DETAILED ACTION
Claim Status
Claims 1-14 are rejected.
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Priority
This application is a 371 of PCT/IN2021/050903, filed 09/14/2021. Receipt is acknowledged of certified copies of papers required by 37 CFR 1.55.
This application claims Foreign Priority to Republic of India application # IN202041040578 , filed 09/18/2020. Foreign Priority is acknowledged. Therefore, the effective filing date of claims 1-14 is 09/18/2020.
Information Disclosure Statement
No IDS was filed herein.
Drawings
The drawings filed on 03/16/2023 are accepted.
Claim Objections
Claim 2 objected to because of the following informalities: “the binding activity prediction system are” should be “the binding activity prediction system is”. Appropriate correction is required.
Claim 10 objected to because of the following informalities: “the pair-wise attention maps comprises” should be “the pair-wise attention maps comprise.” Appropriate correction is required.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1-14 rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claims 1 and 14 recite the limitation "the knowledge data" in line 4. There is insufficient antecedent basis for this limitation in the claim.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-14 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
In accordance with MPEP § 2106, claims found to recite statutory subject matter ( Step 1 : YES) are then analyzed to determine if the claims recite any concepts that equate to an abstract idea, law of nature or natural phenomenon (Step 2A, Prong 1). In the instant application, the claims recite the following limitations that equate to an abstract idea:
• 1. A method for predicting binding affinity between at least one of a chemical or a biological molecule and its protein target using a binding activity predicting system, wherein the method comprises, pre-processing the knowledge data of a chemical or a biological molecule and its protein targets, wherein the pre-processing comprises at least one of (i) correcting outliers, (ii) identifying missing data, (iii) determining latent relationships between different attributes of dataset to obtain a protein data, a molecule data and a binding activity data or (iv) data augmentation; converting the protein data into tokens of proteins; converting the molecule data into tokens of molecules by grouping substructures of the molecule using unique tokens; providing the tokens of molecules and the tokens of proteins to train a first machine learning model for generating a protein and molecule representation model in order to learn protein and molecule representations; processing the binding activity data for a pair of a known protein and a known molecule to convert into tokens of the known protein and tokens of known molecule respectively; generating, using the protein and molecule representation model, embeddings for the known protein and the known molecule in the tokens of known protein and the tokens of known molecules; training a second machine learning model to generate a binding activity prediction model to predict a binding affinity and to generate pairwise attention maps between amino acid residues and atoms involved in binding; predicting, using at least one of the protein and molecule representation model or the binding activity prediction model, the binding affinity of amino acid residues of a test protein and fragments of a test molecule when the test protein and test molecule is provided as an input to the at least one of the protein and molecule representation model or the binding activity prediction model; and generating, using at least one of the protein and molecule representation model or the binding activity prediction model, a pairwise attention map representing the amino acid 31 residues of the test protein and the fragment of the test molecule involved in binding.
• 3. The method as claimed in claim 1, wherein the protein data comprises pre-processing data comprising at least one of protein sequences, annotated proteins or un-annotated proteins, wherein the molecule data comprises pre-processed data of at least one of chemical compounds, biochemical compounds, chemical structures, crystal structures of chemicals or chemical reaction.
• 4. The method as claimed in claim 1, wherein the protein data is converted into the tokens of proteins by (i) annotating amino acid sequences of the protein at conserved or catalytic or binding site, (ii) predicting a secondary structure of the amino acid sequences, (iii) predicting a solvent accessibility of the amino acid sequences, and (iv) converting the amino acid sequences of the protein into the tokens of the protein.
• 5. The method as claimed in claim 1, wherein the substructures of the molecule are grouped, using at least one of a fragment type and properties prediction tool or a graph structure encoding tool, by (i) creating a set of substructures based on molecule data analysis (ii) creating one or more fragments by cleaving the molecule at the bonds of the molecule, and (iii) converting loop identifiers into the unique tokens.
• 7. The method as claimed in claim 1, wherein the molecules data comprises data in a Simplified Molecular Input Line Entry System (SMILES) format.
