Methods, media, and systems for determining changes associated with structure of compound

Abstract

Exemplary embodiments relate to methods, media, and systems that use molecular characteristics of chemical compounds to quantify errors or variations in collision cross-section prediction. For example, the CCS prediction may determine the location of charge on the compound, and the molecular characteristic, such as the length normalized residue or Van der Waals volume of the compound, may be used to assign error values for the prediction. The error values can be used to establish a model of the chemical compound using the error or variance, wherein the compound is capable of exhibiting more than one of the CCS values.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims the benefit of and priority to U.S. Provisional Application No. 63 / 320,419, filed on March 16, 2022, the entire disclosure of which is incorporated herein by reference in its entirety. Background Art

[0003] Mass spectrometry (MS) devices and liquid chromatography-mass spectrometry (MS) devices are used to analyze chemical samples to study the identity, quality or structure of the sample.

[0004] Chemical compounds may exhibit structures that can be measured by LC-MS instruments in the form of collision cross section values. In some cases, molecular modeling (MM) or machine learning (ML) can also be used to predict CCS values. When compared to measured CCS values, many CCS predictions are close to the error range of experimentally obtained results when considered as a whole. However, individual predictions are often not associated with error or variance estimates, as these may depend on many unknown parameters, such as underrepresentation of a given chemical class or combination of features in the model, variability in experimental measurements (conformers, ESI and IM-MS conditions, etc.), structural unambiguity, or any combination of these parameters. Summary of the invention

[0005] The present inventors have discovered that there is a link between CCS prediction errors and certain molecular properties of the chemical samples being modelled.

[0006] Exemplary embodiments relate to methods, media and systems for quantifying errors or variations in collision cross section predictions using molecular properties of chemical compounds. For example, CCS predictions can be associated with charge positions on a compound that determine the CCS value of the compound, and molecular properties (such as the length normalized residue value or van der Waals volume of the compound) can be used to assign error values ​​to the predictions. These error values ​​can be used to build a model of the chemical compound using the error or variance, where the chemical compound can exhibit more than one CCS value.

[0007] Some embodiments may determine that a given compound may be associated with more than one CCS value, or with a CCS prediction value that has more variation (due to the structure not being able to accommodate charge). If a compound can exhibit more than one CCS value, due to the structure being able to accommodate charge at more than one position, this information may be captured / encoded when creating the model, providing the ability to report more than one CCS value. Alternatively, when charge assignment is questionable, this may be flagged and reported in the output when calculating CCS values ​​(both ML and MM).

[0008] For those skilled in the art, other technical features can be easily seen from the following figures, descriptions and claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] To easily identify the discussion of any particular element or act, the most significant digit(s) in a reference number refers to the figure numeral that first introduces that element.

[0010] Figure 1 An exemplary artificial intelligence / machine learning (AI / ML) system suitable for use with the exemplary embodiments is shown.

[0011] Figure 2 An exemplary computer system architecture is depicted that can be used to practice the exemplary embodiments described herein.

[0012] Figure 3 An example of a mass spectrometry system according to an exemplary embodiment is shown.

[0013] Figure 4 is a flow chart depicting an exemplary technique according to an embodiment. DETAILED DESCRIPTION

[0014] Note about data privacy

[0015] Some embodiments described herein utilize training data or metrics that may include information voluntarily provided by one or more users. In such embodiments, data privacy may be protected in a variety of ways.

[0016] For example, users may be required to opt-in to any data collection before their data is collected or used. Users may also be provided with the opportunity to opt-out of any data collection. Before opting in to data collection, users may be provided with a description of how their data will be used, how long the data will be retained, and the security measures in place to protect the data from being disclosed.

[0017] Any information identifying the user from whom data is collected may be removed or separated from that data. In the event that any identifying information needs to be retained (e.g., to meet regulatory requirements), the user may be informed of the collection of the identifying information, the purpose of the identifying information, and the amount of time the identifying information will be retained. Information that specifically identifies the user may be removed and may be replaced with, for example, a universal identification number or other non-specific form of identification.

[0018] Once collected, the data may be stored in a secure data storage location that includes security measures to prevent unauthorized access to the data. The data may be stored in an encrypted format. After a predetermined period of time, identifying information and / or non-identifying information may be purged from the data storage.

[0019] Although specific privacy protection techniques are described herein for purposes of illustration, one of ordinary skill in the art will recognize that privacy can also be protected in other ways. Further details about data privacy will be discussed in the section describing the network implementation scheme below.

[0020] Assuming that the user's privacy conditions are met, the exemplary embodiments can be deployed in a variety of messaging systems, including messaging in social networks or on mobile devices (e.g., via a messaging client application or via a short message service), among other possibilities. An overview of exemplary logic and processes for participating in a synchronous video conversation in a messaging system is provided next.

