MolFeSCue: enhancing molecular property prediction in data-limited and imbalanced contexts using few-shot and contrastive learning

MOTIVATION

Predicting molecular properties is a pivotal task in various scientific domains, including drug discovery, material science, and computational chemistry. This problem is often hindered by the lack of annotated data and imbalanced class distributions, which pose significant challenges in developing accurate and robust predictive models.

RESULTS

This study tackles these issues by employing pretrained molecular models within a few-shot learning framework. A novel dynamic contrastive loss function is utilized to further improve model performance in the situation of class imbalance. The proposed MolFeSCue framework not only facilitates rapid generalization from minimal samples, but also employs a contrastive loss function to extract meaningful molecular representations from imbalanced datasets. Extensive evaluations and comparisons of MolFeSCue and state-of-the-art algorithms have been conducted on multiple benchmark datasets, and the experimental data demonstrate our algorithm's effectiveness in molecular representations and its broad applicability across various pretrained models. Our findings underscore MolFeSCues potential to accelerate advancements in drug discovery.

AVAILABILITY AND IMPLEMENTATION

We have made all the source code utilized in this study publicly accessible via GitHub at http://www.healthinformaticslab.org/supp/ or https://github.com/zhangruochi/MolFeSCue. The code (MolFeSCue-v1-00) is also available as the supplementary file of this paper.

Computational Characterization of Undifferentially Expressed Genes with Altered Transcription Regulation in Lung Cancer

A transcriptome profiles the expression levels of genes in cells and has accumulated a huge amount of public data. Most of the existing biomarker-related studies investigated the differential expression of individual transcriptomic features under the assumption of inter-feature independence. Many transcriptomic features without differential expression were ignored from the biomarker lists. This study proposed a computational analysis protocol (mqTrans) to analyze transcriptomes from the view of high-dimensional inter-feature correlations. The mqTrans protocol trained a regression model to predict the expression of an mRNA feature from those of the transcription factors (TFs). The difference between the predicted and real expression of an mRNA feature in a query sample was defined as the mqTrans feature. The new mqTrans view facilitated the detection of thirteen transcriptomic features with differentially expressed mqTrans features, but without differential expression in the original transcriptomic values in three independent datasets of lung cancer. These features were called dark biomarkers because they would have been ignored in a conventional differential analysis. The detailed discussion of one dark biomarker, GBP5, and additional validation experiments suggested that the overlapping long non-coding RNAs might have contributed to this interesting phenomenon. In summary, this study aimed to find undifferentially expressed genes with significantly changed mqTrans values in lung cancer. These genes were usually ignored in most biomarker detection studies of undifferential expression. However, their differentially expressed mqTrans values in three independent datasets suggested their strong associations with lung cancer.

Undifferentially Expressed CXXC5 as a Transcriptionally Regulatory Biomarker of Breast Cancer

This work hypothesizes that some genes undergo radically changed transcription regulations (TRs) in breast cancer (BC), but don't show differential expressions for unknown reasons. The TR of a gene is quantitatively formulated by a regression model between the expression of this gene and multiple transcription factors (TFs). The difference between the predicted and real expression levels of a gene in a query sample is defined as the mqTrans value of this gene, which quantitatively reflects its regulatory changes. This work systematically screens the undifferentially expressed genes with differentially expressed mqTrans values in 1036 samples across five datasets and three ethnic groups. This study calls the 25 genes satisfying the above hypothesis in at least four datasets as dark biomarkers, and the strong dark biomarker gene CXXC5 (CXXC Finger Protein 5) is even supported by all the five independent BC datasets. Although CXXC5 does not show differential expressions in BC, its transcription regulations show quantitative associations with BCs in diversified cohorts. The overlapping long noncoding RNAs (lncRNAs) may have contributed their transcripts to the expression miscalculations of dark biomarkers. The mqTrans analysis serves as a complementary view of the transcriptome-based detections of biomarkers that are ignored by many existing studies.

Metabolomic analysis for asymptomatic hyperuricemia and gout based on a combination of dried blood spot sampling and mass spectrometry technology

BACKGROUND

Gout is the most common inflammatory arthritis and closely related to metabolic syndrome, leading to excruciating pain and the decline in quality of patients' life. However, the pathogenesis of gout is still unclear, and novel biomarkers are demanded for the early prediction and diagnosis of gout.

OBJECTIVE

This study aimed at profiling the dysregulated metabolic pathways in asymptomatic hyperuricemia (AHU) and gout and elucidating the associations between AHU, gout and metabolomics, which may aid in performing gout screening.

