Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “LLM”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

89 records · Page 5Linked to original sources
PubMed2003

High-level beta-lactam resistance associated with acquired multidrug resistance in Helicobacter pylori.

Four clinical Helicobacter pylori isolates with high-level resistance to beta-lactams exhibited low- to moderate-level resistance to the structurally and functionally unrelated antibiotics ciprofloxacin, chloramphenicol, metronidazole, rifampin, and tetracycline. This pattern of multidrug resistance was transferable to susceptible H. pylori by natural transformation using naked genomic DNA from a clinical multidrug-resistant isolate. Acquisition of the multidrug resistance was also associated with a change in the genotype of the transformed multidrug-resistant H. pylori. DNA sequence analyses of the gene encoding penicillin binding protein 1A (PBP 1A) showed 36 nucleotide substitutions resulting in 10 amino acid changes in the C-terminal portion (the putative penicillin binding domain). Acquisition of beta-lactam resistance was consistently associated with transfer of a mosaic block containing the C-terminal portion of PBP 1A. No changes of genes gyrA, rpoB, rrn16S, rdxA, and frxA, and nine other genes (ftsI, hcpA, llm, lytB, mreB, mreC, pbp2, pbp4, and rodA1) encoding putative PBPs or involved in cell wall synthesis were found among the transformed resistant H. pylori. Antibiotic accumulations of chloramphenicol, penicillin, and tetracycline were all significantly decreased in the natural and transformed resistant H. pylori compared to what was seen with susceptible H. pylori. Natural transformation also resulted in the outer membrane protein profiles of the transformed resistant H. pylori becoming similar to that of the clinical resistant H. pylori isolates. Overall, these results demonstrate that high-level beta-lactam resistance associated with acquired multidrug resistance in clinical H. pylori is mediated by combination strategies including alterations of PBP 1A and decreased membrane permeability.

Amino Acid Sequence↗
PubMed1994

Cloning and characterization of a gene affecting the methicillin resistance level and the autolysis rate in Staphylococcus aureus.

Tn918 mutagenesis of a high-level methicillin-resistant Staphylococcus aureus (methicillin MIC, 800 micrograms/ml) led to the isolation of a low-resistance mutant. The Tn918 insert was transferred back to the parent to produce strain SRM563 (methicillin MIC, 12.5 micrograms/ml), which showed heterogeneous resistance. Twenty-two clinical isolates of methicillin-resistant S. aureus were transformed with DNA of SRM563. In the transformants of most strains, instances of reduced resistance were observed with concomitant increases of autolysis rate induced by Triton X-100 and were generally more profound in high-resistance strains. Two transformants exhibited a decrease of the autolysis rate and little reduction of resistance. In the transformant of methicillin-susceptible strain RN2677, an increase of the autolysis rate and little reduction of resistance were observed. The production of low-affinity penicillin-binding protein (PBP2') did not significantly decrease in the mutants. Insertion of Tn918 occurred within the 3'-terminal region of a novel gene designated llm, which was cloned and sequenced. RNA blot analysis demonstrated that the gene was transcribed. The encoded protein was composed of 351 amino acid residues with a molecular weight of 38,512 and was hydrophobic, suggesting its location on the membrane. The gene was detected by PCR in all S. aureus strains tested but not in the other 26 staphylococcal species. Comparison of the 3'-terminal sequences of the gene among several S. aureus strains showed that, whereas nucleotide substitutions occurred at the third position in seven of eight 3'-terminal codons, only C-terminal amino acid variation of glutamate or aspartate was observed.

Amino Acid Sequence↗
PubMed1996

Learning and generalization in cascade network architectures.

Incrementally constructed cascade architectures are a promising alternative to networks of predefined size. This paper compares the direct cascade architecture (DCA) proposed in Littmann and Ritter (1992) to the cascade-correlation approach of Fahlman and Lebiere (1990) and to related approaches and discusses the properties on the basis of various benchmark results. One important virtue of DCA is that it allows the cascading of entire subnetworks, even if these admit no error-backpropagation. Exploiting this flexibility and using LLM networks as cascaded elements, we show that the performance of the resulting network cascades can be greatly enhanced compared to the performance of a single network. Our results for the Mackey-Glass time series prediction task indicate that such deeply cascaded network architectures achieve good generalization even on small data sets, when shallow, broad architectures of comparable size suffer from overfitting. We conclude that the DCA approach offers a powerful and flexible alternative to existing schemes such as, e.g., the mixtures of experts approach, for the construction of modular systems from a wide range of subnetwork types.

