Biology subjects

Zhang, L.

Publications and source records attributed to Zhang, L..

At least 739 records · Page 41Linked to original sources

bioRxiv2023

The Effects of Different Fatigue Types on Action Anticipation and Physical Performance in High-level Volleyball Players

This study examined the effects of different fatigue types on action anticipation and physical performance in high-level volleyball players. Twenty-four participants underwent four counterbalanced conditions: 60-min of cycling at 60% peak power output, 60-min Stroop task, 60-min cycling at 60% peak power output with Stroop task and 60-min neutral documentary to induce physical fatigue (PF), mental fatigue (MF), dual fatigue (DF) and control group (CG), respectively. Action anticipation (anticipation test and visual search test) and physical performance (countermovement jump, T-test, and spike test) were conducted at baseline, immediately after (Post1), and 40-min after fatigue intervention (Post2). DF and PF led to significantly lower jump height, T-test completion time, and spiking speed at Post1 and Post2 compared with CG and MF. Compared with PF, DF led to a significant decline in jumping, agility, and spiking performance at Post1 and decreased jumping performance at Post2. MF significantly decreased reaction time in the anticipation test at Post1 compared with CG. Reaction times in the visual search test were significantly lower with DF and MF at Post2 compared with CG. PF led to a greater decline in physical performance and this was exacerbated in DF, yet anticipation performance remained lesser impact.

physiology↗

bioRxiv2023

Obesity status and its relative factors of captive Asian elephants (Elephas maximus) in China based on body condition assessment

Obesity is a common health problem in captive wildlife. Since the obesity status of captive Asian elephants (Elephas maximus) in China has not previously been investigated, we recorded seven relevant variables (sex, age, daily feed supply, proportion of high-calorie feed, outdoor enclosure area, outdoor time, and foot disorder) related to obesity in 204 captive Asian elephants through field investigation of 43 elephant-raising facilities. Assessment of obesity was based on visual body condition scoring for each individual. It revealed that obesity was prevalent for captive Asian elephants (especially elephants in zoos) in China. Over 70% of captive Asian elephants in China were overweight or in obesity to various degrees. Statistical analysis showed that for elephants in zoos, insufficient outdoor time might be the primary potential cause of obesity. We suggested facilities to extend the outdoor time and control the supply of high-calorie feed (e.g., fruits, vegetables, pellets, etc.) for captive elephants, thereby alleviating obesity through increased exercise and a suitable energy intake. Moreover, all facilities should implement positive reinforcement training to facilitate regular physical examinations, including foot health checks and blood sampling. This training would improve the ability to collect more precise information relating to elephant health, obesity, and the evaluation of animal welfare.

zoology↗

bioRxiv2023

Electrical impedance spectroscopy with bacterial biofilms: neuronal-like behaviour

Negative capacitance at low frequencies for neurons was first demonstrated in 1941 (Kenneth S. Cole) using extracellular electrodes. The phenomenon subsequently was explained by Cole using the Hodgkin-Huxley model and is due to the activity of voltage-gated potassium ion channels. We show that E. coli biofilms exhibit significant stable negative capacitances at low frequencies when they experience a small DC bias voltage in electrical impedance spectroscopy experiments. Using a frequency domain Hodgkin-Huxley model, we characterize the conditions for the emergence of this feature and demonstrate that the negative capacitance exists only in biofilms containing living cells. Furthermore, we established the importance of the voltage-gated potassium ion channel, Kch, using knock-down mutants. The experiments provide further evidence for voltage-gated ion channels in E. coli and a new, low-cost method to probe biofilm electrophysiology e.g. to understand the efficacy of antibiotics. O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=67 SRC="FIGDIR/small/568527v1_ufig1.gif" ALT="Figure 1"> View larger version (11K): org.highwire.dtl.DTLVardef@e3df05org.highwire.dtl.DTLVardef@46c5d2org.highwire.dtl.DTLVardef@6572a6org.highwire.dtl.DTLVardef@4a104a_HPS_FORMAT_FIGEXP M_FIG C_FIG

biophysics↗

bioRxiv2023

Nitrite deteriorates bioreactor performance by reducing growth of Ca. Brocadia sapporoensis instead of inhibiting the anammox activity

