Deep learning methods applied to chemistry can speed the discovery of novel compounds and facilitate the design of highly complex structures that are both valid and have important societal applications. Here, we present a pioneering exploration into the use of Generative Artificial Intelligence (GenAI) to design coordination cages within the field of supramolecular chemistry. Specifically, the study leverages GraphINVENT, a graph-based deep generative model, to facilitate the automated generation of tetrahedral coordination cages. Through a combination of computational tools and cheminformatics, the research aims to extend the capabilities of GenAI, traditionally applied in simpler chemical contexts, to the complex and nuanced arena of coordination cages. The approach involves a variety of training strategies, including initial pre-training on a large dataset (GDB-13) followed by transfer learning targeted at generating specific coordination cage structures. Data augmentation techniques were also applied to enrich training but did not yield successful outcomes. Several other strategies were employed, including focusing on single metal ion structures to enhance model familiarity with Fe-based cages and extending training datasets with diverse molecular examples from the ChEMBL database. Despite these strategies, the models struggled to capture the complex interactions required for successful cage generation, indicating potential limitations with both the diversity of the training datasets and the model’s architectural capacity to handle the intricate chemistry of coordination cages. However, training on the organic ligands (linkers) yielded successful results, emphasizing the benefits of focusing on smaller building blocks. The lessons learned from this project are substantial. Firstly, the knowledge acquired about generative models and the complex world of supramolecular chemistry has provided a unique opportunity to understand the challenges and possibilities of applying GenAI to such a complicated field. The results obtained in this project have highlighted the need for further refinement of data handling and model training techniques, paving the way for more advanced applications in the future. Finally, this project has not only raised our understanding of the capabilities and limitations of GenAI in coordination cages, but also set a foundation for future research that could eventually lead to breakthroughs in designing novel cage structures. Further study could concentrate on learning from the linkers in future data-driven cage design projects. / Deep learning-metoder (djup lärande metoder) som tillämpas på kemi kan påskynda upptäckten av nya molekyler och underlätta utformningen av mycket komplexa strukturer som både är giltiga och har viktiga samhällstillämpningar. Här presenterar vi en banbrytande undersökning av användningen av generativ artificiell intelligens (GenAI) för att designa koordinationsburar inom supramolekylär kemi. Specifikt utnyttjar studien GraphINVENT, en grafbaserad djup generativ modell, för att underlätta den automatiska genereringen av tetraedriska koordinationsburar. Genom en kombination av beräkningsverktyg och kemiinformatik syftar forskningen till att utöka kapaciteten hos GenAI, som traditionellt tillämpas i enklare kemiska sammanhang, till den komplexa och nyanserade arenan för koordinationsburar. Metoden innebar inledande förträning på ett brett dataset (GDB-13) följt av transferinlärning inriktad på att generera specifika koordinationsburstrukturer. Dataförstärkningstekniker användes också för att berika träningen men gav inte några lyckade resultat. Flera strategier användes, inklusive fokusering på enstaka metalljonsystem för att förbättra modellens förtrogenhet med Fe-baserade burar och utöka träningsdataset med olika molekylära exempel från ChEMBL-databasen. Trots dessa strategier hade modellerna svårt att fånga de komplexa interaktioner som krävs för framgångsrik generering av burar, vilket indikerar potentiella begränsningar inom både mångfalden av träningsdataset och modellens arkitektoniska kapacitet att hantera den invecklade kemin i koordinationsburar. Däremot var träningen på de organiska liganderna (länkarna) framgångsrik, vilket betonar fördelarna med att fokusera på mindre byggstenar. Dock är fördelarna med detta projekt betydande. Den kunskap som förvärvats om hur generativa modeller fungerar och den komplexa världen av supramolekylär kemi har gett en unik möjlighet att förstå utmaningarna och möjligheterna med att tillämpa GenAI på ett så komplicerat område. Erfarenheterna har visat på behovet av ytterligare förfining av datahantering och modellträningstekniker, vilket banar väg för mer avancerade tillämpningar i framtiden. Det här projektet har inte bara ökat vår förståelse för GenAI:s möjligheter och begränsningar i koordinationsburar utan också lagt grunden för framtida forskning som i slutändan kan leda till banbrytande upptäckter i utformningen av nya burstrukturer. Ytterligare studier skulle kunna fokusera på att lära sig från länkarna för att hjälpa framtida datadrivna projekt för burdesign.

