DETAILED ACTION
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 .
Election/Restrictions
Upon further consideration the restriction dated 6/11/2025 is withdrawn. Pursuant to the procedures set forth in MPEP § 821.04(B), claims 28-29, previously withdrawn from consideration (in Applicant’s response received 10/07/2025) as a result of a restriction requirement, are hereby rejoined and fully examined for patentability under 37 CFR 1.104, as presented in the amended claims dated 1/24/2022.
Because all claims previously withdrawn from consideration under 37 CFR 1.142 have been rejoined, the restriction requirement as set forth in the Office action mailed on 6/11/2025 is hereby withdrawn. In view of the withdrawal of the restriction requirement as to the rejoined inventions, applicant(s) are advised that if any claim presented in a divisional application is anticipated by, or includes all the limitations of, a claim that is allowable in the present application, such claim may be subject to provisional statutory and/or nonstatutory double patenting rejections over the claims of the instant application. Once the restriction requirement is withdrawn, the provisions of 35 U.S.C. 121 are no longer applicable. See In re Ziegler, 443 F.2d 1211, 1215, 170 USPQ 129, 131-32 (CCPA 1971). See also MPEP § 804.01.
Status of Claims
Claims 1-4, 7-10, 12-17, 19-23, and 26-29 pending and examined on the merits.
Claims 5-6, 11, 18, and 24-25 cancelled.
Priority
The instant application filed on 11/9/2021 is a 371 national stage entry of PCT/GB2020/051143 having an international filing date of 5/11/2020, and claims the benefit of foreign priority to Application No. GB1906566.3 filed on 5/9/2019. Thus, the effective filing date of the claims is 5/9/2019.
The applicant is reminded that amendments to the claims and specification must comply with 35 U.S.C. § 120 and 37 C.F.R. § 1.121 to maintain priority to an earlier-filed application. Claim amendments may impact the effective filing date if new subject matter is introduced that lacks support in the originally filed disclosure. If an amendment adds limitations that were not adequately described in the parent application, the claim may no longer be entitled to the priority date of the earlier filing.
Information Disclosure Statement
The information disclosure statements (IDS) filed on 11/9/2021 and 2/16/2023 have been entered and considered. A signed copy of the corresponding 1449 forms have been included with this Office action.
The listing of references in the specification is not a proper information disclosure statement.
37 CFR 1.98(b) requires a list of all patents, publications, or other information submitted for
consideration by the Office, and MPEP § 609.04(a) states, "the list may not be incorporated into the
specification but must be submitted in a separate paper." Therefore, unless the references have been
cited by the examiner on form PTO-892, they have not been considered.
Specification
The disclosure is objected to because of the following informalities:
The disclosure is objected to because it contains an embedded hyperlink and/or other form of browser-executable code at least on pages 35-36, 39, 41, 43-45, and 49-51. Applicant is required to delete the embedded hyperlink and/or other form of browser-executable code; references to websites should be limited to the top-level domain name without any prefix such as http:// or other browser-executable code. See MPEP § 608.01.
Appropriate correction is required.
Claim Objections
Claim 1 objected to because of the following informalities: lines 5-6, "at least 104 sequence variants" should read "at least 10^4 sequence variants", per page 1 of the instant specification.
Claim 2 objected to because of the following informalities: line 9, "corresponding to a at least one" should read "corresponding to at least one".
Claim 20 objected to because of the following informalities: line 11, "wherein each fitness scores" should read "wherein each fitness score".
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 1-4, 7-10, 12-17, 19-23, and 26-29 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 28 attempt to claim a process without setting forth any steps involved in the process. Claim 1 recites "a library testing step, in which the sequence variants are tested in parallel, for the one or more desired properties", which has no steps for how the library testing is to be performed. Therefore, the claim is indefinite because it merely recites a use without any active, positive steps delimiting how this use is actually practiced similar to the findings in Ex parte Erlich, 3 USPQ2d 1011 (Bd. Pat. App. & Inter. 1986). However, to further prosecution, the limitation is interpreted as comprising at least one of the "display technologies" described in the specification from page 25 line 10 through page 28 line 15 in order to test the synthesized library of nucleic acids for the one or more desired properties.
