More Gemini Features Coming to Google TV
Google TV integrates Gemini AI for image/video generation, enhances Google Photos, and adds a dedicated YouTube Shorts feed to the homepage.
Read moreIn recent years, artificial intelligence has become a key player in high-tech fields such as drug development projects. AI tools can help scientists uncover the secrets behind big biological data using optimized algorithms. AI methods such as deep neural networks have improved the way biological and chemical applications work, including the prediction of disease-related proteins, the discovery of novel biomarkers, and the de novo design of small molecule drug leads. These state-of-the-art methods can assist scientists in developing potential drugs more effectively and economically.Professor Hongzhe Sun from the Department of Chemistry at the University of Hong Kong, together with Professor Junwen Wang from the Mayo Clinic in Arizona, USA (formerly a colleague at the University of Hong Kong), collaborated on a study that explored powerful deep learning methods for predicting metal-binding sites in proteins and disease-related mutations. This is the first deep learning method for predicting metal-related site mutations in metalloproteins, providing a new platform for addressing human diseases. The research results were recently published in the top scientific journal "Nature Machine Intelligence".
Metal ions play a critical role in the (patho)physiology of human biological systems, either structurally or functionally. Metals such as zinc, iron, and copper are essential for life, but their concentrations must be strictly controlled. Deficiency or excess of these physiological metal ions can lead to serious human diseases. Mutations in the human genome have been found to be closely associated with different diseases. If these mutations occur in the coding region of DNA, they may disrupt the metal-binding sites of proteins, leading to severe human diseases. Understanding mutations on protein metal-binding sites that are associated with diseases can help discover new drugs.
The team first integrated omics data from different databases to establish a comprehensive training dataset. By examining the statistical data from the collected data, the team found that different metals have different disease associations. Mutations in zinc-binding sites play a major role in breast, liver, kidney, immune system, and prostate diseases. In contrast, mutations in calcium and magnesium-binding sites are associated with muscle and immune system diseases, respectively. Mutations in iron-binding sites are related to metabolic diseases. Additionally, mutations in manganese and copper-binding sites are associated with cardiovascular diseases, which are also related to neurological diseases.
The researchers used a novel approach to extract spatial features from metal-binding sites using energy-based affinity grid maps. These spatial features were merged with physicochemical sequence features to train the model. The final results showed that using spatial features improved the predictive performance, with an area under the curve (AUC) of 0.90 and an accuracy of 0.82. Given the limited advanced technologies and platforms in the field of metallomics and metalloproteins, the proposed deep learning method offers an integrated approach to integrate experimental data with bioinformatics analysis. This method will help scientists predict DNA mutations associated with diseases such as cancer, cardiovascular diseases, and genetic diseases.
Professor Sun said, "Machine learning and artificial intelligence play important roles in current biological and chemical sciences. In our group, we use comprehensive omics approaches, including metallomics and metalloproteomics, to study metals in biology and medicine, and we have generated a wealth of valuable information using data obtained from in vivo and in vitro experiments. We are now developing a deep learning-based AI method to transform this raw data into valuable knowledge, enabling us to uncover the secrets behind diseases and fight against them. I believe this novel deep learning method can be applied to other projects currently underway in our laboratory."
Google TV integrates Gemini AI for image/video generation, enhances Google Photos, and adds a dedicated YouTube Shorts feed to the homepage.
Read moreAlphabet Q1 paid subscribers reached 350M, fueled by YouTube & Google One. YouTube ad revenue slightly missed at $9.88B amid Premium growth. Total Q1 revenue hit $109.9B, beating forecasts.
Read moreAnthropic releases Claude connectors for Adobe, Blender, and Ableton, enabling AI workflow automation and app control. It also sponsors the Blender Development Foundation.
Read moreApple introduces an App Store model splitting 12-month plans into monthly installments. On iOS 26.4+, it lowers upfront costs without reducing total price, adding billing tracking.
Read moreGoogle launches Aadhaar digital IDs in Wallet for India, enabling secure QR/NFC verification. A phased partner rollout targets key sectors, while passport-based credentials expand globally.
Read moreYouTube tests "Ask YouTube," an AI tool blending text and video for complex queries. Initially for US Premium users, it supports interactive follow-ups, expanding Google's AI search.
Read moreGoogle grants US DoD classified AI access, joining OpenAI and xAI in defense deals amid Anthropic's dispute. Contractual safeguards against surveillance and lethal weapons remain unenforceable.
Read moreMistral AI launches Workflows, a Temporal-powered orchestration platform for secure, Python-driven enterprise AI automation featuring human-in-the-loop approvals.
Read moreCustom subliminal audio maker

AI Social Media Manager

AI Search Visibility

Workout and Calorie Tracker
Stock research platform

AI interview assistant

Scientific figure generator

AI courses with real code