Mohammad R. K. Mofrad

Salmonn Talebi, Elizabeth Tong, Mohammad R. K. Mofrad

The use of large language models (LLMs) in healthcare is gaining popularity, but their practicality and safety in clinical settings have not been thoroughly assessed. In high-stakes environments like medical settings, trust and safety are critical issues for LLMs. To address these concerns, we present an approach to evaluate the performance and trustworthiness of a GPT3.5 model for medical image protocol assignment. We compare it with a fine-tuned BERT model and a radiologist. In addition, we have a radiologist review the GPT3.5 output to evaluate its decision-making process. Our evaluation dataset consists of 4,700 physician entries across 11 imaging protocol classes spanning the entire head. Our findings suggest that the GPT3.5 performance falls behind BERT and a radiologist. However, GPT3.5 outperforms BERT in its ability to explain its decision, detect relevant word indicators, and model calibration. Furthermore, by analyzing the explanations of GPT3.5 for misclassifications, we reveal systematic errors that need to be resolved to enhance its safety and suitability for clinical use.

Ali Gharizadeh, Karim Abbasi, Amin Ghareyazi et al.

Motivation: Drug repurposing is a viable solution for reducing the time and cost associated with drug development. However, thus far, the proposed drug repurposing approaches still need to meet expectations. Therefore, it is crucial to offer a systematic approach for drug repurposing to achieve cost savings and enhance human lives. In recent years, using biological network-based methods for drug repurposing has generated promising results. Nevertheless, these methods have limitations. Primarily, the scope of these methods is generally limited concerning the size and variety of data they can effectively handle. Another issue arises from the treatment of heterogeneous data, which needs to be addressed or converted into homogeneous data, leading to a loss of information. A significant drawback is that most of these approaches lack end-to-end functionality, necessitating manual implementation and expert knowledge in certain stages. Results: We propose a new solution, HGTDR (Heterogeneous Graph Transformer for Drug Repurposing), to address the challenges associated with drug repurposing. HGTDR is a three-step approach for knowledge graph-based drug re-purposing: 1) constructing a heterogeneous knowledge graph, 2) utilizing a heterogeneous graph transformer network, and 3) computing relationship scores using a fully connected network. By leveraging HGTDR, users gain the ability to manipulate input graphs, extract information from diverse entities, and obtain their desired output. In the evaluation step, we demonstrate that HGTDR performs comparably to previous methods. Furthermore, we review medical studies to validate our method's top ten drug repurposing suggestions, which have exhibited promising results. We also demon-strated HGTDR's capability to predict other types of relations through numerical and experimental validation, such as drug-protein and disease-protein inter-relations.

Ali Madani, Cyna Shirazinejad, Jia Rui Ong et al.

Graph neural networks are a quickly emerging field for non-Euclidean data that leverage the inherent graphical structure to predict node, edge, and global-level properties of a system. Protein properties can not easily be understood as a simple sum of their parts (i.e. amino acids), therefore, understanding their dynamical properties in the context of graphs is attractive for revealing how perturbations to their structure can affect their global function. To tackle this problem, we generate a database of 2020 mutated calponin homology (CH) domains undergoing large-scale separation in molecular dynamics. To predict the mechanosensitive force response, we develop neural message passing networks and residual gated graph convnets which predict the protein dependent force separation at 86.63 percent, 81.59 kJ/mol/nm MAE, 76.99 psec MAE for force mode classification, max force magnitude, max force time respectively-- significantly better than non-graph-based deep learning techniques. Towards uniting geometric learning techniques and biophysical observables, we premiere our simulation database as a benchmark dataset for further development/evaluation of graph neural network architectures.

Ehsaneddin Asgari, Fabienne Braune, Benjamin Roth et al.

In this paper, we introduce UniSent universal sentiment lexica for $1000+$ languages. Sentiment lexica are vital for sentiment analysis in absence of document-level annotations, a very common scenario for low-resource languages. To the best of our knowledge, UniSent is the largest sentiment resource to date in terms of the number of covered languages, including many low resource ones. In this work, we use a massively parallel Bible corpus to project sentiment information from English to other languages for sentiment analysis on Twitter data. We introduce a method called DomDrift to mitigate the huge domain mismatch between Bible and Twitter by a confidence weighting scheme that uses domain-specific embeddings to compare the nearest neighbors for a candidate sentiment word in the source (Bible) and target (Twitter) domain. We evaluate the quality of UniSent in a subset of languages for which manually created ground truth was available, Macedonian, Czech, German, Spanish, and French. We show that the quality of UniSent is comparable to manually created sentiment resources when it is used as the sentiment seed for the task of word sentiment prediction on top of embedding representations. In addition, we show that emoticon sentiments could be reliably predicted in the Twitter domain using only UniSent and monolingual embeddings in German, Spanish, French, and Italian. With the publication of this paper, we release the UniSent sentiment lexica.

Ali Madani, Ramy Arnaout, Mohammad Mofrad et al.

Echocardiography is essential to modern cardiology. However, human interpretation limits high throughput analysis, limiting echocardiography from reaching its full clinical and research potential for precision medicine. Deep learning is a cutting-edge machine-learning technique that has been useful in analyzing medical images but has not yet been widely applied to echocardiography, partly due to the complexity of echocardiograms' multi view, multi modality format. The essential first step toward comprehensive computer assisted echocardiographic interpretation is determining whether computers can learn to recognize standard views. To this end, we anonymized 834,267 transthoracic echocardiogram (TTE) images from 267 patients (20 to 96 years, 51 percent female, 26 percent obese) seen between 2000 and 2017 and labeled them according to standard views. Images covered a range of real world clinical variation. We built a multilayer convolutional neural network and used supervised learning to simultaneously classify 15 standard views. Eighty percent of data used was randomly chosen for training and 20 percent reserved for validation and testing on never seen echocardiograms. Using multiple images from each clip, the model classified among 12 video views with 97.8 percent overall test accuracy without overfitting. Even on single low resolution images, test accuracy among 15 views was 91.7 percent versus 70.2 to 83.5 percent for board-certified echocardiographers. Confusional matrices, occlusion experiments, and saliency mapping showed that the model finds recognizable similarities among related views and classifies using clinically relevant image features. In conclusion, deep neural networks can classify essential echocardiographic views simultaneously and with high accuracy. Our results provide a foundation for more complex deep learning assisted echocardiographic interpretation.

Ehsaneddin Asgari, Mohammad R. K. Mofrad

We introduce a new measure of distance between languages based on word embedding, called word embedding language divergence (WELD). WELD is defined as divergence between unified similarity distribution of words between languages. Using such a measure, we perform language comparison for fifty natural languages and twelve genetic languages. Our natural language dataset is a collection of sentence-aligned parallel corpora from bible translations for fifty languages spanning a variety of language families. Although we use parallel corpora, which guarantees having the same content in all languages, interestingly in many cases languages within the same family cluster together. In addition to natural languages, we perform language comparison for the coding regions in the genomes of 12 different organisms (4 plants, 6 animals, and two human subjects). Our result confirms a significant high-level difference in the genetic language model of humans/animals versus plants. The proposed method is a step toward defining a quantitative measure of similarity between languages, with applications in languages classification, genre identification, dialect identification, and evaluation of translations.

Ehsaneddin Asgari, Kiavash Garakani, Mohammad R. K Mofrad

Microbial communities play important roles in the function and maintenance of various biosystems, ranging from human body to the environment. Current methods for analysis of microbial communities are typically based on taxonomic phylogenetic alignment using 16S rRNA metagenomic or Whole Genome Sequencing data. In typical characterizations of microbial communities, studies deal with billions of micobial sequences, aligning them to a phylogenetic tree. We introduce a new approach for the efficient analysis of microbial communities. Our new reference-free analysis tech- nique is based on n-gram sequence analysis of 16S rRNA data and reduces the processing data size dramatically (by 105 fold), without requiring taxonomic alignment. The proposed approach is applied to characterize phenotypic microbial community differ- ences in different settings. Specifically, we applied this approach in classification of microbial com- munities across different body sites, characterization of oral microbiomes associated with healthy and diseased individuals, and classification of microbial communities longitudinally during the develop- ment of infants. Different dimensionality reduction methods are introduced that offer a more scalable analysis framework, while minimizing the loss in classification accuracies. Among dimensionality re- duction techniques, we propose a continuous vector representation for microbial communities, which can widely be used for deep learning applications in microbial informatics.

Ehsaneddin Asgari, Mohammad R. K. Mofrad

We introduce a new representation and feature extraction method for biological sequences. Named bio-vectors (BioVec) to refer to biological sequences in general with protein-vectors (ProtVec) for proteins (amino-acid sequences) and gene-vectors (GeneVec) for gene sequences, this representation can be widely used in applications of deep learning in proteomics and genomics. In the present paper, we focus on protein-vectors that can be utilized in a wide array of bioinformatics investigations such as family classification, protein visualization, structure prediction, disordered protein identification, and protein-protein interaction prediction. In this method, we adopt artificial neural network approaches and represent a protein sequence with a single dense n-dimensional vector. To evaluate this method, we apply it in classification of 324,018 protein sequences obtained from Swiss-Prot belonging to 7,027 protein families, where an average family classification accuracy of 93%+-0.06% is obtained, outperforming existing family classification methods. In addition, we use ProtVec representation to predict disordered proteins from structured proteins. Two databases of disordered sequences are used: the DisProt database as well as a database featuring the disordered regions of nucleoporins rich with phenylalanine-glycine repeats (FG-Nups). Using support vector machine classifiers, FG-Nup sequences are distinguished from structured protein sequences found in Protein Data Bank (PDB) with a 99.8% accuracy, and unstructured DisProt sequences are differentiated from structured DisProt sequences with 100.0% accuracy. These results indicate that by only providing sequence data for various proteins into this model, accurate information about protein structure can be determined.