Effects of nitrite on anammox activities have been of widespread concern. However, the molecular mechanisms of specific microorganisms in anammox systems responding to nitrite remain unexplored. This study investigated the effects of excess nitrite on core metabolism of AnAOB and symbiotic bacteria, and further elucidated the response mechanism of these effects on microbial growth and nitrogen removal performance. Specifically, nitrogen removal process in a continuous-flow anaerobic ammonia oxidation membrane bioreactor completely collapsed when the nitrite concentration reached 243 mg N/L. Integrated meta-omics analyses demonstrated that excess nitrite disrupted the energy metabolism of Ca. Brocadia sapporoensis (AMXB1), reducing the energy available for establishing tolerance. It disrupted cell replication by impairing biosynthesis process of AMXB1, especially DNA replication and the formation of vital cell structures, e.g., cell membrane and cell wall, as well as the cellular protection system, leading to the collapse of the anammox system. In addition, the cross-feeding of glycogen, lipopolysaccharide and amino acid between AMXB1 and symbiotic bacteria was hindered by excess nitrite, which also contributed to the anomalous cell proliferation and metabolism of AMXB1. These findings contribute to our understanding of the ability of anammox consortia to respond to nitrite stress and process stability in engineered ecosystems. HighlightsO_LINO --N concentration of 243 mg N/L caused the performance collapse of a continuous-flow anammox MBR. C_LIO_LIExcess nitrite likely disrupted the energy metabolism of AMXB1, reducing the energy availability for mitigating nitrite toxicity. C_LIO_LIThe cross-feeding between AMXB1 and symbiotic bacteria was hindered by excess nitrite. C_LIO_LIThe hindrance of cross-feeding was reversed as the concentration of nitrite decreased. C_LI Graphical abstract O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=132 SRC="FIGDIR/small/568540v1_ufig1.gif" ALT="Figure 1"> View larger version (45K): org.highwire.dtl.DTLVardef@6b199forg.highwire.dtl.DTLVardef@15f2a74org.highwire.dtl.DTLVardef@dc2d8eorg.highwire.dtl.DTLVardef@132deb1_HPS_FORMAT_FIGEXP M_FIG C_FIG

bioengineering↗

bioRxiv2023

Upstream open reading frames dynamically modulate CLOCK protein translation to regulate circadian rhythm and sleep

The circadian rhythm is an evolutionarily conserved mechanism with translational regulation increasingly recognized as pivotal in its modulation. In this study, we found that upstream open reading frames (uORFs) are enriched in circadian rhythm genes, with particularly conserved uORFs present in core circadian clock genes. We demonstrate evidence that the uORFs of the core clock gene, Clock (Clk), rhythmically and substantially attenuate CLK protein translation in Drosophila, with pronounced suppression occurring during daylight hours. Eliminating Clk uORFs results in elevated CLK protein levels during the day and a compressed circadian cycle, along with a broad shift in clock gene expression rhythms. Interestingly, Clk uORF deletion also augments morning sleep by reducing dopaminergic activity. Beyond daily circadian adjustments, Clk uORFs play a role in modulating sleep patterns in response to the varying day lengths of different seasons, inhibiting translation in a day-length contingent manner. Furthermore, the Clk uORFs act as a master regulator to shape the rhythmic expression of a vast array of genes and influence multifaceted physiological outcomes. Collectively, our research sheds light on the intricate ways uORFs dynamically adjust downstream coding sequences to acclimate to environmental shifts.

neuroscience↗

bioRxiv2023

Rapid and prolonged response of oligodendrocyte lineage cells in standard acute cuprizone demyelination model revealed by in situ hybridization

Dietary administration of a copper chelator, cuprizone (CPZ), has long been reported to induce intense and reproducible demyelination of several brain structures such as the corpus callosum (CC) in mice, followed by spontaneous remyelination after drug withdrawal. Despite the widespread use of CPZ as an animal model for demyelinating diseases such as multiple sclerosis (MS), the mechanism by which it induces demyelination and then allows robust remyelination is still unclear. An intensive mapping of the oligodendrocyte (OL) lineage cell dynamics during the de-and remyelination course would be of particular importance for a deeper understanding of this model. Here, using a panel of OL lineage cell markers as in situ hybridization (ISH) probes, including Pdgfra, Plp, Mbp, Mog, Enpp6, combined with immunofluorescence staining of CC1, SOX10, we provide a detailed dynamic profile of OL lineage cells during the entire course of the model from 3.5 days, 1, 2, 3, 4,5 weeks of CPZ treatment, i.e. the demyelination period, as well as after 1, 2, 3, 4 weeks of recovery (drug withdrawal) from 5 weeks of CPZ treatment, i.e. the remyelination period. The result showed an unexpected early death of mature OLs and response of OL progenitor cells (OPCs) in vivo upon CPZ challenge, and a prolonged upregulation of myelin-forming OLs compared to the intact control even 4 weeks after CPZ withdrawal. These data may point to the need to optimize the timing windows for the introduction of pro-remyelination therapies in demyelinating diseases such as MS, and may serve as a basic reference system for future studies of the effects of any intervention on demyelination and remyelination using the CPZ model.

