The escalating adoption of high-resolution, large-field-of-view imagery amplifies the need for efficient compression methodologies. Conventional techniques frequently fail to preserve critical image details, while data-driven approaches exhibit limited generalizability. Implicit Neural Representations (INRs) present a promising alternative by learning continuous mappings from spatial coordinates to pixel intensities for individual images, thereby storing network weights rather than raw pixels and avoiding the generalization problem. However, INR-based compression of large images faces challenges including slow compression speed and suboptimal compression ratios. To address these limitations, we introduce COLI (Compressor for Large Images), a novel framework leveraging Neural Representations for Videos (NeRV). First, recognizing that INR-based compression constitutes a training process, we accelerate its convergence through a pretraining-finetuning paradigm, mixed-precision training, and reformulation of the sequential loss into a parallelizable objective. Second, capitalizing on INRs' transformation of image storage constraints into weight storage, we implement Hyper-Compression, a novel post-training technique to substantially enhance compression ratios while maintaining minimal output distortion. Evaluations across two medical imaging datasets demonstrate that COLI consistently achieves competitive or superior PSNR and SSIM metrics at significantly reduced bits per pixel (bpp), while accelerating NeRV training by up to 4 times.

The extent to which foundation models can disclose novel chemical, biological, radiation, and nuclear (CBRN) threats to expert users is unclear due to a lack of test cases. I leveraged the unique opportunity presented by an upcoming publication describing a novel catastrophic biothreat - "Technical Report on Mirror Bacteria: Feasibility and Risks" - to conduct a small controlled study before it became public. Graduate-trained biologists tasked with predicting the consequences of releasing mirror E. coli showed no significant differences in rubric-graded accuracy using Claude Sonnet 3.5 new (n=10) or web search only (n=2); both groups scored comparably to a web baseline (28 and 43 versus 36). However, Sonnet reasoned correctly when prompted by a report author, but a smaller model, Haiku 3.5, failed even with author guidance (80 versus 5). These results suggest distinct stages of model capability: Haiku is unable to reason about mirror life even with threat-aware expert guidance (Stage 1), while Sonnet correctly reasons only with threat-aware prompting (Stage 2). Continued advances may allow future models to disclose novel CBRN threats to naive experts (Stage 3) or unskilled users (Stage 4). While mirror life represents only one case study, monitoring new models' ability to reason about privately known threats may allow protective measures to be implemented before widespread disclosure.

Recent advances in deep learning-based image reconstruction techniques have led to significant progress in phase retrieval using digital in-line holographic microscopy (DIHM). However, existing deep learning-based phase retrieval methods have technical limitations in generalization performance and three-dimensional (3D) morphology reconstruction from a single-shot hologram of biological cells. In this study, we propose a novel deep learning model, named MorpHoloNet, for single-shot reconstruction of 3D morphology by integrating physics-driven and coordinate-based neural networks. By simulating the optical diffraction of coherent light through a 3D phase shift distribution, the proposed MorpHoloNet is optimized by minimizing the loss between the simulated and input holograms on the sensor plane. Compared to existing DIHM methods that face challenges with twin image and phase retrieval problems, MorpHoloNet enables direct reconstruction of 3D complex light field and 3D morphology of a test sample from its single-shot hologram without requiring multiple phase-shifted holograms or angle scanning. The performance of the proposed MorpHoloNet is validated by reconstructing 3D morphologies and refractive index distributions from synthetic holograms of ellipsoids and experimental holograms of biological cells. The proposed deep learning model is utilized to reconstruct spatiotemporal variations in 3D translational and rotational behaviors and morphological deformations of biological cells from consecutive single-shot holograms captured using DIHM. MorpHoloNet would pave the way for advancing label-free, real-time 3D imaging and dynamic analysis of biological cells under various cellular microenvironments in biomedical and engineering fields.

We introduce a protein language model for determining the complete sequence of a peptide based on measurement of a limited set of amino acids. To date, protein sequencing relies on mass spectrometry, with some novel edman degregation based platforms able to sequence non-native peptides. Current protein sequencing techniques face limitations in accurately identifying all amino acids, hindering comprehensive proteome analysis. Our method simulates partial sequencing data by selectively masking amino acids that are experimentally difficult to identify in protein sequences from the UniRef database. This targeted masking mimics real-world sequencing limitations. We then modify and finetune a ProtBert derived transformer-based model, for a new downstream task predicting these masked residues, providing an approximation of the complete sequence. Evaluating on three bacterial Escherichia species, we achieve per-amino-acid accuracy up to 90.5% when only four amino acids ([KCYM]) are known. Structural assessment using AlphaFold and TM-score validates the biological relevance of our predictions. The model also demonstrates potential for evolutionary analysis through cross-species performance. This integration of simulated experimental constraints with computational predictions offers a promising avenue for enhancing protein sequence analysis, potentially accelerating advancements in proteomics and structural biology by providing a probabilistic reconstruction of the complete protein sequence from limited experimental data.