[0021] Exemplary embodiments

[0022] To aid understanding, a series of examples will first be presented before describing a detailed description of the underlying implementation. It should be noted that these examples are merely illustrative, and the present invention is not limited to the embodiments shown.

[0023] Reference is now made to the accompanying drawings, in which like reference numerals are used to refer to like elements throughout. In the following description, for the purpose of explanation, many specific details are set forth in order to provide a thorough understanding thereof. However, novel embodiments may be practiced without these specific details. In other cases, well-known structures and devices are shown in the form of block diagrams for ease of description thereof. It is intended to cover all modifications, equivalents, and substitutes consistent with the claimed subject matter.

[0024] In the drawings and accompanying description, the names "a", "b", and "c" (and similar designations) are intended to be variables representing any positive integer. Thus, for example, if an implementation sets a value of a=5, the complete set of components 122, shown as components 122-1 through 122-a, may include components 122-1, 122-2, 122-3, 122-4, and 122-5. The embodiments are not limited in this context.

[0025] Example embodiments may utilize artificial intelligence / machine learning (AI / ML). Figure 1 An AI / ML environment 100 suitable for use with an exemplary embodiment is depicted.

[0026] First, note that Figure 1 A specific AI / ML environment 100 is depicted and discussed in conjunction with a specific type of AI / ML architecture. However, other AI / ML systems exist, and one of ordinary skill in the art will recognize that any suitable technology may be used to implement the AI / ML environment in addition to the depicted AI / ML environment.

[0027] The AI / ML environment 100 may include an AI / ML system 102, such as a computing device that applies an AI / ML algorithm to learn the relationships between the above-mentioned protein parameters.

[0028] The AI / ML system 102 can utilize training data 108. In some cases, the training data 108 can include pre-existing labeled data from a database, library, repository, etc. The training data 108 can include, for example, rows and / or columns of data values ​​114. The training data 108 can be co-located with the AI / ML system 102 (e.g., stored in a storage device 110 of the AI / ML system 102), can be remote from the AI / ML system 102 and accessed via a network interface 104, or can be a combination of local and remote data. Each unit of the training data 108 can be labeled with an assigned category 116 (or multiple assigned categories); for example, each row and / or each column can be labeled with a classification. In some embodiments, the training data can include individual data elements (e.g., not organized into rows or columns) and can be labeled on an individual basis.

[0029] As described above, the AI / ML system 102 may include a storage device 110 , which may include a hard drive, a solid-state storage device, and / or a random access memory.

[0030] The training data 112 may be used to train a model 122. Depending on the particular application, different types of models 122 may be appropriate for use. For example, exemplary embodiments may utilize a Bayesian hierarchical model, or a gradient boosted tree may be particularly suitable for learning the association of data values ​​114 and assigned categories 116. In other examples, deep learning architectures such as recurrent neural networks (RNNs) may be used. Other types of models 122 or non-model-based systems may also be well suited for the tasks described herein, depending on the designer's goals, available resources, the amount of input data available, etc.

[0031] Any suitable training algorithm 118 may be used to train the model 122. However, Figure 1 The example shown in may be particularly suitable for supervised training algorithms. For supervised training algorithms, AI / ML system 102 can apply data values ​​114 as input data, and the resulting assigned categories 116 can be mapped to the input data to learn the association between the input and the label. In this case, the assigned category 116 can be used as a label for the data value 114.

[0032] The training algorithm 118 may be applied using processor circuitry 106, which may include suitable hardware processing resources to operate on logic and structures in storage device 110. Development of the training algorithm 118 and / or training model 122 may depend, at least in part, on model hyperparameters 120; in an exemplary embodiment, the model hyperparameters 120 may be automatically selected based on hyperparameter optimization logic 128, which may include any known hyperparameter optimization techniques appropriate to the selected model 122 and training algorithm 118 to be used.

[0033] Optionally, model 122 may be retrained over time.

[0034] In some embodiments, some of the training data 112 may be used to initially train the model 122, while some of the training data may be retained as a validation subset. The portion of the training data 112 that does not include the validation subset may be used to train the model 122, while the validation subset may be retained and used to test the trained model 122 to verify that the model 122 is able to generalize its predictions to new data.

[0035] Once the model 122 is trained, it can be applied (by the processor circuit 106) to new input data. The new input data can include unlabeled data stored in a data structure, potentially organized into rows and / or columns. This input to the model 122 can be formatted according to a predefined input structure 124, which reflects the manner in which the training data 112 is provided to the model 122. The model 122 can generate an output structure 126, which can be, for example, a prediction of the assigned category 116 to be applied to the unlabeled input.

[0036] The above description relates to a specific kind of AI / ML system 102 that applies supervised learning techniques given available training data with input / result pairs. However, the present invention is not limited to use with a specific AI / ML paradigm, and other types of AI / ML techniques may be used.

