Related papers: BioT5+: Towards Generalized Biological Understandi…
Pre-trained encoder-decoder transformer architectures have become increasingly popular recently with the advent of T5 models. T5 has also become more favorable over other architectures like BERT due to the amount of data that it is…
Cytology is essential for cancer diagnostics and screening due to its minimally invasive nature. However, the development of robust deep learning models for digital cytology is challenging due to the heterogeneity in staining and…
This work-in-progress research paper explores the effectiveness of tutorials in interdisciplinary learning environments, specifically focusing on bioinformatics. Tutorials are typically designed for a single audience, but our study aims to…
To enhance the performance of large language models (LLMs) in biomedical natural language processing (BioNLP) by introducing a domain-specific instruction dataset and examining its impact when combined with multi-task learning principles.…
Quantitative methods and mathematical modeling are playing an increasingly important role across disciplines. As a result, interdisciplinary mathematics courses are increasing in popularity. However, teaching such courses at an advanced…
Multi-modal data abounds in biomedicine, such as radiology images and reports. Interpreting this data at scale is essential for improving clinical care and accelerating clinical research. Biomedical text with its complex semantics poses…
Biomedical Question Answering systems play a critical role in processing complex medical queries, yet they often struggle with the intricate nature of medical data and the demand for multi-hop reasoning. In this paper, we propose a model…
The challenge of replicating research results has posed a significant impediment to the field of molecular biology. The advent of modern intelligent systems has led to notable progress in various domains. Consequently, we embarked on an…
Transformer-based encoder-decoder models have demonstrated impressive results in chemical reaction prediction tasks. However, these models typically rely on pretraining using tens of millions of unlabelled molecules, which can be…
Adopting Convolutional Neural Networks (CNNs) in the daily routine of primary diagnosis requires not only near-perfect precision, but also a sufficient degree of generalization to data acquisition shifts and transparency. Existing CNN…
There is increasing adoption of artificial intelligence in drug discovery. However, existing studies use machine learning to mainly utilize the chemical structures of molecules but ignore the vast textual knowledge available in chemistry.…
Recent advances in single cell sequencing and multi-omics techniques have significantly improved our understanding of biological phenomena and our capacity to model them. Despite combined capture of data modalities showing similar progress,…
Our understanding of the physics of biological molecules, such as proteins and DNA, is limited because the approximations we usually apply to model inert materials are not in general applicable to soft, chemically inhomogeneous systems. The…
Automatic Question Answering (QA) has been successfully applied in various domains such as search engines and chatbots. Biomedical QA (BQA), as an emerging QA task, enables innovative applications to effectively perceive, access and…
The complexity of biological systems, governed by molecular interactions across hierarchical scales, presents a challenge for computational modeling. While advances in multiomic profiling have enabled precise measurements of biological…
Recent advancements in music large language models (LLMs) have significantly improved music understanding tasks, which involve the model's ability to analyze and interpret various musical elements. These improvements primarily focused on…
We study the pre-train + fine-tune strategy for data-to-text tasks. Our experiments indicate that text-to-text pre-training in the form of T5, enables simple, end-to-end transformer based models to outperform pipelined neural architectures…
Despite the recent progress in speech emotion recognition (SER), state-of-the-art systems lack generalisation across different conditions. A key underlying reason for poor generalisation is the scarcity of emotion datasets, which is a…
As natural image understanding moves towards the pretrain-finetune era, research in pathology imaging is concurrently evolving. Despite the predominant focus on pretraining pathological foundation models, how to adapt foundation models to…
Developing therapeutics is a lengthy and expensive process that requires the satisfaction of many different criteria, and AI models capable of expediting the process would be invaluable. However, the majority of current AI approaches…