At the beginning of the year, I have a feeling that Graph Neural Nets (GNNs) became a buzzword. As a researcher in this field, I feel a little bit proud (at least not ashamed) to say that I work on this. It was not always the case: three years ago when I was talking to my peers, who got busy working on GANs and Transformers, the general impression that they got on me was that I was working on exotic niche problems. Well, the field has matured substantially and here I propose to have a look at the top applications of GNNs that we have recently had. If this in-depth educational content on graph neural networks is useful for you, you can subscribe to our AI research mailing list to be alerted when we release new material.
The existential threat of Covid-19 has highlighted an acute need to develop working therapeutics against emerging health concerns. One of the luxuries deep learning has afforded us is the ability to modify the landscape as it unfolds -- so long as we can keep up with the viral threat, and access the right data. As with all new medical maladies, oftentimes the data need time to catch up, and the virus takes no time to slow down, posing a difficult challenge as it can quickly mutate and become resistant to existing drugs. This led scientists from MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL) and the Jameel Clinic for Machine Learning in Health to ask: How can we identify the right synergistic drug combinations for the rapidly spreading SARS-CoV-2? Typically, data scientists use deep learning to pick out drug combinations with large existing datasets for things like cancer and cardiovascular disease, but, understandably, they can't be used for new illnesses with limited data.
The existential threat of COVID-19 has highlighted an acute need to develop working therapeutics against emerging health threats. One of the luxuries deep learning has afforded us is the ability to modify the landscape as it unfolds -- so long as we can keep up with the viral threat, and access the right data. As with all new medical maladies, oftentimes the data needs time to catch up, and the virus takes no time to slow down, posing a difficult challenge as it can quickly mutate and become resistant to existing drugs. This led scientists from MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL) to ask: how can we identify the right synergistic drug combinations for the rapidly spreading SARS-CoV-2? Typically, data scientists use deep learning to pick out drug combinations with large existing datasets for things like cancer and cardiovascular disease, but, understandably, they can't be used for new illnesses with limited data.
Most excitingly, in the hands of scientists around the world, this new protein almanac will enable and accelerate research that will advance our understanding of these building blocks of life. Already, through our early collaborations, we've seen promising signals from researchers using AlphaFold in their own work. For instance, the Drugs for Neglected Diseases Initiative (DNDi) has advanced their research into life-saving cures for diseases that disproportionately affect the poorer parts of the world, and the Centre for Enzyme Innovation at the University of Portsmouth (CEI) is using AlphaFold to help engineer faster enzymes for recycling some of our most polluting single-use plastics. For those scientists who rely on experimental protein structure determination, AlphaFold's predictions have helped accelerate their research. As another example, a team at the University of Colorado Boulder is finding promise in using AlphaFold predictions to study antibiotic resistance, while a group at the University of California San Francisco has used them to increase their understanding of SARS-CoV-2 biology.
Bommasani, Rishi, Hudson, Drew A., Adeli, Ehsan, Altman, Russ, Arora, Simran, von Arx, Sydney, Bernstein, Michael S., Bohg, Jeannette, Bosselut, Antoine, Brunskill, Emma, Brynjolfsson, Erik, Buch, Shyamal, Card, Dallas, Castellon, Rodrigo, Chatterji, Niladri, Chen, Annie, Creel, Kathleen, Davis, Jared Quincy, Demszky, Dora, Donahue, Chris, Doumbouya, Moussa, Durmus, Esin, Ermon, Stefano, Etchemendy, John, Ethayarajh, Kawin, Fei-Fei, Li, Finn, Chelsea, Gale, Trevor, Gillespie, Lauren, Goel, Karan, Goodman, Noah, Grossman, Shelby, Guha, Neel, Hashimoto, Tatsunori, Henderson, Peter, Hewitt, John, Ho, Daniel E., Hong, Jenny, Hsu, Kyle, Huang, Jing, Icard, Thomas, Jain, Saahil, Jurafsky, Dan, Kalluri, Pratyusha, Karamcheti, Siddharth, Keeling, Geoff, Khani, Fereshte, Khattab, Omar, Kohd, Pang Wei, Krass, Mark, Krishna, Ranjay, Kuditipudi, Rohith, Kumar, Ananya, Ladhak, Faisal, Lee, Mina, Lee, Tony, Leskovec, Jure, Levent, Isabelle, Li, Xiang Lisa, Li, Xuechen, Ma, Tengyu, Malik, Ali, Manning, Christopher D., Mirchandani, Suvir, Mitchell, Eric, Munyikwa, Zanele, Nair, Suraj, Narayan, Avanika, Narayanan, Deepak, Newman, Ben, Nie, Allen, Niebles, Juan Carlos, Nilforoshan, Hamed, Nyarko, Julian, Ogut, Giray, Orr, Laurel, Papadimitriou, Isabel, Park, Joon Sung, Piech, Chris, Portelance, Eva, Potts, Christopher, Raghunathan, Aditi, Reich, Rob, Ren, Hongyu, Rong, Frieda, Roohani, Yusuf, Ruiz, Camilo, Ryan, Jack, Ré, Christopher, Sadigh, Dorsa, Sagawa, Shiori, Santhanam, Keshav, Shih, Andy, Srinivasan, Krishnan, Tamkin, Alex, Taori, Rohan, Thomas, Armin W., Tramèr, Florian, Wang, Rose E., Wang, William, Wu, Bohan, Wu, Jiajun, Wu, Yuhuai, Xie, Sang Michael, Yasunaga, Michihiro, You, Jiaxuan, Zaharia, Matei, Zhang, Michael, Zhang, Tianyi, Zhang, Xikun, Zhang, Yuhui, Zheng, Lucia, Zhou, Kaitlyn, Liang, Percy