Claim 2 recites "a library assembly step" (page 1 lines 22-23) and "assembling each of the plurality of first and at least one further nucleic acid molecules to form the nucleic acid library, each variant in the library comprising a first variable part and at least one further part" (page 2 lines 13-15). It is not clear if "assemble" is referring to a dry lab (compiling the list of nucleic acid molecules) or wet lab (physical synthesis of each nucleic acid molecule of the library) step. To further prosecution, the limitation is interpreted as a step of "physically synthesizing each designed nucleic acid molecule, each of the plurality of first and at least one further nucleic acid molecules to form the nucleic acid library, each variant in the library comprising a first variable part and at least one further part", as illustrated by Figure 1, and described in the specification on pages 18-20.
Claim 8 recites "wherein including random variability comprises" in lines 4-5. There is insufficient antecedent basis for “random variability” in the claim, as this term is not in claim 1 from which this claim depends. However, "random variability" is mentioned in claim 7. Therefore, to further prosecution, claim 8 is interpreted as depending from claim 7 instead of claim 1.
Claim 13 recites "producing the protein library" in line 7. There is insufficient antecedent basis for “the protein library” in the claim, as this term is not in claim 1 from which this claim depends. However, "a protein library" is first mentioned in claim 12. Therefore, to further prosecution, claim 13 is interpreted as depending from claim 12 instead of claim 1.
Claim 14 recites "producing the protein library" in line 12. There is insufficient antecedent basis for “the protein library” in the claim, as this term is not in claim 1 from which this claim depends. However, "a protein library" is first mentioned in claim 12. Therefore, to further prosecution, claim 14 is interpreted as depending from claim 12 instead of claim 1.
Claim 15 recites "separating the protein library into at least 2 samples depending on the results of the one or more assays" in lines 18-20. It is not clear what result of the one or more assays would trigger the separation of the protein library into at least 2 samples. It is however clear that the invention is concerned with identifying variants effect on a "desired property", whether that be an improvement or a degradation of said property. Therefore, the result of the assay on which the separation depends upon will be the desired property as identified by the one or more assays being run on the sample. Additionally, there is insufficient antecedent basis for “the protein library” in the claim, as this term is not in claim 1 from which this claim depends. However, "a protein library" is first mentioned in claim 12. Therefore, to further prosecution: claim 15 is interpreted as depending from claim 12 instead of claim 1; and the separation of the protein library into at least 2 samples occurs when a desired property is identified by the one or more assays.
Claim 16 recites "aligning the sequences obtained by sequencing". There is insufficient antecedent basis for "sequences obtained by sequencing" in the claim, or in claim 1 from which claim 16 depends. However, there is a sequencing step in claim 15. Therefore, to further prosecution, claim 16 is interpreted as depending from claim 15 instead of claim 1.
Claim 21 recites "the one or more fitness scores associated with each sequence variant depends on the number of times that each sequence appears in a first sample and the number of times that each sequence appears in a second sample". It is not clear whether the intent of the limitation is for an additional attribute of how the fitness score is calculated, or if the intention is to simply add a filter for "true reads" as described on page 9 lines 12-14 of the specification: "a fitness score is only calculated for a sequence variant if the sequence appears at least one in each of the first and second samples. This may be useful to exclude sequences that appear due to mistakes in the sequencing process and are not 'true reads'." To further prosecution, the limitation is interpreted as a step for filtering true reads or variants by requiring that the variant will not be assigned a fitness score unless the associated reads for the variant are present in both samples at least one time as determined by sequence read alignment.
All other claims depend from either claim 1 or 28, therefore are also rejected under 35 U.S.C. 112(b) 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.
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 1-4, 7-10, 12-17, 19-23, and 26-29 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea of a mental process, a mathematical concept, organizing human activity, or a law of nature or natural phenomenon 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:
Claim 1: “a library design step, in which a nucleic acid library comprising at least 104 sequence variants is designed, wherein each sequence variant comprises a coding sequence for a protein and each sequence variant comprises at least one constant region and at least one variable region, wherein one or more constant regions are common to all sequence variants within the library, and the one or more variable regions are not common to all sequence variants within the library” provides an evaluation (designing a nucleic acid library to specific parameters) that may be performed in the human mind and is therefore considered a mental process, which is an abstract idea.
“the sequence variants are each assigned a fitness score based at least in part on the result of the library testing step” provides an evaluation (assigning a score based on a result involves evaluating results) that may be performed in the human mind and is therefore considered a mental process, which is an abstract idea.
