Background: In protein sequences—as there are 61 sense codons but only 20 standard amino acids— most amino acids are encoded by more than one codon. Although such synonymous codons do not alter the encoded amino acid sequence, their selection can dramatically affect the expression of the resulting protein. Codon optimization of synthetic DNA sequences is important for heterologous expression. However, existing solutions are primarily based on choosing high-frequency codons only, neglecting the important effects of rare codons. In this paper, we propose a novel recurrent-neural-network based codon optimization tool, ICOR, that aims to learn codon usage bias on a genomic dataset of Escherichia coli . We compile a dataset of over 7,000 non-redundant, high-expression, robust genes which are used for deep learning. The model uses a bidirectional long short-term memory-based architecture, allowing for the sequential context of codon usage in genes to be learned. Our tool can predict synonymous codons for synthetic genes toward optimal expression in Escherichia coli . Results: We demonstrate that sequential context achieved via RNN may yield codon selection that is more similar to the host genome. Based on computational metrics that predict protein expression, ICOR theoretically optimizes protein expression more than frequency-based approaches. ICOR is evaluated on 1,481 Escherichia coli genes as well as a benchmark set of 40 select DNA sequences whose heterologous expression has been previously characterized. ICOR’s performance is measured across five metrics: the Codon Adaptation Index, GC-content, negative repeat elements, negative cis-regulatory elements, and codon frequency distribution. Conclusions: The results, based on in silico metrics, indicate that ICOR codon optimization is theoretically more effective in enhancing recombinant expression of proteins over other established codon optimization techniques. Our tool is provided as an open-source software package that includes the benchmark set of sequences used in this study.
Glioblastoma multiforme is an aggressive brain tumor with the lowest survival rate of any human cancer due to its invasive growth dynamics. These dynamics result in recurrent tumor pockets hidden from medical imaging, which standard radio-treatment and surgical margins fail to cover. Mathematical modeling of tumor growth via partial differential equations (PDE) is well-known; however, it remains unincorporated in clinical practice due to prolonged run-times, inter-patient anatomical variation, and initial conditions that ignore a patient’s current tumor. This study proposes a glioblastoma multiforme tumor evolution model, GlioMod, that aims to learn spatiotemporal features of tumor concentration and brain geometry for personalized therapeutic planning. A dataset of 6,000 synthetic tumors is generated from real patient anatomies using PDE-based modeling. Our model employs image-to-image regression using a novel encoder-decoder architecture to predict tumor concentration at future states. GlioMod is tested in its simulation of forward tumor growth and reconstruction of patient anatomy on 900 pairs of unseen brain geometries against their corresponding PDE-solved future tumor concentrations. We demonstrate that spatiotemporal context achieved via neural modeling yields tumor evolution predictions personalized to patients and still generalizable to unseen anatomies. Its performance is measured in three areas: (1) regression error rates, (2) quantitative and qualitative tissue agreement, and (3) run-time compared to state-of-the-art numerical solvers. The results demonstrate that GlioMod can predict tumor growth with high accuracy, being 2 orders of magnitude faster and therefore suitable for clinical use. GlioMod is provided as an open-source software package, which includes the synthetic tumor data generated from the patients in our study.
The use of artificial intelligence (AI) in research across all disciplines is becoming ubiquitous. However, this ubiquity is largely driven by hyperspecific AI models developed during scientific studies for accomplishing a well-defined, data-dense task. These AI models introduce apparent, human-recognizable biases because they are trained with finite, specific data sets and parameters. However, the efficacy of using large language models (LLMs) -- and LLM-powered generative AI tools, such as ChatGPT -- to assist the research process is currently indeterminate. These generative AI tools, trained on general and imperceptibly large datasets along with human feedback, present challenges in identifying and addressing biases. Furthermore, these models are susceptible to goal misgeneralization, hallucinations, and adversarial attacks such as red teaming prompts -- which can be unintentionally performed by human researchers, resulting in harmful outputs. These outputs are reinforced in research -- where an increasing number of individuals have begun to use generative AI to compose manuscripts. Efforts into AI interpretability lag behind development, and the implicit variations that occur when prompting and providing context to a chatbot introduce uncertainty and irreproducibility. We thereby find that incorporating generative AI in the process of writing research manuscripts introduces a new type of context-induced algorithmic bias and has unintended side effects that are largely detrimental to academia, knowledge production, and communicating research.
Gliomas, a type of brain tumor, have become increasingly important in oncology as they are difficult to treat due to their location deep in the brain. While some research has been done on spatiotemporal prediction of future glioma growth—something that can aid in surgical resections of gliomas once a patient has been diagnosed—modeling efforts for pre-diagnostic gliomas remain limited. The lack of retrospective, pre-diagnostic data makes this a challenging task; yet, pre-symptomatic serum glucose levels in patients have been shown to have a relationship with the emergence of gliomas, motivating this area of research. In 2015, Sturrock et al. presented an ordinary differential equation model of pre-diagnostic glioma growth that describes glioma-glucose-immune interactions. This report reproduces the major findings of Sturrock et al., revising their model to incorporate more biological phenomena—namely vascularization and mutational burden—testing additional medically relevant patient scenarios, and providing an extended discussion on the implications of the model. In-silico simulations performed in this report provide further insight into models describing glioma-glucose-immune interactions, and how they can be expanded to incorporate physiologically relevant features. Future work is necessary to refine model parameters and validate predictions with the limited, albeit steadily growing, amount of longitudinal patient data.