Mediaboss Marketing

I heard a new song last weekend called Soul Of The Machine. Its a simple, old-timey number in E minor with a standard blues chord progression (musicians in the know would call it a 1-4-5 progression). In it, a voice sings about being a trapped soul with a heart that once beat but is now cold and weak.

Soul Of The Machine is not a real song at all. Or is it? Its getting harder to say. Whatever it is, its the creation of Suno, an AI tool from a startup of the same name focused on music generation. Rolling Stone said this songs prompt was solo acoustic Mississippi Delta blues about a sad AI. And you know what? I doubt Id glance askance at it if I heard it in a mix of human-recorded Delta blues tunes. The track is technically impressive, fairly convincing, and not all that good.

I spent 10 years or so as a semiprofessional or professional musician, onstage at least four nights a week. For some of that time, I played in a genre called Western Swing. Bob Wills is the most famous example of the style, but some very smart people have argued that more of his credit should go to Milton Brown, who drew more directly from early blues and swing acts like The Hokum Boys (which featured Big Bill Broonzy) or Bessie Smith. I preferred to play more like Milton Brown.

Ive played the basic chord progression from Soul Of The Machine and variations of it countless times. So, when I say that the chords meander in nonsensical ways, its because Ive also wandered in this style. Playing with the rhythm and structure is supposed to build tension and release it, and this song doesnt do that. For contrast, notice the difference in the way Mississippi John Hurt smartly plays with the rhythm in It Aint Nobodys Business, using tricks like dragging out pauses or singing sections on a different beat than youd expect.

But when I tried to play my guitar along with Soul Of The Machine, I couldnt stay on tempo. The song just steadily winds down, like a steam engine creeping to a stop. Bad tempo or weird chord changes arent wrong or bad on their own nothing is definitively wrong or bad in music but people who struggle with rhythm dont just slow down like that. Instead, their tempo rises and falls. And when they make weird chord choices, its because they like how it sounds. AI doesnt have such motivations.

Sunos model might eventually make music that doesnt have the quirky artifacts like the dragging tempo or weird chord changes that draw attention to its algorithmic core. But not making mistakes is only part of what it needs to do to compete with human music.

As a musician, performing for a live audience was necessary for making money and becoming a known quantity. But we also needed to be good. Doing it well means reacting during a show, lingering on part of a song when the crowd loves it, or switching the setlist up on the fly. When we were at our best, we formed something like a symbiosis with our audience for a few fleeting moments or sometimes for a whole set. The best performers can make that happen almost at will. (I was not one of those performers.)

Its hard to imagine Suno or anything like it ever being able to pull that off. So I dont expect it to be a straight-up replacement for live music, which is one of the most important parts of the medium, anytime soon. But thats only one part of the package, right? Before we get to a robotic band drawing people to a dance floor or making folks cry in an auditorium, AI needs to transcend the parlor trick of imitation and start demonstrating an understanding of what moves people.

Suno co-founder Mikey Shulman told Rolling Stone that the relationship with listeners and music makers is currently so lopsided but that Suno can fix that. He said Sunos goal isnt to replace musicians but to get a billion people much more engaged with music than they are now. The companys founders imagine a world of wildly democratized music making. Thats an idea that people often float for AI art as well. It sounds like a friendly, lofty goal, and I get the appeal its not all that different from what made Neo learning Kung Fu through a neck plug in The Matrix such an attractive idea. No, Suno wont instantly teach someone how to make music, but if you want to make a blues song and youve never picked up a guitar, Soul Of The Machine could make that feel almost within reach.

But I always get stuck on that word: democratized. Rolling Stone was paraphrasing Suno in that instance, but plenty of AI art proponents have used the word democratizing while extolling the benefits of creating text or art through an algorithmic proxy, and it carries this unsettling implication that, somehow, creative people are gatekeeping the creative process.

Even if that were true, its not very clear that Suno could help with that. Its questionable whether tools like it are anywhere close to making the leap, on their own, from digital facsimile to human-style creativity.

Image created with ChatGPT by Wes Davis / The Verge

AI image generators have the same problems with details, like the image above, where I tried to get ChatGPT to give me something like Mike Mignolas Hellboy. As a teenager, I would pull Mignolas comic pages as close as my eyes would let me so I could soak up the details. Here, the details make it worse, not better. My enjoyment crumbles when I see quirks like a missing foot or a jacket morphing into the fake Hellboys arms.

