Search

Simple methods to detect biomolecules including specific nucleic acid sequences have received renewed attention since the Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) virus pandemic. Notably, biomolecule detection that uses some form of signal amplification will have some form of amplification-related error, which in the polymerase chain reaction involves mispriming and subsequent signal amplification in the no template control, ultimately providing a limit of detection. To demonstrate the feasibility of the detection of a DNA target sequence without molecular or chemical signal amplification that avoids amplification errors, a gold nanoparticle aggregation assay was developed and tested. Two primers bracketing a 94 base pair target sequence from SARS-CoV-2 were conjugated to 10 nm diameter gold nanoparticles by the salt aging method, with conjugation and primer-target hybridization confirmed by agarose gel electrophoresis and nanospectrophotometry. Upon mixing of both conjugated nanoparticles with target, a surface plasmon resonance shift of 6 nm was observed, and lower electrophoretic mobility of a band containing both DNA fluorescence and gold absorption signals. This did not occur in the presence of a control DNA molecule of the same size and composition as the target but with a randomly scrambled base position. Nanoparticle tracking at 30 frames per second using a sensitive darkfield microscope revealed a lower measured diffusion coefficient of scattering objects in the target mixture than in the control mixture or with bare gold nanoparticles., Comment: 19 pages, 6 figures

Allosteric regulation is a widespread strategy employed by several proteins to transduce chemical signals and perform biological functions. Metal sensor proteins are exemplary in this respect, e.g., in that they selectively bind and unbind DNA depending on the state of a distal ion coordination site. In this work, we carry out an investigation of the structural and mechanical properties of the CzrA transcription repressor through the analysis of microsecond-long molecular dynamics (MD) trajectories; the latter are processed through the mapping entropy optimisation workflow (MEOW), a recently developed information-theoretical method that highlights, in an unsupervised manner, residues of particular mechanical, functional, and biological importance. This approach allows us to unveil how differences in the properties of the molecule are controlled by the state of the zinc coordination site, with particular attention to the DNA binding region. These changes correlate with a redistribution of the conformational variability of the residues throughout the molecule, in spite of an overall consistency of its architecture in the two (ion-bound and free) coordination states. The results of this work corroborate previous studies, provide novel insight into the fine details of the mechanics of CzrA, and showcase the MEOW approach as a novel instrument for the study of allosteric regulation and other processes in proteins through the analysis of plain MD simulations.

The identification of DNA-binding proteins (DBPs) is a critical task due to their significant impact on various biological activities. Understanding the mechanisms underlying protein-DNA interactions is essential for elucidating various life activities. In recent years, machine learning-based models have been prominently utilized for DBP prediction. In this paper, to predict DBPs, we propose a novel framework termed a multiview random vector functional link (MvRVFL) network, which fuses neural network architecture with multiview learning. The proposed MvRVFL model combines the benefits of late and early fusion, allowing for distinct regularization parameters across different views while leveraging a closed-form solution to determine unknown parameters efficiently. The primal objective function incorporates a coupling term aimed at minimizing a composite of errors stemming from all views. From each of the three protein views of the DBP datasets, we extract five features. These features are then fused together by incorporating a hidden feature during the model training process. The performance of the proposed MvRVFL model on the DBP dataset surpasses that of baseline models, demonstrating its superior effectiveness. Furthermore, we extend our assessment to the UCI, KEEL, AwA, and Corel5k datasets, to establish the practicality of the proposed models. The consistency error bound, the generalization error bound, and empirical findings, coupled with rigorous statistical analyses, confirm the superior generalization capabilities of the MvRVFL model compared to the baseline models.

In 1999 Wright and Dyson highlighted the fact that large sections of the proteome of all organisms are comprised of protein sequences that lack globular folded structures under physiological conditions. Since then the biophysics community has made significant strides in unraveling the intricate structural and dynamic characteristics of intrinsically disordered proteins (IDPs) and intrinsically disordered regions (IDRs). Unlike crystallographic beamlines and their role in streamlining acquisition of structures for folded proteins, an integrated experimental and computational approach aimed at IDPs/IDRs has emerged. In this Perspective we aim to provide a robust overview of current computational tools for IDPs and IDRs, and most recently their complexes and phase separated states, including statistical models, physics-based approaches, and machine learning methods that permit structural ensemble generation and validation against many solution experimental data types.

With the emergence of various molecular tasks and massive datasets, how to perform efficient training has become an urgent yet under-explored issue in the area. Data pruning (DP), as an oft-stated approach to saving training burdens, filters out less influential samples to form a coreset for training. However, the increasing reliance on pretrained models for molecular tasks renders traditional in-domain DP methods incompatible. Therefore, we propose a Molecular data Pruning framework for enhanced Generalization (MolPeg), which focuses on the source-free data pruning scenario, where data pruning is applied with pretrained models. By maintaining two models with different updating paces during training, we introduce a novel scoring function to measure the informativeness of samples based on the loss discrepancy. As a plug-and-play framework, MolPeg realizes the perception of both source and target domain and consistently outperforms existing DP methods across four downstream tasks. Remarkably, it can surpass the performance obtained from full-dataset training, even when pruning up to 60-70% of the data on HIV and PCBA dataset. Our work suggests that the discovery of effective data-pruning metrics could provide a viable path to both enhanced efficiency and superior generalization in transfer learning., Comment: 20 pages, under review

Interactions of polyelectrolytes (PEs) with proteins play a crucial role in numerous biological processes, such as the internalization of virus particles into host cells. Although docking, machine learning methods, and molecular dynamics (MD) simulations are utilized to estimate binding poses and binding free energies of small-molecule drugs to proteins, quantitative prediction of the binding thermodynamics of PE-based drugs presents a significant obstacle in computer-aided drug design. This is due to the sluggish dynamics of PEs caused by their size and strong charge-charge correlations. In this paper, we introduce advanced sampling methods based on a force-spectroscopy setup and theoretical modeling to overcome this barrier. We exemplify our method with explicit solvent all-atom MD simulations of interactions of anionic PEs that show antiviral properties, namely heparin and linear polyglycerol sulfate (LPGS), with the SARS-CoV-2 spike protein receptor binding domain (RBD). Our prediction for the binding free energy of LPGS to the wild-type RBD matches experimentally measured dissociation constants within thermal energy, kT, and correctly reproduces the experimental PE-length dependence. We find that LPGS binds to the Delta-variant RBD with an additional free-energy gain of 2.4 kT, compared to the wild-type RBD, in accord with electrostatic arguments. We show that the LPGS-RBD binding is solvent-dominated and enthalpy-driven, though with a large entropy-enthalpy compensation. Our method is applicable to general polymer adsorption phenomena and predicts precise binding free energies and re-configurational friction as needed for drug and drug-delivery design.