• 8. The method as claimed in claim 1, wherein the tokens of protein comprise information of 2 an amino acid type, amino acid annotations and properties of protein, wherein the tokens of 3 molecule comprise information of properties of fragments in the molecule and fragment 4 types.
• 9. The method as claimed in claim 1, wherein the binding activity data comprises pre- processed data of at least one of experimental observed binding data, binding assay data and observed protein-ligand complexes, wherein the binding activity data comprises data of the already proven binding affinity between proteins and molecules.
• 10. The method as claimed in claim 1, wherein the pair-wise attention maps comprises an evidence for at least one of (a) an amino acid fragment or sub-sequences of the protein which is taking part in the binding activity, (b) a set of binding residues from the protein sequence, c) a fragment of the molecule that is taking part in the activity, (d) a map of the molecule fragment to sub-sequences of the protein taking part on the activity, or (e) a map of fragments of the molecules to residues in the protein sequence.
• 11. The method as claimed in claim 1, wherein the method comprises implementing at least one of (i) one or more of traditional deterministic reasoning techniques, (ii) data-modelling using ontologies and knowledge inference rules ,and (iii) machine learning techniques, for pre-processing the protein data and the molecule data.
• 14. A system for predicting binding affinity between at least one of a chemical or a biological molecule and its protein target using a binding activity predicting system, wherein the system 3 comprises a processor that: 4 pre-processes the knowledge data of a chemical or a biological molecule and its 5 protein targets, wherein the pre-processing comprises at least one of (i) correcting outliers, (ii) identifying missing data, (iii) determining latent relationships between different attributes of dataset to obtain a protein data, a molecule data and a binding activity data or (iv) data augmentation; converts the protein data into tokens of proteins; converts the molecule data into tokens of molecules by grouping substructures of the molecule using unique tokens; provides the tokens of molecules and the tokens of proteins to train a first machine learning model for generating a protein and molecule representation model in order to learn protein and molecule representations; processes the binding activity data for a pair of a known protein and a known molecule to convert into tokens of the known protein and tokens of known molecule respectively; generates, using the protein and molecule representation model, embeddings for the known protein and the known molecule in the tokens of known protein and the tokens of known molecules; trains a second machine learning model to generate a binding activity prediction model to predict a binding affinity and to generate pairwise attention maps between amino acid residues and atoms involved in binding; predicts, using at least one of the protein and molecule representation model or the binding activity prediction model, the binding affinity of amino acid residues of a test protein and fragments of a test molecule when the test protein and test molecule is provided as an input to the at least one of the protein and molecule representation model or the binding activity prediction model; and generates, using at least one of the protein and molecule representation model or the binding activity prediction model, a pairwise attention map representing the amino acid 31 residues of the test protein and the fragment of the test molecule involved in binding.
The claims include steps for “pre-processing,” “converting,” “providing,” “processing,” “generating,” “training,” “predicting,” and “implementing.” A series of mathematical transformations are made to data which are passed to a machine learning model. The machine learning model has embodiments which could be practically performed by a human being with a pen and paper Therefore, these limitations fall under the “Mental process” and “mathematical concept” groupings of abstract ideas. While claims 12-14 recite performing some aspects of the analysis with a “processor” or “neural network”, there are no additional limitations that indicate that this analysis engine requires anything other than carrying out the recited mental process or mathematical concept in a generic computer environment. Merely reciting that a mental process is being performed in a generic computer environment does not preclude the steps from being performed practically in the human mind or with pen and paper as claimed. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then if falls within the “Mental processes” grouping of abstract ideas. As such, claims 1-14 recite an abstract idea ( Step 2A, Prong 1 : YES).
Claims found to recite a judicial exception under Step 2A, Prong 1 are then further analyzed to determine if the claims as a whole integrate the recited judicial exception into a practical application or not (Step 2A, Prong 2). This judicial exception is not integrated into a practical application because the claims do not recite an additional element that reflects an improvement to technology or applies or uses the recited judicial exception to effect a particular treatment for a condition. Specifically, the claims recite the following additional elements:
• 2. The method as claimed in claim 1, wherein the method comprises receiving the knowledge data of the chemical or the biological molecule and its protein target from a device comprising a global knowledge database, wherein the binding activity predicting system are communicatively connected to the device; and storing the knowledge data of the chemical or biological molecule and its protein target in a database of a binding activity predicting system.
