We present Lark, a biologically inspired decision-making framework that couples LLM-driven reasoning with an evolutionary, stakeholder-aware Multi-Agent System (MAS). To address verbosity and stakeholder trade-offs, we integrate four mechanisms: (i) plasticity, which applies concise adjustments to candidate solutions; (ii) duplication and maturation, which copy high-performing candidates and specialize them into new modules; (iii) ranked-choice stakeholder aggregation using influence-weighted Borda scoring; and (iv) compute awareness via token-based penalties that reward brevity. The system iteratively proposes diverse strategies, applies plasticity tweaks, simulates stakeholder evaluations, aggregates preferences, selects top candidates, and performs duplication/maturation while factoring compute cost into final scores. In a controlled evaluation over 30 rounds comparing 14 systems, Lark Full achieves a mean rank of 2.55 (95% CI [2.17, 2.93]) and a mean composite score of 29.4/50 (95% CI [26.34, 32.46]), finishing Top-3 in 80% of rounds while remaining cost competitive with leading commercial models ($0.016 per task). Paired Wilcoxon tests confirm that all four mechanisms contribute significantly as ablating duplication/maturation yields the largest deficit (ΔScore = 3.5, Cohen's d_z = 2.53, p < 0.001), followed by plasticity (ΔScore = 3.4, d_z = 1.86), ranked-choice voting (ΔScore = 2.4, d_z = 1.20), and token penalties (ΔScore = 2.2, d_z = 1.63). Rather than a formal Markov Decision Process with constrained optimization, Lark is a practical, compute-aware neuroevolutionary loop that scales stakeholder-aligned strategy generation and makes trade-offs transparent through per-step metrics. Our work presents proof-of-concept findings and invites community feedback as we expand toward real-world validation studies.

Cell and immunotherapy offer transformative potential for treating diseases like cancer and autoimmune disorders by modulating the immune system. The development of these therapies is resource-intensive, with the majority of drug candidates failing to progress beyond laboratory testing. While recent advances in machine learning have revolutionised areas such as protein engineering, applications in immunotherapy remain limited due to the scarcity of large-scale, standardised datasets and the complexity of cellular systems. In this work, we address these challenges by leveraging a high-throughput experimental platform to generate data suitable for fine-tuning protein language models. We demonstrate how models fine-tuned using a preference task show surprising correlations to biological assays, and how they can be leveraged for few-shot hit maturation in CARs. This proof-of-concept presents a novel pathway for applying ML to immunotherapy and could generalise to other therapeutic modalities.

Ewan Morgan, National Luxury Ambassador and Head of Whisky Outreach at Diageo North America, told Fox News Digital how SmokeDNAi technology is being used to understand the aging process of whisky. For two years, Diageo analyzed various Scotch whiskies using AI and algorithms. Diageo, an alcohol beverage company, invested 230 million into a portfolio of whisky tourism projects. Of this lump sum, more than 44 million was dedicated to the exploration of whisky maturation using technology called SmokeDNAi. Using SmokeDNAi, teams tested and analyzed the flavor profiles and mouthfeel of non-identical twin whiskies distilled in different casks – one remnant and one original.

Abstract: MRI connectomics is an emerging approach to study the brain as a network of interconnected brain regions. Understanding and mapping the development of the MRI connectome may offer new insights into the development of brain connectivity and plasticity, ultimately leading to improved understanding of normal development and to more effective diagnosis and treatment of developmental disorders. In this review, we describe the attempts made to date to map the whole-brain structural MRI connectome in the developing brain and pay a special attention to the challenges associated with the rapid changes that the brain is undergoing during maturation. The two main steps in constructing a structural brain network are (i) choosing connectivity measures that will serve as the network "edges" and (ii) finding an appropriate way to divide the brain into regions that will serve as the network "nodes". We will discuss how these two steps are usually performed in developmental studies and the rationale behind different strategies.

Antibody therapeutics has been extensively studied in drug discovery and development within the past decades. One increasingly popular focus in the antibody discovery pipeline is the optimization step for therapeutic leads. Both traditional methods and in silico approaches aim to generate candidates with high binding affinity against specific target antigens. Traditional in vitro approaches use hybridoma or phage display for candidate selection, and surface plasmon resonance (SPR) for evaluation, while in silico computational approaches aim to reduce the high cost and improve efficiency by incorporating mathematical algorithms and computational processing power in the design process. In the present study, we investigated different graph-based designs for depicting antibody-antigen interactions in terms of antibody affinity prediction using deep learning techniques. While other in silico computations require experimentally determined crystal structures, our study took interest in the capability of sequence-based models for in silico antibody maturation. Our preliminary studies achieved satisfying prediction accuracy on binding affinities comparing to conventional approaches and other deep learning approaches. To further study the antibody-antigen binding specificity, and to simulate the optimization process in real-world scenario, we introduced pairwise prediction strategy. We performed analysis based on both baseline and pairwise prediction results. The resulting prediction and efficiency prove the feasibility and computational efficiency of sequence-based method to be adapted as a scalable industry practice.