“a machine learning algorithm uses the fitness score of each of the sequence variants to train a model to predict the fitness score for new sequence variants” provides a mathematical calculation (using the fitness scores with label data [continuous variables between 0 and 1 according to specification page 5] to train "black box" neural network classifiers or "white box" machine learning algorithms [page 32] involves mathematical calculations) that is considered a mathematical concept, which is an abstract idea.
Claim 7: “designing at least one of the one or more variable regions to include random variability in at least one position, optionally wherein the library design step (a) comprises designing at least one of the one or more variable regions to include random variability in one or more specific positions of the at least one variable region” provides an evaluation (designing a nucleic acid library to specific parameters) that may be performed in the human mind and is therefore considered a mental process, which is an abstract idea.
Claim 9: “selecting a nucleic acid sequence encoding for a protein that has at least one of the one or more desired properties” provides an evaluation (selecting a sequence involves evaluating desired protein properties) that may be performed in the human mind and is therefore considered a mental process, which is an abstract idea.
“identifying one or more regions of the sequence where variability is expected to result in an improvement” provides an evaluation (identifying regions of the sequence where variability might result in an improvement in desired properties) that may be performed in the human mind and is therefore considered a mental process, which is an abstract idea.
“defining the one or more variable parts to include the one or more regions of the sequence where variability is expected to result in an improvement” provides an evaluation (defining regions involves making selections based on evaluations) that may be performed in the human mind and is therefore considered a mental process, which is an abstract idea.
Claim 10: “identifying one or more regions of the sequence where variability is expected to be detrimental to the integrity of the protein and /or to at least one of the one or more desired properties” provides an evaluation (identifying regions of the sequence where variability might result in a degradation of desired properties) that may be performed in the human mind and is therefore considered a mental process, which is an abstract idea.
“defining one or more of the one or more constant regions to include the one or more regions of the sequence where variability is expected to be detrimental” provides an evaluation (defining regions involves making selections based on evaluations) that may be performed in the human mind and is therefore considered a mental process, which is an abstract idea.
Claim 15: “separating the protein library into at least 2 samples depending on the results of the one or more assays” provides an evaluation (performing an action based on a result involves evaluation of results) that may be performed in the human mind and is therefore considered a mental process, which is an abstract idea.
Claim 16: “aligning the sequences obtained by sequencing with the sequences designed in step (a)” provides a comparison (aligning sequences involves comparison of strings) that may be performed in the human mind and is therefore considered a mental process, which is an abstract idea.
“quantifying the number of times that each sequence appears in each sample” provides a mathematical calculation (quantifying the number of times a sequence appears in a sample involves arithmetic) that is considered a mathematical concept, which is an abstract idea.
Claim 20: “training a plurality of machine learning algorithms, wherein each machine learning algorithm is trained to predict at least one of the plurality of fitness scores for new sequence variants” provides a mathematical calculation (training machine learning algorithms involves mathematical calculations) that is considered a mathematical concept, which is an abstract idea.
Claim 21: “the one or more fitness scores associated with each sequence variant depends on the number of times that each sequence appears in a first sample and the number of times that each sequence appears in a second sample” provides an evaluation (assessing sequence alignments and counts before calculating a fitness score) that may be performed in the human mind and is therefore considered a mental process, which is an abstract idea.
These recitations are similar to the concepts of collecting information, analyzing it, and displaying certain results of the collection and analysis in Electric Power Group, LLC, v. Alstom (830 F.3d 1350, 119 USPQ2d 1739 (Fed. Cir. 2016)), organizing and manipulating information through mathematical correlations in Digitech Image Techs., LLC v Electronics for Imaging, Inc. (758 F.3d 1344, 111 U.S.P.Q.2d 1717 (Fed. Cir. 2014)) and comparing information regarding a sample or test to a control or target data in Univ. of Utah Research Found. v. Ambry Genetics Corp. (774 F.3d 755, 113 U.S.P.Q.2d 1241 (Fed. Cir. 2014)) and Association for Molecular Pathology v. USPTO (689 F.3d 1303, 103 U.S.P.Q.2d 1681 (Fed. Cir. 2012)) that the courts have identified as concepts that can be practically performed in the human mind or are mathematical relationships. Therefore, these limitations fall under the “Mental process” and “Mathematical concepts” groupings of abstract ideas. Additionally, while claims 28-29 recite performing some aspects of the analysis on “a processor adapted to implement the method of claim 1”, there are no additional limitations that indicate that this requires anything other than carrying out the recited mental processes or mathematical concepts 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 it falls within the “Mental processes” grouping of abstract ideas. As such, claims 1-4, 7-10, 12-17, 19-23, and 26-29 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). The judicial exceptions listed above are not integrated into a practical application because the claims do not recite an additional element or elements that reflects an improvement to technology. Specifically, the claims recite the following additional elements:
Claim 1: “a library testing step, in which the sequence variants are tested in parallel, for the one or more desired properties” provides insignificant extra-solution activities (testing nucleic acid libraries in parallel using known methods is a pre-solution activity involving sample manipulation steps) that do not serve to integrate the judicial exceptions into a practical application.