Proteins are the fundamental macromolecules that play diverse and crucial roles in all living matter and have tremendous implications in healthcare, manufacturing, and biotechnology. Their functions are largely determined by the sequences of amino acids that compose them and their unique three-dimensional structures when folded. The recent surge in highly accurate computational protein structure prediction tools has equipped scientists with the means to derive preliminary structural insights without the onerous costs of experimental structure determination. These breakthroughs hold profound promise for building robust and efficient in silico protein design systems. While the prospect of designing de novo proteins with precise computational accuracy remains a grand challenge in biochemical engineering, conventional assembly-based and rational design methods often grapple with the expansive design space, resulting in suboptimal design success rates. Despite recently emerged deep learning-based models have shown promise in improving the efficiency of the computational protein design process, a significant gap persists between current design paradigms and their experimental realization. This thesis will investigate the potential of deep generative models in refining protein structure and sequence design methods, aiming to develop frameworks capable of crafting novel protein sequences with predetermined structures or specific functionalities. By harnessing extensive protein databases and cutting-edge neural architectures, this research aims to enhance precision and robustness in current protein design paradigms, potentially paving the way for advancements across various scientific fields., Comment: PhD thesis

The AlphaFold series has transformed protein structure prediction with remarkable accuracy, often matching experimental methods. AlphaFold2, AlphaFold-Multimer, and the latest AlphaFold3 represent significant strides in predicting single protein chains, protein complexes, and biomolecular structures. While AlphaFold2 and AlphaFold-Multimer are open-sourced, facilitating rapid and reliable predictions, AlphaFold3 remains partially accessible through a limited online server and has not been open-sourced, restricting further development. To address these challenges, the PaddleHelix team is developing HelixFold3, aiming to replicate AlphaFold3's capabilities. Using insights from previous models and extensive datasets, HelixFold3 achieves an accuracy comparable to AlphaFold3 in predicting the structures of conventional ligands, nucleic acids, and proteins. The initial release of HelixFold3 is available as open source on GitHub for academic research, promising to advance biomolecular research and accelerate discoveries. We also provide online service at PaddleHelix website at https://paddlehelix.baidu.com/app/all/helixfold3/forecast.

The transformer architecture has revolutionized bioinformatics and driven progress in the understanding and prediction of the properties of biomolecules. Almost all research on large-scale biosequence transformers has focused on one domain at a time (single-omic), usually nucleotides or peptides. These models have seen incredible success in downstream tasks in each domain and have achieved particularly noteworthy breakthroughs in sequences of peptides and structural modeling. However, these single-omic models are naturally incapable of modeling multi-omic tasks, one of the most biologically critical being nucleotide-peptide interactions. We present our work training the first multi-omic nucleotide-peptide foundation models. We show that these multi-omic models (MOMs) can learn joint representations between various single-omic distributions that are emergently consistent with the Central Dogma of molecular biology, despite only being trained on unlabeled biosequences. We further demonstrate that MOMs can be fine-tuned to achieve state-of-the-art results on peptide-nucleotide interaction tasks, namely predicting the change in Gibbs free energy ({\Delta}G) of the binding interaction between a given oligonucleotide and peptide, as well as the effect on this binding interaction due to mutations in the oligonucleotide sequence ({\Delta}{\Delta}G). Remarkably, we show that multi-omic biosequence transformers emergently learn useful structural information without any prior structural training, allowing us to predict which peptide residues are most involved in the peptide-nucleotide binding interaction. Lastly, we provide evidence that multi-omic biosequence models are non-inferior to foundation models trained on single-omics distributions, suggesting a more generalized or foundational approach to building these models., Comment: 27 pages, 5 figures

The structural similarities between protein sequences and natural languages have led to parallel advancements in deep learning across both domains. While large language models (LLMs) have achieved much progress in the domain of natural language processing, their potential in protein engineering remains largely unexplored. Previous approaches have equipped LLMs with protein understanding capabilities by incorporating external protein encoders, but this fails to fully leverage the inherent similarities between protein sequences and natural languages, resulting in sub-optimal performance and increased model complexity. To address this gap, we present TourSynbio-7B, the first multi-modal large model specifically designed for protein engineering tasks without external protein encoders. TourSynbio-7B demonstrates that LLMs can inherently learn to understand proteins as language. The model is post-trained and instruction fine-tuned on InternLM2-7B using ProteinLMDataset, a dataset comprising 17.46 billion tokens of text and protein sequence for self-supervised pretraining and 893K instructions for supervised fine-tuning. TourSynbio-7B outperforms GPT-4 on the ProteinLMBench, a benchmark of 944 manually verified multiple-choice questions, with 62.18% accuracy. Leveraging TourSynbio-7B's enhanced protein sequence understanding capability, we introduce TourSynbio-Agent, an innovative framework capable of performing various protein engineering tasks, including mutation analysis, inverse folding, protein folding, and visualization. TourSynbio-Agent integrates previously disconnected deep learning models in the protein engineering domain, offering a unified conversational user interface for improved usability. Finally, we demonstrate the efficacy of TourSynbio-7B and TourSynbio-Agent through two wet lab case studies on vanilla key enzyme modification and steroid compound catalysis.

Molecular Dynamics (MD) simulations are irreplaceable and ubiquitous in fields of materials science, chemistry, pharmacology just to name a few. Conventional MD simulations are plagued by numerical stability as well as long equilibration time issues, which limits broader applications of MD simulations. Recently, a surge of deep learning approaches have been devised for time-coarsened dynamics, which learns the state transition mechanism over much larger time scales to overcome these limitations. However, only a few methods target the underlying Boltzmann distribution by resampling techniques, where proposals are rarely accepted as new states with low efficiency. In this work, we propose a force-guided bridge matching model, FBM, a novel framework that first incorporates physical priors into bridge matching for full-atom time-coarsened dynamics. With the guidance of our well-designed intermediate force field, FBM is feasible to target the Boltzmann-like distribution by direct inference without extra steps. Experiments on small peptides verify our superiority in terms of comprehensive metrics and demonstrate transferability to unseen peptide systems.

