Follow this section to personalize your feed and get instant alerts. Follow Go to your personalized feed WHY FOLLOW? Smart Alerts: Get notified about major news as it happens. Follow this tag to personalize your feed and get instant alerts. Follow Go to your personalized feed WHY FOLLOW?

The lab will beam back data to train AI models to predict how proteins behind age-related diseases like Alzheimer's and certain cancers behave. Space is becoming the next frontier in longevity research. A British startup just launched self-run chemical experiments into orbit, in the hopes zero-gravity data might shine a light on a group of disease-causing proteins too difficult to study on Earth. But first they need to check their autonomous laboratory will work in space. Mass Balance's grapefruit-sized apparatus containing chemicals, sensors and control elements to keep the chemicals functioning launched on a SpaceX transporter on Tuesday morning.

Aqueous solubility is a key property in early-stage drug discovery, but most predictive models merge physicochemical descriptors and molecular graph information into a single representation, obscuring whether a prediction is driven by global chemistry, molecular structure, or both. We present an additive deep-learning framework that keeps these two sources of information separate throughout training: physicochemical descriptors are encoded by a multilayer perceptron (the chemical branch) and molecular graph topology by a graph neural network (the structural branch), with the two outputs combined only at the prediction stage through an additive model with an optional multiplicative interaction. This design provides a direct decomposition of chemical and structural components that can be examined separately after training. Furthermore, pretraining on the larger AqSolDB dataset and fine-tuning on the smaller BigSolDB2 dataset substantially improve accuracy and reduce run-to-run variations, indicating generalizability of the learned features from the data-rich settings. We further interpret the fitted model using best linear projections of the branch outputs, molecule-level embedding summaries across solubility classes, and atom-level GNNExplainer masks aggregated over functional groups. These analyses show that the chemical branch aligns with familiar physicochemical descriptors, while the structural branch captures graph-topological and functional-group patterns associated with solubility. Across both datasets, the framework attains competitive predictive performance while making the distinct roles of chemical and structural information more transparent.

Most existing multitask learning approaches are limited by their reliance on task-specific loss functions tailored to the scale and type of each outcome. When outcomes differ across tasks, these losses are generally not directly comparable, which makes it difficult to formulate a unified objective and may limit information sharing across tasks. We propose a multitask transformation framework in which task-specific responses may differ through unknown monotone transformations. Motivated by high-dimensional biological applications in which the predictor dimension may diverge with the sample size while only a common subset of predictors is informative, we consider shared sparsity across tasks. Under this framework, we estimate the target functions and identify important predictors by optimizing a smoothed rank-based criterion with a group-Lasso penalty, implemented through a multitask deep neural network with a shared first layer. We establish the nonasymptotic excess-risk bounds, and variable-selection consistency for the proposed estimator. Simulation studies show that the proposed method achieves competitive prediction and variable-selection performance compared with competing approaches. Analyses of gene-expression studies with continuous, binary, and mixed outcomes further illustrate that the proposed method improves prediction and identifies biologically meaningful shared predictors.

Scientific reasoning is an increasingly important capability of large language models, yet improving the robustness and efficiency of training such reasoning remains a key open challenge. We study this problem in instruction-based molecular optimization, where answer-only supervised fine-tuning (SFT) collapses multi-step reasoning and reinforcement learning with verifiable rewards (RLVR) suffers from sparse feedback. Reference-guided Policy Optimization (RePO) mitigates both by anchoring policy updates to dataset-provided references, but its effectiveness is tightly coupled to reference quality: weak or misaligned references impose a performance ceiling. To overcome this ceiling, we propose active reasoning, a paradigm in which the policy actively decides, on a per-instance basis, when to imitate a reference and when to reinforce its own discoveries, while continuously upgrading what it imitates. We instantiate this paradigm as Active Group Relative Policy Optimization (Active-GRPO), realized through two coupled mechanisms: active imitate-reinforce and active referencing. The former performs imitation learning when the reference still outperforms the policy's own candidates, and shifts to self-improvement via reinforcement learning once the policy has generated molecules that surpass the reference. The latter continuously upgrades the reference itself by replacing it with the best policy-generated candidate discovered so far, progressively raising the imitation target and ensuring that reference guidance remains informative--rather than restrictive--throughout training. Across TOMG-Bench MOLOPT, Active-GRPO improves average SR Sim from 0.0959 for GRPO and 0.1665 for RePO to 0.1773 under matched three-seed evaluation, with statistically significant gains on LogP, MR, and QED.

Protein engineering is a field primed for artificial intelligence research. Each protein is made up of amino acids; to optimize a protein function, researchers modify proteins by switching out one of 20 different amino acids for another. For a protein that is just 50 amino acids in length, this leads to approximately 1.13 10 potential combinations to test. This number of potential combinations, impossible to test in the lab, makes protein engineering an ideal challenge for AI. Modeling which of these combinations will give the best results is a perfect problem for the technology's massive computing power.

The Download: Anthropic launches Claude Science, and California's carbon manure math Plus: The US has lifted restrictions on Anthropic's Mythos and Fable models. Claude Science is Anthropic's newest flagship product At an event for pharmaceutical executives, biotech founders, and researchers yesterday, Anthropic announced Claude Science, a major new product intended to support scientific research like Claude Code supports software engineering. Like Claude Code, Claude Science can autonomously carry out meaningful work from concise, high-level instructions, with tools for computational biology and drug development. The launch signals that Anthropic is doubling down on AI for science, and the company will also use the product in its own research into drugs for rare, neglected diseases. Discover why Anthropic is betting big on AI for scientific research . Why California's carbon manure math doesn't add up Years ago, the state set up a system that pays cattle farmers to turn the methane emitted from cattle manure into natural gas.

The UN's independent scientific panel for AI has published its first report. Artificial intelligence development has been progressing at such a rapid pace that current governance systems are unable to keep up, the UN's Independent International Scientific Panel on Artificial Intelligence says in its preliminary report . The panel, consisting of members from around the world, will provide the information needed to stage the UN Global Dialogue on AI Governance. It will take place in Geneva, where member states will discuss how to manage the technology, and is scheduled to begin on July 6. In its report, the panel discusses how quickly AI capabilities have evolved over the past few years.

At an event for pharmaceutical executives, biotech founders, and researchers on Tuesday, Anthropic announced Claude Science, a major new product intended to support scientific research in the same way that Claude Code supports software engineering. Like Claude Code, Claude Science can autonomously carry out meaningful work when given concise, high-level instructions, and it has access to tools that make it particularly useful for research in computational biology and drug development. Along with launching and previewing Claude Science, which is now available to all paid Claude subscribers, Anthropic also announced that it will be using the product to pursue some of its own research into drugs for rare, neglected diseases. This is not Anthropic's first foray into AI for science. In October, the company released plug-ins that help Claude make use of scientific software and databases under the heading "Claude for Life Sciences." But unlike this earlier release, Claude Science is a full-featured, standalone product. Anthropic's decision to elevate Claude Science to the same rank as Claude Code and Claude Cowork indicates that the company is taking AI's scientific applications very seriously--or at least wants to give the impression that it is.

Eli Lilly faces a congressional investigation into its China clinical trials at People's Liberation Army hospitals and Xinjiang facilities amid biotechnology competition concerns.