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 .
The preliminary amendment of September 26, 2024 has been received and entered. Claims 1-20 are pending.
Priority
This application is the national stage entry of PCT/EP2022/074403, filed 9/1/2022. A copy of priority document EP21194437 was electronically retrieved on December 31, 2025.
Receipt is acknowledged of certified copies of papers required by 37 CFR 1.55.
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 1-20 are 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.
In claim 1, it is unclear if this is a claim to processing a series of images or a claim to an (iterative) cell culturing process that also uses image processing to adjust parameters. The claim is drafted with three indented steps of obtaining, processing and predicting; however, it also implicitly requires “cell state transitions”, a “base protocol” (presumably with chemical/biological steps), and repetition of the protocol with a series of “interventions defined by one or more process parameters”. This indefiniteness is compounded by the language of Claim 15, where a processor is said to perform the whole process. As the preamble of Claim 1 is a “method for monitoring a cell population in cell culture” the claim has been treated as requiring the cell culture with a protocol and at least one intervention as claimed. That is, this is an actual cell population and not merely a series of executed computer instructions.
Claim 3 is generally unclear; the first limitation is optional and is followed by “and/or”, so seemingly the claim would be met by an absence of any of the limitations. “The plurality of candidate values” lacks antecedent basis, and the five different overlapping ranges in the claim render the scope indefinite. The last limitation seems to amount to “A or not A”; what is the significance of this limitation? It also seems to mean “A and not A”, which is meaningless.
In claim 4 the significance of “and/or” Is unclear, and the “optionally” and “such as” limitations are indefinite.
In claim 7 the language following “optionally” is not required, and the meaning of “optimal” is indefinite as it lacks a reference point to determine optimality or is subjective to the user.
It is unclear how claim 10 limits claim 1 as it includes metrics at the end of the process and/or features from during the process. Claim 1 already requires “images of the cell population acquired using label-free imaging at one or more time points during the cell culture process” – i.e. not after the end – and “metrics indicative of a cell state transition in the cell population are metrics that characterise the outcome of a cell state transition process”. The “outcome” seems synonymous with the end or final stage.
With respect to Claim 15, it is unclear what portions of the method the instructions perform. The method of claim 1 seems to require acquiring images and a cell culture process having parameters that cause certain cell transitions. The seems to be generally described at pages 47-48, but it is not apparent that instructions (e.g. software) running on a processor causes all of Claim 1 to occur. The optional elements of Claim 15 make this problem worse; what is the scope of the claimed system?
Claim 17 appears to repeat the elements of claim 10 from which it depends; it is unclear if these are the same steps previously required or additional steps.
With respect to Claim 19, it is unclear what time point would not satisfy one of these alternative criteria, in that all times are either at the latest time point meeting some criteria or not at that time point. It is unclear what is being excluded or included by this language.
Dependent claims not specifically addressed are rejected by virtue of their dependency on a rejected parent claim.
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.
Claim(s) 1-7, 8-19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Fan et al. “A Machine Learning Assisted, Label-Free, Non-invasive Approach for Somatic Reprogramming in Induced Pluripotent Stem Cell Colony Formation Detection and Prediction”, Scientific Reports, 18 October 2017 (listed on IDS of 2/13/2024) in view of Williams et al., “Prediction of Human induced Pluripotent Stem Cell Cardiac Differentiation Outcome by Multifactorial Process Modeling”, Frontiers in Bioengineering and Biotechnology, July 2020 (listed on IDS of 2/13/2024).
With respect to Claim 1, Fan describes A method for monitoring a cell population in cell culture (abstract, “The system can detect and monitor the earliest cellular texture changes”), the method including the steps of:
obtaining one or more images of the cell population acquired using label-free imaging at one or more time points during the cell culture process (abstract, “Here, we report a time-lapse-based bright-field imaging analysis system that allows us to implement a label-free, non-invasive approach….”), wherein the label-free imaging is an imaging technology that provides information about the spatial configuration of cells, cell structures, or groups of cells, (“ …to measure morphological dynamics.”)
processing the one or more images to obtain one or more label-free image-derived features (Introduction, “This model utilizes a convolution neural network as a classifier in a sliding windows framework for colony recognition. Subsequently, a semi-supervised segmentation method was applied to locate the colonies and detect their boundaries. Moreover, a Hidden Markov Model (HMM) was trained to estimate the growth phase”),
predicting one or more metrics indicative of a cell state transition in the cell population using a statistical model that takes the label-free image-derived features as inputs and provides the one or more metrics indicative of a cell state transition in the cell population as outputs, wherein metrics indicative of a cell state transition in the cell population are metrics that characterise the progress and/or outcome of a cell state transition process occurring in a cell population (Introduction, “Moreover, a Hidden Markov Model (HMM) was trained to estimate the growth phase and maturation time window of colony formation during the reprogramming process.”), wherein the cell culture process is associated with a base protocol for obtaining the cell state transition comprising one or more interventions defined by one or more process parameters (There is necessarily a protocol followed to reach the detected states. From “Quantitative detection….”, “Each iPSC texture feature was monitored individually during the entire reprogramming process. “ The “process” is equivalent to the “protocol”; one process or portion thereof is described at “Human urinal cell culture and reprogramming”.),
and the predicting one or more metrics indicative of the cell state transition process is repeated for a plurality of candidate values of at least one of the one or more process parameters of at least one of said interventions to obtain a plurality of sets of one or more metrics indicative of the cell state transition process; and wherein comparing the predicted plurality of sets of one or more metrics indicative of the cell state transition process provides an indication of the suitability of the candidate values to achieve the cell state transition. (Discussion, “In the application point of view, this computer-aided machine learning approach for iPSCs can detect the cells earlies and predict the optimal selection time. This means that this tool can quantitatively evaluate different somatic reprogramming approaches, such as using engineered transcriptional factor or small molecules, for iPSC generation or further differentiation.” Different reprogramming approaches are different protocols.)