“the machine learning model trained in step (c) is used to design a new library of sequence variants with an improved distribution of fitness scores” provides insignificant extra-solution activities (using a model for library design is a pre- and post-solution activity involving data gathering and manipulation steps) that do not serve to integrate the judicial exceptions into a practical application.
Claim 2: “providing a first plurality of nucleic acid molecules corresponding to a first variable part of the sequence variants in the library, comprising one or more variable regions, and wherein the first plurality of nucleic acid molecules comprises variants of the one or more variable regions” provides insignificant extra-solution activities (providing sequence data is a pre-solution activity involving data gathering steps) that do not serve to integrate the judicial exceptions into a practical application.
“physically synthesizing each designed nucleic acid molecule” provides insignificant extra-solution activities (synthesizing nucleic acids is a pre-solution activity involving sample manipulation steps) that do not serve to integrate the judicial exceptions into a practical application.
Claim 4: “synthesizing a second DNA strand by single primer extension to form double stranded DNA” provides insignificant extra-solution activities (synthesizing nucleic acids is a pre-solution activity involving sample manipulation steps) that do not serve to integrate the judicial exceptions into a practical application.
Claim 12: “a step (a) of producing the proteins encoded by each sequence variant of the nucleic acid library to obtain a protein library, wherein the library testing step (b) comprises subjecting the protein library to one or more assays to test for the one or more desired properties” provides insignificant extra-solution activities (producing proteins of a sequence library and assaying them are a pre-solution activities involving sample manipulation steps) that do not serve to integrate the judicial exceptions into a practical application.
Claim 13: “transcribing and translating the DNA library, wherein translating the library comprises synthesising RNA-polypeptide fusion molecules each comprising an RNA sequence variant bound to the protein that it encodes” provides insignificant extra-solution activities (producing proteins of a sequence library using RNA-polypeptide fusion molecules is a pre-solution activity involving sample manipulation steps) that do not serve to integrate the judicial exceptions into a practical application.
Claim 14: “transcribing and translating the DNA library, wherein translating the library comprises propagating phage that display a coat protein-polypeptide fusion, wherein the polypeptide fused to the coat protein corresponds to a sequence variant of the DNA library” provides insignificant extra-solution activities (producing proteins of a sequence library using RNA-polypeptide fusion molecules is a pre-solution activity involving sample manipulation steps) that do not serve to integrate the judicial exceptions into a practical application.
Claim 15: “separating the protein library into at least 2 samples [], and sequencing the nucleic acids present in at least one of the at least 2 samples” provides insignificant extra-solution activities (separating a protein library into multiple samples and sequencing them is a pre-solution activity involving sample manipulation steps) that do not serve to integrate the judicial exceptions into a practical application.
Claim 19: “incubating the protein library with the specific target immobilised on a surface and separating the protein library into a sample that is bound to the surface and a sample that is not bound to the surface” provides insignificant extra-solution activities (running an immobilization assay is a pre-solution activity involving sample manipulation steps) that do not serve to integrate the judicial exceptions into a practical application.
Claim 23: “the machine learning model trained in step (c) is used to design a new library of sequence variants by iteratively optimising a library of sequence variants in silico, optionally wherein the library of sequence variants is iteratively optimised using a genetic algorithm” provides insignificant extra-solution activities (using a model for library design and optimization is a pre- and post-solution activity involving data gathering and manipulation steps) that do not serve to integrate the judicial exceptions into a practical application.
Claim 28: “a processor adapted to implement the method of claim 1” provides insignificant extra-solution activities (running instructions on generic computer components) that do not serve to integrate the judicial exceptions into a practical application.