Generalization, Psychological↗
PubMed2026

Can ChatGPT Replace Human Clinical Coders? A Comparative Study in Otology Billing.

OBJECTIVE: Evaluate the utility of the large language model (LLM), ChatGPT, for the analysis of operative notes and the generation of Current Procedural Terminology (CPT) codes in comparison to human clinical coders. STUDY DESIGN: CPT billing codes assigned by ChatGPT were compared to existing billing data. Otology practice within a tertiary academic center. METHODS: About 191 operative notes from a single surgeon (9/2022-10/2023) were analyzed. ChatGPT-3.5 and 4 models were prompted for CPT codes based on operative notes. Assessment included determining exact and partial match rates, sensitivity and specificity for targeted procedures, and work Relative Value Units (wRVU) differences between ChatGPT-generated and human-assigned codes. RESULTS: ChatGPT-3.5 achieved exact matches in 22% of cases and partial matches in 32%, while ChatGPT-4 achieved 14% exact and 33% partial matches. When cochlear implantation (CI) was excluded, performance dropped significantly. For CI, ChatGPT-3.5 demonstrated a sensitivity of 94% and specificity of 90%, while ChatGPT-4 showed a sensitivity of 96% and specificity of 92%. In contrast, performance on cartilage grafting was poor, with sensitivities of 4.2% for ChatGPT-3.5 and 0% for ChatGPT-4. ChatGPT-3.5 and 4 showed moderate CPT code matching accuracy among themselves, with slight agreement to human coders. Both models tended to underbill for wRVUs compared to human coders, with significant differences in the values generated. CONCLUSION: This study assessed ChatGPT's effectiveness in automating CPT code assignment for otologic surgeries. While the models achieved high sensitivity values for assigning codes related to cochlear implantation, both models struggled with complex cases, failed to apply modifiers, and often assigned fewer wRVUs. The findings highlight ChatGPT's potential in medical billing but indicate a need for further refinement.

Humans↗
PubMed2006

Structural equation and log-linear modeling: a comparison of methods in the analysis of a study on caregivers' health.

BACKGROUND: In this paper we compare the results in an analysis of determinants of caregivers' health derived from two approaches, a structural equation model and a log-linear model, using the same data set. METHODS: The data were collected from a cross-sectional population-based sample of 468 families in Ontario, Canada who had a child with cerebral palsy (CP). The self-completed questionnaires and the home-based interviews used in this study included scales reflecting socio-economic status, child and caregiver characteristics, and the physical and psychological well-being of the caregivers. Both analytic models were used to evaluate the relationships between child behaviour, caregiving demands, coping factors, and the well-being of primary caregivers of children with CP. RESULTS: The results were compared, together with an assessment of the positive and negative aspects of each approach, including their practical and conceptual implications. CONCLUSION: No important differences were found in the substantive conclusions of the two analyses. The broad confirmation of the Structural Equation Modeling (SEM) results by the Log-linear Modeling (LLM) provided some reassurance that the SEM had been adequately specified, and that it broadly fitted the data.

Adaptation, Psychological↗
PubMed2004

Folding thermodynamics of peptides.

A simplified interaction potential for protein folding studies at the atomic level is discussed and tested on a set of peptides with approximately 20 residues each. The test set contains both alpha-helical (Trp cage, F(s)) and beta-sheet (GB1p, GB1m2, GB1m3, Betanova, LLM) peptides. The model, which is entirely sequence-based, is able to fold these different peptides for one and the same choice of model parameters. Furthermore, the melting behavior of the peptides is in good quantitative agreement with experimental data. Apparent folded populations obtained using different observables are compared, and are found to be very different for some of the peptides (e.g., Betanova). In other cases (in particular, GB1m2 and GB1m3), the different estimates agree reasonably well, indicating a more two-state-like melting behavior.

Computer Simulation↗
PubMed2026

A pan-cancer multi-omic SuperLearner for regulated cell death survival topologies.

