Papers for

biotechnology engineers

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Knowledge evolution improves protein design with modular strategies

KnowEvo: Knowledge Evolution for Protein Optimization

Abstract: Large language models (LLMs) have shown promise in scientific discovery, yet systematically accumulating and refining reusable scientific knowledge remains challenging. Existing approaches primarily improve LLM-based problem solving through parameter optimization or feedback-driven refinement of prompts, programs, and solution trajectories, leaving acquired expertise either embedded in model weights or scattered across iterative problem-solving processes. As a result,knowledge is difficult to systematically inspect, evaluate, and refine. We propose KnowEvo, a framework that treats externalized knowledge itself as the optimization target. Our key insight is that scientific knowledge is inherently modular: multiple interacting mechanisms jointly determine the design outcomes. This makes knowledge evolution fundamentally challenging, as improvements cannot be attributed to individual components in isolation. To address this, KnowEvo represents knowledge as executable expertise blocks and organizes their refinements into strategy mutation trees, enabling structured exploration over a combinatorial knowledge space. The framework combines a Thompson-style forward allocation strategy that adaptively distributes evaluation budgets across strategy variants with a backward revision process, in which a code agent operates in an isolated sandbox to translate rollout evidence into localized program updates. This design enables persistent accumulation, evaluation, and refinement of mechanistic expertise across iterative experimentation. We evaluate KnowEvo on protein optimization tasks including stability and solubility. Results show that knowledge evolution consistently improves over initial strategy blocks and outperforms monolithic program evolution and prior LLM-guided evolution baselines across metrics such as pass@k, MRR, MAP,and NDCG@5. Code is available at https://github.com/recynie/KnowEvo.

Fri 6 NovMachine Learning
The gist
Designing better proteins can be tricky because many factors work together in complex ways. The authors propose KnowEvo, a framework that treats scientific knowledge as building blocks that can be improved over time. These blocks can be tested, refined, and combined in different ways to get better protein designs. They show that this approach works better than previous methods on protein tasks like stability and solubility. This makes it easier to improve and understand how protein design knowledge evolves.
Open → 2611.09013v1

Protein design improved by guided search with folding model hints

ProteoCraft: Protein Design as Proposal-Verification Search

Abstract: Protein-protein interactions underpin nearly all biological processes. Yet, designing proteins with desired interactions remains challenging due to the structural complexity governing molecular recognition. This study views protein design as a search optimization problem over a combinatorial sequence space under expensive structural evaluation. Toward this goal, we introduce a novel tree-based search framework, ProteoCraft, that employs approximate structural gradients from diffusion-based structure predictors as effective proposal policies to specify where the search should explore. Complete no-gradient inference of folding models separately assigns values to the resulting sequences, determining what is good. ProteoCraft allocates this verification budget through a coarse-to-fine paradigm: multi-site edits first explore distinct sequence basins, then verified promising states undergo strict single-site refinement. Across fourteen de novo binder-design settings spanning eight target proteins, five immune-relevant TCR-facing targets, and four localized CDR redesign tasks, ProteoCraft improves design quality and high-confidence yield. These improvements persist under independent AF2-IG and Rosetta-based interface evaluation. Prospective experimental validation further yielded an 82.9% binding hit rate for PD-L1 miniproteins, with a best measured KD of 0.879 nM, and confirmed binding of designed IFNAR2 VHH. Our code is available at https://github.com/smiles724/ProteoCraft_v1.

Mon 2 NovComputational Engineering, Finance, and ScienceArtificial Intelligence
The gist
Designing proteins that bind to specific targets is very hard because of the complex way proteins fold and interact. The authors treat protein design like a search problem where many possibilities must be checked carefully. They created ProteoCraft, a new tool that guides this search using rough structure predictions and then verifies the best candidates more strictly. Tested on many protein targets, their method finds better protein designs, and experiments confirmed some high-quality protein binders it created. This approach helps design proteins for use in medicine and research more effectively.
Open → 2611.03963v1

Agents can design therapeutic antibodies with mixed success

Can agents reliably design therapeutic antibodies?

Abstract: Recent work has demonstrated agents driving protein design workflows, either through orchestration of specialized tools or direct manipulation of sequences. Yet the fidelity with which agents follow protein design instructions and the factors contributing to their effectiveness remain understudied. We examine agentic antibody design under two settings: when explicit molecular-editing instructions are provided and when agents receive only previously-scored sequences and are prompted to propose improvements. We call the first task-guided and the second black-box design. For the task-guided setting, we curate ten expert-validated affinity-improvement tasks and show that LLM judges closely reproduce programmatic evaluations of instruction following. We then study two augmentations: access to antibody-relevant tools and to previously scored design history. Tools improve instruction following (IF) and sequence space exploration while reducing optimization performance, whereas design history reduces IF but improves optimization performance at the expense of exploration. Finally, we combine taskguided and black-box design within an in silico optimization loop and show that our agentic optimizer performs comparably to an established Bayesian optimization baseline.

