Skip to content

EXPERIMENTAL BIOLOGY · QUANTITATIVE IMAGING · EVIDENCE-GROUNDED AI

Bio × AI Research &Scientific Platforms

I connect experimental cell biology, quantitative imaging and computational modelling to investigate biological organisation, predict cellular behaviour and build traceable scientific platforms.

My work spans biological feature design, prospective validation, multimodal evidence integration and human-guided interpretation—keeping models accountable to biological evidence.

INTERACTIVE LEARNING & RESOURCES

01

Supervised
Machine Learning

Models, validation, ensembles

Explore →
02

SQL
Playground

Query relational data interactively

Explore →
03
Software project

Sankey Motion

Animated flow visualisation

04

Interactive
Machine Learning

50 interactive experiments in classical machine learning

Explore →
05

Deep Learning

20 interactive experiments in representation learning & neural systems

Explore →
06

Infrastructure
Atlas

From laptop to production, global scale & AI infrastructure

Explore →
09

AI Agents

RAG, MCP, A2A, tools, evaluation and evidence-grounded orchestration.

Explore →
10

Reference
Library

Shared RAG concepts, Python examples, provenance and evidence boundaries.

Explore →
12

Data Visualization

Evidence-focused charts, uncertainty, annotation and visual reasoning.

Explore →
13

Unsupervised
Learning

PCA, clustering, nonlinear maps and anomaly detection.

Explore →
14

Reinforcement
Learning

Agents, value, policy, safety and bounded decision-making.

Explore →
15

Life Sciences,
Language & AI

Representation, retrieval, reasoning, evaluation and responsible AI for biological knowledge systems.

Explore →
25

Time Series
Analysis

Temporal structure, diagnostics, baselines, uncertainty and decision boundaries.

Explore →
26

Sequence to
Behaviour

Labels, baselines, base rates and prediction boundaries.

Explore →
27

Model Drift

When a live model stops being valid, and how you would know.

Explore →
28

Validation
Design

Leakage, split design and scores that mean what they say.

Explore →
29

Experiment
Design

Randomisation, peeking, confounding and what a test cannot tell you.

Explore →
30

Calibration &
Confidence

What a 0.9 claims, where a threshold comes from, and when to withhold a number.

Explore →

TRIMCode & predictive frameworks

Animated explainer · schematic

TRIM protein architecture

Sequence, domains and interactions — the modular architecture TRIMCode connects to cellular organisation and, downstream, to predictive modelling.

Animated explainer · schematic

Segment cells & compartments

A proposed computer-vision framework converting microscopy into analysis-ready masks — reference annotations, predictions and experiments kept explicitly distinct.

Animated explainer · schematic

PICNIC: features beyond disorder

Sequence, predicted structure and disorder combined into a proteome-scale prediction of condensate-forming proteins, validated against cellular evidence. Developed with the Tóth-Petróczy lab, MPI-CBG.

Animated explainer · schematic

Can condensation be read from sequence?

The open question connecting sequence-level features to condensate-forming behaviour — the boundary this Bio × AI work, with the Tóth-Petróczy lab at MPI-CBG, is testing against cellular evidence.

RESEARCH AREAS, METHODS & SYSTEMS

Emerging initiatives

New directions in Bio × AI

State & perturbation

Biological State & Perturbation Intelligence

Models and interfaces for understanding how biological systems respond, recover and change state.

Scientific agents

Scientific Agents for Biology

Assistive systems for evidence synthesis, experimental planning and reproducible analysis.

Knowledge systems

Language & Scientific Knowledge Systems

Structured retrieval and reasoning across literature, mechanisms and biological evidence.

Data & atlases

Data Platforms & Biological Atlases

Connected systems for organising biological measurements, relationships and multiscale data.

Translation

Translational Decision Intelligence

Evidence structures connecting disease biology, biomarkers and therapeutic hypotheses.

Scientific software

Interactive Research Tools

Exploratory tools that make biological data, models and scientific decisions inspectable.

Multidisciplinary life sciences

Many disciplines, one living system.

Synthesis & living systems

Synthetic Biology & Biotechnology

Designing, testing and translating biological mechanisms into engineered living systems and useful biotechnology.

  • Synthetic Biology
  • Biotechnology
  • Molecular Engineering
  • Cellular Engineering
Explore →
Measurement & matter

Physics, Chemistry & Quantitative Biology

Revealing structure, dynamics, energy and interaction through physical principles, chemical reasoning and multiscale measurement.

  • Physics
  • Chemistry
  • Biophysics
  • Quantitative Imaging
Explore →
Modelling & construction

Mathematics, Computation & Engineering

Turning quantitative and imaging-derived observations into models, software, AI systems and engineered tools that generate testable scientific decisions.

  • Mathematics
  • Computational Science
  • Data & AI
  • Engineering
In progress

Highlights

Science in the public interest.

Interactive methodsWorked examples with adjustable parameters.
Data and visualisationDatasets, analytical views and scientific visualisation.
Inspectable modelsModels, parameters and outputs remain inspectable.
Evidence and limitsExamine methods, assumptions, provenance and limits.