Im sympathetic to the desire to use AI to make up for any shortcomings I have as an artist, but every time I hear talk about democratizing creativity, I cant help but picture someone arguing with one of these gatekeepers when they could just walk around them by simply doing creative things.

Thats not to say you wont find people trying to gatekeep art, but Ive found there are more artists offering help and encouragement than demanding my bona fides before I can join their ranks. You could sum up many artists attitudes with this quote from songwriter Dan Reeder: You can make a mess of the simplest song, and no one will laugh at you. And if they do, they can blow me, too, cause no one should laugh at you.

None of this is to say AI needs to replace creativity outright to be useful. I wouldnt argue if you told me you thought Dustin Ballards There I Ruined It AI voice parody songs which work because of his impressive singing ability and musical understanding are art. And as The Verges Becca Farsace showed in a December video, Boris Eldagsen spends months on AI-generated artwork that shows how his promptography can create thought-provoking work.

In both cases, AI isnt used as a shortcut to creativity. Instead, it enhances the ideas they already had and may even inspire new ones. If anything, they reinforce the idea that if you want to create something, theres only one way: just be creative.

View original post here:

AI-generated blues misses a human touch and a metronome - The Verge

Key Takeaways

Microsoft Corp. (MSFT) continued to point the company toward a generative artificial intelligence (AI) future with the launch Thursday of its first business-focused Surface PCs. Here are the new features you can expect to find in the Surface Pro 10 for Business and Surface Laptop 6 for Business.

The new Surface PCs are driven by Intel Corp. (INTC) Core ultra processors designed to provide powerful and reliable performance for business applications. Microsoft said its Surface Laptop 6 is two times faster than Laptop 5, while the Surface Pro 10 is up to 53% faster than the Pro 9. The enhanced speed and Neural Processing Unit (NPU) technology allow users to benefit from AI tools such as Windows Studio Effects and give business users and developers an opportunity to build their own AI apps and experiences.

Microsoft said the Surface Pro 10 for Business is its most powerful model to date and includes a new Copilot key. The new addition to the Windows keyboard will allow shortcut access to the company's flagship Copilot AI tool. Other improvements to the keyboard include a bold keyset, larger font size, and backlighting to make typing easier, alongside a screen that is 33% brighter, according to the company. Microsoft 365 apps like OneNote and Copilot also will be able to use AI to analyze handwritten notes on the Surface Slim Pen.

For the Surface Pro 10, Microsoft has focused much of its upgrade on an enhanced video calling experience. A new Ultrawide Studio Camera is its best front-facing camera on a Windows 2-in-1 or laptop that features a 114 field of view, captures video in 1440 pixels, and uses AI-powered Windows Studio Effects to ensure presentation quality, Microsoft said. The company also has launched a series of new accessories for users who want an alternative to the traditional mouse. These include custom grips on the Surface Pen and an adaptive hub device that offers three USB ports.

Finally, the new Surface PCs for business have added security features for business users, which include smart card reader technology. Surface users can access the PC with "chip-to-cloud" ID card security for authentication. Surface 10 users can get access to new near-field communication (NFC) reader technology that allows for secure, password-less authentication with NFC security keys.

Microsoft will host a special Windows and Surface AI event on May 20, at which Chief Executive Officer (CEO) Satya Nadella will outline the company's "AI vision for software and hardware. Earlier this week, the company announced that it had hired DeepMind co-founder Mustafa Suleyman as the CEO of its growing AI unit.

Go here to read the rest:

Microsoft's First AI Surface PC: What Does It Offer? - Investopedia

The Financial Times has a new generative AI chatbot called Ask FT that can answer questions its subscribers ask. Similar to generalized AI bots (like ChatGPT, Copilot, or Gemini), users can expect a curated natural language answer to whatever they want to know but with answers derived from the outlets decades of published information rather than sources that are harder to explain or are subject to ongoing legal action. So dont expect it to give you an answer for the best recipe for fettucini alfredo.

When we asked, Who runs Microsofts AI products? the tool returned an up-to-date answer and referenced news that broke this week about Microsoft hiring DeepMind co-founder Mustafa Suleyman as the head of its new AI team:

Mustafa Suleyman currently runs Microsofts consumer-facing AI products and division as the head of Microsoft AI, reporting directly to Satya Nadella [1,2,3]. He was brought in from Inflection AI to expand Microsofts focus on developing generative AI for personal consumer use [1,2,3,4,6].

