Mikel Landajuela

Mikel Landajuela

Senior Staff Scientist in AI for Science, Machine Learning, and Scientific Computing

Sitemap

A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.

Pages

Mikel Landajuela

Senior Staff Scientist in AI for Science, Machine Learning, and Scientific Computing

Awards

Selected awards and distinctions across research, publications, and early-career academic achievement.

Projects

Selected research and software projects spanning antibody engineering, interpretable AI, and scientific computing.

Publications

Selected peer-reviewed publications across AI for science, antibody design, interpretable machine learning, and scientific computing.

Research

Research at the intersection of AI for science, interpretable machine learning, antibody design, and high-performance scientific computing.

Talks and presentations

Selected keynotes, invited talks, conference presentations, posters, and workshops across AI for science, machine learning, and scientific computing.

Writing

Notes and research writing on AI for science, symbolic optimization, machine learning, and scientific computing.

Posts

Combinatorial Optimization of Antibody Libraries via Constrained Integer Programming

19 minute read

Published:

In this blog post, we present ProtLib‑Designer (PLD), a novel method for designing diverse and high-quality antibody libraries through combinatorial optimization. PLD leverages AI-based in silico deep mutational scanning to evaluate the effects of mutations on antibody properties, and formulates library design as a constrained integer linear programming (ILP) problem. By explicitly optimizing for multiple objectives—binding affinity, developability, and diversity—PLD generates antibody libraries that outperform traditional greedy and evolutionary approaches. We will explore the key components of ProtLib‑Designer, its optimization framework, and empirical results demonstrating its effectiveness in generating superior antibody libraries.

DisCo-DSO: Joint Optimization in Hybrid Discrete-Continuous Spaces

5 minute read

Published:

In this blog post, we introduce DisCo-DSO (Discrete-Continuous Deep Symbolic Optimization), a novel approach for joint optimization in hybrid discrete-continuous spaces. DisCo-DSO leverages autoregressive models and deep reinforcement learning to optimize discrete tokens and continuous parameters simultaneously. This unified approach leads to more efficient optimization, robustness to non-differentiable objectives, and superior performance in tasks like decision tree learning and symbolic regression. Let’s dive into the key innovations, applications, and results of DisCo-DSO.

Grounding ChatGPT-like systems in the real world with Wolfram Alpha

4 minute read

Published:

In this blog post, we will explore the potential of integrating ChatGPT with a computational knowledge engine like Wolfram Alpha. In his recent blog post Wolfram Alpha as the Way to Bring Computational Knowledge Superpowers to ChatGPT, Stephen Wolfram describes how ChatGPT excels in the “human-like parts” of language processing but may struggle with precise answers. By connecting ChatGPT with Wolfram Alpha and its vast computational knowledge, we aim to bridge this gap and provide ChatGPT with the “grounding” into the real world that large language models like GPT are missing. We will create reports with real data and visuals to showcase the potential of this integration. Let’s get started!

Neural-Guided Search for Scientific Discovery

3 minute read

Published:

In recent years, the field of scientific discovery has seen a surge of interest in the application of machine learning techniques. One promising approach is Deep Symbolic Optimization (DSO), a computational framework for scientific discovery that treats the discovery problem as a sequential decision-making task. In this blog post, we provide an overview of the DSO framework and its applications to scientific discovery.

Machine Learning for Cardiac Electrocardiography

9 minute read

Published:

In this blog, we explore the possibility of using machine learning to reconstruct electroanatomical maps at clinically relevant resolutions using only standard 12-lead electrocardiograms (ECGs) as input. The blog post is also available in Medium.

Wolfram Demonstrations Project

less than 1 minute read

Published:

The Wolfram Demonstrations Project is a collection of interactive examples in the Wolfram Language to illustrate different concepts in mathematics, physics, engineering, and other fields. During the last years, I contributed with some of them. I decided to collect all my Wolfram Demonstrations in a single place.

portfolio

publications

talks

teaching

Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post.

Teaching experience 2

Workshop, University 1, Department, 2015

This is a description of a teaching experience. You can use markdown like any other post.