The rapid advancement of single-cell ATAC sequencing (scATAC-seq) technologies holds great promise for investigating the heterogeneity of epigenetic landscapes at the cellular level. The amplification process in scATAC-seq experiments often introduces noise due to dropout events, which results in extreme sparsity that hinders accurate analysis. Consequently, there is a significant demand for the generation of high-quality scATAC-seq data in silico. Furthermore, current methodologies are typically task-specific, lacking a versatile framework capable of handling multiple tasks within a single model. In this work, we propose ATAC-Diff, a versatile framework, which is based on a latent diffusion model conditioned on the latent auxiliary variables to adapt for various tasks. ATAC-Diff is the first diffusion model for the scATAC-seq data generation and analysis, composed of auxiliary modules encoding the latent high-level variables to enable the model to learn the semantic information to sample high-quality data. Gaussian Mixture Model (GMM) as the latent prior and auxiliary decoder, the yield variables reserve the refined genomic information beneficial for downstream analyses. Another innovation is the incorporation of mutual information between observed and hidden variables as a regularization term to prevent the model from decoupling from latent variables. Through extensive experiments, we demonstrate that ATAC-Diff achieves high performance in both generation and analysis tasks, outperforming state-of-the-art models.

Drug discovery and development is a highly complex and costly endeavor, typically requiring over a decade and substantial financial investment to bring a new drug to market. Traditional computer-aided drug design (CADD) has made significant progress in accelerating this process, but the development of quantum computing offers potential due to its unique capabilities. This paper discusses the integration of quantum computing into drug discovery and development, focusing on how quantum technologies might accelerate and enhance various stages of the drug development cycle. Specifically, we explore the application of quantum computing in addressing challenges related to drug discovery, such as molecular simulation and the prediction of drug-target interactions, as well as the optimization of clinical trial outcomes. By leveraging the inherent capabilities of quantum computing, we might be able to reduce the time and cost associated with bringing new drugs to market, ultimately benefiting public health., Comment: 27 pages, 10 figures

Artificial intelligence-assisted drug design is revolutionizing the pharmaceutical industry. Effective molecular features are crucial for accurate machine learning predictions, and advanced mathematics plays a key role in designing these features. Persistent homology theory, which equips topological invariants with persistence, provides valuable insights into molecular structures. The calculation of Betti numbers is based on differential that typically satisfy \(d^2 = 0\). Our recent work has extended this concept by employing Mayer homology with a generalized differential that satisfies \(d^N = 0\) for \(N \geq 2\), leading to the development of persistent Mayer homology (PMH) theory and richer topological information across various scales. In this study, we utilize PMH to create a novel multiscale topological vectorization for molecular representation, offering valuable tools for descriptive and predictive analysis in molecular data and machine learning prediction. Specifically, benchmark tests on established protein-ligand datasets, including PDBbind-2007, PDBbind-2013, and PDBbind-2016, demonstrate the superior performance of our Mayer homology models in predicting protein-ligand binding affinities.

The concept of personalised medicine in cancer therapy is becoming increasingly important. There already exist drugs administered specifically for patients with tumours presenting well-defined mutations. However, the field is still in its infancy, and personalised treatments are far from being standard of care. Personalised medicine is often associated with the utilisation of omics data. Yet, implementation of multi-omics data has proven difficult, due to the variety and scale of the information within the data, as well as the complexity behind the myriad of interactions taking place within the cell. An alternative approach to precision medicine is to employ a function-based profile of the cell. This involves screening a range of drugs against patient derived cells. Here we demonstrate a proof-of-concept, where a collection of drug screens against a highly diverse set of patient-derived cell lines, are leveraged to identify putative treatment options for a 'new patient'. We show that this methodology is highly efficient in ranking the drugs according to their activity towards the target cells. We argue that this approach offers great potential, as activities can be efficiently imputed from various subsets of the drug treated cell lines that do not necessarily originate from the same tissue type., Comment: 3 figures and 5 tables

Despite significant progress in static protein structure collection and prediction, the dynamic behavior of proteins, one of their most vital characteristics, has been largely overlooked in prior research. This oversight can be attributed to the limited availability, diversity, and heterogeneity of dynamic protein datasets. To address this gap, we propose to enhance existing prestigious static 3D protein structural databases, such as the Protein Data Bank (PDB), by integrating dynamic data and additional physical properties. Specifically, we introduce a large-scale dataset, Dynamic PDB, encompassing approximately 12.6K proteins, each subjected to all-atom molecular dynamics (MD) simulations lasting 1 microsecond to capture conformational changes. Furthermore, we provide a comprehensive suite of physical properties, including atomic velocities and forces, potential and kinetic energies of proteins, and the temperature of the simulation environment, recorded at 1 picosecond intervals throughout the simulations. For benchmarking purposes, we evaluate state-of-the-art methods on the proposed dataset for the task of trajectory prediction. To demonstrate the value of integrating richer physical properties in the study of protein dynamics and related model design, we base our approach on the SE(3) diffusion model and incorporate these physical properties into the trajectory prediction process. Preliminary results indicate that this straightforward extension of the SE(3) model yields improved accuracy, as measured by MAE and RMSD, when the proposed physical properties are taken into consideration. https://fudan-generative-vision.github.io/dynamicPDB/ .

Accurately measuring protein-RNA binding affinity is crucial in many biological processes and drug design. Previous computational methods for protein-RNA binding affinity prediction rely on either sequence or structure features, unable to capture the binding mechanisms comprehensively. The recent emerging pre-trained language models trained on massive unsupervised sequences of protein and RNA have shown strong representation ability for various in-domain downstream tasks, including binding site prediction. However, applying different-domain language models collaboratively for complex-level tasks remains unexplored. In this paper, we propose CoPRA to bridge pre-trained language models from different biological domains via Complex structure for Protein-RNA binding Affinity prediction. We demonstrate for the first time that cross-biological modal language models can collaborate to improve binding affinity prediction. We propose a Co-Former to combine the cross-modal sequence and structure information and a bi-scope pre-training strategy for improving Co-Former's interaction understanding. Meanwhile, we build the largest protein-RNA binding affinity dataset PRA310 for performance evaluation. We also test our model on a public dataset for mutation effect prediction. CoPRA reaches state-of-the-art performance on all the datasets. We provide extensive analyses and verify that CoPRA can (1) accurately predict the protein-RNA binding affinity; (2) understand the binding affinity change caused by mutations; and (3) benefit from scaling data and model size.