The bracketed numbers correspond to the FT articles it pulled information from, which it lists beneath the answer. It also provides the time period when these articles were written. In the case of this Microsoft question, it says it pulled information ranging from March 1st, 2023, to March 20th, 2024.

We found inconsistencies with some answers, however. At the time of our testing, the tool included Nikki Haley in its answer to our question about whos currently running for the 2024 US presidential election, even though shed dropped out of the race already.

Screenshot by Emma Roth / The Verge

Its available to a few hundred paid subscribers in the FT Professional tier, which is geared toward business professionals and institutions. Ask FT is currently powered by Claude, the large language model (LLM) developed by Anthropic, but that could change. In an interview with The Verge, FT chief product officer Lindsey Jayne says the outlet is approaching this as model agnostic and seeing which one meets our needs best.

It can provide responses to questions about current events, like how much funding Intel received from the US government under the CHIPS Act, as well as broader queries, like the effect of cryptocurrency on the environment. The tool then gleans the FTs archives and summarizes the relevant information with citations.

Ask FT will also answer questions that require deeper digging into the FTs archives. When asked how YouTube started, it correctly responded that it was founded by Chad Hurley, Steve Chen, and Jawed Karim in February 2005.

We did a whole bunch of testing internally and use that to refine how we instruct the model and how we construct the code, Jayne says. In this first group of 500, we are tracking every question and response, as well as the users feedback.

Last year, we tried a similar tool deployed by the digital outlets owned by the marketing company Foundry, including Macworld, PCWorld, and Tech Advisor. However, at the time it wasnt as useful as Ask FT is; my colleague Mia Sato found it provided inaccurate results to simple questions like when the last iPod Nano was released.

I dont think youd get to be a 135-year-old institution if you arent constantly evolving and meeting these moments, Jayne says. But you have to be smart and not just get on the hype train ... otherwise people just play with it for novelty and then go about their lives.

Most subscribers wont be able to try out the chatbot just yet. Ask FT will remain in beta for now, as the FT continues to test and evaluate it.

Read the original here:

Financial Times tests an AI chatbot trained on decades of its own articles - The Verge

Posted by Yossi Matias, VP Engineering & Research, and Grey Nearing, Research Scientist, Google Research

Floods are the most common natural disaster, and are responsible for roughly $50 billion in annual financial damages worldwide. The rate of flood-related disasters has more than doubled since the year 2000 partly due to climate change. Nearly 1.5 billion people, making up 19% of the worlds population, are exposed to substantial risks from severe flood events. Upgrading early warning systems to make accurate and timely information accessible to these populations can save thousands of lives per year.

Driven by the potential impact of reliable flood forecasting on peoples lives globally, we started our flood forecasting effort in 2017. Through this multi-year journey, we advanced research over the years hand-in-hand with building a real-time operational flood forecasting system that provides alerts on Google Search, Maps, Android notifications and through the Flood Hub. However, in order to scale globally, especially in places where accurate local data is not available, more research advances were required.

In Global prediction of extreme floods in ungauged watersheds, published in Nature, we demonstrate how machine learning (ML) technologies can significantly improve global-scale flood forecasting relative to the current state-of-the-art for countries where flood-related data is scarce. With these AI-based technologies we extended the reliability of currently-available global nowcasts, on average, from zero to five days, and improved forecasts across regions in Africa and Asia to be similar to what are currently available in Europe. The evaluation of the models was conducted in collaboration with the European Center for Medium Range Weather Forecasting (ECMWF).

These technologies also enable Flood Hub to provide real-time river forecasts up to seven days in advance, covering river reaches across over 80 countries. This information can be used by people, communities, governments and international organizations to take anticipatory action to help protect vulnerable populations.

The ML models that power the FloodHub tool are the product of many years of research, conducted in collaboration with several partners, including academics, governments, international organizations, and NGOs.

In 2018, we launched a pilot early warning system in the Ganges-Brahmaputra river basin in India, with the hypothesis that ML could help address the challenging problem of reliable flood forecasting at scale. The pilot was further expanded the following year via the combination of an inundation model, real-time water level measurements, the creation of an elevation map and hydrologic modeling.

In collaboration with academics, and, in particular, with the JKU Institute for Machine Learning we explored ML-based hydrologic models, showing that LSTM-based models could produce more accurate simulations than traditional conceptual and physics-based hydrology models. This research led to flood forecasting improvements that enabled the expansion of our forecasting coverage to include all of India and Bangladesh. We also worked with researchers at Yale University to test technological interventions that increase the reach and impact of flood warnings.

