Biology subjects

Hope, T.

Publications and source records attributed to Hope, T..

6 recordsLinked to original sources

bioRxiv2024

Benchmarking Stroke Outcome Prediction through Comprehensive Data Analysis - NeuralCup 2023

Stroke remains a leading cause of mortality and long-term disability worldwide, with variable recovery trajectories posing substantial challenges in anticipating post-event care and rehabilitation planning. To address these challenges, we established the NeuralCup consortium to benchmark predictive models of stroke outcome through a collaborative, data-driven approach. This study presents findings from 15 international teams who used a comprehensive dataset including clinical and imaging data, to identify and compare predictors of motor, cognitive, and emotional outcomes one year post-stroke. Our analyses integrated traditional statistical approaches and novel machine learning algorithms to uncover optimal recipes for predicting each domain. The differences in these optimal recipes reflect distinct brain mechanisms in response to different tasks. Key predictors across all domains included infarct characteristics, T1-weighted MRI sequences, and demographic factors. Additionally, integrating FLAIR imaging and white matter tract analysis significantly improved the prediction of cognitive and motor outcomes, respectively. These findings support a multifaceted approach to stroke outcome prediction, underscoring the potential of collaborative data science to develop personalized care strategies that enhance recovery and quality of life for stroke survivors. To encourage further model development and validation, we provide access to the training dataset at http://neuralcup.bcblab.com

neuroscience↗

bioRxiv2023

SynerGPT: In-Context Learning for Personalized Drug Synergy Prediction and Drug Design

Predicting synergistic drug combinations can help accelerate discovery of cancer treatments, particularly therapies personalized to a patients specific tumor via biopsied cells. In this paper, we propose a novel setting and models for in-context drug synergy learning. We are given a small "personalized dataset" of 10-20 drug synergy relationships in the context of specific cancer cell targets. Our goal is to predict additional drug synergy relationships in that context. Inspired by recent work that pre-trains a GPT language model (LM) to "in-context learn" common function classes, we devise novel pre-training schemes that enable a GPT model to in-context learn "drug synergy functions". Our model--which does not use any textual corpora, molecular fingerprints, protein interaction or any other domain-specific knowledge-- is able to achieve competitive results. We further integrate our in-context approach with a genetic algorithm to optimize model prompts and select synergy candidates to test after conducting a patient biopsy. Finally, we explore a novel task of inverse drug design which can potentially enable the design of drugs that synergize specifically to target a given patients "personalized dataset". Our findings can potentially have an important impact on precision cancer medicine, and also raise intriguing questions on non-textual pre-training for LMs.

bioinformatics↗

bioRxiv2022

Extending the Boundaries of Cancer Therapeutic Complexity with Literature Data Mining

Drug combination therapy is a main pillar of cancer therapy but the formation of an effective combinatorial standard of care (SOC) can take many years and its length of development is increasing with complexity of treatment. In this paper, we develop a path to extend the boundaries of complexity in combinatorial cancer treatments using text data mining (TDM). We first use TDM to characterize the current boundaries of cancer treatment complexity and find that the current complexity limit for clinical trials is 6 drugs per plan and for pre-clinical research is 10. We then present a TDM based assistive technology, cancer plan builder (CPB), which we make publicly available and allows experts to create literature-anchored high complexity combination treatment (HCCT) plans of significantly larger size. We develop metrics to evaluate HCCT plans and show that experts using CPB are able to create HCCT plans at much greater speed and quality, compared to experts without CPB. We hope that by releasing CPB we enable more researchers to engage with HCCT planning and demonstrate its clinical efficacy.

bioinformatics↗

bioRxiv2021

Mapping language and non-language cognitive deficits in post-stroke anomic aphasia

While language impairment is the defining symptom of aphasia, the co-occurrence of non-language cognitive deficits and their importance in predicting rehabilitation and recovery outcomes is well documented. Despite this, people with aphasia (PWA) are rarely tested on assessments of higher order cognitive functions, making it difficult for studies to associate these functions with a consistent lesion correlate. Contrary to classic models of speech and language, cumulative evidence shows that Brocas area and surrounding regions in the left inferior frontal cortex (LIFC) are involved in, but not specific to, speech production - suggesting that these regions may be involved in higher-level cognitive functions that support language production. A better understanding of language processing in the context of other domain general cognitive functions is essential for improving aphasia treatments. This study aimed to explore the brain-behaviour relationships between tests of individual cognitive skill and language abilities in people with post-stroke aphasia, with a focus on language production deficits and their associated lesion correlates. We predicted our analysis would reveal a latent (non-language specific) cognitive component, that would be driven by damage to LIFC. We analysed the behavioural and neural correlates of an extensive battery of language and non-language cognitive tests in a sample of thirty-six adults with long-term speech production deficits from post-stroke aphasia. All participants were anomic, with relatively intact speech comprehension and no apraxia of speech. The behavioural variables were analysed using Principal Component Analysis and their neural correlates were estimated using Voxel-Based Correlational Morphology. A significant number of anomic adults showed impaired performance on tests of non-language specific cognitive function. The variance underlying behavioural performance was best captured by four orthogonal components, two higher-order cognitive components (executive functions and verbal working memory) and two linguistic processing components (phonology and semantics). Brain-behaviour relationships revealed separable neural correlates for each component in line with previous studies and an executive functions correlate in the left inferior frontal cortex (LIFC). Our findings suggest that in adults with chronic post-stroke language production deficits (anomia), higher-level cognitive functions explain more of the variance in language function than classical models of the condition imply. Additionally, lesions to the LIFC, including Brocas area, were associated with executive (dys)function, independent of language abilities, suggesting that lesions to this area are associated with non-language specific higher-level cognitive functions that support speech production. These findings support contemporary models of speech production that place language processing within the context of domain-general perception, action and conceptual knowledge.

neuroscience↗

bioRxiv2021

Simulating lesion-dependent functional recovery mechanisms

Functional recovery after brain damage varies widely and depends on many factors, including lesion site and extent. When a neuronal system is damaged, recovery may occur by engaging residual (e.g., perilesional) components. When damage is extensive, recovery depends on the availability of other intact neural structures that can reproduce the same functional output (i.e., degeneracy). A systems response to damage may occur rapidly, require learning or both. Here, we simulate functional recovery from four different types of lesions, using a generative model of word repetition that comprised a default premorbid system and a less used alternative system. The synthetic lesions (i) completely disengaged the premorbid system, leaving the alternative system intact, (ii) partially damaged both premorbid and alternative systems, and (iii) limited the experience-dependent plasticity of both. The results, across 1000 trials, demonstrate that (i) a complete disconnection of the premorbid system naturally invoked the engagement of the other, (ii) incomplete damage to both systems had a much more devastating long-term effect on model performance and (iii) the effect of reducing learning capacity within each system. These findings contribute to formal frameworks for interpreting the effect of different types of lesions.

neuroscience↗

bioRxiv2020

SciSight: Combining faceted navigation and research group detection for COVID-19 exploratory scientific search

The COVID-19 pandemic has sparked unprecedented mobilization of scientists, generating a deluge of papers that makes it hard for researchers to keep track and explore new directions. Search engines are designed for targeted queries, not for discovery of connections across a corpus. In this paper, we present SciSight, a system for exploratory search of COVID-19 research integrating two key capabilities: first, exploring associations between biomedical facets automatically extracted from papers (e.g., genes, drugs, diseases, patient outcomes); second, combining textual and network information to search and visualize groups of researchers and their ties. SciSight1 has so far served over 15K users with over 42K page views and 13% returns.

bioinformatics↗