Artificial intelligence technology helped researchers identify a trio of chemicals that target faulty cells linked to age-related health issues, including certain cancers and Alzheimer's disease. The algorithm comb through a library of more than 4,300 chemical compounds and identified 21 drug candidates that could prompt cell senescence. This is a phenomenon in which faulty cells stop multiplying but do not die off as they should and continue to release chemicals that can trigger inflammation. Of those 21 candidates, the scientists zeroed in on three compounds – ginkgetin, oleandrin, and periplocin – which were able to remove defective cells without harming healthy ones when tested on human cells. AI is increasingly becoming a fixture in medical and scientific research, able to sift through mountains of dense data far faster than a human ever could to aid in the diagnosis of and treatment for diseases.

Cellular senescence is an important factor in aging and many age-related diseases, but understanding its role in health is challenging due to the lack of exclusive or universal markers. Using neural networks, we predict senescence from the nuclear morphology of human fibroblasts with up to 95% accuracy, and investigate murine astrocytes, murine neurons, and fibroblasts with premature aging in culture. After generalizing our approach, the predictor recognizes higher rates of senescence in p21-positive and ethynyl-2’-deoxyuridine (EdU)-negative nuclei in tissues and shows an increasing rate of senescent cells with age in H&E-stained murine liver tissue and human dermal biopsies. Evaluating medical records reveals that higher rates of senescent cells correspond to decreased rates of malignant neoplasms and increased rates of osteoporosis, osteoarthritis, hypertension and cerebral infarction. In sum, we show that morphological alterations of the nucleus can serve as a deep learning predictor of senescence that is applicable across tissues and species and is associated with health outcomes in humans. Senescent cells are typically identified by a combination of senescence-associated markers, and the phenotype is heterogeneous. Here, using deep neural networks, Heckenbach et al. show that nuclear morphology can be used to predict cellular senescence in images of tissues and cell cultures.

Aging (spelled ageing in British English) is the process of becoming older, that involves a series of functional changes that appear over time and are not the result of illness or accident, but occur as a consequence of accumulating disorders in the body's structure and functions. It is an unpreventable chronological, social and biological process and is genetically determined and environmentally modulated. Let's see now how aging and life expectancy are affected. In the case of mammals, life expectancy varies hugely and it ranges from 3–4 years in small rodents to as long as 150–200 years in bowhead whales. As for us humans, we can potentially live for one hundred and twenty years, and just now an international research team has identified more than 2,000 new genes linked to longevity in humans (linked to DNA repair, coagulation and inflammatory response) during an evolutionary comparative genomic study that included 57 species of mammals.

Who wants to live forever? Until recently, the quest to slow ageing or even reverse it was the stuff of legends – or scams. But, today, an evidence-based race to delay or prevent ageing is energising scientists worldwide. Scientists say there are already a number of things we can do to extend life and health, while promising that current and ongoing large-scale trials of drugs and other interventions mean the once-mythical goal of healthy, longer-lived lives is not far away. "Death is inevitable but ageing is not," said Dr Nir Barzilai, founding director of the Institute for Aging Research at the Albert Einstein College of Medicine, New York.

In 2005 I attended a high-level symposium that sought a solution for an obstacle that was delaying the discovery of cures for human illnesses. The obstacle is "information overload." Stated simply, there is too much data being published for any single person to read, analyze, and connect it with over ten million existing biomedical papers. The presenters at the 2005 symposium declared there to be enough published data to cure lethal diseases, but no efficient way to tie it together in a meaningful way. I immediately understood what these computer experts were seeking.