Fan et al. appears to be automating the process of identifying when certain cells reach a developmental stage in a set process rather than trying to optimize the process (i.e. vary parameters such as time, temperature, concentration of additives etc.). Fan does not intend to limit the computer analysis to this specific process. (Discussion, “We expect these combined approach will become an everyday technique for cell biology studies in a quantitative way. It should not limited in cellular reprogramming works.”)
Williams et al. teaches that a desirable use of computer imaging of cellular growth is optimization of the process itself by varying parameters. (“Employing experimental data for feature engineering,”, “From the data, a set of potential input variables, which we refer to as “bioprocess features,” for use in predictive models was generated with the goal of this set fully describing the experimental conditions over the entire differentiation process. For model construction using machine learning, a feature is an individual measurable or derived properties (using measured) of the system that is being modeled. Available experimental conditions included the rotation speed in the bioreactor and measurements such as differentiation day (dd) dependent cell densities, aggregate sizes, and nutrient concentrations, and measurements of DO concentration and pH over the course of the experiment. “)
It would have been obvious to use the image analysis mechanism of Fan et al. in the experiment optimization process of Williams et al. to save time and money using an optimized process (Williams et al., Introduction, “These models provide insight into potential key factors affecting hPSC cardiac differentiation to aid in selecting future experimental conditions and can predict the final CM content at earlier process timepoints, providing cost and time savings.”)
With respect to Claim 2, Williams et al. shows selecting a candidate value of the plurality of candidate values for the at least one intervention using the predicted plurality of sets of one or more metrics indicative of the cell state transition process (Introduction, last paragraph, “As a result, we here report predictive parameters and algorithms for this process (Figure 1). The study supports both the early interruption of failing processes (providing cost and time savings) and the rationale for further process modifications that may ultimately avoid future process failures.” The further process modifications would logically be modifying the most informative parameters.)
With respect to Claim 3, Williams identifies that some process features comprise a time point for intervention (“After mesoderm priming and cardiac progeny specification during the first ∼72–96 h of our differentiation protocol, progressive differentiation into functional, sarcomere protein expressing CMs occurs in the period between dd5 and dd10 (Halloin et al., 2019). It is thus interesting to note the MARS model selection of the features “dd5–dd7 cell density gradient” and “dd5 average DO concentration gradient” as being important for the CM content.”). Given that Williams et al. identifies these parameters as informative, it would have been obvious to modify them to optimize the results.
With respect to Claim 6, Fig. 3 of Williams et al. shows collection of parameter data over time. “Additional features were engineered from this data, as well as other time-dependent measurements, to capture how the conditions in the bioreactor were changing over time.”
With respect to Claim 9, Williams et al. is predicting differentiation (Title).
With respect to claim 10, both Fan et al. and Williams et al. are looking for indications of a cell state transition.
With respect to Claim 12, at least Fan et al. is feeding images to a neural network; the nature of a convolutional neural network (AlexNet in Fan et al.) is that the pixel level image is fed to the network and subsequent calculations are made based on the individual values of the pixels.
With respect to Claim 13, Williams et al. uses models “built using random forests and Gaussian process modeling” in order to determine the effective parameters in the process.
With respect to Claim 19, Williams et al. identifies both values and changes in values at different days in the process (Fig. 3, Tables 1 and 2) in order to identify relevant bioprocess features; based on the results of the regression analysis it would have been obvious to change the conditions at result effective time points.
Claim(s) 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Fan et al. in view of Williams et al. as applied to claim 1 above, and further in view of Argelaguet et al. “Multi-Omics Factor Analysis”. Fan et al. and Williams et al. do not specifically teach that the multifactor statistical model they use is trained to identify the relevant parameters. Argelaguet et al. teaches that biological statistical models are trained to identify which factors are significant (Model training and selection, “In practice, factors are pruned during training using a minimum fraction of variance explained threshold that needs to be specified by the user. Alternatively, the user can fix the number of factors and the minimum variance criterion is ignored. In the analyses presented, we initialized the models with K = 25 factors and they were pruned during training using a threshold of variance explained of 2%.”) As Williams et al has an entire list of factors, it would have been obvious to one of ordinary skill in the art to train the model of Williams to identify which of the factors in Tables 1 and 2 were more or less significant in optimizing the results.
Allowable Subject Matter
Claim 8 would be allowable if rewritten to overcome the rejection(s) under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), 2nd paragraph, set forth in this Office action and to include all of the limitations of the base claim and any intervening claims.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Ruan et al. “Image-derived Models of Cell Organization Changes During Differentiation of PC12 Cells” identify that photobleaching and phototoxicity limit the imaging rate during cellular differentiation and uses different imaging rates.
Katra et al. identify at [0110] that variable imaging frame rates are generally known in medical imaging applications.
Vaz et al. show additional variable image capture rates at [0101-0102] and [0173].
Any inquiry concerning this communication or earlier communications from the examiner should be directed to GREGORY A MORSE whose telephone number is (571)272-3838. The examiner can normally be reached M-F 7:30-4.
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.
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.
/GREGORY A MORSE/Supervisory Patent Examiner, Art Unit 2698