Our hydrological models predict river floods by processing publicly available weather data like precipitation and physical watershed information. Such models must be calibrated to long data records from streamflow gauging stations in individual rivers. A low percentage of global river watersheds (basins) have streamflow gauges, which are expensive but necessary to supply relevant data, and its challenging for hydrological simulation and forecasting to provide predictions in basins that lack this infrastructure. Lower gross domestic product (GDP) is correlated with increased vulnerability to flood risks, and there is an inverse correlation between national GDP and the amount of publicly available data in a country. ML helps to address this problem by allowing a single model to be trained on all available river data and to be applied to ungauged basins where no data are available. In this way, models can be trained globally, and can make predictions for any river location.

Our academic collaborations led to ML research that developed methods to estimate uncertainty in river forecasts and showed how ML river forecast models synthesize information from multiple data sources. They demonstrated that these models can simulate extreme events reliably, even when those events are not part of the training data. In an effort to contribute to open science, in 2023 we open-sourced a community-driven dataset for large-sample hydrology in Nature Scientific Data.

Most hydrology models used by national and international agencies for flood forecasting and river modeling are state-space models, which depend only on daily inputs (e.g., precipitation, temperature, etc.) and the current state of the system (e.g., soil moisture, snowpack, etc.). LSTMs are a variant of state-space models and work by defining a neural network that represents a single time step, where input data (such as current weather conditions) are processed to produce updated state information and output values (streamflow) for that time step. LSTMs are applied sequentially to make time-series predictions, and in this sense, behave similarly to how scientists typically conceptualize hydrologic systems. Empirically, we have found that LSTMs perform well on the task of river forecasting.

Our river forecast model uses two LSTMs applied sequentially: (1) a hindcast LSTM ingests historical weather data (dynamic hindcast features) up to the present time (or rather, the issue time of a forecast), and (2) a forecast LSTM ingests states from the hindcast LSTM along with forecasted weather data (dynamic forecast features) to make future predictions. One year of historical weather data are input into the hindcast LSTM, and seven days of forecasted weather data are input into the forecast LSTM. Static features include geographical and geophysical characteristics of watersheds that are input into both the hindcast and forecast LSTMs and allow the model to learn different hydrological behaviors and responses in various types of watersheds.

Output from the forecast LSTM is fed into a head layer that uses mixture density networks to produce a probabilistic forecast (i.e., predicted parameters of a probability distribution over streamflow). Specifically, the model predicts the parameters of a mixture of heavy-tailed probability density functions, called asymmetric Laplacian distributions, at each forecast time step. The result is a mixture density function, called a Countable Mixture of Asymmetric Laplacians (CMAL) distribution, which represents a probabilistic prediction of the volumetric flow rate in a particular river at a particular time.

The model uses three types of publicly available data inputs, mostly from governmental sources:

Training data are daily streamflow values from the Global Runoff Data Center over the time period 1980 - 2023. A single streamflow forecast model is trained using data from 5,680 diverse watershed streamflow gauges (shown below) to improve accuracy.

We compared our river forecast model with GloFAS version 4, the current state-of-the-art global flood forecasting system. These experiments showed that ML can provide accurate warnings earlier and over larger and more impactful events.

The figure below shows the distribution of F1 scores when predicting different severity events at river locations around the world, with plus or minus 1 day accuracy. F1 scores are an average of precision and recall and event severity is measured by return period. For example, a 2-year return period event is a volume of streamflow that is expected to be exceeded on average once every two years. Our model achieves reliability scores at up to 4-day or 5-day lead times that are similar to or better, on average, than the reliability of GloFAS nowcasts (0-day lead time).

Additionally (not shown), our model achieves accuracies over larger and rarer extreme events, with precision and recall scores over 5-year return period events that are similar to or better than GloFAS accuracies over 1-year return period events. See the paper for more information.

The flood forecasting initiative is part of our Adaptation and Resilience efforts and reflects Google's commitmentto address climate change while helping global communities become more resilient. We believe that AI and ML will continue to play a critical role in helping advance science and research towards climate action.

We actively collaborate with several international aid organizations (e.g., the Centre for Humanitarian Data and the Red Cross) to provide actionable flood forecasts. Additionally, in an ongoing collaboration with the World Meteorological Organization (WMO) to support early warning systems for climate hazards, we are conducting a study to help understand how AI can help address real-world challenges faced by national flood forecasting agencies.