METHODS

A total of 300 participants, including 114 healthy controls, 92 patients with AHU, and 94 patients with gout, were analyzed by using a combination of dried blood spot (DBS) sampling and mass spectrometry (MS) technology. Multiple algorithms were applied to characterize altered metabolic profiles in AHU and gout. The mainly altered metabolites were identified by random forest analysis.

RESULTS

There were significant differences in AHU and gout compared with control group. The altered metabolites were involved in oxidation of fatty acids, carnitine synthesis, urea cycle, and amino acid metabolism in AHU and gout. Random forest classification of 16 metabolites yielded 3 important features to distinguish gout from AHU.

CONCLUSIONS

Distinct metabolomic signatures were observed in AHU and gout. The selected metabolites may have the potential to improve the early detection of gout.

Predictive value of serum lncRNA MALAT1 for the recurrence of persistent atrial fibrillation after radiofrequency ablation

Objective: The authors investigated the predictive value of MALAT1 for persistent atrial fibrillation (PAF) recurrence after radiofrequency ablation. Methods: Serum MALAT1 level was determined. The correlation between MALAT1 and high-sensitivity C-reactive protein/left atrial diameter (LAD) was analyzed. The predictive value of MALAT1 was evaluated. The postoperative recurrence rate in patients with high/low MALAT1 was compared. Independent risk factors for postoperative recurrence were analyzed. Results: MALAT1 was elevated in PAF patients and positively correlated with high-sensitivity C-reactive protein/LAD. MALAT1/high-sensitivity C-reactive protein/LAD were enhanced in patients with recurrent PAF. Patients with high MALAT1 had a higher recurrence rate. Upregulated MALAT1 was an independent risk factor for postoperative PAF recurrence. Conclusion: Serum MALAT1 level >2.03 predicts postoperative recurrence of PAF, and PAF patients with high MALAT1 have a higher risk of postoperative recurrence.

Transcriptional Dysregulations of Seven Non-Differentially Expressed Genes as Biomarkers of Metastatic Colon Cancer

Background: Colon cancer (CC) is common, and the mortality rate greatly increases as the disease progresses to the metastatic stage. Early detection of metastatic colon cancer (mCC) is crucial for reducing the mortality rate. Most previous studies have focused on the top-ranked differentially expressed transcriptomic biomarkers between mCC and primary CC while ignoring non-differentially expressed genes. Results: This study proposed that the complicated inter-feature correlations could be quantitatively formulated as a complementary transcriptomic view. We used a regression model to formulate the correlation between the expression levels of a messenger RNA (mRNA) and its regulatory transcription factors (TFs). The change between the predicted and real expression levels of a query mRNA was defined as the mqTrans value in the given sample, reflecting transcription regulatory changes compared with the model-training samples. A dark biomarker in mCC is defined as an mRNA gene that is non-differentially expressed in mCC but demonstrates mqTrans values significantly associated with mCC. This study detected seven dark biomarkers using 805 samples from three independent datasets. Evidence from the literature supports the role of some of these dark biomarkers. Conclusions: This study presented a complementary high-dimensional analysis procedure for transcriptome-based biomarker investigations with a case study on mCC.

Pharmacokinetic and Bioequivalent Study of Potassium Chloride Sustained-Release Tablet Under Different Dietary Conditions in Healthy Chinese Subjects

Potassium (K⁺ ) is an endogenous substance that is an essential dietary component. However, the interaction between dietary arrangements and specific effects of dietary K⁺ intake in bioequivalence studies remains unclear. To investigate the influence of dietary arrangement on the bioequivalence of potassium chloride (KCl) sustained-release tablets in healthy Chinese volunteers, the pharmacokinetics of KCl were compared in two open-label, single-center, randomized, two-period crossover studies with different dietary conditions. All volunteers received an oral dose of 6 g of KCl sustained-release tablets under fasting conditions, with different dietary arrangements. Urine samples were collected on baseline days and 48 hours after tablet consumption. Inductively coupled plasma-optical emission spectrometry was used to measure the concentration of K⁺ in the urine samples. Pharmacokinetic parameters were analyzed using Phoenix WinNonlin software in a noncompartmental model. In either clinical trial, no significant differences were observed in the maximal rate of urinary excretion and cumulative urinary excretion from 0 to 24 hours of K⁺ between the reference and test drugs. The bioequivalence studies of both KCl sustained-release tablet formulations were successfully conducted under different dietary conditions.