Logan Blaine

Logan Blaine

(he/him)

PhD Candidate in Bioinformatics and Integrative Genomics

Harvard Medical School

Professional Summary

Logan is a Ph.D. candidate in Biomedical Informatics at Harvard Medical School building probabilistic machine learning systems that reason over large-scale biological data. His work in the Pinello Lab develops Bayesian & deep learning models — spanning representation learning, generative modeling, and causal inference — to turn high-throughput single-cell experiments into testable hypotheses about biological mechanism, with the broader goal of building computational systems that can reason under uncertainty and close the loop with experimental biology.

Outside of lab, he enjoys training for marathons (and the occasional IRONMAN triathlon) and bikepacking around Vermont.

Education

Ph.D. in Biomedical Informatics

2020–2026 (Expected)

Harvard Medical School

A.B. in Molecular Biology, magna cum laude

2014–2018

Princeton University

Interests

AI agents for science Representation learning Generative modeling Probabilistic machine learning Bayesian statistics Causal inference Single-cell & spatial -omics CRISPR screens Lineage tracing
Projects

PerTurbo

Robust and efficient analysis of single-cell perturbation studies — a scalable Bayesian analysis framework for large-scale Perturb-seq screens.

IGVF Consortium CRISPR Screen Pipeline featured image

IGVF Consortium CRISPR Screen Pipeline

A Nextflow pipeline for analyzing single-cell CRISPR screen data, developed within the IGVF consortium CRISPR Focus Group.

MEGATRON featured image

MEGATRON

MEGA TRajectories of clONes — a computational framework for single-cell lineage tracing analysis using mitochondrial mutations.

scDNA Analysis Pipeline

In-house pipelines for calling copy number variants, structural variants, and single nucleotide variants from single-cell whole genome sequencing data.

Publications & Manuscripts