While the work presented here demonstrates a significant step forward in flood forecasting, future work is needed to further expand flood forecasting coverage to more locations globally and other types of flood-related events and disasters, including flash floods and urban floods. We are looking forward to continuing collaborations with our partners in the academic and expert communities, local governments and the industry to reach these goals.

Read more:

Using AI to expand global access to reliable flood forecasts - Google Research

Murray, C. J. et al. Global burden of bacterial antimicrobial resistance in 2019: a systematic analysis. Lancet 399, 629655 (2022).

Article CAS Google Scholar

Rice, L. B. Federal funding for the study of antimicrobial resistance in nosocomial pathogens: No ESKAPE. J. Infect. Dis. 197, 10791081 (2008).

Article PubMed Google Scholar

Ma, Y. et al. Considerations and caveats in combating ESKAPE pathogens against nosocomial infections. Adv. Sci. 7, 1901872 (2020).

Article CAS Google Scholar

Tacconelli, E. et al. Discovery, research, and development of new antibiotics: the WHO priority list of antibiotic-resistant bacteria and tuberculosis. Lancet Infect. Dis. 18, 318327 (2018).

Article PubMed Google Scholar

Lee, C. R. et al. Biology of Acinetobacter baumannii: pathogenesis, antibiotic resistance mechanisms, and prospective treatment options. Front. Cell. Infect. Microbiol. 7, 55 (2017).

Article PubMed PubMed Central Google Scholar

Carracedo-Reboredo, P. et al. A review on machine learning approaches and trends in drug discovery. Comput. Struct. Biotechnol. J. 19, 45384558 (2021).

Article CAS PubMed PubMed Central Google Scholar

Gaudelet, T. et al. Utilizing graph machine learning within drug discovery and development. Brief. Bioinform. 22, bbab159 (2021).

Article PubMed PubMed Central Google Scholar

Stokes, J. M. et al. A deep learning approach to antibiotic discovery. Cell 180, 688702.e13 (2020).

Article CAS PubMed PubMed Central Google Scholar

Rahman, A. S. M. Z. et al. A machine learning model trained on a high-throughput antibacterial screen increases the hit rate of drug discovery. PLoS Comput. Biol. 18, e1010613 (2022).

Article CAS PubMed PubMed Central Google Scholar

Zeng, X. et al. Deep generative molecular design reshapes drug discovery. Cell Rep. Med. 3, 100794 (2022).

Article CAS PubMed PubMed Central Google Scholar

Bilodeau, C., Jin, W., Jaakkola, T., Barzilay, R. & Jensen, K. F. Generative models for molecular discovery: recent advances and challenges. WIREs Comput. Mol. Sci. 12, e1608 (2022).

Article Google Scholar

Bian, Y. & Xie, X. Q. Generative chemistry: drug discovery with deep learning generative models. J. Mol. Model. 27, 71 (2021).

Article CAS PubMed Google Scholar

Liu, G. & Stokes, J. M. A brief guide to machine learning for antibiotic discovery. Curr. Opin. Microbiol. 69, 102190 (2022).

Article CAS PubMed Google Scholar

Gao, W. & Coley, C. W. The synthesizability of molecules proposed by generative models. J. Chem. Inf. Model. 60, 57145723 (2020).

Article CAS PubMed Google Scholar

Bradshaw, J., Paige, B., Kusner, M. J., Segler, M. H. S. & Hernndez-Lobato, J. M. A model to search for synthesizable molecules. In Proc. 33rd International Conference on Neural Information Processing Systems (eds Wallach, H. M., Larochelle, H., Beygelzimer, A., d'Alch-Buc, F. & Fox, E. B.) 79377949 (Curran Associates Inc., 2019).

Bradshaw, J., Paige, B., Kusner, M. J., Segler, M. H. S. & Hernndez-Lobato, J. M. Barking up the right tree: an approach to search over molecule synthesis DAGs. In Proc. 34th International Conference on Neural Information Processing Systems (eds Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M. F. & Lin, H.) 68526866 (Curran Associates Inc., 2020).

Gottipati, S. K. et al. Learning to navigate the synthetically accessible chemical space using reinforcement learning. In Proc. 37th International Conference on Machine Learning (eds Daum III, H. & Singh, A.) 36683679 (PMLR, 2020).