Understanding biological processes, drug development, and biotechnological advancements requires detailed analysis of protein structures and sequences, a task in protein research that is inherently complex and time-consuming when performed manually. To streamline this process, we introduce ProteinGPT, a state-of-the-art multi-modal protein chat system, that allows users to upload protein sequences and/or structures for comprehensive protein analysis and responsive inquiries. ProteinGPT seamlessly integrates protein sequence and structure encoders with linear projection layers for precise representation adaptation, coupled with a large language model (LLM) to generate accurate and contextually relevant responses. To train ProteinGPT, we construct a large-scale dataset of 132,092 proteins with annotations, and optimize the instruction-tuning process using GPT-4o. This innovative system ensures accurate alignment between the user-uploaded data and prompts, simplifying protein analysis. Experiments show that ProteinGPT can produce promising responses to proteins and their corresponding questions., Comment: 19 pages, 9 figures, 5 tables

Understanding the structure of the protein-ligand complex is crucial to drug development. Existing virtual structure measurement and screening methods are dominated by docking and its derived methods combined with deep learning. However, the sampling and scoring methodology have largely restricted the accuracy and efficiency. Here, we show that these two fundamental tasks can be accurately tackled with a single model, namely LigPose, based on multi-task geometric deep learning. By representing the ligand and the protein pair as a graph, LigPose directly optimizes the three-dimensional structure of the complex, with the learning of binding strength and atomic interactions as auxiliary tasks, enabling its one-step prediction ability without docking tools. Extensive experiments show LigPose achieved state-of-the-art performance on major tasks in drug research. Its considerable improvements indicate a promising paradigm of AI-based pipeline for drug development.

Protein biologics hold immense potential in therapeutic applications, but their ephemeral nature has hindered their widespread application. The effects of different stressors on protein folding have long been studied, but whether these stressors induce protein unfolding through different pathways remains unclear. In this work, we conduct all-atom molecular dynamics simulations to investigate the unfolding of bovine serum albumin (BSA) under three distinct external stressors: high temperature, acidic pH, and shear stress. Our findings reveal that each stressor induces unique unfolding patterns in BSA, indicating stressor-specific unfolding pathways. Detailed structural analysis showed that high temperature significantly disrupts the protein's secondary structure, while acidic pH causes notable alterations in the tertiary structure, leading to domain separation and an extended shape. Shear stress initially perturbs the tertiary structure, initiating structural rearrangements followed by a loss of secondary structure. These distinct unfolding behaviors suggest that different stabilization strategies are required to enhance protein stability under various denaturation conditions. Insights from these unfolding studies can inform the design of materials, especially polymers, aimed at improving protein stability.

De novo molecule design has become a highly active research area, advanced significantly through the use of state-of-the-art generative models. Despite these advances, several fundamental questions remain unanswered as the field increasingly focuses on more complex generative models and sophisticated molecular representations as an answer to the challenges of drug design. In this paper, we return to the simplest representation of molecules, and investigate overlooked limitations of classical generative approaches, particularly Variational Autoencoders (VAEs) and auto-regressive models. We propose a hybrid model in the form of a novel regularizer that leverages the strengths of both to improve validity, conditional generation, and style transfer of molecular sequences. Additionally, we provide an in depth discussion of overlooked assumptions of these models' behaviour.

Molecular property prediction is a crucial foundation for drug discovery. In recent years, pre-trained deep learning models have been widely applied to this task. Some approaches that incorporate prior biological domain knowledge into the pre-training framework have achieved impressive results. However, these methods heavily rely on biochemical experts, and retrieving and summarizing vast amounts of domain knowledge literature is both time-consuming and expensive. Large Language Models (LLMs) have demonstrated remarkable performance in understanding and efficiently providing general knowledge. Nevertheless, they occasionally exhibit hallucinations and lack precision in generating domain-specific knowledge. Conversely, Domain-specific Small Models (DSMs) possess rich domain knowledge and can accurately calculate molecular domain-related metrics. However, due to their limited model size and singular functionality, they lack the breadth of knowledge necessary for comprehensive representation learning. To leverage the advantages of both approaches in molecular property prediction, we propose a novel Molecular Graph representation learning framework that integrates Large language models and Domain-specific small models (MolGraph-LarDo). Technically, we design a two-stage prompt strategy where DSMs are introduced to calibrate the knowledge provided by LLMs, enhancing the accuracy of domain-specific information and thus enabling LLMs to generate more precise textual descriptions for molecular samples. Subsequently, we employ a multi-modal alignment method to coordinate various modalities, including molecular graphs and their corresponding descriptive texts, to guide the pre-training of molecular representations. Extensive experiments demonstrate the effectiveness of the proposed method.

Recent advancements in computational chemistry have increasingly focused on synthesizing molecules based on textual instructions. Integrating graph generation with these instructions is complex, leading most current methods to use molecular sequences with pre-trained large language models. In response to this challenge, we propose a novel framework, named $\textbf{UTGDiff (Unified Text-Graph Diffusion Model)}$, which utilizes language models for discrete graph diffusion to generate molecular graphs from instructions. UTGDiff features a unified text-graph transformer as the denoising network, derived from pre-trained language models and minimally modified to process graph data through attention bias. Our experimental results demonstrate that UTGDiff consistently outperforms sequence-based baselines in tasks involving instruction-based molecule generation and editing, achieving superior performance with fewer parameters given an equivalent level of pretraining corpus. Our code is availble at https://github.com/ran1812/UTGDiff.

Structure-based drug design (SBDD) is crucial for developing specific and effective therapeutics against protein targets but remains challenging due to complex protein-ligand interactions and vast chemical space. Although language models (LMs) have excelled in natural language processing, their application in SBDD is underexplored. To bridge this gap, we introduce a method, known as Frag2Seq, to apply LMs to SBDD by generating molecules in a fragment-based manner in which fragments correspond to functional modules. We transform 3D molecules into fragment-informed sequences using SE(3)-equivariant molecule and fragment local frames, extracting SE(3)-invariant sequences that preserve geometric information of 3D fragments. Furthermore, we incorporate protein pocket embeddings obtained from a pre-trained inverse folding model into the LMs via cross-attention to capture protein-ligand interaction, enabling effective target-aware molecule generation. Benefiting from employing LMs with fragment-based generation and effective protein context encoding, our model achieves the best performance on binding vina score and chemical properties such as QED and Lipinski, which shows our model's efficacy in generating drug-like ligands with higher binding affinity against target proteins. Moreover, our method also exhibits higher sampling efficiency compared to atom-based autoregressive and diffusion baselines with at most ~300x speedup.

Molecular Property Prediction (MPP) plays a pivotal role across diverse domains, spanning drug discovery, material science, and environmental chemistry. Fueled by the exponential growth of chemical data and the evolution of artificial intelligence, recent years have witnessed remarkable strides in MPP. However, the multifaceted nature of molecular data, such as molecular structures, SMILES notation, and molecular images, continues to pose a fundamental challenge in its effective representation. To address this, representation learning techniques are instrumental as they acquire informative and interpretable representations of molecular data. This article explores recent AI/-based approaches in MPP, focusing on both single and multiple modality representation techniques. It provides an overview of various molecule representations and encoding schemes, categorizes MPP methods by their use of modalities, and outlines datasets and tools available for feature generation. The article also analyzes the performance of recent methods and suggests future research directions to advance the field of MPP., Comment: Submitted to the journal

Molecule design is a multifaceted approach that leverages computational methods and experiments to optimize molecular properties, fast-tracking new drug discoveries, innovative material development, and more efficient chemical processes. Recently, text-based molecule design has emerged, inspired by next-generation AI tasks analogous to foundational vision-language models. Our study explores the use of knowledge-augmented prompting of large language models (LLMs) for the zero-shot text-conditional de novo molecular generation task. Our approach uses task-specific instructions and a few demonstrations to address distributional shift challenges when constructing augmented prompts for querying LLMs to generate molecules consistent with technical descriptions. Our framework proves effective, outperforming state-of-the-art (SOTA) baseline models on benchmark datasets., Comment: Paper was accepted at R0-FoMo: Robustness of Few-shot and Zero-shot Learning in Foundation Models, NeurIPS-2023. Please find the links: https://sites.google.com/view/r0-fomo/accepted-papers?authuser=0 and https://neurips.cc/virtual/2023/workshop/66517

Molecular optimization is a crucial aspect of drug discovery, aimed at refining molecular structures to enhance drug efficacy and minimize side effects, ultimately accelerating the overall drug development process. Many target-based molecular optimization methods have been proposed, significantly advancing drug discovery. These methods primarily on understanding the specific drug target structures or their hypothesized roles in combating diseases. However, challenges such as a limited number of available targets and a difficulty capturing clear structures hinder innovative drug development. In contrast, phenotypic drug discovery (PDD) does not depend on clear target structures and can identify hits with novel and unbiased polypharmacology signatures. As a result, PDD-based molecular optimization can reduce potential safety risks while optimizing phenotypic activity, thereby increasing the likelihood of clinical success. Therefore, we propose a fragment-masked molecular optimization method based on PDD (FMOP). FMOP employs a regression-free diffusion model to conditionally optimize the molecular masked regions without training, effectively generating new molecules with similar scaffolds. On the large-scale drug response dataset GDSCv2, we optimize the potential molecules across all 945 cell lines. The overall experiments demonstrate that the in-silico optimization success rate reaches 94.4%, with an average efficacy increase of 5.3%. Additionally, we conduct extensive ablation and visualization experiments, confirming that FMOP is an effective and robust molecular optimization method. The code is available at:https://anonymous.4open.science/r/FMOP-98C2., Comment: 11 pages, 5 figures, 2 tables

Recent experiments have revealed that single proteins can display high conductivity, which stays finite for low temperatures, decays slowly with distance, and exhibits a rich spatial structure featuring highly conducting and strongly insulating domains. Here, we intruduce a new formula by combining the density matrix of the Liouville-Master Equation simulating quantum transport in nanoscale devices, and the phenomenological model of electronic conductance through molecules, that can account for the observed distance- and temperature dependence of conductance in proteins. We demonstrate its efficacy on experimentally highly conductive extracellular cytochrome nanowires, which are good candidates to illustrate our new approach by calculating and visualizing their electronic wiring, given the interest in the arrangement of their conducting and insulating parts. As proteins and protein nanowires exhibit significant potential for diverse applications, including energy production and sensing, our computational technique can accelerate the design of nano-bioelectronic devices., Comment: 16 pages, 4 figures

The intersection of artificial intelligence and bioinformatics has enabled significant advancements in drug discovery, particularly through the application of machine learning models. In this study, we present a combined approach using genetic algorithms and deep learning models to address two critical aspects of drug discovery: the generation of novel tyrosine kinase inhibitors and the prediction of their bioactivity. The generative model leverages genetic algorithms to create new small molecules with optimized ADMET (absorption, distribution, metabolism, excretion, and toxicity) and drug-likeness properties. Concurrently, a deep learning model is employed to predict the bioactivity of these generated molecules against tyrosine kinases, a key enzyme family involved in various cellular processes and cancer progression. By integrating these advanced computational methods, we demonstrate a powerful framework for accelerating the generation and identification of potential tyrosine kinase inhibitors, contributing to more efficient and effective early-stage drug discovery processes., Comment: Data available at https://www.kaggle.com/datasets/ricardoromeroochoa/tyrosine-kinases-ligands-with-bioactivity-data and https://github.com/ricardo-romero-ochoa/bio-deep-learning

Generative models for molecules have shown considerable promise for use in computational chemistry, but remain difficult to use for non-experts. For this reason, we introduce open-source infrastructure for easily building generative molecular models into the widely used DeepChem [Ramsundar et al., 2019] library with the aim of creating a robust and reusable molecular generation pipeline. In particular, we add high quality PyTorch [Paszke et al., 2019] implementations of the Molecular Generative Adversarial Networks (MolGAN) [Cao and Kipf, 2022] and Normalizing Flows [Papamakarios et al., 2021]. Our implementations show strong performance comparable with past work [Kuznetsov and Polykovskiy, 2021, Cao and Kipf, 2022]., Comment: Presented at the 2024 Molecular Machine Learning Conference (MoML 2024)

In this study, we generate and maintain a database of 10 million virtual lipids through METiS's in-house de novo lipid generation algorithms and lipid virtual screening techniques. These virtual lipids serve as a corpus for pre-training, lipid representation learning, and downstream task knowledge transfer, culminating in state-of-the-art LNP property prediction performance. We propose LipidBERT, a BERT-like model pre-trained with the Masked Language Model (MLM) and various secondary tasks. Additionally, we compare the performance of embeddings generated by LipidBERT and PhatGPT, our GPT-like lipid generation model, on downstream tasks. The proposed bilingual LipidBERT model operates in two languages: the language of ionizable lipid pre-training, using in-house dry-lab lipid structures, and the language of LNP fine-tuning, utilizing in-house LNP wet-lab data. This dual capability positions LipidBERT as a key AI-based filter for future screening tasks, including new versions of METiS de novo lipid libraries and, more importantly, candidates for in vivo testing for orgran-targeting LNPs. To the best of our knowledge, this is the first successful demonstration of the capability of a pre-trained language model on virtual lipids and its effectiveness in downstream tasks using web-lab data. This work showcases the clever utilization of METiS's in-house de novo lipid library as well as the power of dry-wet lab integration.

