Pre-trained large language models(LLMs) have attracted increasing attention in biomedical domains due to their success in natural language processing. However, the complex traits and heterogeneity of multi-sources genomics data pose significant challenges when adapting these models to the bioinformatics and biomedical field. To address these challenges, we present GP-GPT, the first specialized large language model for genetic-phenotype knowledge representation and genomics relation analysis. Our model is fine-tuned in two stages on a comprehensive corpus composed of over 3,000,000 terms in genomics, proteomics, and medical genetics, derived from multiple large-scale validated datasets and scientific publications. GP-GPT demonstrates proficiency in accurately retrieving medical genetics information and performing common genomics analysis tasks, such as genomics information retrieval and relationship determination. Comparative experiments across domain-specific tasks reveal that GP-GPT outperforms state-of-the-art LLMs, including Llama2, Llama3 and GPT-4. These results highlight GP-GPT's potential to enhance genetic disease relation research and facilitate accurate and efficient analysis in the fields of genomics and medical genetics. Our investigation demonstrated the subtle changes of bio-factor entities' representations in the GP-GPT, which suggested the opportunities for the application of LLMs to advancing gene-phenotype research.
Models such as GPT-4 and Med-PaLM 2 have demonstrated impressive performance on a wide variety of biomedical NLP tasks. However, these models have hundreds of billions of parameters, are computationally expensive to run, require users to send their input data over the internet, and are trained on unknown data sources. Can smaller, more targeted models compete? To address this question, we build and release BioMedLM, a 2.7 billion parameter GPT-style autoregressive model trained exclusively on PubMed abstracts and full articles. When fine-tuned, BioMedLM can produce strong multiple-choice biomedical question-answering results competitive with much larger models, such as achieving a score of 57.3% on MedMCQA (dev) and 69.0% on the MMLU Medical Genetics exam. BioMedLM can also be fine-tuned to produce useful answers to patient questions on medical topics. This demonstrates that smaller models can potentially serve as transparent, privacy-preserving, economical and environmentally friendly foundations for particular NLP applications, such as in biomedicine. The model is available on the Hugging Face Hub: https://huggingface.co/stanford-crfm/BioMedLM.
In medical genetics, each genetic variant is evaluated as an independent entity regarding its clinical importance. However, in most complex diseases, variant combinations in specific gene networks, rather than the presence of a particular single variant, predominates. In the case of complex diseases, disease status can be evaluated by considering the success level of a team of specific variants. We propose a high dimensional modelling based method to analyse all the variants in a gene network together. To evaluate our method, we selected two gene networks, mTOR and TGF-Beta. For each pathway, we generated 400 control and 400 patient group samples. mTOR and TGF-? pathways contain 31 and 93 genes of varying sizes, respectively. We produced Chaos Game Representation images for each gene sequence to obtain 2-D binary patterns. These patterns were arranged in succession, and a 3-D tensor structure was achieved for each gene network. Features for each data sample were acquired by exploiting Enhanced Multivariance Products Representation to 3-D data. Features were split as training and testing vectors. Training vectors were employed to train a Support Vector Machines classification model. We achieved more than 96% and 99% classification accuracies for mTOR and TGF-Beta networks, respectively, using a limited amount of training samples.
We were interested to read the recent update on recommendations for reporting of secondary findings in clinical sequencing1, and the accompanying updated list of genes in which secondary findings should be sought (ACMG SF v3.0)2. Though the authors discuss challenges around incomplete penetrance in considerable detail, we are concerned that the recommendations do not fully convey the degree of uncertainty regarding the penetrance of variants in genes associated with inherited cardiomyopathies, which make up almost a quarter of the list. Since penetrance is incomplete and age-related, individuals found to carry variants will often require surveillance, rather than a one-off definitive diagnostic assessment. There is a lack of evidence regarding benefits, harms, and healthcare costs associated with opportunistic screening.
Language modelling provides a step towards intelligent communication systems by harnessing large repositories of written human knowledge to better predict and understand the world. In this paper, we present an analysis of Transformer-based language model performance across a wide range of model scales -- from models with tens of millions of parameters up to a 280 billion parameter model called Gopher. These models are evaluated on 152 diverse tasks, achieving state-of-the-art performance across the majority. Gains from scale are largest in areas such as reading comprehension, fact-checking, and the identification of toxic language, but logical and mathematical reasoning see less benefit. We provide a holistic analysis of the training dataset and model's behaviour, covering the intersection of model scale with bias and toxicity. Finally we discuss the application of language models to AI safety and the mitigation of downstream harms.
Facial analysis technologies have recently measured up to the capabilities of expert clinicians in syndrome identification. To date, these technologies could only identify phenotypes of a few diseases, limiting their role in clinical settings where hundreds of diagnoses must be considered. We developed a facial analysis framework, DeepGestalt, using computer vision and deep learning algorithms, that quantifies similarities to hundreds of genetic syndromes based on unconstrained 2D images. DeepGestalt is currently trained with over 26,000 patient cases from a rapidly growing phenotype-genotype database, consisting of tens of thousands of validated clinical cases, curated through a community-driven platform. DeepGestalt currently achieves 91% top-10-accuracy in identifying over 215 different genetic syndromes and has outperformed clinical experts in three separate experiments. We suggest that this form of artificial intelligence is ready to support medical genetics in clinical and laboratory practices and will play a key role in the future of precision medicine.