Zhu, Hongtu

Abstract With the rapid advancements in large language model technology and the emergence of bioinformatics‐specific language models (BioLMs), there is a growing need for a comprehensive analysis of the current landscape, computational characteristics, and diverse applications. This survey aims to address this need by providing a thorough review of BioLMs, focusing on their evolution, classification, and distinguishing features, alongside a detailed examination of training methodologies, datasets, and evaluation frameworks. We explore the wide‐ranging applications of BioLMs in critical areas such as disease diagnosis, drug discovery, and vaccine development, highlighting their impact and transformative potential in bioinformatics. We identify key challenges and limitations inherent in BioLMs, including data privacy and security concerns, interpretability issues, biases in training data and model outputs, and domain adaptation complexities. Finally, we highlight emerging trends and future directions, offering valuable insights to guide researchers and clinicians toward advancing BioLMs for increasingly sophisticated biological and clinical applications.

Accurate prediction of progression in subjects at risk of Alzheimer's disease is crucial for enrolling the right subjects in clinical trials. However, a prospective comparison of state-of-the-art algorithms for predicting disease onset and progression is currently lacking. We present the findings of "The Alzheimer's Disease Prediction Of Longitudinal Evolution" (TADPOLE) Challenge, which compared the performance of 92 algorithms from 33 international teams at predicting the future trajectory of 219 individuals at risk of Alzheimer's disease. Challenge participants were required to make a prediction, for each month of a 5-year future time period, of three key outcomes: clinical diagnosis, Alzheimer's Disease Assessment Scale Cognitive Subdomain (ADAS-Cog13), and total volume of the ventricles. The methods used by challenge participants included multivariate linear regression, machine learning methods such as support vector machines and deep neural networks, as well as disease progression models. No single submission was best at predicting all three outcomes. For clinical diagnosis and ventricle volume prediction, the best algorithms strongly outperform simple baselines in predictive ability. However, for ADAS-Cog13 no single submitted prediction method was significantly better than random guesswork. Two ensemble methods based on taking the mean and median over all predictions, obtained top scores on almost all tasks. Better than average performance at diagnosis prediction was generally associated with the additional inclusion of features from cerebrospinal fluid (CSF) samples and diffusion tensor imaging (DTI). On the other hand, better performance at ventricle volume prediction was associated with inclusion of summary statistics, such as the slope or maxima/minima of patient-specific biomarkers. On a limited, cross-sectional subset of the data emulating clinical trials, performance of the best algorithms at predicting clinical diagnosis decreased only slightly (2 percentage points) compared to the full longitudinal dataset. The submission system remains open via the website https://tadpole.grand-challenge.org, while TADPOLE SHARE (https://tadpole-share.github.io/) collates code for submissions. TADPOLE's unique results suggest that current prediction algorithms provide sufficient accuracy to exploit biomarkers related to clinical diagnosis and ventricle volume, for cohort refinement in clinical trials for Alzheimer's disease. However, results call into question the usage of cognitive test scores for patient selection and as a primary endpoint in clinical trials.

AbstractAlzheimer's disease (AD) is a chronic neurodegenerative disease characterized by progressive decline in memory and other aspects of cognitive function. Diffusion‐weighted imaging (DWI) offers a non‐invasive approach to delineate the effects of AD on white matter (WM) integrity. Previous studies calculated either some summary statistics over regions of interest (ROI analysis) or some statistics along mean skeleton lines (Tract Based Spatial Statistic [TBSS]), so they cannot quantify subtle local WM alterations along major tracts. Here, a comprehensive WM analysis framework to map disease effects on 3D tracts both locally and globally, based on a study of 200 subjects: 49 healthy elderly normal controls, 110 with mild cognitive impairment, and 41 AD patients has been presented. 18 major WM tracts were extracted with our automated clustering algorithm—autoMATE (automated Multi‐Atlas Tract Extraction); we then extracted multiple DWI‐derived parameters of WM integrity along the WM tracts across all subjects. A novel statistical functional analysis method—FADTTS (Functional Analysis for Diffusion Tensor Tract Statistics) was applied to quantify degenerative patterns along WM tracts across different stages of AD. Gradually increasing WM alterations were found in all tracts in successive stages of AD. Among all 18 WM tracts, the fornix was most adversely affected. Among all the parameters, mean diffusivity (MD) was the most sensitive to WM alterations in AD. This study provides a systematic workflow to examine WM integrity across automatically computed 3D tracts in AD and may be useful in studying other neurological and psychiatric disorders. Hum Brain Mapp 38:1191–1207, 2017. © 2016 Wiley Periodicals, Inc.