Several generative models with elaborate training and sampling procedures have been proposed recently to accelerate structure-based drug design (SBDD); however, perplexingly, their empirical performance turns out to be suboptimal. We seek to better understand this phenomenon from both theoretical and empirical perspectives. Since most of these models apply graph neural networks (GNNs), one may suspect that they inherit the representational limitations of GNNs. We analyze this aspect, establishing the first such results for protein-ligand complexes. A plausible counterview may attribute the underperformance of these models to their excessive parameterizations, inducing expressivity at the expense of generalization. We also investigate this possibility with a simple metric-aware approach that learns an economical surrogate for affinity to infer an unlabelled molecular graph and optimizes for labels conditioned on this graph and molecular properties. The resulting model achieves state-of-the-art results using 100x fewer trainable parameters and affords up to 1000x speedup. Collectively, our findings underscore the need to reassess and redirect the existing paradigm and efforts for SBDD., Comment: 25 pages, 11 figures

Programmable lipid nanoparticles, or LNPs, represent a breakthrough in the realm of targeted drug delivery, offering precise spatiotemporal control essential for the treatment of complex diseases such as cancer and genetic disorders. In order to provide a more modular perspective and a more balanced analysis of the mechanism, this review presents a novel Four-Domain Model that consists of Architecture, Interface, Payload, and Dispersal Domain. We explored the dynamical equilibrium between LNPs components and the surroundings throughout their destiny, from formulation to release. On the basis of this, we delve deep into manufacturing challenges, scalability issues, and regulatory hurdles, associated with the clinical translation of LNP technology. Within the framework focusing on the programmability in each domain, we prioritized patient-centric factors like dosing regimens, administration techniques, and potential consequences. Notably, this review expands to innovative anatomical routes, such as intranasal and intraocular administration, offering a thorough examination of the advantages and disadvantages of each route. We also offered a comprehensive comparison between artificial LNPs and natural exosomes in terms of functionality, biocompatibility, and therapeutic potential. Ultimately, this review highlights the potential of programmable LNPs to evolve into more intelligent, naturally integrated systems, achieving optimal biocompatibility and functionality., Comment: 46 pages, 8 figures

Cryo-electron microscopy (cryo-EM) is a powerful technique for determining high-resolution 3D biomolecular structures from imaging data. As this technique can capture dynamic biomolecular complexes, 3D reconstruction methods are increasingly being developed to resolve this intrinsic structural heterogeneity. However, the absence of standardized benchmarks with ground truth structures and validation metrics limits the advancement of the field. Here, we propose CryoBench, a suite of datasets, metrics, and performance benchmarks for heterogeneous reconstruction in cryo-EM. We propose five datasets representing different sources of heterogeneity and degrees of difficulty. These include conformational heterogeneity generated from simple motions and random configurations of antibody complexes and from tens of thousands of structures sampled from a molecular dynamics simulation. We also design datasets containing compositional heterogeneity from mixtures of ribosome assembly states and 100 common complexes present in cells. We then perform a comprehensive analysis of state-of-the-art heterogeneous reconstruction tools including neural and non-neural methods and their sensitivity to noise, and propose new metrics for quantitative comparison of methods. We hope that this benchmark will be a foundational resource for analyzing existing methods and new algorithmic development in both the cryo-EM and machine learning communities.

High-content phenotypic screening, including high-content imaging (HCI), has gained popularity in the last few years for its ability to characterize novel therapeutics without prior knowledge of the protein target. When combined with deep learning techniques to predict and represent molecular-phenotype interactions, these advancements hold the potential to significantly accelerate and enhance drug discovery applications. This work focuses on the novel task of HCI-guided molecular design. Generative models for molecule design could be guided by HCI data, for example with a supervised model that links molecules to phenotypes of interest as a reward function. However, limited labeled data, combined with the high-dimensional readouts, can make training these methods challenging and impractical. We consider an alternative approach in which we leverage an unsupervised multimodal joint embedding to define a latent similarity as a reward for GFlowNets. The proposed model learns to generate new molecules that could produce phenotypic effects similar to those of the given image target, without relying on pre-annotated phenotypic labels. We demonstrate that the proposed method generates molecules with high morphological and structural similarity to the target, increasing the likelihood of similar biological activity, as confirmed by an independent oracle model.

Stress generation by the actin cytoskeleton shapes cells and tissues. Despite impressive progress in live imaging and quantitative physical descriptions of cytoskeletal network dynamics, the connection between processes at molecular scales and cell-scale spatio-temporal patterns is still unclear. Here we review studies reporting acto-myosin clusters of micrometer size and with lifetimes of several minutes in a large number of organisms ranging from fission yeast to humans. Such structures have also been found in reconstituted systems in vitro and in theoretical analysis of cytoskeletal dynamics. We propose that tracking these clusters can serve as a simple readout for characterising living matter. Spatio-temporal patterns of clusters could serve as determinants of morphogenetic processes that play similar roles in diverse organisms.

A data fitting procedure is devised and thoroughly tested to provide self-consistent estimates of the relevant mechanokinetic parameters involved in a plausible scheme underpinning the output of an ensemble of myosin II molecular motors mimicking the muscle contraction. The method builds on a stochastic model accounting for the force exerted by the motor ensemble operated both in the low and high force-generating regimes corresponding to different temperature ranges. The proposed interpretative framework is successfully challenged against simulated data, meant to mimic the experimental output of a unidimensional synthetic nanomachine powered by pure muscle myosin isoforms.

The Protein Secondary Structure Visualizer ProS2Vi is a novel Python-based visualization tool designed to enhance the analysis and accessibility of protein secondary structures calculated and identified by the Dictionary of Secondary Structure of Proteins algorithm. Leveraging robust Python libraries such as Biopython for data handling, Flask, for Graphical User Interface, Jinja2, and wkhtmltopdf for visualization, ProS2Vi offers a modern and intuitive representation for visualization of the DSSP assigned secondary structures to each residue of any proteins amino acid sequence. Significant features of ProS2Vi include customizable icon colors, the number of residues per line, and the ability to export visualizations as scalable PDFs, enhancing both visual appeal and functional versatility through a user-friendly GUI. We have designed ProS2Vi specifically for secure and local operation, which significantly increases security when dealing with novel protein data.