neuroscience↗

bioRxiv2023

Molecular regulation of retinal regeneration is context specific

Many genes are known to regulate retinal regeneration following widespread tissue damage. Conversely, genes controlling regeneration following limited retinal cell loss, akin to disease conditions, are undefined. Combining a novel retinal ganglion cell (RGC) ablation-based glaucoma model, single cell omics, and rapid CRISPR/Cas9-based knockout methods to screen 100 genes, we identified 18 effectors of RGC regeneration kinetics. Surprisingly, 32 of 33 previously known/implicated regulators of retinal tissue regeneration were not required for RGC replacement; 7 knockouts accelerated regeneration, including sox2, olig2, and ascl1a. Mechanistic analyses revealed loss of ascl1a increased "fate bias", the propensity of progenitors to produce RGCs. These data demonstrate plasticity and context-specificity in how genes function to control regeneration, insights that could help to advance disease-tailored therapeutics for replacing lost retinal cells. One sentence summaryWe discovered eighteen genes that regulate the regeneration of retinal ganglion cells in zebrafish.

neuroscience↗

bioRxiv2023

Fast and efficient root phenotyping via pose estimation

Image segmentation is commonly used to estimate the location and shape of plants and their external structures. Segmentation masks are then used to localize landmarks of interest and compute other geometric features that correspond to the plants phenotype. Despite its prevalence, segmentation-based approaches are laborious (requiring extensive annotation to train), and error-prone (derived geometric features are sensitive to instance mask integrity). Here we present a segmentation-free approach which leverages deep learning-based landmark detection and grouping, also known as pose estimation. We use a tool originally developed for animal motion capture called SLEAP (Social LEAP Estimates Animal Poses) to automate the detection of distinct morphological landmarks on plant roots. Using a gel cylinder imaging system across multiple species, we show that our approach can reliably and efficiently recover root system topology at high accuracy, few annotated samples, and faster speed than segmentation-based approaches. In order to make use of this landmark-based representation for root phenotyping, we developed a Python library (sleap-roots) for trait extraction directly comparable to existing segmentation-based analysis software. We show that landmark-derived root traits are highly accurate and can be used for common downstream tasks including genotype classification and unsupervised trait mapping. Altogether, this work establishes the validity and advantages of pose estimation-based plant phenotyping. To facilitate adoption of this easy-to-use tool and to encourage further development, we make sleap-roots, all training data, models, and trait extraction code available at: https://github.com/talmolab/sleap-roots and https://osf.io/k7j9g/.

plant biology↗

bioRxiv2023

Gain of function in linc-133 compensates for daf-18/PTEN loss and rescues survival

DAF-18, homology of PTEN, possess tumor suppressor activity. Loss of daf-18 causes cell growth in L1 diapause C. elegans is well studied; however, the reason why survival is dramatically shortened is not well elaborated. We found that linc-133 gain of function can fully restore the shortened survival caused by daf-18 loss. When lipid phosphatase activity of DAF-18 is defective, the linc-133 gain of function interacts with 14-3-3 proteins to obstruct DAF-16 translocation from the nucleus to the cytoplasm. However, the dysfunction of protein phosphatase activity of DAF-18 caused high levels of aggregated proteins. The linc-133 gain of function can induce HSP chaperones to select and process the aggregated proteins for degradation through ubiquitination. Our work demonstrates that protein homeostasis controlled by the protein phosphatase activity of DAF-18 is the main factor affecting survival and identifies a new function of the linc-133 gene, which can compensate for the loss of daf-18.

genetics↗

bioRxiv2023

A novel antagonist of the CCL5/CCR5 axis suppresses the tumor growth and metastasis of triple-negative breast cancer by CCR5-YAP1 regulation.