Meiotic maturation is a crucial step of oocyte formation allowing its potential fertilization and embryo development. Elucidating this process is important both for fundamental research and assisted reproductive technology. Few computational tools based on non-invasive measurements are however available to characterize oocyte meiotic maturation. Here, we develop a computational framework to phenotype oocytes based on images acquired in transmitted light. We trained neural networks to segment the contour of oocytes and their zona pellucida using oocytes from diverse species. We defined a comprehensive set of morphological features to describe an oocyte. These steps are implemented in an open-source Fiji plugin. We present a feature based machine learning pipeline to recognize oocyte populations and determine their morphological differences. We first demonstrate its potential to screen oocyte from different strains and automatically identify their morphological characteristics. Its second application is to predict and characterize the maturation potential of oocytes. We identify the texture of the zona pellucida and the cytoplasmic particles size as features to assess mouse oocyte maturation potential and tested whether these features were applicable to human oocyte's developmental potential.

Researchers at the University of Pittsburgh School of Medicine have combined synthetic biology with a machine-learning algorithm to create human liver organoids with blood- and bile-handling systems. When implanted into mice with failing livers, the lab-grown replacement livers extended life. The study, published today in Cell Systems, shows that it's possible to trigger and speed up the maturation of a lab-grown organ without sacrificing precision or control. "Pregnancy is nine months--it takes that long and even months after birth for new organs to mature--but if a person needs a liver, they may not be able to wait that long," said study author Mo Ebrahimkhani, M.D., associate professor of pathology and bioengineering, and member of the Pittsburgh Liver Research Center and the McGowan Institute for Regenerative Medicine. "We showed it's possible to get human liver tissue with four main cell types and vasculature in 17 days. We can mature tissue almost to the third trimester in only three months."

Data science used to be somewhat of a mystery, more of a dark art than a repeatable, scientific process. Companies basically entrusted powerful priests called data scientists to build magical algorithms that used data to make predictions, usually to boost profits or improve customer happiness. But in recent years, the field has matured to a remarkable degree, and that is enabling progress to be made on multiple fronts, from ModelOps and reproducibility to ethics and accountability. About five years ago, the worldwide scientific community was suffering a "reproducibility crises" that impacted a wide range of scientific endeavors, including so-called hard sciences like physics and chemistry. One of the hallmarks of the scientific method is that experiments must be reproducible and will give the same results, but that lofty goal too often was not met.

In the foothills of the Sierra Mountains, a few hours east of San Francisco, are the Moaning Caverns, a cave system that begins, after a narrow, twisting descent of 30-some feet, with an abrupt 180-foot drop. The Park Service has found ancient human skeletons at the bottom of the drop. Instead, these explorers took one step too far in the gloom. The skeletons belonged to adolescents. After all, adolescence is the time of life when someone is most likely to join a cult, kill, be killed, invent an art form, help overthrow a dictator, ethnically cleanse a village, care for the needy, transform physics, adopt a hideous fashion style, commit to God, and be convinced that all the forces of history have converged to make this moment the most consequential ever, fraught with peril and promise. For all this we can thank the teenage brain. Some have argued adolescence is a cultural construct. In traditional cultures, there is typically a single qualitative transition to puberty. After that, the individual is a young adult. Yet the progression from birth to adulthood is not smoothly linear.

Autonomous agents trained via reinforcement learning present numerous safety concerns: reward hacking, negative side effects, and unsafe exploration, among others. In the context of near-future autonomous agents, operating in environments where humans understand the existing dangers, human involvement in the learning process has proved a promising approach to AI Safety. Here we demonstrate that a precise framework for learning from human input, loosely inspired by the way humans parent children, solves a broad class of safety problems in this context. We show that our PARENTING algorithm solves these problems in the relevant AI Safety gridworlds of Leike et al. (2017), that an agent can learn to outperform its parent as it "matures", and that policies learnt through PARENTING are generalisable to new environments.