Enzyme design plays a crucial role in both industrial production and biology. However, this field faces challenges due to the lack of comprehensive benchmarks and the complexity of enzyme design tasks, leading to a dearth of systematic research. Consequently, computational enzyme design is relatively overlooked within the broader protein domain and remains in its early stages. In this work, we address these challenges by introducing MetaEnzyme, a staged and unified enzyme design framework. We begin by employing a cross-modal structure-to-sequence transformation architecture, as the feature-driven starting point to obtain initial robust protein representation. Subsequently, we leverage domain adaptive techniques to generalize specific enzyme design tasks under low-resource conditions. MetaEnzyme focuses on three fundamental low-resource enzyme redesign tasks: functional design (FuncDesign), mutation design (MutDesign), and sequence generation design (SeqDesign). Through novel unified paradigm and enhanced representation capabilities, MetaEnzyme demonstrates adaptability to diverse enzyme design tasks, yielding outstanding results. Wet lab experiments further validate these findings, reinforcing the efficacy of the redesign process., Comment: Accepted to ACM Multimedia 2024

The increase in high-dimensional multiomics data demands advanced integration models to capture the complexity of human diseases. Graph-based deep learning integration models, despite their promise, struggle with small patient cohorts and high-dimensional features, often applying independent feature selection without modeling relationships among omics. Furthermore, conventional graph-based omics models focus on homogeneous graphs, lacking multiple types of nodes and edges to capture diverse structures. We introduce a Heterogeneous Graph ATtention network for omics integration (HeteroGATomics) to improve cancer diagnosis. HeteroGATomics performs joint feature selection through a multi-agent system, creating dedicated networks of feature and patient similarity for each omic modality. These networks are then combined into one heterogeneous graph for learning holistic omic-specific representations and integrating predictions across modalities. Experiments on three cancer multiomics datasets demonstrate HeteroGATomics' superior performance in cancer diagnosis. Moreover, HeteroGATomics enhances interpretability by identifying important biomarkers contributing to the diagnosis outcomes., Comment: 29 pages, 13 figures

The assembly of proteins in membranes plays a key role in many crucial cellular pathways. Despite their importance, characterizing transmembrane assembly remains challenging for experiments and simulations. Equilibrium molecular dynamics simulations do not cover the time scales required to sample the typical transmembrane assembly. Hence, most studies rely on enhanced sampling schemes that steer the dynamics of transmembrane proteins along a collective variable that should encode all slow degrees of freedom. However, given the complexity of the condensed-phase lipid environment, this is far from trivial, with the consequence that free energy profiles of dimerization can be poorly converged. Here, we introduce an alternative approach, which relies only on simulating short, dynamically unbiased trajectory segments, avoiding using collective variables or biasing forces. By merging all trajectories, we obtain free energy profiles, rates, and mechanisms of transmembrane dimerization with the same set of simulations. We showcase our algorithm by sampling the spontaneous association and dissociation of a transmembrane protein in a lipid bilayer, the popular coarse-grained Martini force field. Our algorithm represents a promising way to investigate assembly processes in biologically relevant membranes, overcoming some of the challenges of conventional methods.

Myosin II is the muscle molecular motor that works in two bipolar arrays in each thick filament of the striated (skeletal and cardiac) muscle, converting the chemical energy into steady force and shortening by cyclic ATP--driven interactions with the nearby actin filaments. Different isoforms of the myosin motor in the skeletal muscles account for the different functional requirements of the slow muscles (primarily responsible for the posture) and fast muscles (responsible for voluntary movements). To clarify the molecular basis of the differences, here the isoform--dependent mechanokinetic parameters underpinning the force of slow and fast muscles are defined with a unidimensional synthetic nanomachine powered by pure myosin isoforms from either slow or fast rabbit skeletal muscle. Data fitting with a stochastic model provides a self--consistent estimate of all the mechanokinetic properties of the motor ensemble including the motor force, the fraction of actin--attached motors and the rate of transition through the attachment--detachment cycle. The achievements in this paper set the stage for any future study on the emergent mechanokinetic properties of an ensemble of myosin molecules either engineered or purified from mutant animal models or human biopsies., Comment: Buonfiglio V, Pertici I, Marcello M, Morotti I, Caremani M, Reconditi M, Linari M, Fanelli D, Lombardi V, Bianco P. Force and kinetics of fast and slow muscle myosin determined with a synthetic sarcomere-like nanomachine. Commun Biol. 2024 Mar 23;7(1):361. doi: 10.1038/s42003-024-06033-8. PMID: 38521889; PMCID: PMC10960843

We introduce a protein language model for determining the complete sequence of a peptide based on measurement of a limited set of amino acids. To date, protein sequencing relies on mass spectrometry, with some novel edman degregation based platforms able to sequence non-native peptides. Current protein sequencing techniques face limitations in accurately identifying all amino acids, hindering comprehensive proteome analysis. Our method simulates partial sequencing data by selectively masking amino acids that are experimentally difficult to identify in protein sequences from the UniRef database. This targeted masking mimics real-world sequencing limitations. We then modify and finetune a ProtBert derived transformer-based model, for a new downstream task predicting these masked residues, providing an approximation of the complete sequence. Evaluating on three bacterial Escherichia species, we achieve per-amino-acid accuracy up to 90.5% when only four amino acids ([KCYM]) are known. Structural assessment using AlphaFold and TM-score validates the biological relevance of our predictions. The model also demonstrates potential for evolutionary analysis through cross-species performance. This integration of simulated experimental constraints with computational predictions offers a promising avenue for enhancing protein sequence analysis, potentially accelerating advancements in proteomics and structural biology by providing a probabilistic reconstruction of the complete protein sequence from limited experimental data.

Proteins play a vital role in biological processes and are indispensable for living organisms. Accurate representation of proteins is crucial, especially in drug development. Recently, there has been a notable increase in interest in utilizing machine learning and deep learning techniques for unsupervised learning of protein representations. However, these approaches often focus solely on the amino acid sequence of proteins and lack factual knowledge about proteins and their interactions, thus limiting their performance. In this study, we present GOProteinGNN, a novel architecture that enhances protein language models by integrating protein knowledge graph information during the creation of amino acid level representations. Our approach allows for the integration of information at both the individual amino acid level and the entire protein level, enabling a comprehensive and effective learning process through graph-based learning. By doing so, we can capture complex relationships and dependencies between proteins and their functional annotations, resulting in more robust and contextually enriched protein representations. Unlike previous fusion methods, GOProteinGNN uniquely learns the entire protein knowledge graph during training, which allows it to capture broader relational nuances and dependencies beyond mere triplets as done in previous work. We perform a comprehensive evaluation on several downstream tasks demonstrating that GOProteinGNN consistently outperforms previous methods, showcasing its effectiveness and establishing it as a state-of-the-art solution for protein representation learning.