[0037] Figure 2An example of a system architecture and data processing device that can be used to implement one or more illustrative aspects described herein in a standalone and / or networked environment is shown. Various network nodes such as data server 210, web server 206, computer 204, and laptop computer 202 can be interconnected via a wide area network (WAN) 208 such as the Internet. Other networks can also or alternatively be used, including a private intranet, a company network, a LAN, a metropolitan area network (MAN), a wireless network, a personal network (PAN), etc. Network 208 is for illustrative purposes and can be replaced by fewer or more computer networks. A local area network (LAN) can have one or more topologies in any known LAN topology, and can use one or more protocols in a variety of different protocols, such as Ethernet. Device data server 210, web server 206, computer 204, laptop computer 202 and other devices (not shown) can be connected to one or more networks in the network via twisted pair, coaxial cable, optical fiber, radio waves or other communication media.

[0038] The computer software, hardware, and networks may be used in a variety of different system environments, including stand-alone, networked, remote access (also known as remote desktop), virtualized, and / or cloud-based environments, among others.

[0039] The term "network" as used herein and depicted in the accompanying drawings refers not only to a system in which remote storage devices are coupled together via one or more communication paths, but also to independent devices that may be coupled to such a system from time to time with storage capabilities. Thus, the term "network" includes not only a "physical network" but also a "content network" consisting of data residing on all physical networks that can be attributed to a single entity.

[0040] Components may include a data server 210, a web server 206, a client computer 204, and a laptop computer 202. The data server 210 provides overall access, control, and management of databases and control software for performing one or more illustrative aspects described herein. The data server 210 may be connected to the web server 206, through which a user interacts with the requested data and obtains the data. Alternatively, the data server 210 itself may act as a web server and be directly connected to the Internet. The data server 210 may be connected to the web server 206 via a network 208 (e.g., the Internet), via a direct or indirect connection, or via some other network. A user may interact with the data server 210 using a remote computer 204, a laptop computer 202, such as using a web browser to connect to the data server 210 via one or more external public web sites hosted by the web server 206. The client computer 204, the laptop computer 202 may be used together with the data server 210 to access data stored therein, or may be used for other purposes. For example, from a client computer 204, a user may access the web server 206 using an Internet browser (as is known in the art) or by executing a software application that communicates with the web server 206 and / or data server 210 via a computer network (such as the Internet).

[0041] The server and application can be combined on the same physical machine and retain separate virtual or logical addresses, or can reside on separate physical machines. Figure 2 Only one example of a network architecture that may be used is shown, and those skilled in the art will appreciate that the specific network architecture and data processing devices used may vary and are secondary to the functionality they provide, as further described herein. For example, the services provided by web server 206 and data server 210 may be combined on a single server.

[0042] Each component data server 210, web server 206, computer 204, laptop computer 202 can be any type of known computer, server or data processing device. Data server 210 can include, for example, a processor 212 that controls the overall operation of data server 210. Data server 210 can also include RAM 216, ROM 218, network interface 214, input / output interface 220 (e.g., keyboard, mouse, display, printer, etc.) and memory 222. Input / output interface 220 can include various interface units and drivers for reading, writing, displaying and / or printing data or files. Memory 222 can also store operating system software 224 for controlling the overall operation of data server 210, control logic 226 for instructing data server 210 to perform various aspects described herein, and other application software 228 that provides auxiliary, support and / or other functions that can be used in conjunction with or without the various aspects described herein. Control logic can also be referred to as data server software control logic 226 in this article. The functionality of the data server software may refer to a combination of operations or decisions made automatically based on rules encoded into the control logic, manually by a user providing input to the system, and / or automatic processing based on user input (e.g., queries, data updates, etc.).

[0043] The memory 1122 may also store data for performing one or more aspects described herein, including a first database 232 and a second database 230. In some embodiments, the first database may include the second database (e.g., as a separate table, report, etc.). That is, the information may be stored in a single database, or divided into different logical, virtual or physical databases, depending on the system design. The web server 206, computer 204, laptop computer 202 may have an architecture similar to or different from that described with respect to the data server 210. Those skilled in the art will appreciate that the functionality of the data server 210 (or web server 206, computer 204, laptop computer 202) as described herein may be distributed across multiple data processing devices, for example, to distribute processing loads across multiple computers, to separate transactions based on geographic location, user access level, quality of service (QoS), etc.

[0044] One or more aspects may be embodied in computer-usable or readable data and / or computer-executable instructions, such as embodied in one or more program modules executed by one or more computers or other devices as described herein. Typically, program modules include routines, programs, objects, components, data structures, etc., which perform specific tasks or implement specific abstract data types when executed by a processor in a computer or other device. These modules can be written in source code programming languages, which are then compiled for execution, or these modules can be written in scripting languages ​​such as (but not limited to) HTML or XML. Computer executable instructions can be stored on a computer-readable medium such as a non-volatile storage device. Any suitable computer-readable storage medium can be used, including hard disks, CD-ROMs, optical storage devices, magnetic storage devices, and / or any combination thereof. In addition, various transmission (non-storage) media representing data or events as described herein can be transmitted between a source and a destination in the form of electromagnetic waves propagated through a signal-conducting medium (such as a metal wire, an optical fiber, and / or a wireless transmission medium). The various aspects described herein can be embodied as a method, a data processing system, or a computer program product. Thus, the various functions may be embodied in whole or in part in software, firmware, and / or hardware or hardware equivalents such as integrated circuits, field programmable gate arrays (FPGAs), etc. Certain data structures may be used to more efficiently implement one or more aspects described herein, and such data structures are contemplated to be within the scope of the computer-executable instructions and computer-usable data described herein.