Gao, W., Mercado, R. & Coley, C. W. Amortized tree generation for bottom-up synthesis planning and synthesizable molecular design. In Proc. 10th International Conference on Learning Representations (2022); https://openreview.net/forum?id=FRxhHdnxt1

Pedawi, A., Gniewek, P., Chang, C., Anderson, B. M. & Bedem, H. van den. An efficient graph generative model for navigating ultra-large combinatorial synthesis libraries. In Proc. 36th International Conference on Neural Information Processing Systems (eds Oh, A. H., Agarwal. A., Belgrave, D. & Cho, K.) (2022); https://openreview.net/forum?id=VBbxHvbJd94

Kocsis, L. & Szepesvri, C. Bandit based Monte-Carlo planning. In Proc. European Conference on Machine Learning, ECML 2006 Vol. 4212 (eds Furnkranz, J. et al.) 282293 (Springer, 2006).

Coulom, R. Efficient selectivity and backup operators in Monte-Carlo tree search. In Proc. International Conference on Computers and Games, CG 2006 Vol. 4630 (eds van den Herik, H. J. et al.) 7283 (Springer, 2007).

Grygorenko, O. O. et al. Generating multibillion chemical space of readily accessible screening compounds. iScience 23, 101681 (2020).

Article CAS PubMed PubMed Central Google Scholar

Stokes, J. M., Davis, J. H., Mangat, C. S., Williamson, J. R. & Brown, E. D. Discovery of a small molecule that inhibits bacterial ribosome biogenesis. eLife 3, e03574 (2014).

Article PubMed PubMed Central Google Scholar

van der Maaten, L. & Hinton, G. Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 25792605 (2008).

Google Scholar

Mendez, D. et al. ChEMBL: towards direct deposition of bioassay data. Nucleic Acids Res. 47, D930D940 (2019).

Article CAS PubMed Google Scholar

Yang, K. et al. Analyzing learned molecular representations for property prediction. J. Chem. Inf. Model. 59, 33703388 (2019).

Article CAS PubMed PubMed Central Google Scholar

RDKit: open-source cheminformatics. RDKit https://www.rdkit.org/. Accessed 28 Mar 2022.

Breiman, L. Random forests. Mach. Learn. 45, 532 (2001).

Article Google Scholar

Silver, D. et al. Mastering the game of Go with deep neural networks and tree search. Nature 529, 484489 (2016).

Article CAS PubMed Google Scholar

Tversky, A. Features of similarity. Psychol. Rev. 84, 327352 (1977).

Article Google Scholar

Rogers, D. & Hahn, M. Extended-connectivity fingerprints. J. Chem. Inf. Model. 50, 742754 (2010).

Article CAS PubMed Google Scholar

Arthur, D. & Vassilvitskii, S. K-Means++: the advantages of careful seeding. In Proc. Eighteenth Annu. ACM-SIAM Symp. Discrete Algorithms 10271035 (SIAM, 2007).

Maggiora, G., Vogt, M., Stumpfe, D. & Bajorath, J. Molecular similarity in medicinal chemistry: miniperspective. J. Med. Chem. 57, 31863204 (2014).

Article CAS PubMed Google Scholar

Tanimoto, T. T. IBM Internal Report (IBM, 1957).

Nikaido, H. Molecular basis of bacterial outer membrane permeability revisited. Microbiol. Mol. Biol. Rev. 67, 593656 (2003).

Article CAS PubMed PubMed Central Google Scholar

Zurawski, D. V. et al. SPR741, an antibiotic adjuvant, potentiates the in vitro and in vivo activity of rifampin against clinically relevant extensively drug-resistant Acinetobacter baumannii. Antimicrob. Agents Chemother. 61, e01239-17 (2017).

Article PubMed PubMed Central Google Scholar

Eckburg, P. B. et al. Safety, tolerability, pharmacokinetics, and drug interaction potential of SPR741, an intravenous potentiator, after single and multiple ascending doses and when combined with -lactam antibiotics in healthy subjects. Antimicrob. Agents Chemother. 63, e00892-19 (2019).

Article PubMed PubMed Central Google Scholar

Moffatt, J. H. et al. Colistin resistance in Acinetobacter baumannii is mediated by complete loss of lipopolysaccharide production. Antimicrob. Agents Chemother. 54, 49714977 (2010).