Sat 31 OctMachine Learning
The gist
Designing better antibodies for therapies is hard and sometimes done by computer programs called agents. This paper studied how well these agents follow instructions when designing antibodies and what helps them do better. The authors tested agents working with clear instructions and agents working by improving existing designs without instructions. They found that tools help agents follow instructions but hurt how well they optimize, while learning from design history has the opposite effect. Combining these methods, agents worked about as well as a standard optimization technique.
Open → 2611.00558v1

New method improves learning smooth dynamics from position and velocity data

Learning smooth dynamics via Kinematic Interpolants

Abstract: Inferring dynamics from real-world experimental data is inherently ambiguous, as many plausible dynamical systems can explain the same positional observations at measurement times. For higher fidelity modeling of applications ranging from single-cell RNA to vortex dynamics and even flocking of birds, scientific observables increasingly also include velocity estimates that serve to resolve this issue. However, incorporating this rich information in a scalable manner, free of simulation or unnecessary approximations, has remained a difficult challenge. In this paper, we introduce Kinematic Interpolants (KI), a novel framework that extends the seminal methodology of stochastic interpolants to infer nonlinear dynamics across multiple snapshots in phase space, i.e., observables with position and velocity measurements. Empirically, we demonstrate that across several scientific datasets, KI achieves superior reconstruction of the underlying dynamics compared to existing baselines while requiring only a fraction of the training time.

Thu 15 OctMachine Learning
The gist
Many different rules can explain how things move when we only look at their positions at certain times. The authors found a better way to use information about both positions and speeds to learn the underlying rules of movement. Their approach, called Kinematic Interpolants, works well for complex systems like cells, fluids, or birds moving together, and it learns faster than other methods.
Open → 2610.22519v1

Attentive geometric learning improves antibody design accuracy and affinity

AbGaze: Attentive Geometric Representation Learning for End-to-End Antibody Design

Abstract: Computational antibody design requires representations that capture the geometric patterns underlying antigen--antibody interactions, yet existing approaches often rely on scalar distances or surface-intrinsic features, leaving cross-molecular geometry largely implicit. We present AbGaze, an end-to-end antibody design framework based on attentive geometric representation learning, which encodes distance, spatial direction, and surface-normal orientation of antigen surfaces relative to antibody-residue local frames, and adaptively aggregates these geometric interactions according to their interfacial context. The learned interaction representation is shared across multi-CDR co-design, complex structure prediction, and affinity optimization, with local-frame geometric supervision further constraining the representation. AbGaze outperforms prior methods across all three tasks: relative to the second-best method, it improves amino-acid recovery by 7.1% and reduces structural error by 14.9% on average over the six CDRs, improves interface docking quality (DockQ) by 6.6%, and raises the affinity improvement rate (IMP) by 32.5%.

Mon 28 SeptArtificial Intelligence
The gist
Designing antibodies that fit well with antigens is important for medicine, but it requires understanding complex 3D shapes and interactions. The authors created AbGaze, a method that looks closely at distances, directions, and surface shapes to better capture these details. This helps design antibodies more accurately, predict their structures, and improve how strongly they bind. AbGaze works better than earlier methods in several tests involving antibody parts, docking, and strength of binding.
Open → 2609.35296v1

CAGenMol-2 enables versatile drug molecule design from one model

One Sequence, Many Decodings: CAGenMol-2 Recasts Drug Design as Masked Molecular Inference

Abstract: Drug design couples property evaluation, conditional generation, structure-based design, and local optimization, yet machine learning systems typically address these capabilities with separate task-specific models. We introduce CAGenMol-2, a masked diffusion molecular language model that represents molecules, continuous scalar properties, and 3D protein pockets within a single wrapped sequence. Within this pretrained interface, downstream operations are selected by which sequence regions are observed or masked at inference, allowing one checkpoint to perform property prediction, property- and pocket-conditioned generation, and partial-constraint design without task-specific architectures or backbone fine-tuning. We further propose Adaptive Fragment Optimization (AdaFO), a gradient-free mask-and-refill search that turns the masked decoder into an iterative local molecular optimizer. On CrossDocked2020, AdaFO increases Success Rate from 30.2\% to 70.8\%, the best reported under this protocol, while largely preserving drug-likeness and diversity. Finally, scaffold-preserving directional editing and CRBN/VHL case studies demonstrate its use in compound design workflows spanning local molecular editing, structure-based prioritization, and downstream simulation-based screening.

Mon 28 SeptMachine LearningArtificial Intelligence
The gist
Designing new drug molecules usually requires many different specialized tools. The authors present CAGenMol-2, a single AI model that can understand molecules, predict properties, design new molecules, and optimize parts of them all at once. By selectively revealing or hiding different pieces of information during use, this one model can perform many tasks without needing separate setups. They also introduce AdaFO, a new method that improves molecule design success without needing gradients, leading to better drug candidates. This approach works well with preserving important molecule structures and helps guide drug discovery workflows.
Open → 2609.34301v1