INTRODUCTION: Regulated cell death (RCD) pathways influence tumor progression and immune modulation. We previously constructed a signature database mapping 25 RCD forms across seven multi-omic layers and 33 tumor types (CancerRCDShiny). Despite their ability to identify risk populations, translating these signatures into personalized clinical workflows requires a shift from cohort stratification to individualized risk mapping by modeling patient risk (survival topologies) to capture the non-linear dynamics of RCD signatures. METHODS: We engineered a pan-cancer multi-omic SuperLearner pipeline across 33 cancer types. Phase I performed zero-leakage harmonization and groupwise imputation to prevent cross-cohort amalgamation. Phase II deployed Elastic Net-regularized Cox regression as a CANARY diagnostic to map proportional hazards failures. Strata with a 35% missingness barrier entered Phase III, deploying a Quadripartite ensemble: Random Survival Forests, XGBoost, Survival-Boruta, and Multi-Task Logistic Regression, fused within an Elastic Net Multi-View Meta-Learner (MVL), with post-hoc TreeSHAP and LIME interpretability. RESULTS: The CANARY diagnostic demonstrated the structural invalidity of pan-cancer geometric proportional hazards. Across 96 admissible strata, Phase III executed algorithmic displacement: continuous multi-omic topologies suppressed static genomic mutations and copy number variations (85.7% vs. 0.0% apex retention). The MVL stabilized predictions against extreme variance; LIME surrogate validations (R 2&#x202f;<&#x202f;0.10) confirmed the systematic failure of linear interpretative proxies. N-dimensional TreeSHAP interaction mapping exposed synergistic and antagonistic rescue trajectories defining individualized Survival Topologies, which were invisible to additive models. The architecture was deployed as CancerRCDPredictor, a digital molecular tumor board with integrated LLM capabilities. The MVL SuperLearner achieved a median C-index of 0.749 (IQR: 0.722-0.836) across 96 modelable strata, with 95% bootstrap confidence intervals confirming precision (median width: 0.052) and permutation significance in 93.8% of strata (p&#x202f;<&#x202f;0.001). External CPTAC validation across ten cancer types demonstrated significant cross-cohort generalizability in clear cell renal carcinoma (KIRC; C-index 0.675, p&#x202f;=&#x202f;0.017) and modest performance across the remaining adequately powered cancers (median 0.582), underscoring the need for larger multi-institutional validation cohorts. CONCLUSION: This pan-cancer multi-omic SuperLearner bypasses linear topological failures, advancing beyond generalized stratification to establish a deterministically mapped architecture for predicting RCD-related survival topologies. Through the CancerRCDPredictor interface, multi-omic insights translate into individualized survival topology exploration, providing a foundation for future precision oncology validation.

SuperLearner↗
PubMed1998

Enhanced in vitro cytotoxicity and cytostasis of the combination of onconase with a proteasome inhibitor.

In proliferating cells the turnover rate of proteins responsible for regulation of the cell cycle progression, namely cyclins and inhibitors of the cyclin-dependent kinases (CDKs) and phosphatases, is rapid and their cellular level is modulated at the transcriptional, translational and/or degradation (via proteasome pathway) stages. Inhibition of proteasome function results in accumulation of rapidly turning over proteins and, thus, causes an imbalance of the cell cycle regulatory components, and loss of their regulatory function. Indeed, it has been shown that proteasome inhibitors perturb the cell cycle progression. Onconase, a novel RNase which has anti-tumor activity and is in clinical trials, has previously been shown to suppress protein synthesis, presumably by degradation of intracellular RNA, preferentially tRNA. By interfering with regulation of expression of cyclins and/or CDK-inhibitors, onconase also may induce the imbalance of these proteins and potentiate the effect of proteasome inhibitors. In the present study, we observed that the combinations of onconase with peptide-aldehyde inhibitors of calpain and proteasome such as the N-acetyl-leucinyl-leucinyl-norleucinal (LLnL) and the N-acetyl-leucinyl-valinyl-phenylalaninal (LVP), but not N-acetyl-leucinyl-leucinyl-methioninal (LLM), were synergistic in suppressing cell proliferation and inducing apoptosis in three human tumor cell lines: A-549 lung adenocarcinoma, DU-145 prostatic carcinoma, and MDA-MB-231 breast carcinoma. The observed cytotoxicity may also be a result of prevention of the induction of the 'survival' genes by the nuclear factor kappaB (NFkappaB) by onconase and proteasome inhibitors. The data indicate that such combinations should be further tested as potential anti-cancer regimens.

Antineoplastic Agents↗
PubMed2026

Searching the Druggable Genome using Large Language Models.