• 6. The method as claimed in claim 2, wherein the global knowledge database comprises a universal protein resource (UNIPROT), a protein data bank (PDB), ZINC, ChEMBL and Binding Database (BINDINGDB).
• 12. The method as claimed in claim 1, wherein the second machine learning model is trained using the protein and molecule representation model to generate the binding activity prediction model, wherein the binding activity prediction model comprises a deep learning model or a neural network model, wherein the binding activity prediction model is trained using a supervised method.
• 13. The method as claimed in claim 1, wherein the protein and molecule representation model comprise a deep learning model or a neural network model, wherein the protein and molecule representation model is trained using an unsupervised method, wherein the unsupervised method comprises a masked language model or an autoregressive model.
There are no limitations that indicate that the claimed “processor”, “neural network,” or the formats of the provided data require anything other than generic computing systems. The limitations As such, these limitations equate to mere instructions to implement the abstract idea on a generic computer that the courts have stated does not render an abstract idea eligible in Alice Corp., 573 U.S. at 223, 110 USPQ2d at 1983. See also 573 U.S. at 224, 110 USPQ2d at 1984. Claim 2 and 6’s limitations are mere data gathering and storage, similar to presenting offers and gathering statistics, OIP Technologies, 788 F.3d at 1363, 115 USPQ2d at 1092-93. As such, claims 1-14 are directed to an abstract idea ( Step 2A, Prong 2 : NO).
Claims found to be directed to a judicial exception are then further evaluated to determine if the claims recite an inventive concept that provides significantly more than the judicial exception itself (Step 2B). The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the claims recite additional elements that equate to mere instructions to apply the recited exception in a generic way or in a generic computing environment. The instant claims recite additional elements enumerated above, in the section on step 2A.
As discussed above, there are no additional limitations to indicate that the claimed “processor” or “neural network” requires anything other than generic computer components in order to carry out the recited abstract idea in the claims. Claims that amount to nothing more than an instruction to apply the abstract idea using a generic computer do not render an abstract idea eligible. Alice Corp., 573 U.S. at 223, 110 USPQ2d at 1983. See also 573 U.S. at 224, 110 USPQ2d at 1984. The limitations of claim 2 and 6 are well-understood, routine and conventional because it is data gathering similar to presenting offers and gathering statistics, OIP Techs., 788 F.3d at 1362-63, 115 USPQ2d at 1092-93. The additional elements do not comprise an inventive concept when considered individually or as an ordered combination that transforms the claimed judicial exception into a patent-eligible application of the judicial exception. Therefore, the claims do not amount to significantly more than the judicial exception itself ( Step 2B : No). As such, claims 1-14 are not patent eligible.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-5 and 8-14 are rejected under 35 U.S.C. 103 as being unpatentable over Wallach et al. (EP3140763B1) in view of Wei et al. (WO2019191777A1), as evidenced by GeeksForGeeks (https://www.geeksforgeeks.org/nlp/autoregressive-models-in-natural-language-processing/, 2025).
Regarding claims 1 and 14, the instant application uses a set of two models, a “protein and molecule representation model” and a “binding activity prediction model” that determine representations of molecules, and calculate their binding affinity, respectively.
Wallach’s disclosure reads on the limitations for the binding activity model and the tokenization.
Wallach discloses a computer-implemented method for predicting binding affinity ([0008] - [0009]) that includes “storing records reflecting input data (e.g., molecule data, protein data, affinity data & transformations data), an analyzer having a data encoder module and a predictive model module. The analyzer receives inputs from the various databases and/or remote systems and provides them to the data encoder module that encodes selected or defined biological data to one or more geometric data representations.” ([0041] - [0051])
The data encoder module has many embodiments discussed in the specification, and the authors state that many kinds of encoding can be used depending on the model type, which could include tokenization ([0060]-[0065]).
