Charting the future of cardiology with large language model artificial intelligence
Related Articles
A unified acoustic-to-speech-to-language embedding space captures the neural basis of natural language processing in everyday conversations
This study introduces a unified computational framework connecting acoustic, speech and word-level linguistic structures to study the neural basis of everyday conversations in the human brain. We used electrocorticography to record neural signals across 100 h of speech production and comprehension as participants engaged in open-ended real-life conversations. We extracted low-level acoustic, mid-level speech and contextual word embeddings from a multimodal speech-to-text model (Whisper). We developed encoding models that linearly map these embeddings onto brain activity during speech production and comprehension. Remarkably, this model accurately predicts neural activity at each level of the language processing hierarchy across hours of new conversations not used in training the model. The internal processing hierarchy in the model is aligned with the cortical hierarchy for speech and language processing, where sensory and motor regions better align with the model’s speech embeddings, and higher-level language areas better align with the model’s language embeddings. The Whisper model captures the temporal sequence of language-to-speech encoding before word articulation (speech production) and speech-to-language encoding post articulation (speech comprehension). The embeddings learned by this model outperform symbolic models in capturing neural activity supporting natural speech and language. These findings support a paradigm shift towards unified computational models that capture the entire processing hierarchy for speech comprehension and production in real-world conversations.
Language measures correlate with other measures used to study emotion
Researchers are increasingly using language measures to study emotion, yet less is known about whether language relates to other measures often used to study emotion. Building on previous work which focuses on associations between language and self-report, we test associations between language and a broader range of measures (self-report, observer report, facial cues, vocal cues). Furthermore, we examine associations across different dictionaries (LIWC-22, NRC, Lexical Suite, ANEW, VADER) used to estimate valence (i.e., positive versus negative emotion) or discrete emotions (i.e., anger, fear, sadness) in language. Associations were tested in three large, multimodal datasets (Ns = 193–1856; average word count = 316.7–2782.8). Language consistently related to observer report and consistently related to self-report in two of the three datasets. Statistically significant associations between language and facial cues emerged for language measures of valence but not for language measures of discrete emotions. Language did not consistently show significant associations with vocal cues. Results did not tend to significantly vary across dictionaries. The current research suggests that language measures (in particular, language measures of valence) are correlated with a range of other measures used to study emotion. Therefore, researchers may wish to use language to study emotion when other measures are unavailable or impractical for their research question.
An artificial market model for the forex market
As financial markets have transitioned toward electronic trading, there has been a corresponding increase in the number of algorithmic strategies and degree of transaction frequency. This move to high-frequency trading at the millisecond level, propelled by algorithmic strategies, has brought to the forefront short-term market reactions, like market impact, which were previously negligible in low-frequency trading scenarios. Such evolution necessitates a new framework for analyzing and developing algorithmic strategies in these rapidly evolving markets. Employing artificial markets stands out as a solution to this problem. This study aims to construct an artificial foreign exchange market referencing market microstructure theory, without relying on the assumption of information or technical traders. Furthermore, it endeavors to validate the model by replicating stylized facts, such as fat tails, which exhibit a higher degree of kurtosis in the return distribution than that predicted by normal distribution models. The validated artificial market model will be used to simulate market dynamics and algorithm strategies; its generated rates could also be applied to pricing and risk management for currency options and other foreign exchange derivatives. Moreover, this work explores the importance of order flow and the underlying factors of stylized facts within the artificial market model.
Responsive DNA artificial cells for contact and behavior regulation of mammalian cells
Artificial cells have emerged as synthetic entities designed to mimic the functionalities of natural cells, but their interactive ability with mammalian cells remains challenging. Herein, we develop a generalizable and modular strategy to engineer DNA-empowered stimulable artificial cells designated to regulate mammalian cells (STARM) via synthetic contact-dependent communication. Constructed through temperature-controlled DNA self-assembly involving liquid-liquid phase separation (LLPS), STARMs feature organized all-DNA cytoplasm-mimic and membrane-mimic compartments. These compartments can integrate functional nucleic acid (FNA) modules and light-responsive gold nanorods (AuNRs) to establish a programmable sense-and-respond mechanism to specific stimuli, such as light or ions, orchestrating diverse biological functions, including tissue formation and cellular signaling. By combining two designer STARMs into a dual-channel system, we achieve orthogonally regulated cellular signaling in multicellular communities. Ultimately, the in vivo therapeutic efficacy of STARM in light-guided muscle regeneration in living animals demonstrates the promising potential of smart artificial cells in regenerative medicine.
Modelling and design of transcriptional enhancers
Transcriptional enhancers are the genomic elements that contain critical information for the regulation of gene expression. This information is encoded through precisely arranged transcription factor-binding sites. Genomic sequence-to-function models, computational models that take DNA sequences as input and predict gene regulatory features, have become essential for unravelling the complex combinatorial rules that govern cell-type-specific activities of enhancers. These models function as biological ‘oracles’, capable of accurately predicting the activity of novel DNA sequences. By leveraging these oracles, DNA sequences can be optimized towards designed synthetic enhancers with tailored cell-type-specific or cell-state-specific activities. In parallel, generative artificial intelligence is rapidly advancing in genomics and enhancer design. Synthetic enhancers hold great promise for a wide range of biomedical applications, from facilitating fundamental research to enabling gene therapies.
Responses