Triple-negative breast cancer (TNBC) is the most aggressive subtype of breast cancer (BC) with a high mortality rate, and few effective therapeutic strategies are available. CCL5/CCR5 is an appealing immunotherapeutic target for TNBC. However, its signaling mechanism is poorly understood and its direct antagonists have not been reported. Here, we developed a high-throughput screening (HTS) assay for discovering its antagonists. Verteporfin was identified as a more selective and potent antagonist than the known CCR5 antagonist maraviroc. Without photodynamic therapy, verteporfin demonstrated significant inhibition on TNBC tumor growth through immune regulation, remarkable suppression of lung metastasis by cell-intrinsic mechanism, and a significant extension of overall survival in vivo. Mechanistically, CCR5 was found to be essential for expression of the key hippo effector YAP1. It promoted YAP1 transcription via HIF-1 and exerted further control over the migration of CD8+ T, NK, and MDSC immune cells through chemokines CXCL16 and CXCL8 which were identified from RNA-seq. Moreover, the CCR5-YAP1 axis played a vital role in promoting metastasis by modulating {beta}-catenin and core epithelial-mesenchymal transition transcription factors ZEB1 and ZEB2. It is noteworthy that the regulatory relationship between CCR5 and YAP1 was observed across various BC subtypes, TNBC patients, and showed potential relevance in fifteen additional cancer types. Overall, this study introduced an easy-to-use HTS assay that streamlines the discovery of CCL5/CCR5 axis antagonists. Verteporfin was identified as a specific molecular probe of this axis with great potentials as a therapeutic agent for treating sixteen malignant diseases characterized by heightened CCR5 and YAP1 levels.

cancer biology↗

bioRxiv2023

DeepMRG: a multi-label deep learning classifier forpredicting bacterial metal resistance genes

The widespread misuse of antibiotics has escalated antibiotic resistance into a critical global public health concern. Beyond antibiotics, metals function as antibacterial agents. Metal resistance genes (MRGs) enable bacteria to tolerate metal-based antibacterials and may also foster antibiotic resistance within bacterial communities through co-selection. Thus, predicting bacterial MRGs is vital for elucidating their involvement in antibiotic resistance and metal tolerance mechanisms. The "best hit" approach is mainly utilized to identify and annotate MRGs. This method is sensitive to cutoff values and produces a high false negative rate. Other than the best hit approach, only a few antimicrobial resistance (AMR) detection tools exist for predicting MRGs. However, these tools lack comprehensive annotation for MRGs conferring resistance to multiple metals. To address such limitations, we introduce DeepMRG, a deep learning-based multi-label classifier, to predict bacterial MRGs. Because a bacterial MRG can confer resistance to multiple metals, DeepMRG is designed as a multi-label classifier capable of predicting multiple metal labels associated with an MRG. It leverages bit score-based similarity distribution of sequences with experimentally verified MRGs. To ensure unbiased model evaluation, we employed a clustering method to partition our dataset into six subsets, five for cross-validation and one for testing, with non-homologous sequences, mitigating the impact of sequence homology. DeepMRG consistently achieved high overall F1-scores and significantly reduced false negative rates across a wide range of datasets. It can be used to predict bacterial MRGs in metagenomic or isolate assemblies. The web server of DeepMRG can be accessed at https://deepmrg.cs.vt.edu/deepmrg and the source code is available at https://github.com/muhit-emon/DeepMRG under the MIT license.

bioinformatics↗

bioRxiv2023

Abnormal white matter development during early childhood in autism and developmental disability

The abnormal maturation of white matter microstructure in autism spectrum disorder (ASD) compared with typical developing (TD) and developmental delay/intellectual disorder (DD/ID) during early childhood and their associations with clinical implications remain unclear. Here, we characterized spatial and temporal patterns of white matter development in 364 children (including ASD, DD/ID and TD) under 8 years old using neurite orientation dispersion and density imaging. Using neurite density index (NDI), we consistently detected three white matter clusters across all the groups through clustering analysis, indicating the conserved spatial layout in atypical development. Further, three developmental stages with successively lower growth rates were identified in ASD, similar to those in TD but delayed overall. Meanwhile, DD/ID children showed the slowest growth rates and lacked staging features. Finally, for ASD children, the NDI was correlated with cognitive impairments at the fast developmental stage but associated with social deficits during the moderate-to-slow stage.

neuroscience↗

bioRxiv2023

TranSiGen: Deep representation learning of chemical-induced transcriptional profile

