When the biotech company Insilico Medicine used its computer models to propose a promising drug for pulmonary fibrosis, it enthusiastically claimed in a press release that the molecule had been "discovered by" its generative AI platform. Insilico leads a pack of companies using AI to rapidly come up with drug ideas humans might never think of, potentially speeding the race to new cures. AI models are now able to generate atomic designs for drugs almost as easily as ChatGPT can write a thank-you note. However, when it came time to file for an all-important patent to protect that new chemical structure, the company made no mention of AI. Instead the patent names five humans, including CEO Alex Zhavoronkov, as the drug's "inventors."

Health care company Abbott has entered into a partnership to connect Google Health to its Lingo continuous glucose monitor (CGM). According to the press release, this multi-year collaboration will allow users of the over-the-counter Lingo device to see their metabolic data within the Google Health app, which could help a person "make better lifestyle and nutrition choices in the moment." The Lingo data can also be shared with the Google Health Coach, which offers AI-driven recommendations based on an individual's information. Lingo is explicitly intended for adults who are not using insulin. Engadget reported on the growing trend of non-diabetics using continuous glucose monitors back in 2023 and found little research that supported the benefits for that population to track blood sugar spikes so closely.

To meet this moment, we need YOU. For five decades, has been exposing the corruption that the powerful would rather keep buried. That fight for the truth is at a pivotal point, and it takes readers like you to make it possible. To meet this moment, we need YOU. That fight for the truth is at a pivotal point, and it takes readers like you to make it possible. Amid public outcry over water-guzzling server farms, a Guardian analysis indicates trouble ahead.

Truncated curves reflect early stopping due to zero train error. Error bars are standard deviationsacrossfiveruns.

Convolutional neural networks (CNNs) have become widely adopted in gravitational wave (GW) detection pipelines due to their ability to automatically learn hierarchical features from raw strain data. However, the physical meaning of these learned features remains underexplored, limiting the interpretability of such models. In this work, we propose a hybrid architecture that combines a CNN-based feature extractor with a random forest (RF) classifier to improve both detection performance and interpretability. Unlike prior approaches that directly connect classifiers to CNN outputs, our method introduces four physically interpretable metrics - variance, signal-to-noise ratio (SNR), waveform overlap, and peak amplitude - computed from the final convolutional layer. These are jointly used with the CNN output in the RF classifier to enable more informed decision boundaries. Tested on long-duration strain datasets, our hybrid model outperforms a baseline CNN model, achieving a relative improvement of 21\% in sensitivity at a fixed false alarm rate of 10 events per month. Notably, it also shows improved detection of low-SNR signals (SNR $\le$ 10), which are especially vulnerable to misclassification in noisy environments. Feature attribution via the RF model reveals that both CNN-extracted and handcrafted features contribute significantly to classification decisions, with learned variance and CNN outputs ranked among the most informative. These findings suggest that physically motivated post-processing of CNN feature maps can serve as a valuable tool for interpretable and efficient GW detection, bridging the gap between deep learning and domain knowledge.

The World Health Organization (WHO) has sent an internal memo about potential problems with a major company's malaria tests after scientists reported issues with test sensitivity and warned it could delay patients' access to critical treatment. Abbott's Bioline rapid diagnostic tests (RDTs) for malaria are used by health workers around the world, particularly in remote areas where lab techniques such as microscopy and DNA detection aren't available. Investigations at several institutions in Southeast Asia suggest at least some of these RDTs fail to detect infections or show faint test lines for some positive cases. Daniel Ngamije Madandi, director of WHO's Global Malaria Programme (GMP), issued the memo to WHO's six regional offices on 30 April. It lists 11 "affected" lots from two Abbott RDTs--Pf/Pv and Pf/Pan--that were associated with "faint lines and false negative results" in reports from "multiple research groups." The memo follows a public notice by WHO in March that warned of reports of faint lines in malaria RDTs without mentioning particular brands or products.

In 2017, soon after Google researchers invented a new kind of neural network called a transformer, a young OpenAI engineer named Alec Radford began experimenting with it. What made the transformer architecture different from that of existing A.I. systems was that it could ingest and make connections among larger volumes of text, and Radford decided to train his model on a database of seven thousand unpublished English-language books--romance, adventure, speculative tales, the full range of human fantasy and invention. Then, instead of asking the network to translate text, as Google's researchers had done, he prompted it to predict the most probable next word in a sentence. The machine responded: one word, then another, and another--each new term inferred from the patterns buried in those seven thousand books. Radford hadn't given it rules of grammar or a copy of Strunk and White.

Scientific discoveries are often made by finding a pattern or object that was not predicted by the known rules of science. Oftentimes, these anomalous events or objects that do not conform to the norms are an indication that the rules of science governing the data are incomplete, and something new needs to be present to explain these unexpected outliers. The challenge of finding anomalies can be confounding since it requires codifying a complete knowledge of the known scientific behaviors and then projecting these known behaviors on the data to look for deviations. When utilizing machine learning, this presents a particular challenge since we require that the model not only understands scientific data perfectly but also recognizes when the data is inconsistent and out of the scope of its trained behavior. In this paper, we present three datasets aimed at developing machine learning-based anomaly detection for disparate scientific domains covering astrophysics, genomics, and polar science. We present the different datasets along with a scheme to make machine learning challenges around the three datasets findable, accessible, interoperable, and reusable (FAIR). Furthermore, we present an approach that generalizes to future machine learning challenges, enabling the possibility of large, more compute-intensive challenges that can ultimately lead to scientific discovery.

Last week a video showing 60-year-old Peter Abbott screaming abuse at TV producer Samantha Isaacs gained a viral audience, after Abbott was found guilty at Poole magistrates court of "using threatening words or behaviour to cause alarm, distress or fear of violence". In the phone-filmed video, Abbott is seen snarling and shouting as he presses his face up against Isaacs' car window. He looks as if he's channelling the Harry Enfield character Angry Frank, so cartoonishly aggressive are his contorted facial expressions and confrontational behaviour. Not only did he hammer on Isaacs' car but he also called her a "slag" and a "whore". When another male driver pointed out the terrible optics of bullying a woman, he replied: "She's a fucking bloody annoying woman."

The advancement of The Laser Interferometer Gravitational-Wave Observatory (LIGO) has significantly enhanced the feasibility and reliability of gravitational wave detection. However, LIGO's high sensitivity makes it susceptible to transient noises known as glitches, which necessitate effective differentiation from real gravitational wave signals. Traditional approaches predominantly employ fully supervised or semi-supervised algorithms for the task of glitch classification and clustering. In the future task of identifying and classifying glitches across main and auxiliary channels, it is impractical to build a dataset with manually labeled ground-truth. In addition, the patterns of glitches can vary with time, generating new glitches without manual labels. In response to this challenge, we introduce the Cross-Temporal Spectrogram Autoencoder (CTSAE), a pioneering unsupervised method for the dimensionality reduction and clustering of gravitational wave glitches. CTSAE integrates a novel four-branch autoencoder with a hybrid of Convolutional Neural Networks (CNN) and Vision Transformers (ViT). To further extract features across multi-branches, we introduce a novel multi-branch fusion method using the CLS (Class) token. Our model, trained and evaluated on the GravitySpy O3 dataset on the main channel, demonstrates superior performance in clustering tasks when compared to state-of-the-art semi-supervised learning methods. To the best of our knowledge, CTSAE represents the first unsupervised approach tailored specifically for clustering LIGO data, marking a significant step forward in the field of gravitational wave research. The code of this paper is available at https://github.com/Zod-L/CTSAE