Novaflow, founded by Aman and Amulya, is tackling a critical bottleneck in life sciences: the slow and costly process of bioinformatics data analysis. Now part of the latest Y Combinator batch, Novaflow is building an accessible platform to help researchers make sense of large-scale experimental data quickly, affordably, and without needing to write code.

What Problem Are They Solving?

1. High cost of analysis: Many life science labs spend $100k+ per year per analyst; larger labs run into the millions.
2. Shortage of skilled analysts: Most labs operate at a 5:1 ratio of experimentalists to analysts, creating long wait times for data interpretation.
3. Dual-skill gap: Effective analysis demands both programming proficiency and biological insight—most researchers lack both.
4. Fragmented tools & infrastructure: Labs often juggle outdated scripts, limited compute, and inconsistent workflows.

Novaflow’s Approach

Novaflow combines natural language processing and intelligent automation to streamline the analysis process:

1. LLM-powered pipelines automate the selection and execution of appropriate workflows for various data types (e.g., scRNA-seq, ATAC-seq).
2. Upload and query: Users simply upload datasets (CSV, FASTQ, BAM, etc.) and describe their experiment in plain English.
3. Rapid output: Get publication-ready plots, summary insights, and exportable Jupyter notebooks in minutes.
4. Reproducible science: Each run is versioned and auditable, supporting better collaboration and confidence in results.

How It Works

1. Upload experimental data and describe the setup (e.g., “scRNA-seq of treated vs. control organoids”).

2. Novaflow selects the workflow: e.g., normalization, clustering/UMAP for scRNA-seq; DE analysis for bulk RNA-seq.

3. The system runs on cloud compute and returns clear visualizations, summaries, and code you can tweak or reuse.

With Novaflow, life scientists can upload experimental data, ask questions in plain English, and get instant, publication-ready plots, giving them results in minutes instead of months.