The steps for using models and providing sequence data; and synthesizing, testing/assaying, separating, and sequencing libraries are insignificant extra-solution activities that do not serve to integrate the recited judicial exceptions into a practical application because they are pre- and post-solution activities involving data gathering, data manipulation, and sample manipulation steps (see MPEP 2106.04(d)(2)). Furthermore, the limitations regarding implementing program instructions do not indicate that they require anything other than mere instructions to implement the abstract idea in a generic way or in a generic computing environment. As such, this limitation equates 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. Therefore, claims 1-4, 7-10, 12-17, 19-23, and 26-29 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 are insignificant extra-solution activities that do not serve to integrate the recited judicial exceptions into a practical application, or equate to mere instructions to apply the recited exception in a generic way or in a generic computing environment.
As discussed above, there are no additional elements to indicate that the claimed “processor adapted to implement the method of claim 1” 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. MPEP 2106.05(f) discloses that mere instructions to apply the judicial exception cannot provide an inventive concept to the claims. Additionally, the limitations for using models and providing sequence data; and synthesizing, testing/assaying, separating, and sequencing libraries are insignificant extra-solution activities that do not serve to integrate the recited judicial exceptions into a practical application. Furthermore, no inventive concept is claimed by these limitations as they are well-understood, routine, and conventional.
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 1-4, 7-10, 12-17, 19-23, and 26-29 are not patent eligible.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
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 1-4, 7-10, 12-17, 19-20, 22-23, and 26-29 rejected under 35 U.S.C. 103 as being unpatentable over Baynes et al. (US-20110160071) in view of Gustafsson et al. (US-20040161796).
Regarding claim 1, Baynes teaches a method for producing a protein having one or more desired properties (Para.0002 "Methods and compositions of the invention relate to novel proteins, protein variant libraries and methods of designing and using the same. More particularly, methods and compositions of the invention relate to novel protein variants that exhibit a desired characteristic").
Baynes also teaches step (a) a library design step, in which a nucleic acid library comprising at least 10^4 sequence variants is designed, wherein each sequence variant comprises a coding sequence for a protein and each sequence variant comprises at least one constant region and at least one variable region, wherein one or more constant regions are common to all sequence variants within the library, and the one or more variable regions are not common to all sequence variants within the library (Para.0132 "Practitioners have a desire to synthesize and test more than about 10 of their in silico designs, perhaps 100 to 1000 or even 10000 proteins instead, to avoid missing possible solutions to the design problem due to only a slight error in the model", para.0253 "Each variable region may include between about 5 and about 10,000 different variants (e.g., about 10, about 50, about 100, about 1,000 or more). However, fewer or more variants may be included in a variable region. According to the invention, the theoretical final number of variants will be the product of the number of variants in each variable region that are combined together to form the final library. By assembling a plurality of relatively short variable regions each with relatively few variants, a relatively large number of final variants may be generated. []. one or more constant regions may be identified or selected (e.g., between variable regions) [] each variable region is separated by a constant region", and para.0259 "Each fragment represent a pool of variants containing one or more varied bases within the variable region and sequences that are common (identical) among the variants within the pool of fragments. For example, a variable region (e.g., VI) may encode a peptide that corresponds to a defined motif of a protein, where a set of residues are selected to be varied for altered function, stability and/or structure, etc. The adjacent constant regions represent sequences that are identical among the variants of the particular pool of oligonucleotides. Therefore, a constant region is at least one base, but preferably more (e.g., about 2, 3, 4, 5, 6, 7, 8, 9, 10, 10-100, 100-1,000, or more than 1,000)").
Baynes also teaches step (b) a library testing step, in which the sequence variants are tested in parallel, for the one or more desired properties (Para.0030 "the system further includes a testing module for testing the fabricated specific construct against a predetermined criterion" and para.0099 "To validate the improvement of properties due to a pre-filtering strategy, parallel DNA libraries may be generated initially with and without the theoretical pre-filtering step. Randomly selected members of pre-filtered and unfiltered libraries may then be translated into protein and tested for the property under investigation. In addition, in-vitro selections may be performed under identical conditions for pre-filtered and unfiltered libraries, and the properties of the selected proteins from each may be compared").
Baynes also teaches an iterative in silico design process (Para.0133 "In silico designs can be made to produce a library of constructs that can serve as a pool or plural separate species that can be tested or selected for a good candidate, or can serve as a starting places for other purposeful design iterations or for evolutionary techniques utilizing random mutagenesis. A screen or selection can be applied to the pool, and if necessary, the process (starting from design or another library expansion) can be iterated").