[0045] For illustration purposes, Figure 3 is a schematic diagram of a system that can be used in conjunction with the techniques herein. Figure 3 A specific type of device in a specific LCMS configuration is depicted, but one of ordinary skill in the art will appreciate that different types of chromatography devices (eg, MS, tandem MS, etc.) may also be used in conjunction with the present disclosure.

[0046] Sample 302 is injected into liquid chromatograph 304 via injector 306. Pump 308 can pump the sample through column 310 to separate the mixture into component parts based on retention time through the column.

[0047] The output of the column is input into a mass spectrometer 312 for analysis. Initially, the sample is desolvated and ionized by a desolvation / ionization device 114. Desolvation can be any desolvation technique, including, for example, a heater, a gas, a heater in combination with a gas, or other desolvation techniques. Ionization can be achieved using any ionization technique, including, for example, electrospray ionization (ESI), atmospheric pressure chemical ionization (APCI), matrix-assisted laser desorption (MALDI), or other ionization techniques. The ions produced by the ionization are sent into a collision chamber 318 by the voltage gradient being applied to an ion guide 316. The collision chamber 318 can be used to transfer ions (low energy) or to fragment ions (high energy).

[0048] Various techniques can be used, including those described in U.S. Pat. No. 6,717,130 to Bateman et al., which is incorporated herein by reference, in which an alternating voltage can be applied across the collision cell 318 to induce fragmentation. Spectra are collected of the precursor (no collision) at low energy and the fragments (products of collision) at high energy.

[0049] The output of the collision cell 318 is input to a mass analyzer 320. The mass analyzer 320 can be any mass analyzer, including a quadrupole, a time of flight (TOF), an ion trap, a magnetic sector mass analyzer, and a combination thereof. A detector 322 detects ions emitted from the mass analyzer 122. The detector 322 can be integrated with the mass analyzer 320. For example, in the case of a TOF mass analyzer, the detector 322 can be a microchannel plate detector that counts ion intensities (i.e., counts incident ions).

[0050] The raw data repository 324 can provide permanent storage for storing ion counts for analysis. For example, the raw data repository 324 can be an internal or external computer data storage device, such as a disk, a flash-based storage device, etc. The acquisition device 326 analyzes the stored data. The data can also be analyzed in real time without being stored in the storage medium 124. In real-time analysis, the detector 322 passes the data to be analyzed directly to the computer 126, rather than first storing it in a permanent storage device.

[0051] Collision cell 318 performs the fragmentation of precursor ions. Fragmentation can be used to determine the primary sequence of peptides, and then the origin protein is identified. Collision cell 318 contains gas, such as helium, argon, nitrogen, air or methane. When charged precursor interacts with gas atoms, the collision produced can fragment the precursor by decomposing the precursor into the resulting fragment ions. This fragmentation can use the technology described in Bateman, by switching the voltage in the collision cell between a low voltage state (e.g., low energy, <5V) and a high voltage state (e.g., high energy or elevated energy, >15V), wherein the low voltage state is used to obtain the MS spectrum of the peptide precursor, and the high voltage state is used to obtain the MS spectrum of the collision-induced fragment of the precursor. High voltage and low voltage can be referred to as high energy and low energy, because high voltage or low voltage is used to give kinetic energy to ions, respectively.

[0052] Various procedures can be used to determine when and how to switch the voltage for this MS / MS collection. For example, conventional methods trigger voltage with a target or data-dependent mode (data-dependent analysis, i.e., DDA). These methods also include gas phase isolation (or preselection) of the coupling of the target precursor. The low-energy spectrum is acquired and checked by software in real time. When the required mass reaches the specified intensity value in the low-energy spectrum, the voltage in the collision cell is switched to a high-energy state. The high-energy spectrum for the preselected precursor ion is then obtained. These spectra include fragments of the precursor peptides seen under low energy. After collecting enough high-energy spectra, data acquisition returns to the low-energy state, and continues to look for the precursor mass with suitable intensity to be used for high-energy collision analysis.

