Unsupervised Learning of Molecular Embeddings for Enhanced Clustering and Emergent Properties for Chemical Compounds

The detailed analysis of molecular structures and properties holds great potential for drug development discovery through machine learning. Developing an emergent property in the model to understand molecules would broaden the horizons for development with a new computational tool. We introduce various methods to detect and cluster chemical compounds based on their SMILES data. Our first method, analyzing the graphical structures of chemical compounds using embedding data, employs vector search to meet our threshold value. The results yielded pronounced, concentrated clusters, and the method produced favorable results in querying and understanding the compounds. We also used natural language description embeddings stored in a vector database with GPT3.5, which outperforms the base model. Thus, we introduce a similarity search and clustering algorithm to aid in searching for and interacting with molecules, enhancing efficiency in chemical exploration and enabling future development of emergent properties in molecular property prediction models.

Two Timin': Repairing Smart Contracts With A Two-Layered Approach

Due to the modern relevance of blockchain technology, smart contracts present both substantial risks and benefits. Vulnerabilities within them can trigger a cascade of consequences, resulting in significant losses. Many current papers primarily focus on classifying smart contracts for malicious intent, often relying on limited contract characteristics, such as bytecode or opcode. This paper proposes a novel, two-layered framework: 1) classifying and 2) directly repairing malicious contracts. Slither's vulnerability report is combined with source code and passed through a pre-trained RandomForestClassifier (RFC) and Large Language Models (LLMs), classifying and repairing each suggested vulnerability. Experiments demonstrate the effectiveness of fine-tuned and prompt-engineered LLMs. The smart contract repair models, built from pre-trained GPT-3.5-Turbo and fine-tuned Llama-2-7B models, reduced the overall vulnerability count by 97.5% and 96.7% respectively. A manual inspection of repaired contracts shows that all retain functionality, indicating that the proposed method is appropriate for automatic batch classification and repair of vulnerabilities in smart contracts.

Sentiment Analysis on the News to Improve Mental Health

The popularization of the internet created a revitalized digital media. With monetization driven by clicks, journalists have reprioritized their content for the highly competitive atmosphere of online news. The resulting negativity bias is harmful and can lead to anxiety and mood disturbance. We utilized a pipeline of 4 sentiment analysis models trained on various datasets - using Sequential, LSTM, BERT, and SVM models. When combined, the application, a mobile app, solely displays uplifting and inspiring stories for users to read. Results have been successful - 1,300 users rate the app at 4.9 stars, and 85% report improved mental health by using it.