Postdoctoral Fellow- Computational Biology and Machine Learning

Postdoctoral Fellow – Computational Biology and Machine Learning

Join to apply for the Postdoctoral Fellow – Computational Biology and Machine Learning role at Wellcome Sanger Institute

Do you want to help us improve human health and understand life on Earth? Make your mark by shaping the future to enable or deliver life‑changing science to solve some of humanity’s greatest challenges.

We are hiring a Postdoctoral Fellow/Senior Postdoctoral Fellow to join our interdisciplinary team at the forefront of computational biology and AI for a 3 year fixed term contract. You will contribute to (lead – Senior Postdoctoral Fellow) transformative projects that integrate single‑cell genomics, spatial transcriptomics, and generative AI to build next‑generation models for understanding tissue biology and cellular dynamics across organs such as the pancreas, kidney, skin, and liver.

We welcome applicants from diverse technical and scientific backgrounds— from those interested in fundamental questions in biology and medicine, to those focused on ML/AI method development. We are particularly excited to work with individuals who are passionate about biology, foundation model development, modelling cellular perturbation responses, predicting patient behaviours, and analysing multi‑modal biological data.

• Spatial & Multi‑omics Atlas Construction:
  Build large‑scale spatial and single‑cell atlases across diseased tissues (pancreas, kidney, skin, liver) using spatial transcriptomics, scRNA‑seq, and multiome data in collaboration with leading Sanger groups.
• Generative AI for Cell Fate & Perturbations:
  Develop diffusion, flow‑matching, and transformer‑based generative models to predict cell fate, tissue remodelling, and drug or perturbation responses in silico.
• Foundational Models for Single‑Cell Biology:
  Train large, generalizable deep models across public and internal datasets to support the Human Cell Atlas and broad Sanger research programs.
• Open Targets Translational AI Projects:
  Apply foundational and multi‑omics models to real‑world challenges in drug discovery, target identification, and target safety in collaboration with major pharma partners.
• Agentic AI for Scientific Reasoning & Experiment Design (new):
  Develop AI agents capable of hypothesis generation, experiment planning, and multi‑step scientific workflows using reinforcement learning and tool‑use models.
• Core Machine Learning Research:
  Advance fundamental ML methods—including advanced generative modelling, scalable training algorithms, representation learning, and uncertainty modelling—tailored for biological data.
• Multimodal Learning (Imaging + Genomics + Clinical Data):
  Create models that integrate histopathology imaging, spatial proteomics, single‑cell genomics, and patient‑level clinical data to learn unified biological and clinical representations.
• Leap Project:
  We are interested in developing large‑scale AI models to stratify patients using diverse multi‑omics data, with a strong commitment to equity and inclusion, particularly in women’s health. This work is being undertaken in collaboration with Roser Vento‑Tormo at the Sanger Institute.

The Open Targets (OT) research programme generates and analyses data to connect targets to diseases, assess the strength of this evidence, and help identify and prioritise targets for drug discovery. This includes evidence that causally links targets and diseases, as well as foundational data that helps us understand biological processes and disease progression more deeply.

You will join the Lotfollahi Group
, an interdisciplinary team of ML researchers, computational biologists, clinicians and experimentalists. Our mission is to develop data‑driven and biologically grounded AI tools for decoding complex cellular systems. We collaborate closely with the Human Cell Atlas, Sanger's single‑cell programs, and international leaders in the field.

• Akbar Nejat et al., Mapping and reprogramming human tissue microenvironments with Mint Flow (bioRxiv, 2025)
• Birk et al., Quantitative characterization of cell niches in spatially resolved omics data, Nature Genetics…