Three-dimensional generative models increasingly drive structure-based drug discovery, yet it remains constrained by the scarce publicly available protein-ligand complexes. Under such data scarcity, almost all existing pipelines struggle to learn transferable geometric priors and consequently overfit to training-set biases. As such, we present IBEX, an Information-Bottleneck-EXplored coarse-to-fine pipeline to tackle the chronic shortage of protein-ligand complex data in structure-based drug design. Specifically, we use PAC-Bayesian information-bottleneck theory to quantify the information density of each sample. This analysis reveals how different masking strategies affect generalization and indicates that, compared with conventional de novo generation, the constrained Scaffold Hopping task endows the model with greater effective capacity and improved transfer performance. IBEX retains the original TargetDiff architecture and hyperparameters for training to generate molecules compatible with the binding pocket; it then applies an L-BFGS optimization step to finely refine each conformation by optimizing five physics-based terms and adjusting six translational and rotational degrees of freedom in under one second. With only these modifications, IBEX raises the zero-shot docking success rate on CBGBench CrossDocked2020-based from 53% to 64%, improves the mean Vina score from $-7.41 kcal mol^{-1}$ to $-8.07 kcal mol^{-1}$, and achieves the best median Vina energy in 57 of 100 pockets versus 3 for the original TargetDiff. IBEX also increases the QED by 25%, achieves state-of-the-art validity and diversity, and markedly reduces extrapolation error.

We introduce Ibex, a pan-immunoglobulin structure prediction model that achieves state-of-the-art accuracy in modeling the variable domains of antibodies, nanobodies, and T-cell receptors. Unlike previous approaches, Ibex explicitly distinguishes between bound and unbound protein conformations by training on labeled apo and holo structural pairs, enabling accurate prediction of both states at inference time. Using a comprehensive private dataset of high-resolution antibody structures, we demonstrate superior out-of-distribution performance compared to existing specialized and general protein structure prediction tools. Ibex combines the accuracy of cutting-edge models with significantly reduced computational requirements, providing a robust foundation for accelerating large molecule design and therapeutic development.

Ibex Medical Analytics, a Tel Aviv, Israel-based startup developing a product suite for clinical decision-making and pathology laboratory workflows, today announced that it raised $38 million in funding. The global big data analytics market for health care was valued at $16.87 billion in 2017 and is projected to reach $67.82 billion by 2025, according to a recent report from Allied Market Research. It's believed that health care organizations' implementation of big data analytics might reduce annual costs by over 25% in the coming years. Better diagnosis and disease predictions, assisted by AI and analytics, can lead to cost reduction by decreasing hospital readmission rates, among other factors. Ibex, whose competitors include Paige, PathAI, and ContextVision, among others, was founded by Joseph Mossel and Dr. Chaim Linhart. Mossel's background is in computer science, product development, and management, whereas Linhart is an AI and machine learning researcher.

An Israeli startup developing a digital pathology system based around artificial intelligence has published what it calls "outstanding outcomes" in a clinical validation study. Tel Aviv-based Ibex Medical Analysis said Tuesday that it had published data on Galen Prostate, its AI-based system for use by pathologists to detect and measure prostate cancer, in The Lancet Digital Health. The company called it the first and only AI-based system used by pathologists in routine clinical practice. The study took place at the University of Pittsburgh Medical Center, led by Drs. According to the data, sensitivity measured for prostate cancer was 98.46%, and specificity was 97.33%, while the operating characteristic curve was 0.991.

"Humans are good at recognizing anomalies, but they have their own biases or past experience," said senior author Rajiv Dhir, M.D., M.B.A., chief pathologist and vice chair of pathology at UPMC Shadyside and professor of biomedical informatics at Pitt. "Machines are detached from the whole story. To train the AI to recognize prostate cancer, Dhir and his colleagues provided images from more than a million parts of stained tissue slides taken from patient biopsies. Each image was labeled by expert pathologists to teach the AI how to discriminate between healthy and abnormal tissue. The algorithm was then tested on a separate set of 1,600 slides taken from 100 consecutive patients seen at UPMC for suspected prostate cancer. During testing, the AI demonstrated 98% sensitivity and 97% specificity at detecting prostate cancer -- significantly higher than previously reported for algorithms working from tissue slides. Also, this is the first algorithm to extend beyond cancer detection, reporting high performance for tumor grading, sizing and invasion of the surrounding nerves. These all are clinically important features required as part of the pathology report. AI also flagged six slides that were not noted by the expert pathologists. But Dhir explained that this doesn't necessarily mean that the machine is superior to humans. For example, in the course of evaluating these cases, the pathologist could have simply seen enough evidence of malignancy elsewhere in that patient's samples to recommend treatment. For less experienced pathologists, though, the algorithm could act as a failsafe to catch cases that might otherwise be missed. "Algorithms like this are especially useful in lesions that are atypical," Dhir said. "A nonspecialized person may not be able to make the correct assessment.

Healthcare has long been lagging behind when it comes to implementing digital strategies. High levels of regulation, local barriers to entry and persistent reluctance to change did not help. But one could sense digitization would ultimately leave no healthcare area untouched. As an advisor exclusively focused on technology, we felt the tide turning when we saw generalist VCs significantly raise their interest in healthcare, while they used to shy away from the segment. We now see both specialists and generalist VCs heavily pouring euros in European healthtech.

Leader in AI-powered cancer diagnostics, Ibex Medical Analytics and provider of digital pathology services in the NHS, LDPath, have announced the UK's first rollout of clinical grade AI application for cancer detection in pathology. This platform will support pathologists in enhancing diagnostic accuracy and efficiency. Over the years, a global increase in cancer cases has coincided with a decline in the number of pathologists around the world. Traditional pathology involves manual processes that have remained the same for years. These processes involve slides to be analysed by pathologists using microscopes, and reporting is often carried out on pieces of paper.

A healthcare provider in Israel has begun to use what its vendor claims is the first-ever artificial intelligence-driven (AI) pathology diagnostic tool to go live in a clinical setting, according to an announcement. Maccabi Healthcare Services, which runs a pathology institute responsible for 160,000 histology accessions every year, recently started leveraging Ibex Medical Analytics' Second Read system, the tech developer said yesterday. The launch came after a pilot period in which the AI tool "identified isolated major errors" regarding prostate core needle biopsies, which were incorrectly diagnosed benign, according to Ibex. Although this is not the first clinical application of AI, Ibex said it is the first in this particular space, helping patients with prostate cancer and adding to a growing portfolio of the technology's diagnostic capabilities. READ: Leo Celi and the'Holy Grail of Personalized Medicine' "We are excited to be the first company to ever deploy an AI-based system in a clinically active pathology lab, leveraging the enormous potential of [AI] to make a real impact on human lives," said Joseph Mossel, MS, co-founder and CEO of Ibex Medical Analytics.

The Ibex Pro is one supercharged machine that will probably hurt your electric bill. It's got the same number of GPUs as Nvidia's superfast DGX-1, which is being used for deep learning. System76 is targeting the Ibex Pro -- which is a rack server -- at the same market as the DGX-1. The server has fewer, but newer, CPUs, compared to the DGX-1. An entry-level Ibex Pro priced at US $9,575 will run Ubuntu Server 16.10, with a six-core Intel Xeon E5-2603v4 chip, 16GB of memory, a Tesla K40 GPU, and 250GB of storage.