The predictive model of Wallach reads on the binding activity representation model. “The predictive model module may further be configured to be trained over time as more inputs are processed.” ([0033] - [0039]) “The analyzer may then apply the predictive model to the information received and the analyzer may return one or more outputs. The outputs provided from the system may vary, and may range from numerical scores to lists of molecules selected from the set of molecules to be analyzed which have a score greater than a pre-determined threshold. The output may be an indicator of binding affinity for one or more molecules to one or more target proteins (or types of protein).” ([0100] - [0112])
A pairwise map is a possible output in Wallach, ([0046]).
Wallach is silent to: “pre-processes the knowledge data of a chemical or a biological molecule and its protein targets, wherein the pre-processing comprises at least one of (i) correcting outliers, (ii) identifying missing data, (iii) determining latent relationships between different attributes of dataset to obtain a protein data, a molecule data and a binding activity data or (iv) data augmentation.”
Wallach is also silent as to the protein and molecule representation model.
However, Wei discloses a method of predicting binding affinity for a protein-ligand or protein-protein complex using element interactive curvatures and a trained machine learning model. (abstract, [0048]) The method further comprises a step of identifying a set of compounds based on one or more of a defined target clinical application, a set of desired characteristics, and a defined class of compounds, pre-processing each compound of the set of compounds to generate respective sets of feature data. Processing the sets of feature data with one or more trained machine learning models to produce predicted characteristic values for each compound of the set of compounds for each of the set of desired characteristics ([0011] - [0020]). The pre-processing of the set of compounds may include performing persistent homology and/or ESPH calculations for each compound of the set of compounds, calculating barcodes (e.g., TF/ESTF/ASTF/EH barcodes) for each compound, calculating BBR for each compound, and/or calculating/identifying auxiliary features for each compound. The pre-processing may further include the generation of feature data using feature vectors calculated based on the barcodes, the BBR, and/or the auxiliary features. It should be understood that the pre-processing tasks performed may change depending on the desired characteristics and the trained machine learning algorithms/models being used. ([0330])
Wei also discloses that machine learning may be used in its step of using “DG-GDA” to build 3D representations of proteins, which reads on the protein and molecule representation model trained on geometric protein data. ([0295)]
Regarding claims 2 and 3, Wallach states that “As depicted, the system includes an analyzer 10. The analyzer 10 may be linked to one or more data bases 12 that store records reflecting input data (e.g., biological data). These databases, may include, data bases such as, molecule database 12a, protein database 12b, affinity database 12c, transformations database 12d. The various databases are collectively referred to as databases 12. Alternatively or in conjunction, the system may obtain biological data from one or more remote systems 13 that may also have additional biological data.”
Regarding claim 4, Wei states that the input of data into the machine learning model (tokenization) includes annotating the binding site ([0108]) and predicting a secondary structure ([0115]). Wei provides a suggestion to use a QSPR model to predict aqueous solubility and adding this to the model, and states that the QSPR model includes solvent accessible area. ([0147]). The machine learning model receives and processes these features (fig. 4). [0329] shows an embodiment as an RNN, which would require tokenization of the data to receive it.
Regarding claim 5, Wei’s method breaks down a molecule into fragments and computes their geometry ([0010]). Loop identifiers are part of the features (ESTF) of Wei ([0088]).
Regarding claim 8, Wei writes: “[0123] lt should be understood the features described here are intended to be illustrative and not limiting. Other applicable features may be calculated and included in the feature data provided as inputs to the machine learning algorithm/model. For example, such auxiliary features may include geometric descriptors containing surface area and/or van der Waals interactions, electrostatics descriptors such as atomic partial charge, Coulomb interaction, and atomic electrostatic solvation energy, neighborhood amino acid composition, predicted pKa shifts, sequence descriptors describing secondary structure and residue conversion score collected from Position-specific scoring matrices (PSSM).”
Regarding claim 9, Wei uses binding data from protein data bank in an embodiment ([0248)]. The binding data is made up of proven binding affinity data ([0107]).