Accurate prediction of drug-target interactions is critical for advancing drug discovery. By reducing time and cost, machine learning and deep learning can accelerate this laborious discovery process. In a novel approach, BarlowDTI, we utilise the powerful Barlow Twins architecture for feature-extraction while considering the structure of the target protein. Our method achieves state-of-the-art predictive performance against multiple established benchmarks using only one-dimensional input. The use of gradient boosting machine as the underlying predictor ensures fast and efficient predictions without the need for substantial computational resources. We also investigate how the model reaches its decision based on individual training samples. By comparing co-crystal structures, we find that BarlowDTI effectively exploits catalytically active and stabilising residues, highlighting the model's ability to generalise from one-dimensional input data. In addition, we further benchmark new baselines against existing methods. Together, these innovations improve the efficiency and effectiveness of drug-target interaction predictions, providing robust tools for accelerating drug development and deepening the understanding of molecular interactions. Therefore, we provide an easy-to-use web interface that can be freely accessed at https://www.bio.nat.tum.de/oc2/barlowdti ., Comment: Refined model architecture, additional results added

Persistent homology is an effective method for extracting topological information, represented as persistent diagrams, of spatial structure data. Hence it is well-suited for the study of protein structures. Attempts to incorporate Persistent homology in machine learning methods of protein function prediction have resulted in several techniques for vectorizing persistent diagrams. However, current vectorization methods are excessively artificial and cannot ensure the effective utilization of information or the rationality of the methods. To address this problem, we propose a more geometrical vectorization method of persistent diagrams based on maximal margin classification for Banach space, and additionaly propose a framework that utilizes topological data analysis to identify proteins with specific functions. We evaluated our vectorization method using a binary classification task on proteins and compared it with the statistical methods that exhibit the best performance among thirteen commonly used vectorization methods. The experimental results indicate that our approach surpasses the statistical methods in both robustness and precision.

Predicting interactions between biomolecules, such as protein-protein complexes, remains a challenging problem. Despite the many advancements done so far, the performances of docking protocols are deeply dependent on their capability of identify binding regions. In this context, we present a novel approach that builds upon our previous works modeling protein surface patches via sets of orthogonal polynomials to identify regions of high shape/electrostatic complementarity. By incorporating another key binding property, such as the balance between hydrophilic and hydrophobic contributions, we define new binding matrices that serve an effective inputs for training a neural network. Our approach also allows for the quantitative definition of a typical binding site area - approximately 10\AA~in radius - where hydrophobic contribution and shape complementarity, which reflects the Lennard-Jones interaction, are maximized. Using this new architecture, CIRNet (Core Interacting Residues Network), we achieve an accuracy of approximately 0.82 in identifying pairs of core interacting residues on a balanced dataset. In a blind search for core interacting residues, CIRNet distinguishes these from decoys with a ROC AUC of 0.72. This protocol can enahnce docking algorithms by rescaling the proposed poses. When applied to the top ten models from three popular docking server, CIRNet improves docking outcomes, reducing the the average RMSD between the refined poses and the native state by up to 58%., Comment: 15 pages, 5 figures, 1 table

Trans-activating transcriptional activator (TAT), a cell-penetrating peptide, has been extensively used for facilitating cellular uptake and nuclear targeting of drug delivery systems. However, the positively charged TAT peptide usually strongly interacts with serum components and undergoes substantial phagocytosis by the reticuloendothelial system, causing a short blood circulation in vivo. In this work, an acid-active tumor targeting nanoplatform DA-TAT-PECL was developed to effectively inhibit the nonspecific interactions of TAT in the bloodstream. 2,3-dimethylmaleic anhydride (DA) was first used to convert the TAT amines to carboxylic acid, the resulting DA-TAT was further conjugated to get DA-TAT-PECL. After self-assembly into polymeric micelles, they were capable of circulating in the physiological condition for a long time and promoting cell penetration upon accumulation at the tumor site and de-shielding the DA group. Moreover, camptothecin (CPT) was used as the anticancer drug and modified into a dimer (CPT)2-ss-Mal, in which two CPT molecules were connected by a reduction-labile maleimide thioether bond. The FRET signal between CPT and maleimide thioether bond was monitored to visualize the drug release process and effective targeted delivery of antitumor drugs was demonstrated. This pH/reduction dual-responsive micelle system provides a new platform for high fidelity cancer therapy.

Analysis of bacterial biofilms is particularly challenging and important with diverse applications from systems biology to biotechnology. Among the variety of techniques that have been applied, time-of-flight secondary ion mass spectrometry (ToF-SIMS) has many promising features in studying the surface characteristics of biofilms. ToF-SIMS offers high spatial resolution and high mass accuracy, which permit surface sensitive analysis of biofilm components. Thus, ToF-SIMS provides a powerful solution to addressing the challenge of bacterial biofilm analysis. This dataset covers ToF-SIMS analysis of Shewanella oneidensis MR-1 isolated from freshwater lake sediment in New York state. The MR-1 strain is known to have metal and sulfur reducing properties and it can be used for bioremediation and wastewater treatment. There is a current need to identify small molecules and fragments produced from bacterial biofilms. Static ToF-SIMS spectra of MR-1 were obtained using an IONTOF TOF.SIMS V instrument equipped with a 25 keV Bi3+ metal ion gun. Identified molecules and molecular fragments are compared against known biological databases and the reported peaks have at least 65 ppm mass accuracy. These molecules range from lipids and fatty acids to flavonoids, quinolones, and other naturally occurring organic compounds. It is anticipated that the spectral identification of key peaks will assist detection of metabolites, extracellular polymeric substance molecules like polysaccharides, and biologically relevant small molecules using ToF-SIMS in future surface and interface research., Comment: 7 pages, 2 figures

Quantum computing combined with machine learning (ML) is an extremely promising research area, with numerous studies demonstrating that quantum machine learning (QML) is expected to solve scientific problems more effectively than classical ML. In this work, we successfully apply QML to drug discovery, showing that QML can significantly improve model performance and achieve faster convergence compared to classical ML. Moreover, we demonstrate that the model accuracy of the QML improves as the number of qubits increases. We also introduce noise to the QML model and find that it has little effect on our experimental conclusions, illustrating the high robustness of the QML model. This work highlights the potential application of quantum computing to yield significant benefits for scientific advancement as the qubit quantity increase and quality improvement in the future.