AI Paper Atlas

Research map / Probabilistic and scientific modeling

Molecules and proteins: research map

2,120 papers on Molecules and proteins in Probabilistic and scientific modeling, from ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR (2016–2026), grouped into 6 clusters and 26 approaches. The busiest year so far is 2026.

What it is

Machine learning for science, especially chemistry and biology: generating new molecules and proteins, predicting their properties and how they bind, and modelling trajectories and events over time. Models respect the 3D symmetry of molecules and are increasingly generative (diffusion and flow matching).

Terms you will see on this page:

Equivariance
the model's output rotates or moves consistently when the 3D input does.
Structure-based design
designing a molecule to fit a given protein pocket.
Flow matching
a way to train generative models by learning a velocity field that moves noise to data.

Start reading with the most cited papers here:

Within Probabilistic and scientific modeling, its share grew from 24.1% in 2023–24 to 30.4% in 2025–26 (490 → 927 papers at ICML, NeurIPS, ICLR, CVPR and AAAI, the venues with data for all four years).

2016: 57162017: 55172018: 61182019: 72192020: 97202021: 159212022: 135222023: 228232024: 292242025: 433252026: 53126

Explore Molecules and proteins in the interactive map

Working on something in this topic? Describe your idea in scime atlas to see which approach it falls under, the closest papers by meaning and how crowded the spot has become.

What changed recently

Approaches whose share of the topic moved most between 2023–24 and 2025–26 (ICML, NeurIPS, ICLR, CVPR and AAAI):

Papers from 2025–2026 that are already cited most:

Approaches and key papers

Statistical tools for scientific ML · 607 papers
Keywords: decision, machine, statistical

Approaches in this cluster:

Most cited and most cited since 2024:

Latent representations for science · 462 papers
Keywords: latent, space, representations

Approaches in this cluster:

Most cited and most cited since 2024:

Protein design and prediction · 367 papers
Keywords: proteins, binding, sequence

Approaches in this cluster:

Most cited and most cited since 2024:

Molecule generation and chemistry · 309 papers
Keywords: molecules, drug, chemical

Approaches in this cluster:

Most cited and most cited since 2024:

Flow matching and trajectories · 298 papers
Keywords: flow, trajectory, matching

Approaches in this cluster:

Most cited and most cited since 2024:

Event sequences and survival analysis · 77 papers
Keywords: event, point processes, temporal

Approaches in this cluster:

Most cited and most cited since 2024:

Related topics in Probabilistic and scientific modeling

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy