We present a new unified graph-based representation of medical data, combining genetic information and medical records of patients with medical knowledge via a unique knowledge graph. This approach allows us to infer meaningful information and explanations that would be unavailable by looking at each data set separately. The systematic use of different databases, managed throughout the built knowledge graph, gives new insights toward a better understanding of oncology medicine. Indeed, we reduce some useful medical tasks to well-known problems in theoretical computer science for which efficient algorithms exist.

Owing to the high cost and time associated with developing and validating anti-cancer drugs in clinical trials which is further exacerbated by the 96% failure rate, the development of preclinical computational models that can accurately predict whether a cell line is sensitive or resistant to a particular drug is imperative. The availability of large-scale pharmacogenomics datasets collected via high-throughput screening technologies offers feasible resources to develop robust drug response models and identify the important biomarkers predictive of drug sensitivity. Large language models (LLM), such as the Generative Pre-trained Transformer (GPT-3) from OpenAI, are "taskagnostic models" pre-trained on large textual corpora crawled from the Web that have exhibited unprecedented capabilities on a broad array of NLP tasks.

Abstract: Multiple Instance Learning (MIL) has been widely applied in pathology towards solving critical problems such as automating cancer diagnosis and grading, predicting patient prognosis, and therapy response. Deploying these models in a clinical setting requires careful inspection of these black boxes during development and deployment to identify failures and maintain physician trust. In this work, we propose a simple formulation of MIL models, which enables interpretability while maintaining similar predictive performance. Our Additive MIL models enable spatial credit assignment such that the contribution of each region in the image can be exactly computed and visualized. We show that our spatial credit assignment coincides with regions used by pathologists during diagnosis and improves upon classical attention heatmaps from attention MIL models.

Dogs were first domesticated around 29,000 years ago and have since become one of the most popular species of companion animals around the world. But until now, exactly why the animals became'man's best friend' has remained unclear. Now, scientists from Azabu University in Japan believe they have the answer, having discovered two key gene mutations in dogs. These mutations may have played a role in their domestication by lowering stress and making pups more comfortable interacting with humans, according to the team. Researchers from Duquesne University in Pittsburgh recently found that dogs have similar muscles in their faces to humans, allowing them to form facial expressions close to our own.

In the natural selection process, beneficial gene mutations are preserved from generation to generation until they become dominant in our genomes. The protection against pathogens drives the process. However, gene mutations that are protective against one pathogen could make people susceptible to new diseases whenever there is a change in the environment. Familial Mediterranean Fever (FMF) is one example of such disease. It is an autoimmune disease that has emerged over the past 20,000 years in southern Europe, the Middle East, and northern Africa.

Researchers have used advanced AI and large sets of genomic data to unveil how humans have adapted to recent diseases. The method could also be applied to new pathogens such as the coronavirus that causes COVID-19, helping identify which gene mutations may be associated with more severe cases of the disease. The study, by researchers from Imperial College London, the Middle East Technical University, Turkey, and the Universita degli Studi di Bari Aldo Moro, Italy, is published today in a Special Issue of Molecular Ecology Resources, "Machine Learning techniques in Evolution and Ecology." Natural selection is the process by which beneficial gene mutations are preserved from generation to generation, until they become dominant in our genomes--the catalog of all our genes. One thing that can drive natural selection is protection against pathogens.

Gene mutation prediction in hepatocellular carcinoma (HCC) is of great diagnostic and prognostic value for personalized treatments and precision medicine. In this paper, we tackle this problem with multi-instance multi-label learning to address the difficulties on label correlations, label representations, etc. Furthermore, an effective oversampling strategy is applied for data imbalance. Experimental results have shown the superiority of the proposed approach.

And now, an algorithm can predict not only whether they carry a genetic mutation, but which genes were mutated. The study, published Monday in Nature Medicine, is the latest from a Boston-based company called FDNA, one of a few organizations creating software that can help physicians diagnose genetic syndromes based just on a face -- and may serve an important validation of the company's technology, said Yaron Gurovich, the company's chief technology officer. "We went for this high-impact journal to prove beyond any doubt that this technology is good, it performs as we say, we can stand behind it, and now it opens a lot of doors to publish more," he said. The study itself is a collection of experiments testing how the results of algorithms -- FDNA refers to them as DeepGestalt -- stack up against clinicians' diagnoses. In one of the experiments, DeepGestalt's performance was better than random chance when picking which of five genetic mutations might be causing a condition called Noonan syndrome.

An international team of scientists are using data on genetic material, cell surface texture and typical facial features derived by artificial intelligence methods to simulate disease models for deficiencies in the molecule glycosylphosphatidylinositol (GPI) anchor, which is known to cause various diseases. One of the diseases is Mabry syndrome, a rare disease that is triggered by a change in a single gene, causing mental retardation. "This disease belongs to a group that we describe as GPI anchor deficiencies and which includes more than 30 genes," physician and physicist Dr. Peter Krawitz from the Institute for Genome Statistics and Bioinformatics of the University Hospital Bonn, said in a statement. GPI anchors attach specific proteins to the cell membrane and if they do not properly function due to a gene mutation, signal transmission and further steps in the cell-cell communication are impaired. The researchers investigated how a diagnosis of GPI anchor deficiencies can be improved with modern and fast DNA sequencing methods, cell surface analysis and computer aided image recognition.

The World Health Organization has estimated that there is a global shortfall of approximately 4.3 million doctors and nurses, with poorer countries disproportionately impacted. In the U.S., these shortages are less acute; instead, the country struggles with ever-increasing health care costs, which often translate into limits on the time a patient is able to spend with a doctor. One study estimated that U.S. doctors spend on average just 13 to 16 minutes with each patient. So against this backdrop of a global shortage in doctors and nurses, and cost-driven strains in patient care, let's take a look at some of the ways AI systems are being evaluated for use in medical care. In August 2016, an artificially intelligent supercomputer did in 10 minutes what would have taken human doctors weeks to achieve.