Let's Talk Research: AI & Mechanisms of Life (UPLAMANNO)
LauzHack presents its new initiative: "Let's Talk Research".
Have you ever wondered how research is done? Do you want to do research but think it is hard and too complicated? Or just want to get into a new research topic?
Join us for the "Let's Talk Research" events and we will show you that you can do research too!
NOTE: the lab is actively looking for interns and has several semester/thesis projects!
---
Event description:
Speakers: Luca Fusar Bassini, Alireza Gargoori Motlagh
Affiliation: Laboratory of brain development and biological data science (SV)
Recent engineering advances have revolutionized biological research by enabling the measurement of thousands of molecules simultaneously in single cells and entire tissues. This seminar will first introduce you to the fundamental biological concepts needed to understand cellular function in accessible terms. We will discuss the significant medical applications driving the single-cell analysis field—from improved disease diagnosis to personalized treatment strategies—highlighting how computational approaches matter beyond academic interest.
The core of our presentation focuses on biological challenges particularly amenable to computational and AI solutions. We'll explain what single-cell analysis entails and outline its key computational tasks:
· Batch integration (combining datasets while controlling for technical variation)
· Clustering cellular populations to find the “types” of cells in a dataset
· Discovering molecules that change in disease
· Identifying regulatory interactions between molecules
· Integrating data from different measurement technologies – for examples, single cells and tissue images
We'll explore current trends in applying machine learning to single-cell data, including innovative approaches to analyzing cellular responses to experimental perturbations such as drug treatments. The seminar includes practical components: a tutorial on Scanpy (a Python-based toolkit for analyzing single-cell data) and an introduction to GenePT, which leverages ChatGPT embeddings to incorporate decades of scientific literature into single-cell analysis while potentially improving interpretability.
Examples from our laboratory will demonstrate these concepts in action, showing how computational methods solve real biological questions. We are currently assembling a team of summer interns for a supercool, collaborative project at the interface of single-cell analysis, knowledge graphs, and LLMs. We also have open Master’s thesis positions and potentially other project positions will open soon.
---
Requirements: Prior experience in Biology is NOT required. But you need to have basic understanding of deep learning (Back-propagation; linear/convolutional layers; RNNs/Transformers). If you are not familiar with these techniques or want to refresh your memory, check our Deep Learning bootcamp GitHub and Recordings (Week01 is enough).