Mikel Landajuela

Mikel Landajuela

Senior Staff Scientist at Lawrence Livermore National Laboratory

Blog posts

2025

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.

2024

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.

2023

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

3 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.

2022

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.