[0053] Different suitable methods can be used together with systems such as described herein to obtain ion information, such as information on precursor and product ions of mass spectrometry for analyzing samples. Although conventional switching techniques can be adopted, embodiments can use the technology described in Bateman, which can be characterized as a fragmentation procedure that switches voltage with a simple alternating cycle. This switching is completed at a sufficiently high frequency so that multiple high-energy spectra and multiple low-energy spectra are included in a single chromatographic peak. Different from conventional switching procedures, the cycle is independent of the content of the data. This switching technique described in Bateman provides effective simultaneous mass analysis of both precursor ions and product ions. In Bateman, the use of high-energy and low-energy switching procedures can be applied as a part of LC / MS analysis of a single injection of a peptide mixture. In the data collected from a single injection or experimental run, the low-energy spectrum contains ions mainly from unfragmented precursors, and the high-energy spectrum contains ions mainly from fragmented precursors. For example, a portion of the precursor ions can be fragmented to form product ions, and the precursor ions and product ions can be analyzed substantially simultaneously, or simultaneously, or, for example, using rapid succession, by applying a rapid switching or alternating voltage to the collision cell of the MS module, switching between low voltage (e.g., mainly generating precursors) and high voltage or elevated voltage (e.g., mainly generating fragments) to adjust the fragmentation. According to the above-mentioned Bateman's technique, MS operation using rapid succession alternating between high (or elevated) energy and low energy can also be referred to as Bateman technique and high-low protocol in this article.

[0054] The data collected by the high-low procedure allows the retention time, mass-to-charge ratio and intensity of all ions collected under both low energy mode and high energy mode to be accurately determined. Generally speaking, different ions are seen in two different modes, and the spectrum collected under each mode can be further analyzed individually or in combination. As seen in one or both modes, ions from a common precursor will share the same retention time (and therefore have substantially the same scan time) and peak shape. The high-low procedure allows the different features of ions to be meaningfully compared within a single mode and between modes. This comparison can then be used to group the ions seen in the low energy spectrum and the high energy spectrum.

[0055] In summary, such as when the Bateman technique is used to operate the system, a sample 302 is injected into the LC / MS system. The LC / MS system generates two sets of spectra, a set of low energy spectra and a set of high energy spectra. The set of low energy spectra mainly contains ions associated with precursors. The set of high energy spectra mainly contains ions associated with fragments. These spectra are stored in a raw data repository 324. After data acquisition, these spectra can be extracted from the raw data repository 324 and displayed and processed by a post-acquisition algorithm in an acquisition device 326.

[0056] Metadata describing various parameters related to data collection can be generated with the raw data. This information can include the configuration of the liquid chromatograph 304 or mass spectrometer 312 (or other chromatographic device that collected the data), which can define the data type. An identifier (e.g., a key) of a codec configured to decode the data can also be stored as part of the metadata and / or with the raw data. The metadata can be stored in a metadata catalog 330 in the document repository 328.

[0057] The collection device 326 can operate according to the workflow, provide the analyst with visualization of the data at each of the workflow steps, and allow the analyst to generate output data by performing processing specific to the workflow steps. The workflow can be generated and retrieved via the client browser 332. When the collection device 326 performs the steps of the workflow, it can read the raw data from the data stream located in the raw data repository 324. When the collection device 326 performs the steps of the workflow, it can generate processed data stored in the metadata directory 330 in the document repository 328; alternatively or in addition, the processed data can be stored in different locations specified by the user of the collection device 326. It can also generate audit records that can be stored in the audit log 334.

[0058] The example embodiments described herein may be executed at the client browser 332 and the collection device 326, among other locations. Figure 2 Examples of devices suitable for use as acquisition device 326 and / or client browser 332 as well as various data storage devices are depicted in FIG.

[0059] Figure 4 is a flow chart depicting exemplary logic suitable for practicing the exemplary embodiments. Figure 4 The logic depicted in can be implemented as a method performed by a suitable computing device, a non-transitory computer-readable medium storing instructions for performing the logic, and / or a computing device configured to perform the logic (among other possibilities). Figure 4Depict specific steps or processes performed in a specific order, but those of ordinary skill in the art will recognize that certain steps / processes may be performed out of order or omitted entirely. In addition, additional or different steps or processes may be added to the logic.

[0060] At block 402, a computing device may receive a description of a chemical compound. Among other possibilities, the compound may represent a peptide or a small molecule.

[0061] At block 404, the computing device may calculate one or more properties of the chemical compound described in block 402. For example, in the case of a peptide, the molecular property may represent one or more of a length normalized residue value or a van der Waals volume. In particular, in the case of a length normalized residue value, the value may be used to distinguish 3+ (and possibly other higher charge states) branches of the compound. In some embodiments, the molecular property may represent structural flexibility.

[0062] At block 406, one or more collision cross section (CCS) values ​​for the chemical compound may be predicted. The predicted CCS values ​​may represent the distribution of charge at specific locations in the chemical compound. In some cases, the charge may be present at different locations (e.g., at different times) in the chemical compound depending on the structure of the compound.

