#Computational Biology

8 posts tagged with "Computational Biology"

The Historical Accident That Split Drug Design in Two (And the Contrastive Model That Reunites It)

2026-01-30T16:00:00Z•12 min read

#drug discovery #contrastive learning #computational biology #virtual screening #protein-ligand interactions #graph neural networks #machine learning

Structure-based and ligand-based drug design evolved as separate fields solving the same problem. ConGLUDe, a contrastive geometric learning model, unifies both approaches and outperforms specialist methods on realistic benchmarks without requiring pre-defined binding pockets.

How AlphaGenome Tackles Variant Effect Prediction

2026-01-29T12:00:00Z•8 min read

#genomics #deep learning #variant effect prediction #alphagenome #computational biology

AlphaGenome processes 1 million DNA base pairs to predict variant effects across 7,000+ genomic tracks in one second, outperforming specialized models on 25 of 26 VEP benchmarks.

How AlphaGenome Models Gene Regulation: 2D Embeddings, Splicing, and the Race to Read Non-Coding DNA

2026-01-29T11:00:00Z•18 min read

#alphagenome #genomics #deep learning #splicing #computational biology #google deepmind #variant interpretation

A technical look at AlphaGenome's architecture, its 2D pairwise embeddings for splicing prediction, and what the model means for clinical variant interpretation.

EDEN: 28 Billion Parameters for Programming Biology

2026-01-28T14:00:00Z•16 min read

#foundation models #computational biology #gene therapy #metagenomics #drug discovery #eden #basecamp research

Basecamp Research's EDEN model trains on proprietary environmental metagenomics to design gene-insertion enzymes, antimicrobial peptides, and synthetic microbiomes -- all validated in the wet lab.

When 62 Days of Compute Becomes 3: Diffusion Models as Fast Surrogates for Agent-Based Biological Simulations

2026-01-03T12:00:00Z•14 min read

#diffusion models #agent-based modeling #computational biology #cellular potts #surrogates #machine learning

How generative diffusion models can serve as fast surrogates for expensive biological simulations, achieving 22x speedup while preserving the stochastic diversity that makes these models scientifically useful.

Biological World Models: The Projects You're Not Building (But Should Be)

2025-12-18T14:00:00Z•16 min read

#world models #computational biology #machine learning #single cell #neural ode #flow matching

Why computational biologists should stop building embeddings and start building simulators, with three tractable project ideas you can implement today using flow matching, Neural ODEs, and cell fate trajectory modeling.

Biology's Secret Weapon: Physics-Based Benchmarks for Training RL Agents

2025-12-03•16 min read

#reinforcement learning #biological benchmarks #protein design #rna design #computational biology #machine learning #alphafold #drug discovery

Why biological systems offer the ideal training ground for reinforcement learning: automated verification through physics, not human judgment. From protein design with AlphaFold to RNA folding with ViennaRNA, biology provides the verifiable inverse problems that RL needs at scale.

The Dark Matter of Biology: What Machine Learning Reveals About the Invisible Proteome

2025-12-02•20 min read

#machine learning #computational biology #protein structure #rna #alphafold #intrinsic disorder

Machine learning is illuminating biology's hidden half: intrinsically disordered proteins and RNA structures that traditional methods could never capture. But can we trust what we're seeing?