Join me at the Nextflow Summit in Boston on May 1st to learn about "Building Multi-agentic Bioworkflows with Microsoft Foundry and Nextflow".

Link: summit.nextflow.io/2026/boston/...

#bioinformatics #genomics #microsoftfoundry #ai #agents #nextflow

Connecting OpenClaw to Models in Microsoft Foundry OpenClaw has taken the AI world by storm as it enables users to build local, personal AI agents to perform various tasks. Some people are…

🦞 New blog post ⤑ Connect #OpenClaw to #AI models deployed in your own private Microsoft Foundry project.

Link: medium.com/@colbyford/c...

Structuring Proteomics Data from Multiple Lab Vendors in Cloud Data Warehouses When dealing with genomics and transcriptomics data, the bioinformatics community has mostly settled on a few file formats (e.g., BAM, VCF…

New blog post! Structuring #Proteomics Data from Multiple Lab Vendors in #Cloud Data Warehouses

medium.com/@colbyford/s...

🐿 Feeling squirrely about #AI #agents? I have a new O'Reilly book coming out that might help! "Building Agentic Solutions with Microsoft Foundry" comes out in a few months, but you can read chapters 1-3 today!

🔗: www.oreilly.com/library/view...
#microsoftfoundry #azure #finetuning #knowledgebases 🌰

Building Data-Heavy Bioinformatics APIs using Serverless Azure Functions and Cosmos DB I’ve been using Azure Functions and Cosmos DB for years across various clients and use cases. However, it was only recently that I…

🧬 New Blog Post: Building Data-Heavy Bioinformatics APIs using Serverless Azure Functions and Cosmos DB medium.com/p/building-d...

Today seemed like a good day to open-source some AI antibody design code! Using our 🦋 peleke-1 antibody languages models, we generated many antibody sequences that target Nipah virus with decent affinity.

Repo: github.com/silicobio/Ni...

#MoML @ MIT just kicked off. It’s cool to see so many people excited about #ML and #molecularmodeling. Let’s see what un-“folds” next!

Our 🦋 #peleke-1 paper was accepted this year and the poster is in spot #13.

#molecules #ai #llm #plm #bioinformatics #computationalbiology #biochemistry

peleke-1: A Suite of Protein Language Models Fine-Tuned for Targeted Antibody Sequence Generation The discovery of therapeutic antibodies is a traditionally arduous process. Today, the lab-based process of antibody discovery consists of several time-consuming steps that involve live animal immuniz...

New paper! peleke-1: A Suite of Protein Language Models Fine-Tuned for Targeted Antibody Sequence Generation 🦋

Link: www.biorxiv.org/content/10.1...

Model. Package. Deploy. Repeat: A DevOps Approach to Biomolecular Scalability YouTube video by Boston Protein Design and Modeling Club

If you missed seeing @colby.tuple.xyz's excellent talk back in July, you can now check out the recording 👇 youtu.be/k63Xh-oJMs0

5 Tips for Fine-Tuning Protein Language Models (PLMs) on Azure Machine Learning Protein Language Models (PLMs) are ramping up as the next frontier in AI-assisted drug design. We have seen the utility of models like…

5 Tips for Fine-Tuning Protein Language Models (PLMs) on Azure Machine Learning

blog.colbyford.com/5-tips-for-f...

New research shows how bird flu is evolving It is evolving and researchers at UNC Charlotte have discovered that could be a problem

Our new research shows how bird flu is evolving:
www.wbtv.com/video/2025/0...

quick reminder to join us tonight at @harvardmed.bsky.social for a great talk by Colby Ford @colby.tuple.xyz

H5N1 Adapts for a Human Host YouTube video by UNC Charlotte

H5N1 Adapts for a Human Host youtu.be/FNWdzaZCemk?... via
@YouTube

AI-Based Antibody Design Targeting Recent H5N1 Avian Influenza Strains In 2025 alone, H5N1 avian influenza is responsible for thousands of infections across various animal species, including avian and mammalian livestock such as chickens and cows, and poses a threat to h...