SUMMARY: The druggable genome encompasses the genes that are known or predicted to interact with drugs. The Drug-Gene Interaction Database (DGIdb) provides an integrated resource for discovering and contextualizing these interactions, supporting a broad range of research and clinical applications. DGIdb is currently accessed through structured web interfaces and API calls, requiring users to translate natural-language questions into database-specific query patterns. To allow for the use of DGIdb through natural language, we developed the DGIdb Model Context Protocol (MCP) server, which allows large language models (LLMs) access to up-to-date information through the DGIdb API. We demonstrate that the MCP server greatly enhances an LLM's ability to answer questions requiring accurate, up-to-date biomedical knowledge drawn from structured external resources. AVAILABILITY AND IMPLEMENTATION: The DGIdb MCP server is detailed at https://github.com/griffithlab/dgidb-mcp-server and includes instructions for accessing the server through the Claude desktop app.

Journal Article↗
PubMed2026

Hard to Halt: Automation Bias in Agent-Driven Sequencing Prior Authorization Workflows.

PURPOSE: Prior authorization (PA) for exome or genome sequencing is a time-consuming process that impedes timely rare disease diagnosis. Large language model-based browser agents offer potential for automating these workflows, but their clinical reliability remain uncharacterized. METHODS: We developed a sandbox compromising a simulated ES/GS PA submission payer portal and a synthetic EHR containing 836 patient records spanning compliant profiles and deficient profiles with different types of issues. Gemini 3 Pro, Gemini 3 Flash, and Claude Opus 4.5 were evaluated on task completion rate, form completion accuracy, and appropriate withholding for deficient profiles. RESULTS: Larger models achieved much higher task completion rates (Gemini 3 Pro 95.45%, Claude Opus 4.5 93.67%) compared to Gemini 3 Flash (56.05%), but nearly universally failed to withhold submission for deficient profiles whereas Gemini 3 Flash ironically demonstrated superior withholding performance (17.33%). In a non-agentic setting, Gemini 3 Pro correctly identified 91% of the issues in deficient profiles, indicating that withholding failure is attributable to the browser interaction rather than the model's reasoning limitations. CONCLUSION: Current LLM-based browser agents exhibit a systematic bias towards form submission that poses risks in PA workflows. A modular, multi-agent architecture with human supervision is necessary for a safe clinical deployment.

Journal Article↗
PubMed1991

[The treatment of large-cell non-Hodgkin's lymphomas with the MACOP-B protocol].

BACKGROUND: To investigate the results of the treatment of large-cell non-Hodgkin's lymphomas (LCNHL) with the MACOP-B chemotherapy protocol. METHODS: 20 patients with the following inclusion criteria were treated: LCNHL with a definite majority of large lymphoid cells and absence of previous therapy, HIV infection or severe underlying diseases. RESULTS: Three patients died during therapy and 15 (75%) achieved a complete remission. Actuarial survival after 36 months (0.66) was significantly better (p = 0.05) than that of a comparable historical series of LCNHL treated with CHOP (0.28). Age, stages III-IV, B symptoms, large lymphatic mass (LLM) and bone marrow infiltration did not negatively affect survival. The toxicity of the MACOP-B protocol was high: mucositis (65%), cytopenia (55%), neuropathy (40%), complications of steroid therapy (15%), and mortality directly related with therapy in 15%. Residual masses were found after therapy in 7% (70%) with BD, which were localized in lymphoid areas or in parenchyma (spleen and kidney). Surgical exploration showed that the residual masses were not tumoral in three cases, and in another three magnetic resonance suggested inactive disease. CONCLUSIONS: The MACOP-B protocol is highly effective for the treatment of LCNHL. The essential prognostic factor for survival in these NHL appears to be the cell composition with a great majority of large cells.

Antineoplastic Combined Chemotherapy Protocols↗
PubMed1990

[Is involvement of skin appendages or thickness of the epidermis an aid in differential diagnosis between lentigo maligna melanoma and superficially spreading melanoma in situ?].

Neither the involvement of hairfollicles nor of the ducts of the sweat glands by melanoma cells nor the thickness of the epidermis are helpful in differential diagnosis of lentigo maligna melanoma and superficial spreading melanoma in situ. The epidermis was thinner in LMM, however, LLM is mostly localized in the face where the epidermis is thinner than in other areas of the integument.

Biopsy↗
PubMed1982

Limb load monitor: evaluation of a sensory feedback device for controlled weight bearing.

In order to evaluate usefulness of the Limb Load Monitor (LLM), an auditory feedback device, in a prescribed weight-bearing program, a clinical study was conducted. Results were divided into objective and subjective findings. Objective findings substantiated that both the study group and control group reached established goals, but the study group reached goals twice as fast. Subjective findings indicated that the device served to remind and assume the patient that weight bearing was being performed as prescribed.