[0063] CCS values ​​can be predicted using molecular modeling or machine learning. An exemplary process for predicting CSS values ​​using molecular modeling and / or machine learning is described in U.S. Patent No. 11,226,309, entitled “Techniques for Predicting Collision Cross-Section Values,” issued on January 18, 2022.

[0064] At box 408, an error or variance can be assigned to each of the CCS values ​​predicted at box 406. The system can use the molecular properties calculated at box 404 to assign errors / variances. For example, there is a qualitative relationship between the structure and the observed prediction errors. Such a relationship is related to the location of the charge, such as whether the charge is present in one or more locations or distributed on the surface of the molecule. The location where the charge remains most of the time may affect the error / variance. Other factors, such as the flexibility of the compound structure, van der Waals radius (for peptides), or "light" molecular modeling (for small molecules) may also be factors in the error / variance determination.

[0065] When the system assigns a charge to a particular location, this assignment may be associated with a degree of uncertainty (e.g., when a charge may exist in multiple possible locations based on a machine learning process or molecular modeling). This uncertainty may affect the error or variance. In addition, when the uncertainty or error / variance exceeds a certain predetermined threshold (which may be a default value or may be user-configurable), this condition may be flagged in the output generated at block 414.

[0066] At block 410, the computing device may determine whether the compound can exhibit more than one of the CCS values. Different CCS values ​​may represent, for example, multiple possible locations of charge on the compound.

[0067] If the determination at block 410 is "no," processing may proceed to block 414 and may output the error / variance assigned at block 408. For example, the error / variance may be displayed in a GUI on a suitable display device, or may be provided to other programs or algorithms to perform calculations based on the error or variance values.

[0068] If the determination at block 410 is "yes," processing may proceed to block 412 where the computing device builds a model of the compound. When building the model, multiple different possible locations of charge on the compound may be captured and represented in the model.

[0069] For example, some embodiments may determine that a given compound may be associated with more than one CCS value, or with a CCS prediction value with more variation (due to the structure being unable to accommodate charge). If a compound can exhibit more than one CCS value, because the structure can accommodate charge at more than one position, this information may be captured / encoded when creating the model, thereby providing the ability to report more than one CCS value. Alternatively, when charge assignment is questionable, this may be flagged and reported in the output when calculating CCS values ​​(both ML and MM).

[0070] Processing may then proceed to block 410 where the error or variance may be output.

[0071] Experimental Example

[0072] In an example provided here, twenty small molecules were randomly selected from the library for detailed analysis to illustrate the concept. Five conformers using two models (root mean square deviation (RMSD) diversity or energy optimization) were created for each set of 20 structures (20 compounds with CCS prediction errors >90% percentile range (greater than) and 20 compounds with CCS prediction errors <100% percentile range) using openBabel (obabel).

[0073] Next, each conformer was energy minimized (first pass) using openBabel(obgen).

[0074] The obtained 3D structure files were converted into pdb files and the CCS values ​​were determined using the Windows version of MobCal, which proved the CCS values ​​calculated by accurate hard sphere scattering (EHS) and projection approximation (PA).

[0075] For each compound and model, the mean and standard deviation were calculated.

[0076] The standard deviation / mean (measure of structural flexibility) frequency distributions were calculated for both groups and both models.

[0077] For the protonated (top) and deprotonated (bottom) molecules, the machine learning predicted and molar calculated CCS values ​​are compared with the experimental CCS measurements and show that the errors are structure-dependent (and method-independent).

[0078] Based on the above, the chemical diversity and characteristics of the molecules in solutions at pH 2 and 12 (dependence on the ionization mode) were examined by manual and computational attempts to charge the molecules.

[0079] Isoelectric point (pI) / pKA calculations were performed for the so-called LessThan group (where there is good agreement between the predicted and experimental CCS values). The results show that in solutions at pH 2, the charge distribution is unambiguous.

[0080] Equivalents were then calculated for the MoreThan group (in which the agreement between the predicted and experimental CCS values ​​is relatively poor), which showed that the charge distribution is more ambiguous in solutions at pH 2 (charge ranges from 0 to 0.42).

[0081] All compounds were then considered (20 (LessThan) vs. 20 (MoreThan)). Charge assignments were manually classified, indicating some separation of groups - mainly those for which charges could be unambiguously assigned to structures / molecules (both manually and computationally).

[0082] When various pKa metrics are used to provide a summary of the results, the separation is less clear. It should be noted that at this stage of the analysis, the protonated and deprotonated structures were not analyzed separately.

[0083] Chemical compounds that are known to form conformers, and therefore can be considered as chemical compounds with ambiguous charge assignment, are treated in a similar manner as described above.

[0084] The results show that these molecules (Q) are clustered more closely together with compounds with larger prediction errors (MoreThan group).

[0085] A number of compounds were selected for Gaussian sum treatment (compounds with median mass and on / not on the CCS-m / z trend line of structural flexibility-standard deviation / median calculation).