This paper analyzes the current possible implementations and limitations of generative AI applications such as Chat-GPT, DALL-E, and Midjourney. The applications were used in a specific scenario to gauge whether it was able to effectively handle a potential request from a client, the scenario was to create a visual identity for a shoe company called WalkWise. The creations are then analyzed using Gestalt theories of perception and the machine-learning mechanisms that run these applications. To understand just how graphic designers may introduce these tools into their process, a process chart describing a typical graphic design process for a project has been created using data gathered from 8 professionals in the field who were interviewed. Using a thematic analysis, common occurring themes/activities were found and visualized in a process chart. The process was later analyzed using theories in process value analysis. Using all this information a conclusion was made that AI-generated art has several limitations that inhibit it from completely replacing human designers. These included: not understanding/generating vector graphics, not understanding objects in 3D space from less natural angles, often generating visual clichés, some potential copyright issues, and not being able to generate words. The implementation was therefore limited to a visual brainstorming tool which could aid graphic designers in quickly visualizing an idea or visualizing several different versions of one idea without having to sketch these differences, thereby making the idea-generating parts of the process more efficient.

[pt] No contexto de comércio eletrônico, descrições de produtos exercem grande influência na experiência de compra. Descrições bem feitas devem idealmente informar um potencial consumidor sobre detalhes relevantes do produto, esclarecendo potenciais dúvidas e facilitando a compra. Gerar boas descrições, entretanto, é uma atividade custosa, que tradicionalmente exige esforço humano. Ao mesmo tempo, existe uma grande quantidade de produtos sendo lançados a cada dia. Nesse contexto, este trabalho apresenta uma nova metodologia para a geração automatizada de descrições de produtos, usando as avaliações deixadas por usuários como fonte de informações. O método proposto é composto por três etapas: (i) a extração de sentenças adequadas para uma descrição a partir das avaliações (ii) a seleção de sentenças dentre as candidatas (iii) a geração da descrição de produto a partir das sentenças selecionadas usando um Large Language Model (LLM) de forma zero-shot. Avaliamos a qualidade das descrições geradas pelo nosso método comparando-as com descrições de produto reais postadas pelos próprios anunciantes. Nessa avaliação, contamos com a colaboração de 30 avaliadores, e verificamos que nossas descrições são preferidas mais vezes do que as descrições originais, sendo consideradas mais informativas, legíveis e relevantes. Além disso, nessa mesma avaliação replicamos um método da literatura recente e executamos um teste estatístico comparando seus resultados com o nosso método, e dessa comparação verificamos que nosso método gera descrições mais informativas e preferidas no geral. / [en] In the context of e-commerce, product descriptions have a great influence on the shopping experience. Well-made descriptions should ideally inform a potential consumer about relevant product details, clarifying potential doubt sand facilitating the purchase. Generating good descriptions, however, is a costly activity, which traditionally requires human effort. At the same time, there are a large number of products being launched every day. In this context, this work presents a new methodology for the automated generation of product descriptions, using reviews left by users as a source of information. The proposed method consists of three steps: (i) the extraction of suitable sentences for a description from the reviews (ii) the selection of sentences among the candidates (iii) the generation of the product description from the selected sentences using a Large Language Model (LLM) in a zero-shot way. We evaluate the quality of descriptions generated by our method by comparing them to real product descriptions posted by sellers themselves. In this evaluation, we had the collaboration of 30 evaluators, and we verified that our descriptions are preferred more often than the original descriptions, being considered more informative, readable and relevant. Furthermore, in this same evaluation we replicated a method from recent literature and performed a statistical test comparing its results with our method, and from this comparison we verified that our method generates more informative and preferred descriptions overall.

This thesis addresses the intersection of reception history in biblical studies, Generative Artificial Intelligence (GAI) and phenomenology. Three images, from text prompts using different English translations of Mark 1:1–8 (KJV, NRSV and NIV) have been generated by GAI. In addition to the three translations, a more encompassing body of information, based on exegetical analysis, reception history and recent scholarly literature on John the Baptist and Mark 1, was also provided. Mark 1 is analyzed using narrative criticism with special focus on John the Baptist. Current research on the historical John is discussed, alongside interpretations of John from Late Ancient Christian Sources seen from a phenomenological perspective.  Traditionally, interpreting biblical art and text has assumed an artist portraying a narrative reading using methods such as visual exegesis. With GAI, this has changed moving the artist from the canvas to the text prompt. It puts the biblical text in a direct causal connection to the created image. Previously the artist had to decide when the image was finished but with GAI the decision is about which image to keep. The purpose of the image becomes a focal point. Images created with this modern technology can be relevant in at least two regards. First, they do represent a new type of biblical art. Second, the iterative process itself is a novel approach to studying and interacting with the Bible. Challenges exists, such as a bias towards Western/American cultural, sociological, and economical values. Data scientists and mathematicians are determining the probabilistic models without problematizing the content. Ethical questions in this field need to be addressed. GAI learning from AI-produced data – instead of human data – will likely become an issue, thus reinforcing existing biases and prejudices further.