life on DNA sequences. Enable generative design of genes, regulatory elements, and CRISPR guides.
RFdiffusion
Baker Lab, UW
Diffusion model for de novo protein design - binders, enzymes, vaccine candidates - designed from scratch and experimentally validated.
BioNeMo
NVIDIA
An open platform wrapping biological foundation models - ESMFold, DiffDock, MolMIM - behind accessible APIs. Used by Amgen, Genentech, AstraZeneca, GSK, and Novo Nordisk. Over 100 firms on the platform as of 2024.
DiffDock & MolMIM
NVIDIA / MIT
DiffDock predicts protein-ligand binding poses using diffusion - faster than traditional docking. MolMIM generates novel small molecules optimised for target properties.
Geneformer
Broad Institute
Transformer pre-trained on 30M single-cell transcriptomes. Supports in silico gene perturbation and network inference - useful for target identification without wet-lab experiments.
scGPT
University of Toronto
Single-cell foundation model pre-trained on 33M cells. Enables cell type annotation, perturbation prediction, and gene regulatory network inference.
TxGNN
Harvard / Broad
Graph neural network trained on biomedical knowledge graphs for drug indication and contraindication prediction - a practical tool for repurposing existing compounds.
Pharma.AI / INS018_055
Insilico Medicine
End-to-end AI drug discovery platform. Used to design INS018_055, the first fully AI-generated drug to show efficacy in a Phase IIa trial (Nature Biotechnology, 2024). Target to Phase I in under 30 months.

The industry case studies are moving fast. I cover specific partnerships, what the deals actually involve, and what they mean for how drugs get made - in the Industry & Research blog posts below.

Projects & Hackathons

Things I've built and worked on.

A mix of published tools, hackathon projects, and pipelines built for real research problems.

🏆 1st Place · Cambridge

Mapping novel compounds to biological pathways

Led the winning team at GetSeen Ventures' AI × Cancer Bio Hackathon. Used transformer encoders on SMILES strings and high-content image embeddings from the RxRx3-core dataset to predict molecular pathways. Ongoing collaboration likely to result in publication.

TransformersSMILESImage EmbeddingsDrug Discovery
View project
🏆 1st Place · Wellcome Collection

Deep learning for protein fitness prediction

Led the winning team at the Roche & HDR Hackathon. Encoded protein sequences with pre-trained language models (ESM, AntiBERT) and explored CNNs to model sequence-function relationships using DMS data from Protein Gym. Secured a Roche AI internship as a direct result.

ESMAntiBERTCNNsDMSPyTorch
View project
Flow Cytometry

Automated flow cytometry analysis pipeline

Built a post-acquisition flow cytometry analysis pipeline with an intuitive Streamlit interface, applying unsupervised ML - clustering and dimensionality reduction - to high-dimensional cytometry data to uncover cell population patterns and accelerate downstream reporting.

PythonStreamlitScikit-learnUnsupervised ML
View project
Cancer Genomics

DrivR-Base - variant annotation toolkit

Published a data mining toolkit integrating molecular annotations for SNVs, creating a centralised resource that reduces redundancy and accelerates machine learning model development for variant effect prediction.

PythonRDockerCOSMICGnomAD
Read paper
Antibody Optimisation

Predicting mutation impact on antibody-antigen binding

At Roche pRED, used TensorFlow models grounded in global epistasis and pre-trained protein language models to predict binding affinity from deep mutational scanning data. Ongoing collaboration with University of Oslo, aiming for publication.

TensorFlowESMHPCDMS
Global Epistasis repo
Community

Bristol AI in Health Meeting

Co-organised Bristol's first interdisciplinary AI in Health Meeting in collaboration with the Elizabeth Blackwell Institute. Facilitated cross-disciplinary collaboration that resulted in two interdisciplinary grants for applied AI projects.

LeadershipEvent OrganisationGrant Facilitation
Learn more

Skills & Tools

The craft behind the work.

Picked up across academia, industry, and a few hackathons.