[0086] Both neutral and charged conformers were generated. Interestingly, openBabel automatically assigned charges to these structures when creating conformers for a set of compounds that showed good agreement between the predicted and experimental CCS values ​​(LessThan). Therefore, charges (protons) were removed to generate neutral equivalents. For another set of compounds, indicating poor agreement between predictions and measurements (MoreThan), a tool was used to assign charges to the most likely positions by calculation. In these cases, openBabel created neutral versions of the conformer structures.

[0087] The software was used to determine the proton affinity and zero-point energy values. Intermediate calculations were used to illustrate the differences between the two sets of structures. The results show the total energy (left) and coulombic energy (right) for all compounds and ionization modes combined. Normalized total energy and coulombic energy values ​​were determined (energy values ​​divided by molecular weight equivalent).

[0088] Next, for a given set of conformers, the proton affinity values ​​were calculated using the minimum energy values ​​for the charged and neutral species.

[0089] Next, the results of the solution and gas phase calculations are compared. The left figure summarizes the overall calculations based on pKa for both structure groups. The correlation seems to exist, but can get "messy" when different charge types (protonation / deprotonation) are combined.

[0090] The final comparison considers only protonated species, excluding “outliers”, and shows, from left to right, ΔpKa (highest minus lowest), protein affinity, and ΔpKa vs. proton affinity.

[0091] The proton affinity calculations were confirmed with a higher level theoretical method (DFT Gaussian). The proton affinity values ​​calculated using ADF and DFT were correlated, with better correlations obtained for the "LessThan" group, i.e., more ambiguous results for the "MoreThan" group. The proton affinity values ​​calculated using DFT were used to determine the equivalent of the summary distribution of the proton affinity to the ΔpKa. The same data were calculated with one of the compounds removed to illustrate that the results obtained using DFT and ADF theory show similar trends.

[0092] In summary, in general, MoreThan structures are less specific in the predicted results, charge assignments in group-consistent molecular modeling and separate themselves from the group of “LessThan” molecules based on these “characteristics”.

[0093] in conclusion

[0094] The components and features of the devices described above may be implemented using any combination of discrete circuit systems, application specific integrated circuits (ASICs), logic gates, and / or single chip architectures. In addition, where appropriate, microcontrollers, programmable logic arrays, and / or microprocessors, or any combination of the foregoing, may be used to implement the features of these devices. It should be noted that hardware, firmware, and / or software elements may be collectively or individually referred to herein as "logic" or "circuitry."

[0095] It should be understood that the exemplary devices shown in the above block diagrams may represent a functional descriptive example of many possible specific implementations. Therefore, the division, omission or inclusion of block functions depicted in the drawings does not mean that the hardware components, circuits, software and / or elements used to implement these functions will necessarily be divided, omitted or included in the implementation.

[0096] At least one computer-readable storage medium may include instructions that, when executed, cause a system to perform any of the computer-implemented methods described herein.

[0097] Some embodiments may be described using the expressions "one embodiment" or "an embodiment" and their derivatives. These terms mean that a particular feature, structure, or characteristic described in conjunction with the embodiment is included in at least one embodiment. The appearance of the phrase "in one embodiment" in different places in the specification does not necessarily refer to the same embodiment. In addition, unless otherwise stated, the above-mentioned features are considered to be usable together in any combination. Therefore, any features discussed separately can be used in combination with each other, unless it is stated that these features are incompatible with each other.

[0098] The detailed description herein may be presented in terms of program processes executed on a computer or computer network with general reference to the notations and nomenclature used herein. These program descriptions and representations are used by those skilled in the art to most effectively convey the substance of their work to others skilled in the art.

[0099] A process is generally considered to be a self-consistent sequence of operations that brings about a desired result. These operations are those requiring physical manipulation of physical quantities. Although not required, these quantities usually take the form of electrical, magnetic or optical signals capable of being stored, transferred, combined, compared and otherwise manipulated. In practice, it has proven convenient at times to refer to these signals as bits, values, elements, symbols, characters, terms, numbers, etc., primarily for common reasons. It should be noted, however, that all of these and similar terms are associated with the appropriate physical quantities and are merely convenient labels applied to these quantities.

[0100] In addition, the manipulations performed are often referred to by terms such as adding or comparing, which are often associated with mental operations performed by a human operator. In any of the operations described herein that form a part of one or more embodiments, in most cases, such capabilities of a human operator are not necessary or desirable. Instead, these operations are machine operations. Useful machines for performing the operations of the various embodiments include general purpose digital computers or similar devices.

[0101] The expressions "coupled" and "connected," as well as their derivatives, may be used to describe some embodiments. These terms are not necessarily intended to be synonymous with each other. For example, the terms "connected" and / or "coupled" may be used to describe some embodiments to indicate that two or more elements are in direct physical or electrical contact with each other. However, the term "coupled" may also mean that two or more elements are not in direct contact with each other, but still cooperate or interact with each other.

