Search

Large language models (LLMs) have revolutionized the global landscape of technology beyond the field of natural language processing. Owing to their extensive pre-training using vast datasets, contemporary LLMs can handle tasks ranging from general functionalities to domain-specific areas, such as radiology, without the need for additional fine-tuning. Importantly, LLMs are on a trajectory of rapid evolution, addressing challenges such as hallucination, bias in training data, high training costs, performance drift, and privacy issues, along with the inclusion of multimodal inputs. The concept of small, on-premise open source LLMs has garnered growing interest, as fine-tuning to medical domain knowledge, addressing efficiency and privacy issues, and managing performance drift can be effectively and simultaneously achieved. This review provides conceptual knowledge, actionable guidance, and an overview of the current technological landscape and future directions in LLMs for radiologists.

Hybrid organic–inorganic perovskite solar cells (PSCs) are receiving huge attention owing to their marvelous advantages, such as low cost, high efficiency, and superior optoelectronics characteristics. Despite their promising potential, charge-carrier dynamics at the interfaces are still ambiguous, causing carrier recombination and hindering carrier transport, thus lowering the open-circuit voltages (Voc) of PSCs. To unveil this ambiguous phenomenon, we intensively performed various optoelectronic measurements to investigate the impact of interfacial charge-carrier dynamics of PSCs under various light intensities. This is because the charge density can exhibit different mobility and charge transport properties depending on the characteristics of the charge transport layers. We explored the influence of the hole transport layer (HTL) by investigating charge transport properties using photoluminescence (PL) and time-resolved (TRPL) to unveil interfacial recombination phenomena and optoelectronic characteristics. We specifically investigated the impact of various thicknesses of HTLs, such as 2,2′,7,7′-tetrakis[N,N-di(4-methoxyphenyl)amino]-9,9′-spirobifluorene (spiro-OMeTAD), and poly(triaryl)amine (PTAA), on FA0.83MA0.17Pb(Br0.05I0.95)3 perovskite films. The HTLs are coated on perovskite film by altering the HTL’s concentration and using F4-TCNQ and 4-tert-butylpyridine (tBP) and lithium bis(trifluoromethanesulfonyl)imide (LiTFSi) as dopants both for spiro-OMeTAD and PTAA. These HTLs diversified the charge concentration gradients in the absorption layer, thus leading to different recombination rates based on the employed laser intensities. At the same time, the generated charge carriers are rapidly transferred to the interface of the HTL/absorption layer and accumulate holes at the interface because of inefficient capacitance and mobility differences caused by differently doped HTL thicknesses. Notably, the charge concentration gradient is low at lower light intensities and did not accumulate holes at the HTL/absorption layer interface, even though they have high charge mobility. Therefore, this study highlights the importance of interfacial charge recombination and charge transport phenomena to achieve highly efficient and stable PSCs.

Heterocycle substitution plays a key role in designing an ultra-narrower bandgap (ultra-NBG) small molecule-based (SM) non-fullerene acceptors (NFAs) for organic solar cells (OSCs). The NFAs molecules have great significance because of their ability to improve efficiency, narrow band gap, better charge separation, higher absorption spectra, and overall device performance. However, the impact of heterocycles such as benzoselenadiazole (BSe) on optoelectronics characteristics is still unclear. Herein, seven asymmetric NFAs based on BSe electron-deficient fused-ring core were designed from the reference (R) BTP-Se. All seven NFAs exhibited a strong absorption phenomenon from visible to near-infrared (NIR) region, corresponding to the ultra-NBG and lower excitation energy (Ex). These designed asymmetric materials (BTP1-BTP7) along with R are fully characterized theoretically with various advanced quantum chemical techniques. The optical and optoelectronics features were explored with density functional theory (DFT) and time-dependent (TD-DFT) simulations. The in-depth calculations related to density of state (DOS), transition density of state (TDM), open-circuit voltage, fill factor, and reorganization energy of electrons and holes are performed intensively. BTP3 has an optical band gap narrow of 1.76 eV and an outstanding absorption maximum of 906.85 nm. For charge transfer, a donor:acceptor complex study of BTP3:PBDBT is carried-out. We hope that this may provide a favourable strategy for building highly efficient near infrared (NIR)-based OSCs.

The IDG-DREAM Challenge carried out crowdsourced benchmarking of predictive algorithms for kinase inhibitor activities on unpublished data. This study provides a resource to compare emerging algorithms and prioritize new kinase activities to accelerate drug discovery and repurposing efforts.

A variety of real-world systems can be formulated as bipartite link prediction problems where two different types of nodes exist and no links connect nodes of the same type. In link prediction, triadic closure is an important property that describes how new links are formed. However, triadic closure is difficult to apply to bipartite link prediction tasks because the triadic closure property, which states that new edges tend to form triangles, does not hold true in bipartite settings. In this paper, we introduce Intra-class Connection based Triadic Closure (ICTC) which is a method that can use triadic closure even when the nodes in the same set are unconnected. ICTC aggregates the link probabilities of many local triads, which are edges between triples of nodes, to predict the probability of a link existing between nodes. Specifically, the probability of an edge in a triangle is calculated by multiplying the probabilities of two other edges. The experimental results on eight real-world datasets show that our method outperforms state-of-the-art methods in most cases.

Most electronic medical records, such as free-text radiological reports, are unstructured; however, the methodological approaches to analyzing these accumulating unstructured records are limited. This article proposes a deep-transfer-learning-based natural language processing model that analyzes serial magnetic resonance imaging reports of rectal cancer patients and predicts their overall survival. To evaluate the model, a retrospective cohort study of 4,338 rectal cancer patients was conducted. The experimental results revealed that the proposed model utilizing pre-trained clinical linguistic knowledge could predict the overall survival of patients without any structured information and was superior to the carcinoembryonic antigen in predicting survival. The deep-transfer-learning model using free-text radiological reports can predict the survival of patients with rectal cancer, thereby increasing the utility of unstructured medical big data.