AI is undergoing a paradigm shift with the rise of models (e.g., BERT, DALL-E, GPT-3) that are trained on broad data at scale and are adaptable to a wide range of downstream tasks. We call these models foundation models to underscore their critically central yet incomplete character. This report provides a thorough account of the opportunities and risks of foundation models, ranging from their capabilities (e.g., language, vision, robotics, reasoning, human interaction) and technical principles(e.g., model architectures, training procedures, data, systems, security, evaluation, theory) to their applications (e.g., law, healthcare, education) and societal impact (e.g., inequity, misuse, economic and environmental impact, legal and ethical considerations). Though foundation models are based on standard deep learning and transfer learning, their scale results in new emergent capabilities,and their effectiveness across so many tasks incentivizes homogenization. Homogenization provides powerful leverage but demands caution, as the defects of the foundation model are inherited by all the adapted models downstream. Despite the impending widespread deployment of foundation models, we currently lack a clear understanding of how they work, when they fail, and what they are even capable of due to their emergent properties. To tackle these questions, we believe much of the critical research on foundation models will require deep interdisciplinary collaboration commensurate with their fundamentally sociotechnical nature.
Working with researchers on both sides of the Atlantic, he has found a few good options. But his task is that of the most demanding locksmith: to pinpoint the chemical compounds that on their own will twist and fold into the microscopic shape that can fit perfectly into the molecules of a plastic bottle and split them apart, like a key opening a door. Determining the exact chemical contents of any given enzyme is a fairly simple challenge these days. But identifying its 3D shape can involve years of biochemical experimentation. So last fall, after reading that an artificial intelligence lab in London called DeepMind had built a system that automatically predicts the shapes of enzymes and other proteins, McGeehan asked the lab if it could help with his project.
The Annotated Germs for Automated Recognition (AGAR) dataset is an image database of microbial colonies cultured on agar plates. It contains 18000 photos of five different microorganisms as single or mixed cultures, taken under diverse lighting conditions with two different cameras. All the images are classified into "countable", "uncountable", and "empty", with the "countable" class labeled by microbiologists with colony location and species identification (336442 colonies in total). This study describes the dataset itself and the process of its development. In the second part, the performance of selected deep neural network architectures for object detection, namely Faster R-CNN and Cascade R-CNN, was evaluated on the AGAR dataset. The results confirmed the great potential of deep learning methods to automate the process of microbe localization and classification based on Petri dish photos. Moreover, AGAR is the first publicly available dataset of this kind and size and will facilitate the future development of machine learning models. The data used in these studies can be found at https://agar.neurosys.com/.
Microorganisms are widely distributed in the human daily living environment. They play an essential role in environmental pollution control, disease prevention and treatment, and food and drug production. The identification, counting, and detection are the basic steps for making full use of different microorganisms. However, the conventional analysis methods are expensive, laborious, and time-consuming. To overcome these limitations, artificial neural networks are applied for microorganism image analysis. We conduct this review to understand the development process of microorganism image analysis based on artificial neural networks. In this review, the background and motivation are introduced first. Then, the development of artificial neural networks and representative networks are introduced. After that, the papers related to microorganism image analysis based on classical and deep neural networks are reviewed from the perspectives of different tasks. In the end, the methodology analysis and potential direction are discussed.
The human mediator complex has long been one of the most challenging multi-protein systems for structural biologists to understand.Credit: Yuan He The human genome holds the instructions for more than 20,000 proteins. But only about one-third of those have had their 3D structures determined experimentally. And in many cases, those structures are only partially known. Now, a transformative artificial intelligence (AI) tool called AlphaFold, which has been developed by Google's sister company DeepMind in London, has predicted the structure of nearly the entire human proteome (the full complement of proteins expressed by an organism). In addition, the tool has predicted almost complete proteomes for various other organisms, ranging from mice and maize (corn) to the malaria parasite (see'Folding options').
Marcelo Sousa, a biochemist at the University of Colorado Boulder, had spent ten years trying to crack a particularly tricky puzzle. Sousa and his team had collected reams of experimental data on a single bacterial protein linked to antibiotic resistance. Working out its structure, they hoped, would help to find inhibitors that could stop that resistance from building. But, year after year, the puzzle remained unsolved. Within 15 minutes, DeepMind's machine learning system had solved the structure.