New paper: #AI -Based #Antibody Design Targeting Recent #H5N1 Avian Influenza Strains

www.biorxiv.org/content/10.1...

New avian #influenza (H5N1) paper: Large-scale computational modelling of H5 influenza variants against HA1-neutralising antibodies!

We used #AI- and #physics-based modeling of over 18k H5N1 isolates.

Paper: lnkd.in/ekikJrE9
Code: lnkd.in/eY8Y4vmt

#bioinformatics #genomics #computationalbiology

Comprehensive guide for epigenetics and transcriptomics data quality control Host response to environmental exposures such as pathogens and chemicals can include modifications to the epigenome and transcriptome. Improved signat…

New paper! Transcriptomic analyses in bioinformatics are only as good as the data we give them. In this article, we outline some best practices for QC in sequencing and bioinformatics in RNA-seq, scRNA-seq, ATAC-seq, ChIP-seq, and a ton more.

Read the article: www.sciencedirect.com/science/arti...

I've created a new plugin for #PyMOL (called PyMOLfold) that allows you to fold protein sequences right in the GUI. Simply select your model of choice (e.g., #ESM3, Boltz-1) and paste in your amino acid sequence.
github.com/colbyford/Py...

#ai #proteinfolding #alphafold

Human cytokine and coronavirus nucleocapsid protein interactivity using large-scale virtual screens Understanding the interactions between SARS-CoV-2 and the human immune system is paramount to the characterization of novel variants as the virus co-evolves with the human host. In this study, we empl...

New Paper Alert! We're very excited that our SARS-CoV-2 N <> cytokine modeling paper has been accepted in Frontiers in Bioinformatics. In this work, we showcase the use of high-performance computing for large-scale molecular modeling.

Give it a read: www.frontiersin.org/articles/10....

CAGI, the Critical Assessment of Genome Interpretation, establishes progress and prospects for computational genetic variant interpretation methods - Genome Biology Background The Critical Assessment of Genome Interpretation (CAGI) aims to advance the state-of-the-art for computational prediction of genetic variant impact, particularly where relevant to disease. ...

Our consortium paper for CAGI: The Critical Assessment of Genome Interpretation was just released.

Read the paper in Genome Biology here: genomebiology.biomedcentral.com/articles/10....

#bioinformatics #genomics #genetics #computationalbiology #machinelearning #ai #datascience #rarediseases

PD-1 Targeted Antibody Discovery Using AI Protein Diffusion bioRxiv - the preprint server for biology, operated by Cold Spring Harbor Laboratory, a research and educational institution

I'm very excited to present some exciting research that I've been working on. PD-1 is a very important target in cancer therapeutics, so using AI to speed up the drug discovery process is certainly of interest.

AI-designed anti-PD-1 antibodies - bioRvix preprint (www.biorxiv.org/content/10.1...)

I'm very excited to share this collaborative research project that included myself and researchers from MIT Lincoln Lab where we showcased the utility of high-performance computing to scale molecular modeling in SARS-CoV-2 research.

Read the preprint here: www.biorxiv.org/content/10.1...

Hello!

Exploring AI-Based Protein Sequence Generation with EvoDiff from Microsoft Research EvoDiff is a new, state-of-the-art protein sequence generation system from Microsoft Research. How well does it work?

Protein Sequence Generation with EvoDiff: colbyford.medium.com/exploring-ai...

#proteins #diffusion #ai #computationalbiology #bioinformatics #rfdiffusion #alphafold #colabfold

Hello, BlueSky. ☁️

Behavioral and transcriptomic analyses of mecp2 function in zebrafish https://www.biorxiv.org/content/10.1101/2023.09.13.557635v1 Rett Syndrome (RTT), a human neurodevelopmental disorder characterized by severe cognitive and motor

Behavioral and transcriptomic analyses of mecp2 function in zebrafish www.biorxiv.org/content/10.1101/2023.09....