You have probably heard of ChatGPT and DALLE-E, a new class of AI-powered software tools that can create new images or write text. The algorithm brings to life any idea you may have by putting together fragments of what it has previously seen – such as images annotated with meta-descriptions of what they represent – to generate original content from user-defined input. But now generative AI technology is revolutionizing drug discovery. Absci Corporation (Nasdaq: ABSI) is using machine learning to transform the field of antibody therapeutics: Absci has put out a press release today announcing the ability to create new antibodies with the use of generative AI. Their founder and CEO, Sean McClain, will be presenting the news later today at the annual JPM Healthcare Conference happening this week in San Francisco.

Check out all the on-demand sessions from the Intelligent Security Summit here. For many, hearing the word E. coli is often a reason to be concerned, as the bacteria can lead to incidents of food poisoning in humans. As it turns out, E. coli might well be the panacea that enables a new form of generative AI for healthcare that could help enable researchers to generate new antibodies. Generative AI in recent years has captured popular imagination by enabling users to generate text or images on demand, but its uses go much deeper, too. Generative models that provide large machine learning (ML) models that can create new things is an emerging area in science helping to accelerate discovery.

Experts from the University of Nottingham have developed new software which combines DNA sequencing and machine learning to help them find where, and to what extent, antibiotic resistant bacteria is being transmitted between humans, animals and the environment. The study, which is published in PLOS Computational Biology, was led by Dr. Tania Dottorini from the School of Veterinary Medicine and Science at the University. Anthropogenic environments (spaces created by humans), such as areas of intensive livestock farming, are seen as ideal breeding grounds for antimicrobial-resistant bacteria and antimicrobial resistant genes, which are capable of infecting humans and carrying resistance to drugs used in human medicine. This can have huge implications for how certain illnesses and infections can be treated effectively. In this new study, a team of experts looked at a large scale commercial poultry farm in China, and collected 154 samples from animals, carcasses, workers and their households and environments.

In September 2020, Regina Barzilay was announced as the winner of the inaugural AAAI Squirrel AI award. Regina was formally presented with the prize during an award ceremony at the AAAI2021 conference, following which she delivered an invited talk. She spoke about two particular areas of medicine that she has been researching: drug discovery and cancer diagnosis. It is well-known that the development of drugs is slow and expensive. Currently, drug discovery is primarily experimentally driven, with properties of molecules investigated empirically.

Testing for pathogens is a critical component of maintaining public health and safety. Having a method to rapidly and reliably test for harmful germs is essential for diagnosing diseases, maintaining clean drinking water, regulating food safety, conducting scientific research, and other important functions of modern society. In recent research, scientists from University of California, Los Angeles (UCLA), have demonstrated that artificial intelligence (AI) can detect harmful bacteria from a water sample up to 12 hours faster than the current gold-standard Environmental Protection Agency (EPA) methods. In a new study published yesterday in Light: Science and Applications, the researchers created a time-lapse imaging platform that uses two separate deep neural networks (DNNs) for the detection and classification of bacteria. The team tested the high-throughput bacterial colony growth detection and classification system using water suspensions with added coliform bacteria of E. coli (including chlorine-stressed E. coli), K. pneumoniae and K. aerogenes, grown on chromogenic agar as the culture medium.

Researchers announced the breakthrough discovery of a new type of antibiotic compound that is capable of killing many types of harmful bacteria, including deadly antibiotic-resistant strains, and published their findings in Cell on February 20. What makes this remarkable is that the researchers, from the Massachusetts Institute of Technology (MIT), Harvard, and McMaster University, used machine learning (a form of artificial intelligence) to discover the new antibiotic--an achievement that heralds the disruption of traditional research and drug development processes deployed by pharmaceutical industry behemoths. Antibiotic resistance is a global threat that is exacerbated by the overuse of antibiotics in livestock, the proliferation of antimicrobials in consumer products, and over-prescription in health care. Though estimating the future impact is challenging, one report predicted that by 2050, 10 million deaths per year could result from antimicrobial-resistant (AMR) infections. Combating the problem of antimicrobial resistance requires bringing novel compounds to market.