With the advancement of high-throughput RNA sequencing technologies, the use of chemical-induced transcriptional profiling has greatly increased in biomedical research. However, the usefulness of transcriptomics data is limited by inherent random noise and technical artefacts that may cause systematical biases. These limitations make it challenging to identify the true signal of perturbation and extract knowledge from the data. In this study, we propose a deep generative model called Transcriptional Signatures Generator (TranSiGen), which aims to denoise and reconstruct transcriptional profiles through self-supervised representation learning.TranSiGen uses cell basal gene expression and compound molecular structure representation to infer the chemical-induced transcriptional profile. Results demonstrate the effectiveness of TranSiGen in learning and predicting differential expression genes. The representation derived from TranSiGen can also serve as an alternative phenotype information, with applications in ligand-based virtual screening, drug response prediction, and phenotype-based drug repurposing. We envisage that integrating TranSiGen into the drug discovery and mechanism research pipeline will promote the development of biomedicine.

bioinformatics↗

bioRxiv2023

UNSEG: unsupervised segmentation of cells and their nuclei in complex tissue samples

Multiplexed imaging technologies have made it possible to interrogate complex tumor microenvironments at sub-cellular resolution within their native spatial context. However, proper quantification of this complexity requires the ability to easily and accurately segment cells into their sub-cellular compartments. Within the supervised learning paradigm, deep learning based segmentation methods demonstrating human level performance have emerged. However, limited work has been done in developing such generalist methods within the label-free unsupervised context. Here we present an unsupervised segmentation (UNSEG) method that achieves deep learning level performance without requiring any training data. UNSEG leverages a Bayesian-like framework and the specificity of nucleus and cell membrane markers to construct an a posteriori probability estimate of each pixel belonging to the nucleus, cell membrane, or background. It uses this estimate to segment each cell into its nuclear and cell-membrane compartments. We show that UNSEG is more internally consistent and better at generalizing to the complexity of tissue morphology than current deep learning methods. This allows UNSEG to unambiguously identify the cytoplasmic compartment of a cell, which we employ to demonstrate its use in an exemplar biological scenario. Within the UNSEG framework, we also introduce a new perturbed watershed algorithm capable of stably and automatically segmenting a cluster of cell nuclei into individual cell nuclei that increases the accuracy of classical watershed. Perturbed watershed can also be used as a standalone algorithm that researchers can incorporate within their supervised or unsupervised learning approaches to extend classical watershed, particularly in the multiplexed imaging context. Finally, as part of developing UNSEG, we have generated a high-quality annotated gastrointestinal tissue (GIT) dataset, which we anticipate will be useful for the broader research community. We demonstrate the efficacy of UNSEG on the GIT dataset, publicly available datasets, and on a range of practical scenarios. In these contexts, we also discuss the possibility of bias inherent in quantification of segmentation accuracy based on F1 score. Segmentation, despite its long antecedents, remains a challenging problem, particularly in the context of tissue samples. UNSEG, an easy-to-use algorithm, provides an unsupervised approach to overcome this bottleneck, and as we discuss, can help improve deep learning based segmentation methods by providing a bridge between unsupervised and supervised learning paradigms.

bioinformatics↗

bioRxiv2023

Genome folding principles revealed in condensin-depleted mitotic chromosomes

During mitosis, condensin activity interferes with interphase chromatin structures. Here, we generated condensin-free mitotic chromosomes to investigate genome folding principles. Co- depletion of condensin I and II, but neither alone, triggered mitotic chromosome compartmentalization in ways that differ from interphase. Two distinct euchromatic compartments, indistinguishable in interphase, rapidly emerged upon condensin loss with different interaction preferences and dependence on H3K27ac. Constitutive heterochromatin gradually self-aggregated and co-compartmentalized with the facultative heterochromatin, contrasting with their separation during interphase. While topologically associating domains (TADs) and CTCF/cohesin mediated structural loops remained undetectable, cis-regulatory element contacts became apparent, providing an explanation for their quick re-establishment during mitotic exit. HP1 proteins, which are thought to partition constitutive heterochromatin, were absent from mitotic chromosomes, suggesting, surprisingly, that constitutive heterochromatin can self-aggregate without HP1. Indeed, in cells traversing from M- to G1-phase in the combined absence of HP1, HP1{Pi} and HP1{gamma}, re-established constitutive heterochromatin compartments normally. In sum, "clean-slate" condensin-deficient mitotic chromosomes illuminate mechanisms of genome compartmentalization not revealed in interphase cells.