[0102] Various embodiments also relate to devices or systems for performing these operations. The device may be specially constructed for the desired purpose, or it may include a general-purpose computer selectively activated or reconfigured by a computer program stored in the computer. The processes presented herein are not inherently related to a particular computer or other device. Various general-purpose machines may be used with programs written according to the teachings of this article, or it may prove convenient to construct more specialized devices to perform the desired method steps. The desired structures of various of these machines will appear in the description given.

[0103] It should be emphasized that the abstract of the present disclosure is provided so as to allow the reader to quickly determine the essence of the technical disclosure. It should be understood that the submitted abstract will not be used to interpret or limit the scope or meaning of the claims. In addition, in the aforementioned specific embodiments, it can be seen that various features can be grouped together in a single embodiment for the purpose of simplifying the present disclosure. This method of the present disclosure should not be interpreted as reflecting the intention that the claimed embodiment requires more features than the features explicitly stated in each claim. On the contrary, as reflected in the following claims, the subject matter of the present invention is less than all the features of a single disclosed embodiment. Therefore, the following claims are hereby incorporated into the specific embodiments, wherein each claim exists independently as a separate embodiment. In the appended claims, the terms "including" and "in which" are used as the colloquial English equivalents of the corresponding terms "comprising" and "wherein", respectively. In addition, the terms "first", "second", "third", etc. are used only as markers and are not intended to impose numerical requirements on their objects.

[0104] What has been described above includes examples of the disclosed architecture. Of course, it is not possible to describe every conceivable combination of components and / or methods, but one of ordinary skill in the art will recognize that many further combinations and permutations are possible. Therefore, the novel architecture is intended to encompass all such changes, modifications, and variations that fall within the spirit and scope of the appended claims.

Claims

1. A computer-implemented method, the computer-implemented method comprising: receiving a description of a chemical compound; calculating one or more molecular properties of the chemical compound; predicting a collision cross section (CCS) value of the chemical compound; as well as The one or more calculated molecular properties are used to assign an error or variance to the predicted CCS value.

2. The method of claim 1, wherein the CCS value is an assignment of charge to a specific position in the chemical compound.

3. The method of claim 1, wherein the compound is a peptide and the one or more molecular properties include one or more of length-normalized residue value or van der Waals volume. The method of claim 1 , wherein the chemical compound is a small molecule.

5. The method of claim 1, wherein the molecular property comprises structural flexibility.

6. The method according to claim 1, further comprising: determining that the compound can exhibit a plurality of CCS values, the plurality of CCS values ​​indicating a plurality of possible locations of charge on the compound; as well as A model of the chemical compound is constructed, the constructing comprising capturing the plurality of locations of the electric charge.

7. The method of claim 1, wherein the CCS value is predicted using one or more of molecular modeling or machine learning.

8. A non-transitory computer-readable medium storing instructions which, when executed by a processor, cause the processor to receiving a description of a chemical compound; calculating one or more molecular properties of the chemical compound; predicting a collision cross section (CCS) value for the chemical compound; and The one or more calculated molecular properties are used to assign an error or variance to the predicted CCS value.

9. The medium of claim 8, wherein the CCS value is a charge distribution at a specific position in the chemical compound.

10. The method of claim 1, wherein the compound is a peptide and the one or more molecular properties include one or more of length normalized residue value or van der Waals volume.

11. The medium of claim 8, wherein the chemical compound is a small molecule.

12. The medium of claim 8, wherein the molecular property comprises structural flexibility.

13. The medium of claim 8, further storing instructions for: determining that the compound is capable of exhibiting a plurality of CCS values, the plurality of CCS values ​​being indicative of a plurality of possible locations of charge on the compound; and A model of the chemical compound is constructed, the constructing comprising capturing the plurality of locations of the electric charge.

14. The medium of claim 8, wherein the CCS value is predicted using one or more of molecular modeling or machine learning.

15. A device, comprising: Hardware processor; and a non-transitory computer-readable medium storing instructions that, when executed by the processor, cause the processor to: receiving a description of a chemical compound; calculating one or more molecular properties of the chemical compound; predicting a collision cross section (CCS) value of the chemical compound; as well as The one or more calculated molecular properties are used to assign an error or variance to the predicted CCS value.

16. The apparatus of claim 15, wherein the CCS value is an assignment of charge to a specific location in the chemical compound.

17. The apparatus of claim 15, wherein the compound is a peptide and the one or more properties include one or more of length normalized residue value or van der Waals volume.

18. The device of claim 15, wherein the molecular property comprises structural flexibility.

19. The apparatus of claim 15, wherein the medium further stores instructions for: determining that the compound is capable of exhibiting a plurality of CCS values, the plurality of CCS values ​​being indicative of a plurality of possible locations of charge on the compound; and A model of the chemical compound is constructed, the constructing comprising capturing the plurality of locations of the electric charge.

20. The apparatus of claim 15, wherein the CCS value is predicted using one or more of molecular modeling or machine learning.

Images