Baynes does not explicitly teach: step (c) a learning step, in which the sequence variants are each assigned a fitness score based at least in part on the result of the library testing step, and a machine learning algorithm uses the fitness score of each of the sequence variants to train a model to predict the fitness score for new sequence variants; or the machine learning model trained in step (c) is used to design a new library of sequence variants with an improved distribution of fitness scores.
However, Gustafsson teaches step (c) a learning step, in which the sequence variants are each assigned a fitness score based at least in part on the result of the library testing step, and a machine learning algorithm uses the fitness score of each of the sequence variants to train a model to predict the fitness score for new sequence variants (Para.0102 "Examples of the mathematical/logical form of models include linear and non-linear mathematical expressions of various orders, neural networks, classification and regression trees/graphs, clustering approaches, recursive partitioning, support vector machines, and the like" and para.0154 "The phrase "most suitable for artificial evolution" refers to those members of the variant population that lie at least proximal to a Pareto front, e.g., when the variants are scored (e.g., screened or selected) and plotted for desired objectives. These variants are generally the most suitable for artificial evolution, because they are not dominated by other variants (or at least most other variants) in at least one of the desired objectives").
Therefore, it would have been obvious to one of ordinary skill in the art as of the effective filing date of the claimed invention to modify the methods of Baynes as taught by Gustafsson in order to develop a model for protein activity versus sequence information (para.0103 "Models are developed from a training set of activity versus sequence information to provide the mathematical/logical relationship between activity and sequence. This relationship is typically validated prior to use for predicting activity of new sequences or residue importance"). One skilled in the art would have a reasonable expectation of success because both methods are concerned with identifying functional biomolecules using an iterative design/test/model/update approach.
Gustafsson also teaches the machine learning model trained in step (c) is used to design a new library of sequence variants with an improved distribution of fitness scores (Para.0121 "The rank ordered list of regression coefficients can be used to construct a new library of protein variants that is optimized with respect to a desired activity (i.e., improved fitness)").
Regarding claim 2, Baynes in view of Gustafsson teach the methods of Claim 1 on which this claim depends/these claims depend, respectively. Baynes also teaches a step (a’) a library assembly step, comprising: providing a first plurality of nucleic acid molecules corresponding to a first variable part of the sequence variants in the library, comprising one or more variable regions, and wherein the first plurality of nucleic acid molecules comprises variants of the one or more variable regions (para.0253 "Each variable region may include between about 5 and about 10,000 different variants").
Baynes also teaches at least one further plurality of nucleic acid molecules corresponding to a at least one constant part of the sequence variants in the library, each constant part comprising a constant region and no variable region, wherein the at least one further plurality of nucleic acid molecules are substantially identical (para.0259 "Each fragment represent a pool of variants containing one or more varied bases within the variable region and sequences that are common (identical) among the variants within the pool of fragments").
Gustafsson teaches physically synthesizing each designed nucleic acid molecule, each of the plurality of first and at least one further nucleic acid molecules to form the nucleic acid library, each variant in the library comprising a first variable part and at least one further part (Para.0159 "the methods further include synthesizing polynucleotide or polypeptide sequence variants that correspond to members of the set of biopolymer character string variants identified in step B4").
Regarding claims 3 and 4, Baynes in view of Gustafsson teach the methods of Claims 1 and 2 on which this claim depends/these claims depend, respectively. Baynes also teaches: the library design step (a) utilizes USER assembly, Darwin assembly and/or inverse PCR; and the nucleic acid molecules corresponding to each of the one or more variable parts are provided as single stranded DNA, optionally wherein providing a plurality of nucleic acid molecules corresponding to the variants of one or more variable parts comprises synthesizing a second DNA strand by single primer extension to form double stranded DNA (Para.0124 "assembly reactions may be performed using assembly nucleic acids that have not been amplified (e.g., assembly oligonucleotides that were synthesized and released from an array without an amplification step). In some embodiments, a plurality of non-amplified overlapping nucleic acids may be assembled to generate one variant sequence for a library. This variant fragment may be amplified. In some embodiments, this variant fragment may be amplified using one or more universal primers if the flanking assembly nucleic acids have sequences (e.g., sequences that may need to be removed) that are complementary to the universal primers").