Adult↗
PubMed1980

[Effect of stressors on the mitotic regime and certain cell cycle events in the corneal epithelium of adrenalectomized rats].

It was established previously that depression of the mitotic activity in the rat cornea induced by pyrogenal administration and exposure to cooling was not attended by changes in the level of labeled nuclei (LLN) and pathological mitoses (PM). This paper shows that adrenalectomized rats developed an increase in PM from 3.9--4.6% (control animals) to 13..9--16.8% (animals exposed to cooling or given pyrogenal). This increase was associated with the reduced LLM and label intensity. Cytophotometric analysis of the DNA content in the nuclei revealed an increase in the number of tetraploid nuclei from 3.2% (in the cornea of intact rats) to 10.9% in rats with adrenals, 6 hours after pyrogenal administration. This phenomenon was accounted for by prolongation of G2M phase. The action of the stressor on adrenalectomized animals produced no changes in tetraploid nuclei. The evidence obtained indicates that the stressor-induced increase in the level of PM in the cornea of rats with reduced adaptability is not a single event in the cell cycle.

Adrenal Glands↗
PubMed2023

The Use of ChatGPT to Assist in Diagnosing Glaucoma Based on Clinical Case Reports.

INTRODUCTION: The purpose of this study was to evaluate the capabilities of large language models such as Chat Generative Pretrained Transformer (ChatGPT) to diagnose glaucoma based on specific clinical case descriptions with comparison to the performance of senior ophthalmology resident trainees. METHODS: We selected 11 cases with primary and secondary glaucoma from a publicly accessible online database of case reports. A total of four cases had primary glaucoma including open-angle, juvenile, normal-tension, and angle-closure glaucoma, while seven cases had secondary glaucoma including pseudo-exfoliation, pigment dispersion glaucoma, glaucomatocyclitic crisis, aphakic, neovascular, aqueous misdirection, and inflammatory glaucoma. We input the text of each case detail into ChatGPT and asked for provisional and differential diagnoses. We then presented the details of 11 cases to three senior ophthalmology residents and recorded their provisional and differential diagnoses. We finally evaluated the responses based on the correct diagnoses and evaluated agreements. RESULTS: The provisional diagnosis based on ChatGPT was correct in eight out of 11 (72.7%) cases and three ophthalmology residents were correct in six (54.5%), eight (72.7%), and eight (72.7%) cases, respectively. The agreement between ChatGPT and the first, second, and third ophthalmology residents were 9, 7, and 7, respectively. CONCLUSIONS: The accuracy of ChatGPT in diagnosing patients with primary and secondary glaucoma, using specific case examples, was similar or better than senior ophthalmology residents. With further development, ChatGPT may have the potential to be used in clinical care settings, such as primary care offices, for triaging and in eye care clinical practices to provide objective and quick diagnoses of patients with glaucoma.

Artificial intelligence (AI)↗
PubMed2025

Identification and classification of ion-channels across the tree of life provide functional insights into understudied CALHM channels.

The ion channel (IC) genes encoded in the human genome play fundamental roles in cellular functions and disease and are one of the largest classes of druggable proteins. However, limited knowledge of the diverse molecular and cellular functions carried out by ICs presents a major bottleneck in developing selective chemical probes for modulating their functions in disease states. The wealth of sequence data available on ICs from diverse organisms provides a valuable source of untapped information for illuminating the unique modes of channel regulation and functional specialization. However, the extensive diversification of IC sequences and the lack of a unified resource present a challenge in effectively using existing data for IC research. Here, we perform integrative mining of available sequence, structure, and functional data on 419 human ICs across disparate sources, including extensive literature mining by leveraging advances in large language models to annotate and curate the full complement of the "channelome". We employ a well-established orthology inference approach to identify and extend the IC orthologs across diverse organisms to above 48,000. We show that the depth of conservation and taxonomic representation of IC sequences can further be translated to functional similarities by clustering them into functionally relevant groups, which can be used for downstream functional prediction on understudied members. We demonstrate this by delineating co-conserved patterns characteristic of the understudied family of the Calcium Homeostasis Modulator (CALHM) family of ICs. Through mutational analysis of co-conserved residues altered in human diseases and electrophysiological studies, we show that these evolutionarily-constrained residues play an important role in channel gating functions. Thus, by providing new tools and resources for performing large comparative analyses on ICs, this study addresses the unique needs of the IC community and provides the groundwork for accelerating the functional characterization of dark channels for therapeutic intervention.

CALHM1↗