Languages & Systems

  • Python
  • R
  • SQL
  • Linux / HPC
  • Cloud platforms
  • Docker

Machine Learning

  • Scikit-learn
  • XGBoost / SVMs
  • Neural Networks
  • Foundation & Language Models
  • TensorFlow / PyTorch
  • MLflow

RNA-seq & Transcriptomics

  • Alignment: STAR, HISAT2, Salmon
  • QC: FastQC, MultiQC, Trimmomatic
  • Quantification: featureCounts, DESeq2
  • Differential expression: edgeR, limma
  • Unsupervised ML for cell population definition
  • Immunology cell type characterisation
  • UMAP / t-SNE dimensionality reduction
  • Pathway & gene set enrichment analysis

Bioinformatics & Data

  • Flow Cytometry
  • Deep Mutational Scanning
  • CRISPR / Image Analysis
  • COSMIC, GnomAD, TCGA
  • Protein / DNA Sequences
  • Proteomics (Olink)

Visualisation & Comms

  • Streamlit
  • Matplotlib / Seaborn
  • Scientific writing
  • Client consultation
  • Conference presenting

Leadership & Collaboration

  • Interdisciplinary team leadership
  • Hackathon team lead (2× winner)
  • Cross-functional collaboration
  • User-centred design
  • Grant facilitation
  • CRO client management

Publications

Peer-reviewed research.

Four published works spanning cancer genomics, variant effect prediction, and drug discovery.

Journal Article · 2026
CanDrivR-CS: A Cancer-Specific Machine Learning Framework for Distinguishing Recurrent and Rare Variants
Bioinformatics Advances - Accepted & Published
doi.org/10.1093/bioadv/vbag008
Application Note · 2024
DrivR-Base: A Feature Extraction Toolkit For Variant Effect Prediction Model Construction
Bioinformatics - Accepted & Published
doi.org/10.1093/bioinformatics/btae197
Review Article · 2023
Predicting Pathogenicity from Non-Coding Mutations
Nature Biomedical Engineering - Accepted & Published
doi.org/10.1038/s41551-022-00996-x
Online Report · 2024
Toxicity Prediction for Drug Discovery
The Alan Turing Institute, Data Study Group
doi.org/10.5281/zenodo.13882192

Get in touch

Always happy to talk science.

If something I've written resonates, if you're working on an interesting problem, or if you just want to talk about AI in biology - feel free to get in touch. I am always up for a good conversation.

Email[email protected]
GitHubgithub.com/amyfrancis97
LinkedInlinkedin.com/in/Amy-Francis2409

Writing

Thinking out loud.

AI is going to reshape how biology is done. I think scientists at every level need to understand what is actually happening - not the hype version, and not the version that assumes a computer science degree. I write here to try to bridge that gap: covering real tools, real evidence, and real implications, in language that a working scientist can use. Four themes: opinion, industry analysis, technical walkthroughs, and practical guides.

Opinion Published Great science needs more than scientists On what actually makes interdisciplinary teams work - diversity of background, the friction that comes with it, and why that friction is usually the point. Draws on three very different collaborative experiences. Read post →
Opinion Coming soon What makes a team actually work - on feedback, trust, and creating space for honest challenge The leadership questions that rarely get asked directly: how to build teams where people feel safe enough to disagree, how to give feedback that lands well, and why psychological safety is not a soft metric.
Industry & Research Published How AI is changing drug discovery - and what the evidence actually says The industry is reorganising fast - specialist AI partnerships, NVIDIA infrastructure embedded in pharma R&D, and the first AI-designed drugs reaching clinical trials. What is actually happening, what the evidence shows, and the honest open questions. Read post →
Technical Coming soon What NVIDIA's BioNeMo actually means for wet-lab scientists A practical look at what BioNeMo, DiffDock, and the broader NVIDIA biology stack make possible - and what still needs a specialist to get right.
Technical Coming soon Using ESM-2 to predict protein fitness - a walkthrough with real data A hands-on look at Meta's protein language model: what it actually does, how to run it, and how to interpret the output in a biological context.
Technical Coming soon Unsupervised ML for immune cell population discovery in RNA-seq data From alignment to UMAP - how to use clustering and dimensionality reduction to define cell populations without prior labels, and what to watch out for when you do.
Tutorials & Guides Coming soon RNA-seq from scratch - a practical guide for biologists who have never touched the command line A step-by-step walkthrough of a full RNA-seq pipeline - from raw FASTQ files to differential expression results - written for researchers with domain knowledge but no computational background.
Tutorials & Guides Coming soon What AlphaFold actually gives you - and how to make sense of it A plain-language guide to interpreting AlphaFold output: confidence scores, what pLDDT means in practice, and how to decide whether a predicted structure is actually useful for your question.