Regarding claim 7, Baynes in view of Gustafsson teach the methods of Claim 1 on which this claim depends/these claims depend. Baynes also teaches the library design step (a) comprises designing at least one of the one or more variable regions to include random variability in at least one position (Para.0133 "In silico designs can be made to produce a library of constructs that can serve as a pool or plural separate species that can be tested or selected for a good candidate, or can serve as a starting places for other purposeful design iterations or for evolutionary techniques utilizing random mutagenesis").
Regarding claim 8, Baynes in view of Gustafsson teach the methods of Claim 7 on which this claim depends/these claims depend. Baynes also teaches including random variability comprises constraining the variability to sequences that correspond to a DNA codon (Para.0197 "a target nucleic acid may include a functional sequence (e.g., a protein binding sequence, a regulatory sequence, a sequence encoding a functional protein, etc., or any combination thereof)", a functional protein being one assembled from a mature RNA (i.e. comprised of coding portions of spliced exons where codons are found).
Regarding claim 9, Baynes in view of Gustafsson teach the methods of Claim 1 on which this claim depends/these claims depend. Baynes also teaches the library design step (a) comprises: selecting a nucleic acid sequence encoding for a protein that has at least one of the one or more desired properties, and automatically identifying one or more regions of the sequence, and defining the one or more variable parts where variability is expected to result in an improvement of the at least one of the one or more desired properties and/or acquisition of at least one of the one or more desired properties (Para.0324 "It should be appreciated that the building blocks may be selected in any suitable manner, e.g. specified by a designer (or any other user), selected automatically from a data repository or otherwise. It should also be appreciated that the desired construct and/or construct building blocks may be divided into any suitable (smaller) building blocks (e.g., molecular segments), depending on the specification and properties, structure and other features relating to the construct and/or construct building blocks").
Regarding claim 10, Baynes in view of Gustafsson teach the methods of Claim 1 on which this claim depends/these claims depend. Baynes also teaches the library design step (a) further comprises: identifying one or more regions of the sequence where variability is expected to be detrimental to the integrity of the protein and /or to at least one of the one or more desired properties; and defining one or more of the one or more constant regions to include the one or more regions of the sequence where variability is expected to be detrimental to the integrity of the protein and /or to at least one of the one or more desired properties (Para.0017 "methods of the invention are useful for screening nucleic acid sequences that are candidates for inclusion in an expression library and identifying those sequences that encode polypeptides with one or more undesirable properties (e.g., poor solubility, high immunogenicity, low stability, etc.)").
Regarding claim 12, Baynes in view of Gustafsson teach the methods of Claim 1 on which this claim depends/these claims depend. Baynes also teaches a step (a) of producing the proteins encoded by each sequence variant of the nucleic acid library to obtain a protein library, wherein the library testing step (b) comprises subjecting the protein library to one or more assays to test for the one or more desired properties (para.0099 "To validate the improvement of properties due to a pre-filtering strategy, parallel DNA libraries may be generated initially with and without the theoretical pre-filtering step. Randomly selected members of pre-filtered and unfiltered libraries may then be translated into protein and tested for the property under investigation. In addition, in-vitro selections may be performed under identical conditions for pre-filtered and unfiltered libraries, and the properties of the selected proteins from each may be compared").
Regarding claims 13 and 14, Baynes in view of Gustafsson teach the methods of Claim 12 on which this claim depends/these claims depend. Baynes also teaches: the nucleic acid library is a DNA library and producing the protein library comprises transcribing and translating the DNA library, wherein translating the library comprises synthesising RNA-polypeptide fusion molecules each comprising an RNA sequence variant bound to the protein that it encodes; and the nucleic acid library is a DNA library and producing the protein library comprises transcribing and translating the DNA library, wherein translating the library comprises propagating phage that display a coat protein-polypeptide fusion, wherein the polypeptide fused to the coat protein corresponds to a sequence variant of the DNA library (Para.0111 "Examples of display libraries include those generated by phage, bacterial, yeast, mRNA, or ribosome display, where each nucleic acid and corresponding polypeptide are part of the same physical particle (e.g., a bacteriophage, a bacterium, a yeast cell, covalent mRNA-polypeptide fusion, or non-covalent mRNA/ribosome/polypeptide complex)").