Lung squamous cell carcinoma (LSCC) is a considerable global health burden, with an incidence of over 600,000 cases per year. Treatment options are limited, and patient’s 5-year survival rate is less than 5%. The ubiquitin-specific protease 28 (USP28) has been implicated in tumourigenesis through its stabilization of the oncoproteins c-MYC, c-JUN, and Δp63. Here, we show that genetic inactivation of Usp28-induced regression of established murine LSCC lung tumours. We developed a small molecule that inhibits USP28 activity in the low nanomole range. While displaying cross-reactivity against the closest homologue USP25, this inhibitor showed a high degree of selectivity over other deubiquitinases. USP28 inhibitor treatment resulted in a dramatic decrease in c-MYC, c-JUN, and Δp63 proteins levels and consequently induced substantial regression of autochthonous murine LSCC tumours and human LSCC xenografts, thereby phenocopying the effect observed by genetic deletion. Thus, USP28 may represent a promising therapeutic target for the treatment of squamous cell lung carcinoma.

Abstract Background Embedding techniques for converting high-dimensional sparse data into low-dimensional distributed representations have been gaining popularity in various fields of research. In deep learning models, embedding is commonly used and proven to be more effective than naive binary representation. However, yet no attempt has been made to embed highly sparse mutation profiles into densely distributed representations. Since binary representation does not capture biological context, its use is limited in many applications such as discovering novel driver mutations. Additionally, training distributed representations of mutations is challenging due to a relatively small amount of available biological data compared with the large amount of text corpus data in text mining fields. Methods We introduce Mut2Vec, a novel computational pipeline that can be used to create a distributed representation of cancerous mutations. Mut2Vec is trained on cancer profiles using Skip-Gram since cancer can be characterized by a series of co-occurring mutations. We also augmented our pipeline with existing information in the biomedical literature and protein-protein interaction networks to compensate for the data insufficiency. Results To evaluate our models, we conducted two experiments that involved the following tasks: a) visualizing driver and passenger mutations, b) identifying novel driver mutations using a clustering method. Our visualization showed a clear distinction between passenger mutations and driver mutations. We also found driver mutation candidates and proved that these were true driver mutations based on our literature survey. The pre-trained mutation vectors and the candidate driver mutations are publicly available at http://infos.korea.ac.kr/mut2vec. Conclusions We introduce Mut2Vec that can be utilized to generate distributed representations of mutations and experimentally validate the efficacy of the generated mutation representations. Mut2Vec can be used in various deep learning applications such as cancer classification and drug sensitivity prediction.

Abstract Background Molecular biomarkers that can predict drug efficacy in cancer patients are crucial components for the advancement of precision medicine. However, identifying these molecular biomarkers remains a laborious and challenging task. Next-generation sequencing of patients and preclinical models have increasingly led to the identification of novel gene-mutation-drug relations, and these results have been reported and published in the scientific literature. Results Here, we present two new computational methods that utilize all the PubMed articles as domain specific background knowledge to assist in the extraction and curation of gene-mutation-drug relations from the literature. The first method uses the Biomedical Entity Search Tool (BEST) scoring results as some of the features to train the machine learning classifiers. The second method uses not only the BEST scoring results, but also word vectors in a deep convolutional neural network model that are constructed from and trained on numerous documents such as PubMed abstracts and Google News articles. Using the features obtained from both the BEST search engine scores and word vectors, we extract mutation-gene and mutation-drug relations from the literature using machine learning classifiers such as random forest and deep convolutional neural networks. Our methods achieved better results compared with the state-of-the-art methods. We used our proposed features in a simple machine learning model, and obtained F1-scores of 0.96 and 0.82 for mutation-gene and mutation-drug relation classification, respectively. We also developed a deep learning classification model using convolutional neural networks, BEST scores, and the word embeddings that are pre-trained on PubMed or Google News data. Using deep learning, the classification accuracy improved, and F1-scores of 0.96 and 0.86 were obtained for the mutation-gene and mutation-drug relations, respectively. Conclusion We believe that our computational methods described in this research could be used as an important tool in identifying molecular biomarkers that predict drug responses in cancer patients. We also built a database of these mutation-gene-drug relations that were extracted from all the PubMed abstracts. We believe that our database can prove to be a valuable resource for precision medicine researchers.

As the volume of publications rapidly increases, searching for relevant information from the literature becomes more challenging. To complement standard search engines such as PubMed, it is desirable to have an advanced search tool that directly returns relevant biomedical entities such as targets, drugs, and mutations rather than a long list of articles. Some existing tools submit a query to PubMed and process retrieved abstracts to extract information at query time, resulting in a slow response time and limited coverage of only a fraction of the PubMed corpus. Other tools preprocess the PubMed corpus to speed up the response time; however, they are not constantly updated, and thus produce outdated results. Further, most existing tools cannot process sophisticated queries such as searches for mutations that co-occur with query terms in the literature. To address these problems, we introduce BEST, a biomedical entity search tool. BEST returns, as a result, a list of 10 different types of biomedical entities including genes, diseases, drugs, targets, transcription factors, miRNAs, and mutations that are relevant to a user's query. To the best of our knowledge, BEST is the only system that processes free text queries and returns up-to-date results in real time including mutation information in the results. BEST is freely accessible at http://best.korea.ac.kr.