Article CAS PubMed PubMed Central Google Scholar

ONeill, A. J., Cove, J. H. & Chopra, I. Mutation frequencies for resistance to fusidic acid and rifampicin in Staphylococcus aureus. J. Antimicrob. Chemother. 47, 647650 (2001).

Article PubMed Google Scholar

Bjrkholm, B. et al. Mutation frequency and biological cost of antibiotic resistance in Helicobacter pylori. Proc. Natl Acad. Sci. USA 98, 1460714612 (2001).

Article PubMed PubMed Central Google Scholar

Nicholson, W. L. & Maughan, H. The spectrum of spontaneous rifampin resistance mutations in the rpoB Gene of Bacillussubtilis 168 spores differs from that of vegetative cells and resembles that of Mycobacterium tuberculosis. J. Bacteriol. 184, 49364940 (2002).

Article CAS PubMed PubMed Central Google Scholar

Wu, Z. et al. MoleculeNet: a benchmark for molecular machine learning. Chem. Sci. 9, 513530 (2018).

Article CAS PubMed Google Scholar

Melo, M. C. R., Maasch, J. R. M. A. & de la Fuente-Nunez, C. Accelerating antibiotic discovery through artificial intelligence. Commun. Biol. 4, 1050 (2021).

Article CAS PubMed PubMed Central Google Scholar

Yan, J. et al. Recent progress in the discovery and design of antimicrobial peptides using traditional machine learning and deep learning. Antibiotics 11, 1451 (2022).

Article CAS PubMed PubMed Central Google Scholar

Mahlapuu, M., Hkansson, J., Ringstad, L. & Bjrn, C. Antimicrobial peptides: an emerging category of therapeutic agents. Front. Cell. Infect. Microbiol. 6, 194 (2016).

Article PubMed PubMed Central Google Scholar

Mahlapuu, M., Bjrn, C. & Ekblom, J. Antimicrobial peptides as therapeutic agents: opportunities and challenges. Crit. Rev. Biotechnol. 40, 978992 (2020).

Article CAS PubMed Google Scholar

Gmez-Bombarelli, R. et al. Automatic chemical design using a data-driven continuous representation of molecules. ACS Cent. Sci. 4, 268276 (2018).

Article PubMed PubMed Central Google Scholar

Kang, S. & Cho, K. Conditional molecular design with deep generative models. J. Chem. Inf. Model. 59, 4352 (2019).

Article CAS PubMed Google Scholar

Krenn, M., Hse, F., Nigam, A., Friederich, P. & Aspuru-Guzik, A. Self-referencing embedded strings (SELFIES): a 100% robust molecular string representation. Mach. Learn. Sci. Technol. 1, 045024 (2020).

Article Google Scholar

Liu, Q., Allamanis, M., Brockschmidt, M. & Gaunt, A. L. Constrained graph variational autoencoders for molecule design. In Proc. 32nd International Conference on Neural Information Processing Systems (eds Wallach, H. M., Larochelle, H., Grauman, K. & Cesa-Bianchi, N.) 78067815 (Curran Associates Inc., 2018).

You, J., Liu, B., Ying, R., Pande, V. & Leskovec, J. Graph convolutional policy network for goal-directed molecular graph generation. In Proc. 32nd International Conference on Neural Information Processing Systems (eds Wallach, H. M., Larochelle, H., Grauman, K. & Cesa-Bianchi, N.) 64126422 (Curran Associates Inc., 2018).

Jin, W., Barzilay, R. & Jaakkola, T. Junction tree variational autoencoder for molecular graph generation. ICML 80, 23232332 (2018).

Google Scholar

Jin, W., Barzilay, R. & Jaakkola, T. Hierarchical generation of molecular graphs using structural motifs. ICML 119, 48394848 (2020).

Google Scholar

Bilodeau, C. et al. Generating molecules with optimized aqueous solubility using iterative graph translation. React. Chem. Eng. 7, 297309 (2022).

Article CAS Google Scholar

Sadybekov, A. A. et al. Synthon-based ligand discovery in virtual libraries of over 11 billion compounds. Nature 601, 452459 (2022).

Article CAS PubMed Google Scholar

Yang, X., Zhang, J., Yoshizoe, K., Terayama, K. & Tsuda, K. ChemTS: an efficient python library for de novo molecular generation. Sci. Technol. Adv. Mater. 18, 972976 (2017).

Article CAS PubMed PubMed Central Google Scholar

Read this article:

Generative AI for designing and validating easily synthesizable and structurally novel antibiotics - Nature.com