Regarding claim 15, Baynes in view of Gustafsson teach the methods of Claim 12 on which this claim depends/these claims depend, respectively. Baynes also teaches the library testing step (b) comprises separating the protein library into at least 2 samples depending on the results of the one or more assays, and sequencing the nucleic acids present in at least one of the at least 2 samples (Para.0021 "the library nucleic acid may be amplified, sequenced or cloned after it is made" and para.0409 "Up to 100 variant clones with the highest level of the desired characteristic (such as polymerase activity or processivity) are sequenced").
Regarding claim 16, Baynes in view of Gustafsson teach the methods of Claim 15 on which this claim depends/these claims depend, respectively. Baynes also teaches the learning step (c) comprises aligning the sequences obtained by sequencing with the sequences designed in step (a), and quantifying the number of times that each sequence appears in each sample (Para.0157 "As is known in the art, there are a number of sequence alignment methodologies that can be used. For example, sequence homology based alignment methods can be used to create sequence alignments of proteins related to the target structure (Altschul et al., J. Mol. Biol. 215(3):403 (1990), incorporated by reference). These sequence alignments are then examined to determine the observed sequence variations. These sequence variations are tabulated to define a primary library").
Regarding claim 17, Baynes in view of Gustafsson teach the methods of Claim 1 on which this claim depends/these claims depend, respectively. Baynes also teaches the one or more desired properties is selected from the group consisting of physico-chemical properties of the proteins, activity-related properties, physiologically-relevant properties, and pharmacokinetic properties (Para.0015 "the invention relates to expression libraries that can be used to screen or select for polypeptides having one or more functional and/or structural properties (e.g., one or more predetermined catalytic, enzymatic, receptor-binding, therapeutic, or other properties)").
Regarding claim 19, Baynes in view of Gustafsson teach the methods of Claim 15 on which this claim depends/these claims depend, respectively. Gustafsson also teaches one of the one or more desired properties is binding to a specific target, and the library testing step (b) comprises incubating the protein library with the specific target immobilised on a surface and separating the protein library into a sample that is bound to the surface and a sample that is not bound to the surface (Para.0267-268 "Other methods of physical assays, suitable for use in the methods herein, can be based on the use of biosensors specific for reaction product(s), including those comprising antibodies with reporter properties, or those based on in vivo affinity recognition coupled with expression and activity of a reporter gene. Enzyme-coupled assays for reaction product detection and cell life-death-growth selections in vivo can also be used where appropriate. Regardless of the specific nature of the physical assays, they all are used to select a desired activity, or combination of desired activities, provided or encoded by a biomolecule of interest. The specific assay used for the selection will depend on the application. Many assays for proteins, receptors, ligands and the like are known. Formats include binding to immobilized components, cell or organismal viability, production of reporter compositions, and the like").
Regarding claim 20, Baynes in view of Gustafsson teach the methods of Claim 1 on which this claim depends/these claims depend, respectively. Gustafsson also teaches the library testing step comprises testing the variants for a plurality of properties, and the learning step comprises assigning a plurality of fitness scores to each variant tested, wherein each fitness score corresponds to one of the plurality of properties, wherein the learning step comprises training a plurality of machine learning algorithms, wherein each machine learning algorithm is trained to predict at least one of the plurality of fitness scores for new sequence variants (Figure 15 box J3 "score at least one target polypeptide character string using the motif scoring function to predict the at least one property of the at least one target polypeptide character string").
Regarding claim 22, Baynes in view of Gustafsson teach the methods of Claim 1 on which this claim depends/these claims depend, respectively. Gustafsson also teaches the machine learning algorithm is a classifier, wherein the machine learning algorithm is a neural network (Para.0102 "Examples of the mathematical/logical form of models include linear and non-linear mathematical expressions of various orders, neural networks, classification and regression trees/graphs, clustering approaches, recursive partitioning, support vector machines, and the like").
Regarding claim 23, Baynes in view of Gustafsson teach the methods of Claim 1 on which this claim depends/these claims depend, respectively. Baynes also teaches the machine learning model trained in step (c) is used to design a new library of sequence variants by iteratively optimising a library of sequence variants in silico, optionally wherein the library of sequence variants is iteratively optimised using a genetic algorithm (Para.0133 "In silico designs can be made to produce a library of constructs that can serve as a pool or plural separate species that can be tested or selected for a good candidate, or can serve as a starting places for other purposeful design iterations or for evolutionary techniques utilizing random mutagenesis. A screen or selection can be applied to the pool, and if necessary, the process (starting from design or another library expansion) can