Machine Learning

The AI hype in pharma has mostly yielded faster failures. Despite generative models for molecules and AlphaFold for protein folding, the fundamental chasm remains: what works in silico or in vitro still too often flops in vivo. A new proposal — Programmable Virtual Humans (PVHs) — may finally aim high enough: modeling the entire cascade of drug action across human biology, not just optimizing isolated steps. 🧬 The Translational Gap Isn’t Just a Data Problem Most AI models in drug discovery focus on digitizing existing methods. Target-based models optimize binding affinity; phenotype-based approaches predict morphology changes in cell lines. But both ignore the reality that molecular behavior in humans is emergent — shaped by multiscale interactions between genes, proteins, tissues, and organs. ...

In a world where climate models span continents and economic simulators evolve across decades, it’s no longer enough to ask which variable affects the output the most. We must now ask: how does each input reshape the entire output distribution? The R package gsaot brings a mathematically rigorous answer, harnessing the power of Optimal Transport (OT) to provide a fresh take on sensitivity analysis. ...

When electricity markets were deregulated across many U.S. states in the 1990s, economists and policymakers hoped competition would lower consumer prices. But for decades, the results remained ambiguous—until now. A new paper, Causality analysis of electricity market liberalization on electricity price using novel Machine Learning methods, offers the most precise evaluation yet. Using cutting-edge causal machine learning models, the authors demonstrate that liberalization led to a 7% decrease in residential electricity prices in the short term—a finding with major implications for regulatory policy and infrastructure reform. ...

Classic finance assumes that the past doesn’t matter — only the present state of the market matters for decisions. But in a new paper from researchers at Imperial College and Oxford, a kernel-based framework for trading strategy design exposes how this assumption leads to suboptimal choices. Their insight: memory matters, and modern tools can finally make use of it. ...