Regarding claim 10, claim 1 of Wei discloses displaying compounds (fragments) that are taking paqrt in the binding activity under investigation.
Regarding claims 11, the pre-processing takes place by deterministic mathematical reasoning ([0328]).
Regarding claim 12, both machine learning models can be trained with deep learning, and supervised learning is used in some embodiments ([329]).
Regarding claim 13, RNNs are disclosed as a possible model ([329]), which are fundamentally autoregressive, as evidenced by GeeksForGeeks (https://www.geeksforgeeks.org/nlp/autoregressive-models-in-natural-language-processing/, 2025) (see § Popular Autoregressive Models in NLP, #1).
Regarding claims 1-5 and 8-14, an invention would have been prima facie obvious to one of ordinary
skill in the art at the time of the effective filing date of the invention if some teaching, suggestion, or motivation in the prior art would have led that person to combine the prior art teachings to arrive at the claimed invention. There is a teaching to use pre-processing in the text of Wei in order to conform to the desired characteristics of the target binding affinity model ([0330]). There would be a
reasonable expectation of success in making this combination to a person of ordinary skill in the art, as both Wallach and Wei are binding affinity prediction methods. Therefore, it would have been prima facie obvious to one of ordinary skill in the art at the time to modify the method of Wallach by including the pre-processing of Wei, in order to better conform to the desired characteristics of the target binding affinity model ([0330]).
Claims 6-7 are rejected under 35 U.S.C. 103 as being unpatentable over Wallach and Wei as evidenced by Geeks4Geeks as applied to claims 1-5, 7-14 above, and further in view of Uniprot, ChEMBL StackExchange Thread (https://www.biostars.org/p/439986/?__cf_chl_f_tk=j3qQuo_lx.exNbsSFZdHT017Diigws.ASSuW0mktNQU-1782752627-1.0.1.1-a__RfzytGhy.AJOUQnRUjs4STQUznv0DYpCytipgiis, 2020), BINDINGDB About page (https://www.bindingdb.org/rwd/bind/aboutus.jsp, 2018) and Irwin et al. (https://pubs.acs.org/doi/10.1021/ci3001277, 2012).
Regarding claim 6, Wei uses binding data from protein data bank in an embodiment ([0248)]. Uniprot, ChEMBL (https://www.biostars.org/p/439986/?__cf_chl_f_tk=j3qQuo_lx.exNbsSFZdHT017Diigws.ASSuW0mktNQU-1782752627-1.0.1.1-a__RfzytGhy.AJOUQnRUjs4STQUznv0DYpCytipgiis, 2020), BINDINGDB (https://www.bindingdb.org/rwd/bind/aboutus.jsp, 2018) and Irwin’s ZINC (https://pubs.acs.org/doi/10.1021/ci3001277, 2012) are public databases.
Regarding claim 7, Irwin’s ZINC database uses SMILES formatted data (fig. 4 and description).
Regarding claims 6 and 7, under rationale D of MPEP 2143, an invention would have been prima facie obvious to one of ordinary skill in the art at the time of the effective filing date of the invention if it applies a known technique to a known device to yield predictable results. Wei uses data from the protein data bank to predict binding affinity ([0052], [0279]). Uniprot, ChemBL, (Uniprot/ChemBL reference [0001]) and BINDINGDB (BINDINGDB abstract) are all protein databases, and ZINC is a database of molecules that ligate to proteins (ZINC abstract), which make them applicable to the binding affinity prediction method. An ordinary artisan would recognize that applying the data from these databases would bring about predictable results similar to the PDB results, and that combining these databases would result in an improved system from the version with only PDB because it would contain more data for training. Therefore, the invention is prima facie obvious.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to GRACELYN M HILL whose telephone number is (571)272-9871. The examiner can normally be reached Monday-Friday 8:30-5pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Olivia M. Wise can be reached at 571-272-2249. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/G.M.H./Examiner, Art Unit 1685
/OLIVIA M. WISE/Supervisory Patent Examiner, Art Unit 1685
Prosecution Insights