genomics↗

bioRxiv2023

Short internal open reading frames regulate the translation of N-terminally truncated proteoforms

Internal translation initiation sites, as revealed by ribosome profiling experiments can potentially drive the translation of many N-terminally truncated proteoforms. We have identified an mRNA cis-regulatory element which regulates their translation. nTRIP6 represents a short nuclear proteoform of the cytoplasmic protein TRIP6. We have previously reported that nTRIP6 regulates the dynamics of skeletal muscle progenitor differentiation. Here we show that nTRIP6 is generated by translation initiation at an internal AUG. Its translation is repressed by an internal short open reading frame (sORF) immediately upstream of the nTRIP6 AUG. Consistent with this representing a more general regulatory feature, we have identified other N-terminally truncated proteoforms which are repressed by internal sORFs. In an in vitro model of myogenic differentiation, the translation of nTRIP6 is transiently de-repressed in a mechanistic Target of Rapamycin Complex 1-dependent manner. Thus, the translation of N-terminally truncated proteoforms can be regulated independently of the canonical ORF.

molecular biology↗

bioRxiv2023

Global Sensitivity Analysis of the Onset of Nasal Passage Infection by SARS-CoV-2 With Respect to Heterogeneity in Host Physiology and Host Cell-Virus Kinetic Interactions

Throughout the COVID-19 pandemic, positive nasal swab tests have revealed dramatic population heterogeneity in viral titers spanning 6 orders-of-magnitude. Our goal here is to probe potential drivers of infection outcome sensitivity arising from (i) physiological heterogeneity between hosts and (ii) host-variant heterogeneity in the detailed kinetics of cell infection and viral replication. Toward this goal, we apply global sensitivity methods (Partial Rank Correlation Coefficient analysis and Latin Hypercube Sampling) to a physiologically faithful, stochastic, spatial model of inhaled SARS-CoV-2 exposure and infection in the human respiratory tract. We focus on the nasal passage as the primary origin of respiratory infection and site of clinical testing, and we simulate the spatial and dynamic progression of shed viral load and infected cells in the immediate 48 hours post infection. We impose immune evasion, i.e., suppressed immune protection, based on the preponderance of clinical evidence that nasal infections occur rapidly post exposure, largely independent of immune status. Global sensitivity methods provide the de-correlated outcome sensitivities to each source of within-host heterogeneity, including the dynamic progression of sensitivities at 12, 24, 36, and 48 hours post infection. The results reveal a dynamic rank-ordering of the drivers of outcome sensitivity in early infection, providing insights into the dramatic population-scale outcome diversity during the COVID-19 pandemic. While we focus on SARS-CoV-2, the model and methods are applicable to any inhaled virus in the immediate 48 hours post infection.

immunology↗

bioRxiv2023

Bio-Mol:Pretraining Multimodality Bioactivity Profile for Enhancing Small Molecule Property Prediction

Non-optimized pharmacokinetic parameters serve as the primary cause of failure in clinical trials of drugs. Therefore, the successful prediction of pharmacokinetic parameters during the pre-clinical stage is crucial for the success of drug candidates. Conventional methods primarily rely on 2D structural information, while advanced models extend the features to other structural-related information or use advanced computational models to improve prediction accuracy. However, to gain a comprehensive understanding of small molecules, integrating bioactivity profiles with chemical structural information is essential. One significant challenge in this integration is the high proportion of missing values within experimentally validated bioactivity profiles for most small molecules. To address this challenge, we introduce Bio-Mol, an artificial intelligence model designed to effectively handle this issue. Bio-Mol utilizes a pretrain and finetune strategy, enabling the incorporation of a large proportion of missing bioactivity profiles during the small molecule representation learning process. Comprehensive evaluations of Bio-Mol demonstrate a notable improvement in predicting molecule properties. The integration of missing bioactivity profiles enhances the AUROC of average 5.2% compared to the previous state-of-the-art models predictions. Furthermore, we explore the potential of Bio-Mol in predicting synergistic drug combinations, highlighting its versatility and broader applications in the field of drug discovery. The successful implementation of Bio-Mol showcases its efficacy in over-coming the challenges posed by missing bioactivity profile data. This model paves the way for optimizing small molecule pharmacokinetics prediction, providing valuable insights for drug development and discovery processes.

bioinformatics↗